2024-12-02 17:14:15,921 main DEBUG Apache Log4j Core 2.17.2 initializing configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-12-02 17:14:15,932 main DEBUG Took 0.009077 seconds to load 1 plugins from package org.apache.hadoop.hbase.logging 2024-12-02 17:14:15,933 main DEBUG PluginManager 'Core' found 129 plugins 2024-12-02 17:14:15,933 main DEBUG PluginManager 'Level' found 0 plugins 2024-12-02 17:14:15,934 main DEBUG PluginManager 'Lookup' found 16 plugins 2024-12-02 17:14:15,939 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,947 main DEBUG PluginManager 'TypeConverter' found 26 plugins 2024-12-02 17:14:15,958 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.util.MBeans", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,960 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,960 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.logging.TestJul2Slf4j", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,961 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,961 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.zookeeper", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,961 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,962 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSinkAdapter", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,962 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,962 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSystemImpl", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,963 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,963 main DEBUG LoggerConfig$Builder(additivity="false", level="WARN", levelAndRefs="null", name="org.apache.directory", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,964 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,964 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.ipc.FailedServers", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,964 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,965 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsConfig", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,965 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,965 main DEBUG LoggerConfig$Builder(additivity="null", level="INFO", levelAndRefs="null", name="org.apache.hadoop.hbase.ScheduledChore", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,965 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,966 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.regionserver.RSRpcServices", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,966 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,966 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,967 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,967 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,967 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-02 17:14:15,967 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hbase.thirdparty.io.netty.channel", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,968 main DEBUG Building Plugin[name=root, class=org.apache.logging.log4j.core.config.LoggerConfig$RootLogger]. 2024-12-02 17:14:15,969 main DEBUG LoggerConfig$RootLogger$Builder(additivity="null", level="null", levelAndRefs="INFO,Console", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-02 17:14:15,970 main DEBUG Building Plugin[name=loggers, class=org.apache.logging.log4j.core.config.LoggersPlugin]. 2024-12-02 17:14:15,972 main DEBUG createLoggers(={org.apache.hadoop.metrics2.util.MBeans, org.apache.hadoop.hbase.logging.TestJul2Slf4j, org.apache.zookeeper, org.apache.hadoop.metrics2.impl.MetricsSinkAdapter, org.apache.hadoop.metrics2.impl.MetricsSystemImpl, org.apache.directory, org.apache.hadoop.hbase.ipc.FailedServers, org.apache.hadoop.metrics2.impl.MetricsConfig, org.apache.hadoop.hbase.ScheduledChore, org.apache.hadoop.hbase.regionserver.RSRpcServices, org.apache.hadoop, org.apache.hadoop.hbase, org.apache.hbase.thirdparty.io.netty.channel, root}) 2024-12-02 17:14:15,972 main DEBUG Building Plugin[name=layout, class=org.apache.logging.log4j.core.layout.PatternLayout]. 2024-12-02 17:14:15,973 main DEBUG PatternLayout$Builder(pattern="%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n", PatternSelector=null, Configuration(PropertiesConfig), Replace=null, charset="null", alwaysWriteExceptions="null", disableAnsi="null", noConsoleNoAnsi="null", header="null", footer="null") 2024-12-02 17:14:15,974 main DEBUG PluginManager 'Converter' found 47 plugins 2024-12-02 17:14:15,981 main DEBUG Building Plugin[name=appender, class=org.apache.hadoop.hbase.logging.HBaseTestAppender]. 2024-12-02 17:14:15,984 main DEBUG HBaseTestAppender$Builder(target="SYSTEM_ERR", maxSize="1G", bufferedIo="null", bufferSize="null", immediateFlush="null", ignoreExceptions="null", PatternLayout(%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n), name="Console", Configuration(PropertiesConfig), Filter=null, ={}) 2024-12-02 17:14:15,985 main DEBUG Starting HBaseTestOutputStreamManager SYSTEM_ERR 2024-12-02 17:14:15,986 main DEBUG Building Plugin[name=appenders, class=org.apache.logging.log4j.core.config.AppendersPlugin]. 2024-12-02 17:14:15,986 main DEBUG createAppenders(={Console}) 2024-12-02 17:14:15,987 main DEBUG Configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f initialized 2024-12-02 17:14:15,987 main DEBUG Starting configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-12-02 17:14:15,987 main DEBUG Started configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f OK. 2024-12-02 17:14:15,988 main DEBUG Shutting down OutputStreamManager SYSTEM_OUT.false.false-1 2024-12-02 17:14:15,988 main DEBUG OutputStream closed 2024-12-02 17:14:15,988 main DEBUG Shut down OutputStreamManager SYSTEM_OUT.false.false-1, all resources released: true 2024-12-02 17:14:15,988 main DEBUG Appender DefaultConsole-1 stopped with status true 2024-12-02 17:14:15,989 main DEBUG Stopped org.apache.logging.log4j.core.config.DefaultConfiguration@505fc5a4 OK 2024-12-02 17:14:16,052 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6 2024-12-02 17:14:16,054 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=StatusLogger 2024-12-02 17:14:16,055 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=ContextSelector 2024-12-02 17:14:16,056 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name= 2024-12-02 17:14:16,057 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.directory 2024-12-02 17:14:16,057 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSinkAdapter 2024-12-02 17:14:16,057 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.zookeeper 2024-12-02 17:14:16,057 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.logging.TestJul2Slf4j 2024-12-02 17:14:16,058 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSystemImpl 2024-12-02 17:14:16,058 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.util.MBeans 2024-12-02 17:14:16,058 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase 2024-12-02 17:14:16,058 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop 2024-12-02 17:14:16,059 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ipc.FailedServers 2024-12-02 17:14:16,059 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.regionserver.RSRpcServices 2024-12-02 17:14:16,059 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsConfig 2024-12-02 17:14:16,059 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hbase.thirdparty.io.netty.channel 2024-12-02 17:14:16,060 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ScheduledChore 2024-12-02 17:14:16,060 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Appenders,name=Console 2024-12-02 17:14:16,062 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-02 17:14:16,062 main DEBUG Reconfiguration complete for context[name=1dbd16a6] at URI jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-logging/target/hbase-logging-2.7.0-SNAPSHOT-tests.jar!/log4j2.properties (org.apache.logging.log4j.core.LoggerContext@39de3d36) with optional ClassLoader: null 2024-12-02 17:14:16,063 main DEBUG Shutdown hook enabled. Registering a new one. 2024-12-02 17:14:16,063 main DEBUG LoggerContext[name=1dbd16a6, org.apache.logging.log4j.core.LoggerContext@39de3d36] started OK. 2024-12-02T17:14:16,297 DEBUG [main {}] hbase.HBaseTestingUtility(348): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612 2024-12-02 17:14:16,299 main DEBUG AsyncLogger.ThreadNameStrategy=UNCACHED (user specified null, default is UNCACHED) 2024-12-02 17:14:16,299 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-02T17:14:16,320 INFO [main {}] hbase.HBaseClassTestRule(94): Test class org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi timeout: 26 mins 2024-12-02T17:14:16,336 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1126): Starting up minicluster with option: StartMiniClusterOption{numMasters=1, masterClass=null, numRegionServers=1, rsPorts=, rsClass=null, numDataNodes=1, dataNodeHosts=null, numZkServers=1, createRootDir=false, createWALDir=false} 2024-12-02T17:14:16,338 INFO [Time-limited test {}] hbase.HBaseZKTestingUtility(82): Created new mini-cluster data directory: /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2, deleteOnExit=true 2024-12-02T17:14:16,338 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1140): STARTING DFS 2024-12-02T17:14:16,339 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting test.cache.data to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/test.cache.data in system properties and HBase conf 2024-12-02T17:14:16,339 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.tmp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/hadoop.tmp.dir in system properties and HBase conf 2024-12-02T17:14:16,340 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.log.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/hadoop.log.dir in system properties and HBase conf 2024-12-02T17:14:16,341 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.local.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/mapreduce.cluster.local.dir in system properties and HBase conf 2024-12-02T17:14:16,341 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.temp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/mapreduce.cluster.temp.dir in system properties and HBase conf 2024-12-02T17:14:16,341 INFO [Time-limited test {}] hbase.HBaseTestingUtility(811): read short circuit is OFF 2024-12-02T17:14:16,423 WARN [Time-limited test {}] util.NativeCodeLoader(60): Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2024-12-02T17:14:16,501 DEBUG [Time-limited test {}] fs.HFileSystem(310): The file system is not a DistributedFileSystem. Skipping on block location reordering 2024-12-02T17:14:16,505 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.node-labels.fs-store.root-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.node-labels.fs-store.root-dir in system properties and HBase conf 2024-12-02T17:14:16,505 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.node-attribute.fs-store.root-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.node-attribute.fs-store.root-dir in system properties and HBase conf 2024-12-02T17:14:16,506 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.log-dirs to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.nodemanager.log-dirs in system properties and HBase conf 2024-12-02T17:14:16,506 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.remote-app-log-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-02T17:14:16,507 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.timeline-service.entity-group-fs-store.active-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.timeline-service.entity-group-fs-store.active-dir in system properties and HBase conf 2024-12-02T17:14:16,507 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.timeline-service.entity-group-fs-store.done-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.timeline-service.entity-group-fs-store.done-dir in system properties and HBase conf 2024-12-02T17:14:16,508 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.remote-app-log-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-02T17:14:16,508 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-02T17:14:16,508 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.datanode.shared.file.descriptor.paths to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/dfs.datanode.shared.file.descriptor.paths in system properties and HBase conf 2024-12-02T17:14:16,509 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting nfs.dump.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/nfs.dump.dir in system properties and HBase conf 2024-12-02T17:14:16,509 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting java.io.tmpdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/java.io.tmpdir in system properties and HBase conf 2024-12-02T17:14:16,510 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-02T17:14:16,510 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.provided.aliasmap.inmemory.leveldb.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/dfs.provided.aliasmap.inmemory.leveldb.dir in system properties and HBase conf 2024-12-02T17:14:16,510 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting fs.s3a.committer.staging.tmp.path to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/fs.s3a.committer.staging.tmp.path in system properties and HBase conf 2024-12-02T17:14:17,386 WARN [Time-limited test {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-namenode.properties,hadoop-metrics2.properties 2024-12-02T17:14:17,447 INFO [Time-limited test {}] log.Log(170): Logging initialized @2107ms to org.eclipse.jetty.util.log.Slf4jLog 2024-12-02T17:14:17,504 WARN [Time-limited test {}] server.AuthenticationFilter(240): Unable to initialize FileSignerSecretProvider, falling back to use random secrets. Reason: Could not read signature secret file: /home/jenkins/hadoop-http-auth-signature-secret 2024-12-02T17:14:17,555 INFO [Time-limited test {}] server.Server(375): jetty-9.4.53.v20231009; built: 2023-10-09T12:29:09.265Z; git: 27bde00a0b95a1d5bbee0eae7984f891d2d0f8c9; jvm 17.0.11+9 2024-12-02T17:14:17,573 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-02T17:14:17,574 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-02T17:14:17,575 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 660000ms 2024-12-02T17:14:17,588 WARN [Time-limited test {}] server.AuthenticationFilter(240): Unable to initialize FileSignerSecretProvider, falling back to use random secrets. Reason: Could not read signature secret file: /home/jenkins/hadoop-http-auth-signature-secret 2024-12-02T17:14:17,591 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@e483311{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/hadoop.log.dir/,AVAILABLE} 2024-12-02T17:14:17,592 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@6301cfc3{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-12-02T17:14:17,758 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@79eecdfd{hdfs,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/java.io.tmpdir/jetty-localhost-38267-hadoop-hdfs-3_4_1-tests_jar-_-any-11093003957405730772/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/hdfs} 2024-12-02T17:14:17,768 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@da70730{HTTP/1.1, (http/1.1)}{localhost:38267} 2024-12-02T17:14:17,768 INFO [Time-limited test {}] server.Server(415): Started @2429ms 2024-12-02T17:14:18,252 WARN [Time-limited test {}] server.AuthenticationFilter(240): Unable to initialize FileSignerSecretProvider, falling back to use random secrets. Reason: Could not read signature secret file: /home/jenkins/hadoop-http-auth-signature-secret 2024-12-02T17:14:18,260 INFO [Time-limited test {}] server.Server(375): jetty-9.4.53.v20231009; built: 2023-10-09T12:29:09.265Z; git: 27bde00a0b95a1d5bbee0eae7984f891d2d0f8c9; jvm 17.0.11+9 2024-12-02T17:14:18,261 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-02T17:14:18,261 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-02T17:14:18,261 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 600000ms 2024-12-02T17:14:18,262 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@52980ada{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/hadoop.log.dir/,AVAILABLE} 2024-12-02T17:14:18,263 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@1989be99{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-12-02T17:14:18,355 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@ec0120a{datanode,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/java.io.tmpdir/jetty-localhost-40785-hadoop-hdfs-3_4_1-tests_jar-_-any-13426555880899901759/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/datanode} 2024-12-02T17:14:18,356 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@2ed72052{HTTP/1.1, (http/1.1)}{localhost:40785} 2024-12-02T17:14:18,356 INFO [Time-limited test {}] server.Server(415): Started @3017ms 2024-12-02T17:14:18,400 WARN [Time-limited test {}] web.RestCsrfPreventionFilterHandler(75): Got null for restCsrfPreventionFilter - will not do any filtering. 2024-12-02T17:14:19,205 WARN [Thread-72 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/dfs/data/data1/current/BP-283315478-172.17.0.2-1733159656995/current, will proceed with Du for space computation calculation, 2024-12-02T17:14:19,205 WARN [Thread-73 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/dfs/data/data2/current/BP-283315478-172.17.0.2-1733159656995/current, will proceed with Du for space computation calculation, 2024-12-02T17:14:19,235 WARN [Thread-58 {}] datanode.DirectoryScanner(302): dfs.datanode.directoryscan.throttle.limit.ms.per.sec set to value above 1000 ms/sec. Assuming default value of -1 2024-12-02T17:14:19,277 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0xa4feed6f5e2a435f with lease ID 0xf1d1f38c26a0f386: Processing first storage report for DS-9ba310a5-4506-4f12-8f97-b573b73f3f94 from datanode DatanodeRegistration(127.0.0.1:44731, datanodeUuid=06bcb6eb-3ff0-4b9d-9849-66a037818faf, infoPort=36273, infoSecurePort=0, ipcPort=43317, storageInfo=lv=-57;cid=testClusterID;nsid=1964593217;c=1733159656995) 2024-12-02T17:14:19,278 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0xa4feed6f5e2a435f with lease ID 0xf1d1f38c26a0f386: from storage DS-9ba310a5-4506-4f12-8f97-b573b73f3f94 node DatanodeRegistration(127.0.0.1:44731, datanodeUuid=06bcb6eb-3ff0-4b9d-9849-66a037818faf, infoPort=36273, infoSecurePort=0, ipcPort=43317, storageInfo=lv=-57;cid=testClusterID;nsid=1964593217;c=1733159656995), blocks: 0, hasStaleStorage: true, processing time: 1 msecs, invalidatedBlocks: 0 2024-12-02T17:14:19,278 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0xa4feed6f5e2a435f with lease ID 0xf1d1f38c26a0f386: Processing first storage report for DS-7c9ad39f-8070-4bf4-a821-b96d574368c9 from datanode DatanodeRegistration(127.0.0.1:44731, datanodeUuid=06bcb6eb-3ff0-4b9d-9849-66a037818faf, infoPort=36273, infoSecurePort=0, ipcPort=43317, storageInfo=lv=-57;cid=testClusterID;nsid=1964593217;c=1733159656995) 2024-12-02T17:14:19,278 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0xa4feed6f5e2a435f with lease ID 0xf1d1f38c26a0f386: from storage DS-7c9ad39f-8070-4bf4-a821-b96d574368c9 node DatanodeRegistration(127.0.0.1:44731, datanodeUuid=06bcb6eb-3ff0-4b9d-9849-66a037818faf, infoPort=36273, infoSecurePort=0, ipcPort=43317, storageInfo=lv=-57;cid=testClusterID;nsid=1964593217;c=1733159656995), blocks: 0, hasStaleStorage: false, processing time: 0 msecs, invalidatedBlocks: 0 2024-12-02T17:14:19,374 DEBUG [Time-limited test {}] hbase.HBaseTestingUtility(703): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612 2024-12-02T17:14:19,454 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(259): Started connectionTimeout=30000, dir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/zookeeper_0, clientPort=60462, secureClientPort=-1, dataDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/zookeeper_0/version-2, dataDirSize=457 dataLogDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/zookeeper_0/version-2, dataLogSize=457 tickTime=2000, maxClientCnxns=300, minSessionTimeout=4000, maxSessionTimeout=40000, clientPortListenBacklog=-1, serverId=0 2024-12-02T17:14:19,464 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(284): Started MiniZooKeeperCluster and ran 'stat' on client port=60462 2024-12-02T17:14:19,472 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:19,474 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:19,686 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741825_1001 (size=7) 2024-12-02T17:14:20,100 INFO [Time-limited test {}] util.FSUtils(490): Created version file at hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6 with version=8 2024-12-02T17:14:20,101 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1460): Setting hbase.fs.tmp.dir to hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/hbase-staging 2024-12-02T17:14:20,202 DEBUG [Time-limited test {}] channel.MultithreadEventLoopGroup(44): -Dio.netty.eventLoopThreads: 16 2024-12-02T17:14:20,436 INFO [Time-limited test {}] client.ConnectionUtils(129): master/fa731d6f0321:0 server-side Connection retries=6 2024-12-02T17:14:20,451 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-02T17:14:20,452 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-02T17:14:20,452 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-02T17:14:20,452 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-02T17:14:20,452 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-02T17:14:20,560 INFO [Time-limited test {}] ipc.RpcServerFactory(64): Creating org.apache.hadoop.hbase.ipc.NettyRpcServer hosting hbase.pb.MasterService, hbase.pb.RegionServerStatusService, hbase.pb.LockService, hbase.pb.HbckService, hbase.pb.ClientMetaService, hbase.pb.ClientService, hbase.pb.AdminService, hbase.pb.ClientMetaService, hbase.pb.BootstrapNodeService 2024-12-02T17:14:20,607 INFO [Time-limited test {}] metrics.MetricRegistriesLoader(60): Loaded MetricRegistries class org.apache.hadoop.hbase.metrics.impl.MetricRegistriesImpl 2024-12-02T17:14:20,614 DEBUG [Time-limited test {}] util.ClassSize(228): Using Unsafe to estimate memory layout 2024-12-02T17:14:20,618 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-02T17:14:20,642 DEBUG [Time-limited test {}] channel.DefaultChannelId(84): -Dio.netty.processId: 28978 (auto-detected) 2024-12-02T17:14:20,643 DEBUG [Time-limited test {}] channel.DefaultChannelId(106): -Dio.netty.machineId: 02:42:ac:ff:fe:11:00:02 (auto-detected) 2024-12-02T17:14:20,659 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:45999 2024-12-02T17:14:20,665 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:20,667 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:20,678 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=master:45999 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:20,795 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:459990x0, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:20,805 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): master:45999-0x10198534a1d0000 connected 2024-12-02T17:14:20,926 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-02T17:14:20,930 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-02T17:14:20,933 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-02T17:14:20,959 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=45999 2024-12-02T17:14:20,959 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=45999 2024-12-02T17:14:20,960 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=45999 2024-12-02T17:14:20,960 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=45999 2024-12-02T17:14:20,961 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=45999 2024-12-02T17:14:20,972 INFO [Time-limited test {}] master.HMaster(488): hbase.rootdir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6, hbase.cluster.distributed=false 2024-12-02T17:14:21,072 INFO [Time-limited test {}] client.ConnectionUtils(129): regionserver/fa731d6f0321:0 server-side Connection retries=6 2024-12-02T17:14:21,073 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-02T17:14:21,073 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-02T17:14:21,074 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-02T17:14:21,074 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-02T17:14:21,074 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-02T17:14:21,077 INFO [Time-limited test {}] ipc.RpcServerFactory(64): Creating org.apache.hadoop.hbase.ipc.NettyRpcServer hosting hbase.pb.ClientService, hbase.pb.AdminService, hbase.pb.ClientMetaService, hbase.pb.BootstrapNodeService 2024-12-02T17:14:21,079 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-02T17:14:21,080 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:40509 2024-12-02T17:14:21,082 INFO [Time-limited test {}] hfile.BlockCacheFactory(123): Allocating BlockCache size=880 MB, blockSize=64 KB 2024-12-02T17:14:21,091 DEBUG [Time-limited test {}] mob.MobFileCache(124): MobFileCache enabled with cacheSize=1000, evictPeriods=3600sec, evictRemainRatio=0.5 2024-12-02T17:14:21,092 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:21,096 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:21,099 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=regionserver:40509 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:21,115 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:405090x0, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:21,116 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:405090x0, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-02T17:14:21,116 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): regionserver:40509-0x10198534a1d0001 connected 2024-12-02T17:14:21,118 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-02T17:14:21,120 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-02T17:14:21,124 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=40509 2024-12-02T17:14:21,124 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=40509 2024-12-02T17:14:21,131 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=40509 2024-12-02T17:14:21,135 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=40509 2024-12-02T17:14:21,136 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=40509 2024-12-02T17:14:21,160 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(2445): Adding backup master ZNode /hbase/backup-masters/fa731d6f0321,45999,1733159660197 2024-12-02T17:14:21,180 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-02T17:14:21,180 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-02T17:14:21,181 DEBUG [M:0;fa731d6f0321:45999 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:M:0;fa731d6f0321:45999 2024-12-02T17:14:21,183 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/backup-masters/fa731d6f0321,45999,1733159660197 2024-12-02T17:14:21,220 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-02T17:14:21,220 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-02T17:14:21,221 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:21,221 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:21,224 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-02T17:14:21,224 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-02T17:14:21,226 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.ActiveMasterManager(245): Deleting ZNode for /hbase/backup-masters/fa731d6f0321,45999,1733159660197 from backup master directory 2024-12-02T17:14:21,237 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-02T17:14:21,237 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/backup-masters/fa731d6f0321,45999,1733159660197 2024-12-02T17:14:21,238 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-02T17:14:21,238 WARN [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-02T17:14:21,238 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.ActiveMasterManager(255): Registered as active master=fa731d6f0321,45999,1733159660197 2024-12-02T17:14:21,241 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating data MemStoreChunkPool with chunk size 2 MB, max count 396, initial count 0 2024-12-02T17:14:21,248 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating index MemStoreChunkPool with chunk size 204.80 KB, max count 440, initial count 0 2024-12-02T17:14:21,350 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741826_1002 (size=42) 2024-12-02T17:14:21,753 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] util.FSUtils(639): Created cluster ID file at hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/hbase.id with ID: a56154ea-b277-49c8-abc8-799bb07e4f77 2024-12-02T17:14:21,796 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-02T17:14:21,828 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:21,828 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:21,844 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741827_1003 (size=196) 2024-12-02T17:14:22,260 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] region.MasterRegion(372): Create or load local region for table 'master:store', {TABLE_ATTRIBUTES => {METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'proc', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'rs', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'state', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'} 2024-12-02T17:14:22,261 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(132): Injected flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000 2024-12-02T17:14:22,275 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(244): No decryptEncryptedDataEncryptionKey method in DFSClient, should be hadoop version with HDFS-12396 java.lang.NoSuchMethodException: org.apache.hadoop.hdfs.DFSClient.decryptEncryptedDataEncryptionKey(org.apache.hadoop.fs.FileEncryptionInfo) at java.lang.Class.getDeclaredMethod(Class.java:2675) ~[?:?] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.createTransparentCryptoHelperWithoutHDFS12396(FanOutOneBlockAsyncDFSOutputSaslHelper.java:183) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.createTransparentCryptoHelper(FanOutOneBlockAsyncDFSOutputSaslHelper.java:242) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.(FanOutOneBlockAsyncDFSOutputSaslHelper.java:253) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.wal.AsyncFSWALProvider.load(AsyncFSWALProvider.java:147) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.getProviderClass(WALFactory.java:160) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.getProvider(WALFactory.java:200) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.(WALFactory.java:232) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.(WALFactory.java:207) ~[classes/:?] at org.apache.hadoop.hbase.master.region.MasterRegion.create(MasterRegion.java:402) ~[classes/:?] at org.apache.hadoop.hbase.master.region.MasterRegionFactory.create(MasterRegionFactory.java:135) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.finishActiveMasterInitialization(HMaster.java:973) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.startActiveMasterManager(HMaster.java:2470) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.lambda$run$0(HMaster.java:590) ~[classes/:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:187) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:177) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.HMaster.lambda$run$1(HMaster.java:587) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:22,279 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-02T17:14:22,312 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741828_1004 (size=1189) 2024-12-02T17:14:22,338 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(7124): Creating {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''}, tableDescriptor='master:store', {TABLE_ATTRIBUTES => {METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'proc', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'rs', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'state', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '1', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, under table dir hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store 2024-12-02T17:14:22,357 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741829_1005 (size=34) 2024-12-02T17:14:22,363 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] throttle.StoreHotnessProtector(112): StoreHotnessProtector is disabled. Set hbase.region.store.parallel.put.limit > 0 to enable, which may help mitigate load under heavy write pressure. 2024-12-02T17:14:22,363 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-02T17:14:22,364 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1681): Closing 1595e783b53d99cd5eef43b6debb2682, disabling compactions & flushes 2024-12-02T17:14:22,364 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1703): Closing region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-02T17:14:22,364 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1724): Waiting without time limit for close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-02T17:14:22,364 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1791): Acquired close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. after waiting 0 ms 2024-12-02T17:14:22,365 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1801): Updates disabled for region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-02T17:14:22,365 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1922): Closed master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-02T17:14:22,365 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1635): Region close journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-02T17:14:22,367 WARN [master/fa731d6f0321:0:becomeActiveMaster {}] region.MasterRegion(249): failed to clean up initializing flag: hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/.initializing 2024-12-02T17:14:22,368 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] region.MasterRegion(219): WALDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197 2024-12-02T17:14:22,376 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-02T17:14:22,391 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=fa731d6f0321%2C45999%2C1733159660197, suffix=, logDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197, archiveDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/oldWALs, maxLogs=10 2024-12-02T17:14:22,423 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197/fa731d6f0321%2C45999%2C1733159660197.1733159662399, exclude list is [], retry=0 2024-12-02T17:14:22,446 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:44731,DS-9ba310a5-4506-4f12-8f97-b573b73f3f94,DISK] 2024-12-02T17:14:22,450 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.ProtobufDecoder(117): Hadoop 3.3 and above shades protobuf. 2024-12-02T17:14:22,487 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197/fa731d6f0321%2C45999%2C1733159660197.1733159662399 2024-12-02T17:14:22,488 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:36273:36273)] 2024-12-02T17:14:22,489 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(7285): Opening region: {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''} 2024-12-02T17:14:22,489 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-02T17:14:22,493 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(7327): checking encryption for 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,494 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(7330): checking classloading for 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,529 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,547 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName info 2024-12-02T17:14:22,550 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:22,553 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:22,553 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family proc of region 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,556 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName proc 2024-12-02T17:14:22,556 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:22,557 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/proc, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-02T17:14:22,557 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family rs of region 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,560 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName rs 2024-12-02T17:14:22,560 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:22,561 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/rs, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-02T17:14:22,561 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family state of region 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,564 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1595e783b53d99cd5eef43b6debb2682 columnFamilyName state 2024-12-02T17:14:22,565 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:22,566 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/state, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-02T17:14:22,569 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,571 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,579 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.FlushLargeStoresPolicy(65): No hbase.hregion.percolumnfamilyflush.size.lower.bound set in table master:store descriptor;using region.getMemStoreFlushHeapSize/# of families (32.0 M)) instead. 2024-12-02T17:14:22,584 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1085): writing seq id for 1595e783b53d99cd5eef43b6debb2682 2024-12-02T17:14:22,588 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-02T17:14:22,590 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1102): Opened 1595e783b53d99cd5eef43b6debb2682; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=60536549, jitterRate=-0.09793512523174286}}}, FlushLargeStoresPolicy{flushSizeLowerBound=33554432} 2024-12-02T17:14:22,594 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] regionserver.HRegion(1001): Region open journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-02T17:14:22,594 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(122): Constructor flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000, compactMin=4 2024-12-02T17:14:22,627 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@69ce79ef, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:22,657 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(882): No meta location available on zookeeper, skip migrating... 2024-12-02T17:14:22,669 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] region.RegionProcedureStore(104): Starting the Region Procedure Store, number threads=5 2024-12-02T17:14:22,670 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(633): Starting 5 core workers (bigger of cpus/4 or 16) with max (burst) worker count=50 2024-12-02T17:14:22,673 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] region.RegionProcedureStore(255): Starting Region Procedure Store lease recovery... 2024-12-02T17:14:22,674 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(653): Recovered RegionProcedureStore lease in 1 msec 2024-12-02T17:14:22,679 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(667): Loaded RegionProcedureStore in 4 msec 2024-12-02T17:14:22,679 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.RemoteProcedureDispatcher(96): Instantiated, coreThreads=3 (allowCoreThreadTimeOut=true), queueMaxSize=32, operationDelay=150 2024-12-02T17:14:22,719 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.RegionServerTracker(127): Upgrading RegionServerTracker to active master mode; 0 have existingServerCrashProcedures, 0 possibly 'live' servers, and 0 'splitting'. 2024-12-02T17:14:22,731 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Unable to get data of znode /hbase/balancer because node does not exist (not necessarily an error) 2024-12-02T17:14:22,744 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/balancer already deleted, retry=false 2024-12-02T17:14:22,747 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] normalizer.SimpleRegionNormalizer(163): Updated configuration for key 'hbase.normalizer.merge.min_region_size.mb' from 0 to 1 2024-12-02T17:14:22,749 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Unable to get data of znode /hbase/normalizer because node does not exist (not necessarily an error) 2024-12-02T17:14:22,756 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/normalizer already deleted, retry=false 2024-12-02T17:14:22,758 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] normalizer.RegionNormalizerWorker(137): Normalizer rate limit set to unlimited 2024-12-02T17:14:22,761 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Unable to get data of znode /hbase/switch/split because node does not exist (not necessarily an error) 2024-12-02T17:14:22,769 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/split already deleted, retry=false 2024-12-02T17:14:22,771 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Unable to get data of znode /hbase/switch/merge because node does not exist (not necessarily an error) 2024-12-02T17:14:22,781 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/merge already deleted, retry=false 2024-12-02T17:14:22,792 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Unable to get data of znode /hbase/snapshot-cleanup because node does not exist (not necessarily an error) 2024-12-02T17:14:22,838 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/snapshot-cleanup already deleted, retry=false 2024-12-02T17:14:22,897 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-02T17:14:22,897 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-02T17:14:22,898 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:22,898 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:22,899 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(826): Active/primary master=fa731d6f0321,45999,1733159660197, sessionid=0x10198534a1d0000, setting cluster-up flag (Was=false) 2024-12-02T17:14:22,989 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:22,989 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:23,090 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/flush-table-proc/acquired, /hbase/flush-table-proc/reached, /hbase/flush-table-proc/abort 2024-12-02T17:14:23,094 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=fa731d6f0321,45999,1733159660197 2024-12-02T17:14:23,123 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:23,123 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:23,148 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/online-snapshot/acquired, /hbase/online-snapshot/reached, /hbase/online-snapshot/abort 2024-12-02T17:14:23,149 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=fa731d6f0321,45999,1733159660197 2024-12-02T17:14:23,224 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT; InitMetaProcedure table=hbase:meta 2024-12-02T17:14:23,229 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] balancer.BaseLoadBalancer(575): slop=0.2 2024-12-02T17:14:23,231 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] balancer.StochasticLoadBalancer(294): Loaded config; maxSteps=1000000, runMaxSteps=false, stepsPerRegion=800, maxRunningTime=30000, isByTable=false, CostFunctions=[RegionCountSkewCostFunction, PrimaryRegionCountSkewCostFunction, MoveCostFunction, ServerLocalityCostFunction, RackLocalityCostFunction, TableSkewCostFunction, RegionReplicaHostCostFunction, RegionReplicaRackCostFunction, ReadRequestCostFunction, WriteRequestCostFunction, MemStoreSizeCostFunction, StoreFileCostFunction] , sum of multiplier of cost functions = 0.0 etc. 2024-12-02T17:14:23,236 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] balancer.RegionLocationFinder(146): Skipping locality-based refresh due to oldStatus=null, newStatus=Master: fa731d6f0321,45999,1733159660197 Number of backup masters: 0 Number of live region servers: 0 Number of dead region servers: 0 Number of unknown region servers: 0 Average load: 0.0 Number of requests: 0 Number of regions: 0 Number of regions in transition: 0 2024-12-02T17:14:23,239 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_OPEN_REGION-master/fa731d6f0321:0, corePoolSize=5, maxPoolSize=5 2024-12-02T17:14:23,239 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_CLOSE_REGION-master/fa731d6f0321:0, corePoolSize=5, maxPoolSize=5 2024-12-02T17:14:23,240 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SERVER_OPERATIONS-master/fa731d6f0321:0, corePoolSize=5, maxPoolSize=5 2024-12-02T17:14:23,240 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_META_SERVER_OPERATIONS-master/fa731d6f0321:0, corePoolSize=5, maxPoolSize=5 2024-12-02T17:14:23,240 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=M_LOG_REPLAY_OPS-master/fa731d6f0321:0, corePoolSize=10, maxPoolSize=10 2024-12-02T17:14:23,240 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SNAPSHOT_OPERATIONS-master/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,240 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_MERGE_OPERATIONS-master/fa731d6f0321:0, corePoolSize=2, maxPoolSize=2 2024-12-02T17:14:23,240 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_TABLE_OPERATIONS-master/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,242 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.procedure2.CompletedProcedureCleaner; timeout=30000, timestamp=1733159693242 2024-12-02T17:14:23,243 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.DirScanPool(74): log_cleaner Cleaner pool size is 1 2024-12-02T17:14:23,244 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveLogCleaner 2024-12-02T17:14:23,245 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT, locked=true; InitMetaProcedure table=hbase:meta 2024-12-02T17:14:23,245 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(75): BOOTSTRAP: creating hbase:meta region 2024-12-02T17:14:23,247 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.replication.master.ReplicationLogCleaner 2024-12-02T17:14:23,247 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreWALCleaner 2024-12-02T17:14:23,248 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveProcedureWALCleaner 2024-12-02T17:14:23,248 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.LogCleaner(148): Creating 1 old WALs cleaner threads 2024-12-02T17:14:23,248 DEBUG [PEWorker-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:23,249 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=LogsCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,249 INFO [PEWorker-1 {}] util.FSTableDescriptors(133): Creating new hbase:meta table descriptor 'hbase:meta', {TABLE_ATTRIBUTES => {IS_META => 'true', coprocessor$1 => '|org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint|536870911|', METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'rep_barrier', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '2147483647', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'table', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'} 2024-12-02T17:14:23,250 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.DirScanPool(74): hfile_cleaner Cleaner pool size is 2 2024-12-02T17:14:23,252 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreHFileCleaner 2024-12-02T17:14:23,252 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.HFileLinkCleaner 2024-12-02T17:14:23,255 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.snapshot.SnapshotHFileCleaner 2024-12-02T17:14:23,255 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveHFileCleaner 2024-12-02T17:14:23,257 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.HFileCleaner(260): Starting for large file=Thread[master/fa731d6f0321:0:becomeActiveMaster-HFileCleaner.large.0-1733159663256,5,FailOnTimeoutGroup] 2024-12-02T17:14:23,257 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] cleaner.HFileCleaner(275): Starting for small files=Thread[master/fa731d6f0321:0:becomeActiveMaster-HFileCleaner.small.0-1733159663257,5,FailOnTimeoutGroup] 2024-12-02T17:14:23,257 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HFileCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,257 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(1680): Reopening regions with very high storeFileRefCount is disabled. Provide threshold value > 0 for hbase.regions.recovery.store.file.ref.count to enable it. 2024-12-02T17:14:23,257 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741831_1007 (size=1039) 2024-12-02T17:14:23,258 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=ReplicationBarrierCleaner, period=43200000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,259 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=SnapshotCleaner, period=1800000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,263 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:RS:0;fa731d6f0321:40509 2024-12-02T17:14:23,264 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(1008): ClusterId : a56154ea-b277-49c8-abc8-799bb07e4f77 2024-12-02T17:14:23,266 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(43): Procedure flush-table-proc initializing 2024-12-02T17:14:23,283 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(45): Procedure flush-table-proc initialized 2024-12-02T17:14:23,283 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(43): Procedure online-snapshot initializing 2024-12-02T17:14:23,343 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(45): Procedure online-snapshot initialized 2024-12-02T17:14:23,345 DEBUG [RS:0;fa731d6f0321:40509 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@6c6e8b7d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:23,348 DEBUG [RS:0;fa731d6f0321:40509 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@aede2ba, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=fa731d6f0321/172.17.0.2:0 2024-12-02T17:14:23,352 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.RegionServerCoprocessorHost(67): System coprocessor loading is enabled 2024-12-02T17:14:23,352 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.RegionServerCoprocessorHost(68): Table coprocessor loading is enabled 2024-12-02T17:14:23,353 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(1090): About to register with Master. 2024-12-02T17:14:23,355 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(3073): reportForDuty to master=fa731d6f0321,45999,1733159660197 with isa=fa731d6f0321/172.17.0.2:40509, startcode=1733159661070 2024-12-02T17:14:23,367 DEBUG [RS:0;fa731d6f0321:40509 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-02T17:14:23,398 INFO [RS-EventLoopGroup-1-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:50695, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-02T17:14:23,403 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=45999 {}] master.ServerManager(332): Checking decommissioned status of RegionServer fa731d6f0321,40509,1733159661070 2024-12-02T17:14:23,404 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=45999 {}] master.ServerManager(486): Registering regionserver=fa731d6f0321,40509,1733159661070 2024-12-02T17:14:23,418 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(1725): Config from master: hbase.rootdir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6 2024-12-02T17:14:23,418 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(1725): Config from master: fs.defaultFS=hdfs://localhost:45201 2024-12-02T17:14:23,418 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(1725): Config from master: hbase.master.info.port=-1 2024-12-02T17:14:23,436 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/rs 2024-12-02T17:14:23,437 DEBUG [RS:0;fa731d6f0321:40509 {}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/rs/fa731d6f0321,40509,1733159661070 2024-12-02T17:14:23,437 WARN [RS:0;fa731d6f0321:40509 {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-02T17:14:23,437 INFO [RS:0;fa731d6f0321:40509 {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-02T17:14:23,438 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(2100): logDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070 2024-12-02T17:14:23,440 INFO [RegionServerTracker-0 {}] master.RegionServerTracker(179): RegionServer ephemeral node created, adding [fa731d6f0321,40509,1733159661070] 2024-12-02T17:14:23,454 DEBUG [RS:0;fa731d6f0321:40509 {}] regionserver.Replication(140): Replication stats-in-log period=300 seconds 2024-12-02T17:14:23,463 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.MetricsRegionServerWrapperImpl(120): Computing regionserver metrics every 5000 milliseconds 2024-12-02T17:14:23,473 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.MemStoreFlusher(130): globalMemStoreLimit=880 M, globalMemStoreLimitLowMark=836 M, Offheap=false 2024-12-02T17:14:23,475 INFO [RS:0;fa731d6f0321:40509 {}] throttle.PressureAwareCompactionThroughputController(131): Compaction throughput configurations, higher bound: 100.00 MB/second, lower bound 50.00 MB/second, off peak: unlimited, tuning period: 60000 ms 2024-12-02T17:14:23,475 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionThroughputTuner, period=60000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,476 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer$CompactionChecker(1988): CompactionChecker runs every PT1S 2024-12-02T17:14:23,481 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactedHFilesCleaner, period=120000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,481 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_REGION-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,481 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_META-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,481 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_REGION-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_META-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_LOG_REPLAY_OPS-regionserver/fa731d6f0321:0, corePoolSize=2, maxPoolSize=2 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_COMPACTED_FILES_DISCHARGER-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_REGION_REPLICA_FLUSH_OPS-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_REFRESH_PEER-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_SWITCH_RPC_THROTTLE-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,482 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_CLAIM_REPLICATION_QUEUE-regionserver/fa731d6f0321:0, corePoolSize=1, maxPoolSize=1 2024-12-02T17:14:23,483 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_SNAPSHOT_OPERATIONS-regionserver/fa731d6f0321:0, corePoolSize=3, maxPoolSize=3 2024-12-02T17:14:23,483 DEBUG [RS:0;fa731d6f0321:40509 {}] executor.ExecutorService(95): Starting executor service name=RS_FLUSH_OPERATIONS-regionserver/fa731d6f0321:0, corePoolSize=3, maxPoolSize=3 2024-12-02T17:14:23,483 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionChecker, period=1000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,483 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=MemstoreFlusherChore, period=1000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,484 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=nonceCleaner, period=360000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,484 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=BrokenStoreFileCleaner, period=21600000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,484 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,40509,1733159661070-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-02T17:14:23,499 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.HeapMemoryManager(209): Starting, tuneOn=false 2024-12-02T17:14:23,501 INFO [RS:0;fa731d6f0321:40509 {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,40509,1733159661070-HeapMemoryTunerChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:23,517 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.Replication(204): fa731d6f0321,40509,1733159661070 started 2024-12-02T17:14:23,517 INFO [RS:0;fa731d6f0321:40509 {}] regionserver.HRegionServer(1767): Serving as fa731d6f0321,40509,1733159661070, RpcServer on fa731d6f0321/172.17.0.2:40509, sessionid=0x10198534a1d0001 2024-12-02T17:14:23,518 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(51): Procedure flush-table-proc starting 2024-12-02T17:14:23,518 DEBUG [RS:0;fa731d6f0321:40509 {}] flush.RegionServerFlushTableProcedureManager(108): Start region server flush procedure manager fa731d6f0321,40509,1733159661070 2024-12-02T17:14:23,518 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member 'fa731d6f0321,40509,1733159661070' 2024-12-02T17:14:23,518 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/flush-table-proc/abort' 2024-12-02T17:14:23,519 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/flush-table-proc/acquired' 2024-12-02T17:14:23,520 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(53): Procedure flush-table-proc started 2024-12-02T17:14:23,520 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(51): Procedure online-snapshot starting 2024-12-02T17:14:23,520 DEBUG [RS:0;fa731d6f0321:40509 {}] snapshot.RegionServerSnapshotManager(126): Start Snapshot Manager fa731d6f0321,40509,1733159661070 2024-12-02T17:14:23,520 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member 'fa731d6f0321,40509,1733159661070' 2024-12-02T17:14:23,520 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/online-snapshot/abort' 2024-12-02T17:14:23,521 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/online-snapshot/acquired' 2024-12-02T17:14:23,521 DEBUG [RS:0;fa731d6f0321:40509 {}] procedure.RegionServerProcedureManagerHost(53): Procedure online-snapshot started 2024-12-02T17:14:23,522 INFO [RS:0;fa731d6f0321:40509 {}] quotas.RegionServerRpcQuotaManager(64): Quota support disabled 2024-12-02T17:14:23,522 INFO [RS:0;fa731d6f0321:40509 {}] quotas.RegionServerSpaceQuotaManager(80): Quota support disabled, not starting space quota manager. 2024-12-02T17:14:23,626 INFO [RS:0;fa731d6f0321:40509 {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-02T17:14:23,629 INFO [RS:0;fa731d6f0321:40509 {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=fa731d6f0321%2C40509%2C1733159661070, suffix=, logDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070, archiveDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/oldWALs, maxLogs=32 2024-12-02T17:14:23,643 DEBUG [RS:0;fa731d6f0321:40509 {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.1733159663631, exclude list is [], retry=0 2024-12-02T17:14:23,647 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:44731,DS-9ba310a5-4506-4f12-8f97-b573b73f3f94,DISK] 2024-12-02T17:14:23,651 INFO [RS:0;fa731d6f0321:40509 {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:23,651 DEBUG [RS:0;fa731d6f0321:40509 {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:36273:36273)] 2024-12-02T17:14:23,660 INFO [PEWorker-1 {}] util.FSTableDescriptors(140): Updated hbase:meta table descriptor to hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/.tabledesc/.tableinfo.0000000001.1039 2024-12-02T17:14:23,660 INFO [PEWorker-1 {}] regionserver.HRegion(7106): creating {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''}, tableDescriptor='hbase:meta', {TABLE_ATTRIBUTES => {IS_META => 'true', coprocessor$1 => '|org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint|536870911|', METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, {NAME => 'rep_barrier', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '2147483647', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '65536 B (64KB)'}, {NAME => 'table', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '3', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'ROW_INDEX_V1', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROWCOL', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, regionDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6 2024-12-02T17:14:23,668 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741833_1009 (size=32) 2024-12-02T17:14:24,071 DEBUG [PEWorker-1 {}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-02T17:14:24,073 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 1588230740 2024-12-02T17:14:24,076 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName info 2024-12-02T17:14:24,076 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,077 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:24,077 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family rep_barrier of region 1588230740 2024-12-02T17:14:24,080 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName rep_barrier 2024-12-02T17:14:24,080 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,081 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/rep_barrier, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:24,082 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family table of region 1588230740 2024-12-02T17:14:24,084 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName table 2024-12-02T17:14:24,085 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,086 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/table, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:24,087 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740 2024-12-02T17:14:24,088 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740 2024-12-02T17:14:24,091 DEBUG [PEWorker-1 {}] regionserver.FlushLargeStoresPolicy(65): No hbase.hregion.percolumnfamilyflush.size.lower.bound set in table hbase:meta descriptor;using region.getMemStoreFlushHeapSize/# of families (42.7 M)) instead. 2024-12-02T17:14:24,093 DEBUG [PEWorker-1 {}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-02T17:14:24,097 DEBUG [PEWorker-1 {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-02T17:14:24,098 INFO [PEWorker-1 {}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=64011082, jitterRate=-0.04616054892539978}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-02T17:14:24,100 DEBUG [PEWorker-1 {}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-02T17:14:24,100 DEBUG [PEWorker-1 {}] regionserver.HRegion(1681): Closing 1588230740, disabling compactions & flushes 2024-12-02T17:14:24,100 INFO [PEWorker-1 {}] regionserver.HRegion(1703): Closing region hbase:meta,,1.1588230740 2024-12-02T17:14:24,100 DEBUG [PEWorker-1 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:meta,,1.1588230740 2024-12-02T17:14:24,100 DEBUG [PEWorker-1 {}] regionserver.HRegion(1791): Acquired close lock on hbase:meta,,1.1588230740 after waiting 0 ms 2024-12-02T17:14:24,100 DEBUG [PEWorker-1 {}] regionserver.HRegion(1801): Updates disabled for region hbase:meta,,1.1588230740 2024-12-02T17:14:24,102 INFO [PEWorker-1 {}] regionserver.HRegion(1922): Closed hbase:meta,,1.1588230740 2024-12-02T17:14:24,102 DEBUG [PEWorker-1 {}] regionserver.HRegion(1635): Region close journal for 1588230740: 2024-12-02T17:14:24,104 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_ASSIGN_META, locked=true; InitMetaProcedure table=hbase:meta 2024-12-02T17:14:24,104 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(107): Going to assign meta 2024-12-02T17:14:24,109 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=2, ppid=1, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN}] 2024-12-02T17:14:24,117 INFO [PEWorker-5 {}] procedure.MasterProcedureScheduler(786): Took xlock for pid=2, ppid=1, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN 2024-12-02T17:14:24,119 INFO [PEWorker-5 {}] assignment.TransitRegionStateProcedure(264): Starting pid=2, ppid=1, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE, locked=true; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN; state=OFFLINE, location=null; forceNewPlan=false, retain=false 2024-12-02T17:14:24,270 DEBUG [fa731d6f0321:45999 {}] assignment.AssignmentManager(2444): Processing assignQueue; systemServersCount=1, allServersCount=1 2024-12-02T17:14:24,274 INFO [PEWorker-2 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPENING, regionLocation=fa731d6f0321,40509,1733159661070 2024-12-02T17:14:24,279 INFO [PEWorker-2 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as fa731d6f0321,40509,1733159661070, state=OPENING 2024-12-02T17:14:24,321 DEBUG [PEWorker-2 {}] zookeeper.MetaTableLocator(183): hbase:meta region location doesn't exist, create it 2024-12-02T17:14:24,357 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:24,357 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:24,359 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-02T17:14:24,359 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-02T17:14:24,363 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=3, ppid=2, state=RUNNABLE; OpenRegionProcedure 1588230740, server=fa731d6f0321,40509,1733159661070}] 2024-12-02T17:14:24,536 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:24,538 DEBUG [RSProcedureDispatcher-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=AdminService, sasl=false 2024-12-02T17:14:24,541 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:51632, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=AdminService 2024-12-02T17:14:24,550 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(135): Open hbase:meta,,1.1588230740 2024-12-02T17:14:24,550 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-02T17:14:24,551 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] monitor.StreamSlowMonitor(122): New stream slow monitor .meta 2024-12-02T17:14:24,554 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=fa731d6f0321%2C40509%2C1733159661070.meta, suffix=.meta, logDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070, archiveDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/oldWALs, maxLogs=32 2024-12-02T17:14:24,569 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.meta.1733159664555.meta, exclude list is [], retry=0 2024-12-02T17:14:24,573 DEBUG [RS-EventLoopGroup-3-1 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:44731,DS-9ba310a5-4506-4f12-8f97-b573b73f3f94,DISK] 2024-12-02T17:14:24,575 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.meta.1733159664555.meta 2024-12-02T17:14:24,576 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:36273:36273)] 2024-12-02T17:14:24,576 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7285): Opening region: {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''} 2024-12-02T17:14:24,577 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] coprocessor.CoprocessorHost(215): Loading coprocessor class org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint with path null and priority 536870911 2024-12-02T17:14:24,626 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7999): Registered coprocessor service: region=hbase:meta,,1 service=MultiRowMutationService 2024-12-02T17:14:24,630 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.RegionCoprocessorHost(436): Loaded coprocessor org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint from HTD of hbase:meta successfully. 2024-12-02T17:14:24,633 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table meta 1588230740 2024-12-02T17:14:24,633 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-02T17:14:24,633 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7327): checking encryption for 1588230740 2024-12-02T17:14:24,633 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7330): checking classloading for 1588230740 2024-12-02T17:14:24,636 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 1588230740 2024-12-02T17:14:24,637 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName info 2024-12-02T17:14:24,638 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,639 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:24,639 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family rep_barrier of region 1588230740 2024-12-02T17:14:24,640 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName rep_barrier 2024-12-02T17:14:24,640 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,641 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/rep_barrier, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:24,641 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family table of region 1588230740 2024-12-02T17:14:24,642 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName table 2024-12-02T17:14:24,642 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,643 INFO [StoreOpener-1588230740-1 {}] regionserver.HStore(327): Store=1588230740/table, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=ROW_INDEX_V1, compression=NONE 2024-12-02T17:14:24,645 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740 2024-12-02T17:14:24,648 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740 2024-12-02T17:14:24,651 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.FlushLargeStoresPolicy(65): No hbase.hregion.percolumnfamilyflush.size.lower.bound set in table hbase:meta descriptor;using region.getMemStoreFlushHeapSize/# of families (42.7 M)) instead. 2024-12-02T17:14:24,654 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-02T17:14:24,656 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=74744435, jitterRate=0.11377887427806854}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-02T17:14:24,658 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-02T17:14:24,667 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:meta,,1.1588230740, pid=3, masterSystemTime=1733159664530 2024-12-02T17:14:24,678 DEBUG [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:meta,,1.1588230740 2024-12-02T17:14:24,678 INFO [RS_OPEN_META-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(164): Opened hbase:meta,,1.1588230740 2024-12-02T17:14:24,679 INFO [PEWorker-4 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPEN, openSeqNum=2, regionLocation=fa731d6f0321,40509,1733159661070 2024-12-02T17:14:24,681 INFO [PEWorker-4 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as fa731d6f0321,40509,1733159661070, state=OPEN 2024-12-02T17:14:24,760 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-02T17:14:24,760 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-02T17:14:24,760 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-02T17:14:24,760 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-02T17:14:24,768 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=3, resume processing ppid=2 2024-12-02T17:14:24,769 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=3, ppid=2, state=SUCCESS; OpenRegionProcedure 1588230740, server=fa731d6f0321,40509,1733159661070 in 398 msec 2024-12-02T17:14:24,774 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=2, resume processing ppid=1 2024-12-02T17:14:24,774 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=2, ppid=1, state=SUCCESS; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN in 661 msec 2024-12-02T17:14:24,779 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=1, state=SUCCESS; InitMetaProcedure table=hbase:meta in 1.5970 sec 2024-12-02T17:14:24,779 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(1088): Wait for region servers to report in: status=status unset, state=RUNNING, startTime=1733159664779, completionTime=-1 2024-12-02T17:14:24,779 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.ServerManager(907): Finished waiting on RegionServer count=1; waited=0ms, expected min=1 server(s), max=1 server(s), master is running 2024-12-02T17:14:24,779 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] assignment.AssignmentManager(1747): Joining cluster... 2024-12-02T17:14:24,810 DEBUG [hconnection-0x4803368e-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:14:24,812 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:51642, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:14:24,821 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] assignment.AssignmentManager(1759): Number of RegionServers=1 2024-12-02T17:14:24,821 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$RegionInTransitionChore; timeout=60000, timestamp=1733159724821 2024-12-02T17:14:24,821 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$DeadServerMetricRegionChore; timeout=120000, timestamp=1733159784821 2024-12-02T17:14:24,822 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] assignment.AssignmentManager(1766): Joined the cluster in 42 msec 2024-12-02T17:14:24,948 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,45999,1733159660197-ClusterStatusChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:24,948 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,45999,1733159660197-BalancerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:24,949 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,45999,1733159660197-RegionNormalizerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:24,951 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=CatalogJanitor-fa731d6f0321:45999, period=300000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:24,952 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HbckChore-, period=3600000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:24,958 DEBUG [master/fa731d6f0321:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-02T17:14:24,962 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.TableNamespaceManager(92): Namespace table not found. Creating... 2024-12-02T17:14:24,963 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(2425): Client=null/null create 'hbase:namespace', {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '10', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'} 2024-12-02T17:14:24,970 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION; CreateTableProcedure table=hbase:namespace 2024-12-02T17:14:24,973 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_PRE_OPERATION 2024-12-02T17:14:24,974 DEBUG [PEWorker-2 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:24,976 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_WRITE_FS_LAYOUT, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_WRITE_FS_LAYOUT 2024-12-02T17:14:24,986 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741835_1011 (size=358) 2024-12-02T17:14:25,397 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(7106): creating {ENCODED => 75b753686f65c916787e2c95f48b987c, NAME => 'hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c.', STARTKEY => '', ENDKEY => ''}, tableDescriptor='hbase:namespace', {TABLE_ATTRIBUTES => {METADATA => {'hbase.store.file-tracker.impl' => 'DEFAULT'}}}, {NAME => 'info', INDEX_BLOCK_ENCODING => 'NONE', VERSIONS => '10', KEEP_DELETED_CELLS => 'FALSE', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', IN_MEMORY => 'true', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE => '8192 B (8KB)'}, regionDir=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6 2024-12-02T17:14:25,412 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741836_1012 (size=42) 2024-12-02T17:14:25,815 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(894): Instantiated hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-02T17:14:25,815 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1681): Closing 75b753686f65c916787e2c95f48b987c, disabling compactions & flushes 2024-12-02T17:14:25,815 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1703): Closing region hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:25,815 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:25,815 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1791): Acquired close lock on hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. after waiting 0 ms 2024-12-02T17:14:25,815 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1801): Updates disabled for region hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:25,815 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1922): Closed hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:25,816 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1635): Region close journal for 75b753686f65c916787e2c95f48b987c: 2024-12-02T17:14:25,818 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_ADD_TO_META, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_ADD_TO_META 2024-12-02T17:14:25,827 DEBUG [PEWorker-2 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":2,"row":"hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c.","families":{"info":[{"qualifier":"regioninfo","vlen":41,"tag":[],"timestamp":"1733159665820"},{"qualifier":"state","vlen":6,"tag":[],"timestamp":"1733159665820"}]},"ts":"1733159665820"} 2024-12-02T17:14:25,846 INFO [PEWorker-2 {}] hbase.MetaTableAccessor(1516): Added 1 regions to meta. 2024-12-02T17:14:25,849 INFO [PEWorker-2 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_ASSIGN_REGIONS, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_ASSIGN_REGIONS 2024-12-02T17:14:25,852 DEBUG [PEWorker-2 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1733159665849"}]},"ts":"1733159665849"} 2024-12-02T17:14:25,856 INFO [PEWorker-2 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLING in hbase:meta 2024-12-02T17:14:25,875 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:namespace, region=75b753686f65c916787e2c95f48b987c, ASSIGN}] 2024-12-02T17:14:25,879 INFO [PEWorker-3 {}] procedure.MasterProcedureScheduler(786): Took xlock for pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:namespace, region=75b753686f65c916787e2c95f48b987c, ASSIGN 2024-12-02T17:14:25,882 INFO [PEWorker-3 {}] assignment.TransitRegionStateProcedure(264): Starting pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE, locked=true; TransitRegionStateProcedure table=hbase:namespace, region=75b753686f65c916787e2c95f48b987c, ASSIGN; state=OFFLINE, location=fa731d6f0321,40509,1733159661070; forceNewPlan=false, retain=false 2024-12-02T17:14:26,033 INFO [PEWorker-4 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=75b753686f65c916787e2c95f48b987c, regionState=OPENING, regionLocation=fa731d6f0321,40509,1733159661070 2024-12-02T17:14:26,047 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=6, ppid=5, state=RUNNABLE; OpenRegionProcedure 75b753686f65c916787e2c95f48b987c, server=fa731d6f0321,40509,1733159661070}] 2024-12-02T17:14:26,200 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:26,207 INFO [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(135): Open hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:26,208 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7285): Opening region: {ENCODED => 75b753686f65c916787e2c95f48b987c, NAME => 'hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c.', STARTKEY => '', ENDKEY => ''} 2024-12-02T17:14:26,208 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table namespace 75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,209 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(894): Instantiated hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-02T17:14:26,209 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7327): checking encryption for 75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,209 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7330): checking classloading for 75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,212 INFO [StoreOpener-75b753686f65c916787e2c95f48b987c-1 {}] regionserver.HStore(400): Created cacheConfig: cacheDataOnRead=true, cacheDataOnWrite=false, cacheIndexesOnWrite=false, cacheBloomsOnWrite=false, cacheEvictOnClose=false, cacheDataCompressed=false, prefetchOnOpen=false, for column family info of region 75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,215 INFO [StoreOpener-75b753686f65c916787e2c95f48b987c-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 75b753686f65c916787e2c95f48b987c columnFamilyName info 2024-12-02T17:14:26,215 DEBUG [StoreOpener-75b753686f65c916787e2c95f48b987c-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-02T17:14:26,216 INFO [StoreOpener-75b753686f65c916787e2c95f48b987c-1 {}] regionserver.HStore(327): Store=75b753686f65c916787e2c95f48b987c/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-02T17:14:26,218 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,218 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,223 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1085): writing seq id for 75b753686f65c916787e2c95f48b987c 2024-12-02T17:14:26,227 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-02T17:14:26,228 INFO [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1102): Opened 75b753686f65c916787e2c95f48b987c; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=64287781, jitterRate=-0.04203741252422333}}}, FlushLargeStoresPolicy{flushSizeLowerBound=-1} 2024-12-02T17:14:26,229 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1001): Region open journal for 75b753686f65c916787e2c95f48b987c: 2024-12-02T17:14:26,231 INFO [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c., pid=6, masterSystemTime=1733159666199 2024-12-02T17:14:26,235 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:26,235 INFO [RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(164): Opened hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. 2024-12-02T17:14:26,236 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=75b753686f65c916787e2c95f48b987c, regionState=OPEN, openSeqNum=2, regionLocation=fa731d6f0321,40509,1733159661070 2024-12-02T17:14:26,246 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=6, resume processing ppid=5 2024-12-02T17:14:26,248 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=6, ppid=5, state=SUCCESS; OpenRegionProcedure 75b753686f65c916787e2c95f48b987c, server=fa731d6f0321,40509,1733159661070 in 194 msec 2024-12-02T17:14:26,253 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=5, resume processing ppid=4 2024-12-02T17:14:26,254 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=5, ppid=4, state=SUCCESS; TransitRegionStateProcedure table=hbase:namespace, region=75b753686f65c916787e2c95f48b987c, ASSIGN in 372 msec 2024-12-02T17:14:26,255 INFO [PEWorker-3 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_UPDATE_DESC_CACHE, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_UPDATE_DESC_CACHE 2024-12-02T17:14:26,256 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1733159666256"}]},"ts":"1733159666256"} 2024-12-02T17:14:26,259 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLED in hbase:meta 2024-12-02T17:14:26,272 INFO [PEWorker-3 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_POST_OPERATION, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_POST_OPERATION 2024-12-02T17:14:26,274 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKUtil(113): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/namespace 2024-12-02T17:14:26,276 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=4, state=SUCCESS; CreateTableProcedure table=hbase:namespace in 1.3080 sec 2024-12-02T17:14:26,286 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:26,286 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/namespace 2024-12-02T17:14:26,286 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:26,312 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=7, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=default 2024-12-02T17:14:26,336 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-02T17:14:26,352 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=7, state=SUCCESS; CreateNamespaceProcedure, namespace=default in 39 msec 2024-12-02T17:14:26,358 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=8, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=hbase 2024-12-02T17:14:26,386 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-02T17:14:26,398 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=8, state=SUCCESS; CreateNamespaceProcedure, namespace=hbase in 40 msec 2024-12-02T17:14:26,419 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/default 2024-12-02T17:14:26,436 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/hbase 2024-12-02T17:14:26,436 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(1218): Master has completed initialization 5.197sec 2024-12-02T17:14:26,439 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] quotas.MasterQuotaManager(97): Quota support disabled 2024-12-02T17:14:26,441 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] slowlog.SlowLogMasterService(57): Slow/Large requests logging to system table hbase:slowlog is disabled. Quitting. 2024-12-02T17:14:26,442 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] waleventtracker.WALEventTrackerTableCreator(75): wal event tracker requests logging to table REPLICATION.WALEVENTTRACKER is disabled. Quitting. 2024-12-02T17:14:26,443 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] master.ReplicationSinkTrackerTableCreator(90): replication sink tracker requests logging to table REPLICATION.SINK_TRACKER is disabled. Quitting. 2024-12-02T17:14:26,443 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] zookeeper.ZKWatcher(271): not a secure deployment, proceeding 2024-12-02T17:14:26,445 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,45999,1733159660197-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-02T17:14:26,446 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,45999,1733159660197-MobFileCompactionChore, period=604800, unit=SECONDS is enabled. 2024-12-02T17:14:26,454 DEBUG [master/fa731d6f0321:0:becomeActiveMaster {}] master.HMaster(1321): Balancer post startup initialization complete, took 0 seconds 2024-12-02T17:14:26,454 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=RollingUpgradeChore, period=10, unit=SECONDS is enabled. 2024-12-02T17:14:26,455 INFO [master/fa731d6f0321:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=fa731d6f0321,45999,1733159660197-OldWALsDirSizeChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-02T17:14:26,465 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x706227a7 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7551e6f8 2024-12-02T17:14:26,466 WARN [Time-limited test {}] client.ZKConnectionRegistry(90): ZKConnectionRegistry is deprecated. See https://hbase.apache.org/book.html#client.rpcconnectionregistry 2024-12-02T17:14:26,480 DEBUG [Time-limited test {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@695b47c0, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:26,485 DEBUG [Time-limited test {}] nio.NioEventLoop(110): -Dio.netty.noKeySetOptimization: false 2024-12-02T17:14:26,485 DEBUG [Time-limited test {}] nio.NioEventLoop(111): -Dio.netty.selectorAutoRebuildThreshold: 512 2024-12-02T17:14:26,494 DEBUG [hconnection-0xa8f0dca-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:14:26,501 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:51656, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:14:26,509 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1199): Minicluster is up; activeMaster=fa731d6f0321,45999,1733159660197 2024-12-02T17:14:26,510 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x047c7384 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@446c9b12 2024-12-02T17:14:26,522 DEBUG [ReadOnlyZKClient-127.0.0.1:60462@0x047c7384 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@57518d5d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:26,538 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=222, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=170, ProcessCount=11, AvailableMemoryMB=7717 2024-12-02T17:14:26,580 DEBUG [Time-limited test {}] client.ConnectionUtils(573): Start fetching master stub from registry 2024-12-02T17:14:26,581 DEBUG [ReadOnlyZKClient-127.0.0.1:60462@0x047c7384 {}] client.AsyncConnectionImpl(310): The fetched master address is fa731d6f0321,45999,1733159660197 2024-12-02T17:14:26,583 DEBUG [ReadOnlyZKClient-127.0.0.1:60462@0x047c7384 {}] client.ConnectionUtils(581): The fetched master stub is org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$Stub@77d0d7f 2024-12-02T17:14:26,585 DEBUG [ReadOnlyZKClient-127.0.0.1:60462@0x047c7384 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=MasterService, sasl=false 2024-12-02T17:14:26,587 INFO [RS-EventLoopGroup-1-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:56058, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=MasterService 2024-12-02T17:14:26,591 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:26,598 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=9, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:26,603 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-02T17:14:26,616 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:26,617 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:26,628 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:26,628 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0004 connected 2024-12-02T17:14:26,712 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-02T17:14:26,737 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0004, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:26,769 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:26,769 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-02T17:14:26,798 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=10, ppid=9, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:26,921 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-02T17:14:26,960 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:26,961 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=10 2024-12-02T17:14:26,962 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:26,983 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=10}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:27,012 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:27,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=10 2024-12-02T17:14:27,081 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=10 2024-12-02T17:14:27,085 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:27,088 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=10, resume processing ppid=9 2024-12-02T17:14:27,088 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:27,088 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=10, ppid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 287 msec 2024-12-02T17:14:27,090 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 495 msec 2024-12-02T17:14:27,123 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x062bfb45 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7b86ff10 2024-12-02T17:14:27,137 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:27,138 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:27,138 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@415e041, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:27,140 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:27,148 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:27,148 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:27,148 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0006 connected 2024-12-02T17:14:27,231 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-02T17:14:27,232 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:27,235 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:27,238 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=11, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:27,240 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-02T17:14:27,254 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:27,255 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:27,264 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:27,265 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0007 connected 2024-12-02T17:14:27,351 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-02T17:14:27,373 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0007, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:27,389 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=12, ppid=11, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:27,544 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:27,545 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=12 2024-12-02T17:14:27,546 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:27,548 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:27,548 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:27,548 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:27,548 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0006, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:27,549 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0006, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:27,561 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-02T17:14:27,669 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0006, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:27,670 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x062bfb45 to 127.0.0.1:60462 2024-12-02T17:14:27,670 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:27,685 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:27,685 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:27,686 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=12 2024-12-02T17:14:27,686 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=12 2024-12-02T17:14:27,689 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:27,692 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=12, resume processing ppid=11 2024-12-02T17:14:27,692 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:27,692 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=12, ppid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 301 msec 2024-12-02T17:14:27,694 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 457 msec 2024-12-02T17:14:27,720 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7d85a016 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3eaceaef 2024-12-02T17:14:27,732 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:27,732 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:27,733 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5b1ab6bb, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:27,735 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:27,744 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:27,745 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:27,745 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0009 connected 2024-12-02T17:14:27,871 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-02T17:14:27,872 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:27,876 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:27,878 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:27,879 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:27,883 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-02T17:14:27,885 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=13, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:27,886 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-02T17:14:27,902 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:27,904 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:27,915 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:27,915 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d000a connected 2024-12-02T17:14:27,992 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-02T17:14:28,023 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d000a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:28,058 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=14, ppid=13, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:28,201 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-02T17:14:28,212 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:28,213 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=14 2024-12-02T17:14:28,213 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:28,214 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:28,214 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:28,215 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:28,215 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0009, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:28,215 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0009, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:28,323 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0009, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:28,323 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7d85a016 to 127.0.0.1:60462 2024-12-02T17:14:28,323 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:28,344 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:28,344 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:28,344 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=14 2024-12-02T17:14:28,345 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=14 2024-12-02T17:14:28,347 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:28,350 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=14, resume processing ppid=13 2024-12-02T17:14:28,350 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-02T17:14:28,351 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=14, ppid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-02T17:14:28,353 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 468 msec 2024-12-02T17:14:28,371 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x42a1cb46 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1e0919aa 2024-12-02T17:14:28,381 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:28,382 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:28,382 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6192076a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:28,384 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:28,394 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:28,395 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:28,395 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d000c connected 2024-12-02T17:14:28,511 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-02T17:14:28,512 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:28,512 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:28,514 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:28,515 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:28,516 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:28,518 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-02T17:14:28,519 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=15, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:28,520 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-02T17:14:28,535 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:28,536 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:28,544 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:28,545 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d000d connected 2024-12-02T17:14:28,630 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-02T17:14:28,653 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d000d, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:28,666 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=16, ppid=15, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:28,820 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:28,821 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=16 2024-12-02T17:14:28,821 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:28,822 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:28,822 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:28,822 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:28,823 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d000c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:28,823 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d000c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:28,840 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-02T17:14:28,931 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d000c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:28,931 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x42a1cb46 to 127.0.0.1:60462 2024-12-02T17:14:28,932 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:28,948 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:28,948 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:28,948 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=16 2024-12-02T17:14:28,949 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=16 2024-12-02T17:14:28,952 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:28,956 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=16, resume processing ppid=15 2024-12-02T17:14:28,956 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-02T17:14:28,956 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=16, ppid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-02T17:14:28,958 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 438 msec 2024-12-02T17:14:28,974 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6a2cd7ad to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@58c77067 2024-12-02T17:14:28,986 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:28,987 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:28,987 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@52609766, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:28,988 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:28,998 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:28,998 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:28,998 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d000f connected 2024-12-02T17:14:29,150 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-02T17:14:29,151 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:29,151 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:29,152 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:29,153 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:29,154 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:29,156 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=17, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:29,157 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-02T17:14:29,174 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:29,175 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:29,186 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:29,186 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0010 connected 2024-12-02T17:14:29,261 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-02T17:14:29,295 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0010, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:29,308 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=18, ppid=17, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:29,458 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:meta' 2024-12-02T17:14:29,459 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:namespace' 2024-12-02T17:14:29,461 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:29,462 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=18 2024-12-02T17:14:29,463 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:29,464 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:29,464 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:29,464 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:29,464 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d000f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:29,464 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d000f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:29,471 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-02T17:14:29,573 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d000f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:29,573 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6a2cd7ad to 127.0.0.1:60462 2024-12-02T17:14:29,573 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:29,594 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:29,594 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:29,595 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=18 2024-12-02T17:14:29,596 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=18 2024-12-02T17:14:29,599 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:29,603 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:29,603 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=18, resume processing ppid=17 2024-12-02T17:14:29,603 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=18, ppid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 292 msec 2024-12-02T17:14:29,607 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 449 msec 2024-12-02T17:14:29,632 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7dcb7ce4 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5286ccc4 2024-12-02T17:14:29,648 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:29,649 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:29,649 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@12767fb3, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:29,650 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:29,661 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:29,661 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:29,662 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0012 connected 2024-12-02T17:14:29,781 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-02T17:14:29,782 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:29,783 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:29,785 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:29,786 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-02T17:14:29,788 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=19, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:29,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-02T17:14:29,810 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:29,812 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:29,823 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:29,823 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0013 connected 2024-12-02T17:14:29,901 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-02T17:14:29,936 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0013, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:29,950 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=20, ppid=19, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:30,103 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:30,105 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=20 2024-12-02T17:14:30,105 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:30,109 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:30,109 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:30,109 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:30,110 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0012, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:30,110 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0012, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:30,112 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-02T17:14:30,144 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:14:30,220 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0012, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:30,220 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7dcb7ce4 to 127.0.0.1:60462 2024-12-02T17:14:30,220 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:30,237 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:30,238 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:30,238 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=20 2024-12-02T17:14:30,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=20 2024-12-02T17:14:30,241 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:30,244 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=20, resume processing ppid=19 2024-12-02T17:14:30,244 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-02T17:14:30,244 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=20, ppid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 291 msec 2024-12-02T17:14:30,246 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 458 msec 2024-12-02T17:14:30,263 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x018df1f1 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1dbddd0a 2024-12-02T17:14:30,273 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:30,274 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:30,274 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2f03fa4, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:30,275 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:30,286 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:30,286 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:30,286 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0015 connected 2024-12-02T17:14:30,421 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-02T17:14:30,421 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:30,422 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:30,423 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:30,424 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=21, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:30,426 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-02T17:14:30,442 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:30,443 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:30,453 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:30,453 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0016 connected 2024-12-02T17:14:30,531 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-02T17:14:30,561 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0016, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:30,575 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=22, ppid=21, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:30,605 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_meta 2024-12-02T17:14:30,605 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_meta Metrics about Tables on a single HBase RegionServer 2024-12-02T17:14:30,607 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_namespace 2024-12-02T17:14:30,607 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_namespace Metrics about Tables on a single HBase RegionServer 2024-12-02T17:14:30,607 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint 2024-12-02T17:14:30,607 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint Metrics about HBase RegionObservers 2024-12-02T17:14:30,608 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_master_table_store 2024-12-02T17:14:30,608 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_master_table_store Metrics about Tables on a single HBase RegionServer 2024-12-02T17:14:30,729 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:30,729 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=22 2024-12-02T17:14:30,730 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:30,731 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:30,731 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:30,731 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:30,731 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0015, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:30,732 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0015, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:30,741 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-02T17:14:30,839 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0015, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:30,840 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x018df1f1 to 127.0.0.1:60462 2024-12-02T17:14:30,840 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:30,856 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:30,857 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:30,857 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=22 2024-12-02T17:14:30,857 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=22 2024-12-02T17:14:30,860 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:30,863 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=22, resume processing ppid=21 2024-12-02T17:14:30,863 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:30,863 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=22, ppid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-02T17:14:30,865 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 440 msec 2024-12-02T17:14:30,882 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x401e3154 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2c307f79 2024-12-02T17:14:30,895 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:30,895 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:30,895 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@34efcdca, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:30,897 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:30,906 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:30,906 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:30,906 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0018 connected 2024-12-02T17:14:31,050 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-02T17:14:31,051 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:31,051 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:31,054 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:31,054 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:31,058 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:31,058 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=24, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:31,060 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:31,060 DEBUG [PEWorker-1 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=24 2024-12-02T17:14:31,060 DEBUG [PEWorker-1 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:31,062 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:31,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-02T17:14:31,073 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:31,073 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:31,074 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:31,076 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=25, ppid=24, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:31,171 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:31,171 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-02T17:14:31,234 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:31,235 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=25 2024-12-02T17:14:31,235 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:31,235 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:31,235 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:31,235 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:31,235 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0018, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:31,236 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0018, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:31,345 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0018, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:31,345 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x401e3154 to 127.0.0.1:60462 2024-12-02T17:14:31,345 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:31,346 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:31,366 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:31,378 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:31,378 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:31,378 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:31,380 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:31,380 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=25 2024-12-02T17:14:31,381 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:31,381 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=25 2024-12-02T17:14:31,381 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-02T17:14:31,385 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:31,387 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=25, resume processing ppid=24 2024-12-02T17:14:31,387 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=25, ppid=24, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 309 msec 2024-12-02T17:14:31,403 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:31,403 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:31,405 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=24, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 348 msec 2024-12-02T17:14:31,691 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:31,691 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-02T17:14:31,691 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:31,692 INFO [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:31,693 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=26, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:31,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-02T17:14:31,695 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:31,701 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=26, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:31,703 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=26, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=10 msec 2024-12-02T17:14:31,703 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:31,801 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-02T17:14:31,802 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:31,803 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=testing utility connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:31,845 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): testing utility0x0, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:31,845 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): testing utility-0x10198534a1d0019 connected 2024-12-02T17:14:31,871 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=223 (was 222) Potentially hanging thread: RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RPCClient-NioEventLoopGroup-4-2 java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) app//org.apache.hbase.thirdparty.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:62) app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:883) app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RSProcedureDispatcher-pool-2 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1061) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: ForkJoinPool.commonPool-worker-1 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkUntil(LockSupport.java:410) java.base@17.0.11/java.util.concurrent.ForkJoinPool.awaitWork(ForkJoinPool.java:1726) java.base@17.0.11/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1623) java.base@17.0.11/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:165) Potentially hanging thread: RS-EventLoopGroup-1-3 app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: Timer for 'HBase' metrics system java.base@17.0.11/java.lang.Object.wait(Native Method) java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) - Thread LEAK? -, OpenFileDescriptor=452 (was 448) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=164 (was 170), ProcessCount=11 (was 11), AvailableMemoryMB=7637 (was 7717) 2024-12-02T17:14:31,879 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223, OpenFileDescriptor=452, MaxFileDescriptor=1048576, SystemLoadAverage=164, ProcessCount=11, AvailableMemoryMB=7637 2024-12-02T17:14:31,880 INFO [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:31,881 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=27, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:31,882 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-02T17:14:31,899 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:31,900 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:31,919 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:31,920 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d001a connected 2024-12-02T17:14:31,991 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-02T17:14:32,070 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d001a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:32,095 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=28, ppid=27, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:32,201 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:32,201 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-02T17:14:32,248 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:32,250 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=28 2024-12-02T17:14:32,250 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:32,271 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=28}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:32,283 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:32,356 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=28 2024-12-02T17:14:32,357 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=28 2024-12-02T17:14:32,360 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:32,363 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=28, resume processing ppid=27 2024-12-02T17:14:32,363 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:32,363 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=28, ppid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 265 msec 2024-12-02T17:14:32,365 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 483 msec 2024-12-02T17:14:32,381 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x503c6aa2 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@51615a66 2024-12-02T17:14:32,390 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:32,391 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:32,391 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7487c71c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:32,393 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:32,402 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:32,403 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:32,403 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d001c connected 2024-12-02T17:14:32,511 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-02T17:14:32,511 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:32,512 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:32,513 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=29, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:32,514 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-02T17:14:32,527 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:32,528 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:32,583 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:32,584 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d001d connected 2024-12-02T17:14:32,621 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-02T17:14:32,719 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d001d, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:32,758 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=30, ppid=29, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:32,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-02T17:14:32,910 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:32,911 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=30 2024-12-02T17:14:32,911 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:32,912 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:32,912 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:32,913 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:32,913 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d001c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:32,913 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d001c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:33,056 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d001c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:33,056 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x503c6aa2 to 127.0.0.1:60462 2024-12-02T17:14:33,057 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:33,072 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:33,072 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:33,073 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=30 2024-12-02T17:14:33,073 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=30 2024-12-02T17:14:33,076 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:33,079 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=30, resume processing ppid=29 2024-12-02T17:14:33,079 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:33,080 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=30, ppid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 318 msec 2024-12-02T17:14:33,082 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 568 msec 2024-12-02T17:14:33,101 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x071e9dec to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@37936f4a 2024-12-02T17:14:33,141 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-02T17:14:33,142 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:33,142 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:33,143 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-02T17:14:33,145 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=31, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:33,146 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-02T17:14:33,162 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:33,162 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:33,162 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@66176979, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:33,162 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:33,163 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:33,163 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:33,198 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:33,203 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d001f connected 2024-12-02T17:14:33,221 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:33,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-02T17:14:33,263 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:33,263 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:33,264 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0020 connected 2024-12-02T17:14:33,415 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d001f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:33,461 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-02T17:14:33,468 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=32, ppid=31, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:33,621 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:33,622 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=32 2024-12-02T17:14:33,622 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:33,623 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:33,623 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:33,623 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:33,623 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0020, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:33,624 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0020, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:33,771 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-02T17:14:33,776 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0020, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:33,776 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x071e9dec to 127.0.0.1:60462 2024-12-02T17:14:33,777 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:33,794 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:33,795 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:33,795 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=32 2024-12-02T17:14:33,796 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=32 2024-12-02T17:14:33,798 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:33,800 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=32, resume processing ppid=31 2024-12-02T17:14:33,800 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=32, ppid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 331 msec 2024-12-02T17:14:33,800 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-02T17:14:33,802 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 657 msec 2024-12-02T17:14:33,820 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x575e5c15 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@c23719c 2024-12-02T17:14:33,848 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:33,849 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:33,849 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7b91931f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:33,850 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:33,862 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:33,871 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:33,873 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0022 connected 2024-12-02T17:14:34,280 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-02T17:14:34,281 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:34,281 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:34,282 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns1:testNamespacesAndTableCfsConfigConflict1=null},bandwidth=0,serial=false 2024-12-02T17:14:34,284 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=33, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:34,285 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-02T17:14:34,297 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:34,298 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:34,311 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:34,311 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0023 connected 2024-12-02T17:14:34,390 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-02T17:14:34,428 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0023, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:34,428 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:34,430 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=33, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:34,432 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=33, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure exec-time=148 msec 2024-12-02T17:14:34,432 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:34,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-02T17:14:34,602 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 failed with Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config 2024-12-02T17:14:34,602 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:34,604 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-02T17:14:34,606 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=34, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:34,610 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-02T17:14:34,622 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:34,622 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:34,631 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:34,631 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0024 connected 2024-12-02T17:14:34,721 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-02T17:14:34,739 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0024, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:34,749 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=35, ppid=34, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:34,862 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 2000 millis 2024-12-02T17:14:34,901 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:34,902 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=35 2024-12-02T17:14:34,902 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:34,904 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:34,904 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:34,904 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:34,904 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0022, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:34,904 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0022, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:34,931 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-02T17:14:35,015 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0022, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:35,015 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x575e5c15 to 127.0.0.1:60462 2024-12-02T17:14:35,015 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:35,034 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:35,034 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:35,034 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=35 2024-12-02T17:14:35,035 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=35 2024-12-02T17:14:35,037 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:35,041 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=35, resume processing ppid=34 2024-12-02T17:14:35,041 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-02T17:14:35,041 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=35, ppid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-12-02T17:14:35,043 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 437 msec 2024-12-02T17:14:35,064 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3eeb847c to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@574d5c8b 2024-12-02T17:14:35,073 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:35,074 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:35,074 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@24d93473, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:35,075 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:35,086 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:35,086 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:35,086 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0026 connected 2024-12-02T17:14:35,232 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:35,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-02T17:14:35,241 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:35,243 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:35,246 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-02T17:14:35,248 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=36, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:35,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-02T17:14:35,262 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:35,263 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:35,273 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:35,273 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0027 connected 2024-12-02T17:14:35,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-02T17:14:35,381 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0027, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:35,381 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:35,383 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=36, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:35,384 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=36, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure exec-time=137 msec 2024-12-02T17:14:35,384 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:35,571 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-02T17:14:35,572 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 failed with Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config 2024-12-02T17:14:35,572 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:35,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=37, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:35,575 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-02T17:14:35,579 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:35,589 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:35,590 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:35,590 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:35,591 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=38, ppid=37, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:35,682 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-02T17:14:35,743 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:35,744 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=38 2024-12-02T17:14:35,744 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:35,745 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:35,745 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:35,745 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:35,745 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0026, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:35,745 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0026, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:35,857 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0026, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:35,857 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3eeb847c to 127.0.0.1:60462 2024-12-02T17:14:35,857 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:35,858 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:35,870 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:35,877 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:35,877 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:35,877 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:35,878 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:35,878 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=38 2024-12-02T17:14:35,879 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=38 2024-12-02T17:14:35,880 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:35,883 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=38, resume processing ppid=37 2024-12-02T17:14:35,883 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=38, ppid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-02T17:14:35,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-02T17:14:35,895 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:35,895 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:35,898 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 323 msec 2024-12-02T17:14:36,201 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-02T17:14:36,202 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:36,202 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:36,204 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=39, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:36,206 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-02T17:14:36,206 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:36,208 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=39, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:36,209 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=39, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-02T17:14:36,209 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:36,311 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-02T17:14:36,311 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:36,312 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:36,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=40, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:36,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-02T17:14:36,314 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:36,316 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=40, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:36,317 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=40, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:36,317 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:36,421 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-02T17:14:36,422 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:36,441 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=220 (was 223), OpenFileDescriptor=448 (was 452), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=207 (was 164) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=7559 (was 7637) 2024-12-02T17:14:36,453 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=220, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=207, ProcessCount=11, AvailableMemoryMB=7559 2024-12-02T17:14:36,454 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:36,455 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=41, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:36,456 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-02T17:14:36,471 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:36,472 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:36,486 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:36,486 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0028 connected 2024-12-02T17:14:36,560 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-02T17:14:36,602 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0028, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:36,624 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=42, ppid=41, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:36,771 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-02T17:14:36,777 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:36,778 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=42 2024-12-02T17:14:36,778 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:36,799 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=42}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:36,810 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:36,848 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:14:36,852 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=42 2024-12-02T17:14:36,853 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=42 2024-12-02T17:14:36,857 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:36,865 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=42, resume processing ppid=41 2024-12-02T17:14:36,865 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:36,865 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=42, ppid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 233 msec 2024-12-02T17:14:36,868 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 411 msec 2024-12-02T17:14:36,896 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x10801db7 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4bfbe716 2024-12-02T17:14:36,931 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:36,932 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:36,932 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@749a4045, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:36,933 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:36,944 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:36,945 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:36,947 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d002a connected 2024-12-02T17:14:37,081 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-02T17:14:37,081 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:37,082 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:37,083 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=43, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:37,085 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-02T17:14:37,106 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:37,107 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:37,138 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:37,139 ERROR [PEWorker-1-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f6a848d4010@2325ffad rejected from java.util.concurrent.ThreadPoolExecutor@662765ad[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2065) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:833) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1365) ~[?:?] at java.util.concurrent.Executors$DelegatedExecutorService.execute(Executors.java:721) ~[?:?] at org.apache.hadoop.hbase.zookeeper.ZKWatcher.process(ZKWatcher.java:613) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:38) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:579) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-12-02T17:14:37,191 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-02T17:14:37,253 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:37,253 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:37,254 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=43, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:37,256 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=43, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=173 msec 2024-12-02T17:14:37,256 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:37,400 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-02T17:14:37,401 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Replication peer 1 already exists 2024-12-02T17:14:37,405 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:37,409 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:37,410 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=44, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:37,411 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-02T17:14:37,411 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:37,412 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=44, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:37,414 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=44, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:37,414 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:37,520 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-02T17:14:37,521 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:37,522 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:37,523 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=127.0.0.1:60462:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:37,524 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=45, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:37,525 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-02T17:14:37,546 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:37,547 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:37,586 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:37,587 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d002c connected 2024-12-02T17:14:37,630 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-02T17:14:37,698 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d002c, quorum=127.0.0.1:60462, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:37,721 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=46, ppid=45, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:37,841 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-02T17:14:37,874 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:37,875 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=46 2024-12-02T17:14:37,875 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=ADD_PEER 2024-12-02T17:14:37,892 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=46}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:37,909 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.ReplicationSource(229): queueId=2, ReplicationSource: 2, currentBandwidth=0 2024-12-02T17:14:37,936 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=46 2024-12-02T17:14:37,937 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=46 2024-12-02T17:14:37,940 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:37,944 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=46, resume processing ppid=45 2024-12-02T17:14:37,944 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 2, config clusterKey=127.0.0.1:60462:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:37,944 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=46, ppid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 219 msec 2024-12-02T17:14:37,945 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 2000 millis 2024-12-02T17:14:37,947 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 421 msec 2024-12-02T17:14:37,975 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2acf3e45 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@46769628 2024-12-02T17:14:37,986 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test2/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test2/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:37,987 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:37,990 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@326e4762, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:37,992 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 2 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:38,002 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 20x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:38,003 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] regionserver.ReplicationSource(569): peerId=2, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:38,003 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 2-0x10198534a1d002e connected 2024-12-02T17:14:38,151 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-02T17:14:38,151 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 2 completed 2024-12-02T17:14:38,152 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:38,153 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:38,154 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=47, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:38,155 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-02T17:14:38,157 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:38,164 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:38,164 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:38,165 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:38,166 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=48, ppid=47, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:38,261 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-02T17:14:38,319 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:38,320 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=48 2024-12-02T17:14:38,320 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:38,320 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:38,321 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:38,321 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:38,321 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d002a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:38,321 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d002a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:38,431 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d002a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:38,431 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x10801db7 to 127.0.0.1:60462 2024-12-02T17:14:38,431 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:38,432 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:38,440 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:38,448 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:38,448 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:38,448 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:38,448 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:38,448 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=48 2024-12-02T17:14:38,449 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=48 2024-12-02T17:14:38,451 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:38,455 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=48, resume processing ppid=47 2024-12-02T17:14:38,455 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=48, ppid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-02T17:14:38,471 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-02T17:14:38,473 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:38,473 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:38,475 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 320 msec 2024-12-02T17:14:38,781 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-02T17:14:38,782 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:38,782 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:38,783 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:38,785 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=49, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:38,786 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-02T17:14:38,789 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/2/peer-state 2024-12-02T17:14:38,827 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2/peer-state 2024-12-02T17:14:38,827 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-02T17:14:38,827 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-02T17:14:38,829 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=50, ppid=49, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:38,891 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-02T17:14:38,982 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:38,983 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=50 2024-12-02T17:14:38,983 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=REMOVE_PEER 2024-12-02T17:14:38,983 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 2: 0 2024-12-02T17:14:38,983 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSource(657): peerId=2, Closing source 2 because: Replication stream was removed by a user 2024-12-02T17:14:38,983 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] regionserver.ReplicationSource(508): peerId=2, Interrupted while sleeping between retries 2024-12-02T17:14:38,983 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] zookeeper.ZKUtil(165): connection to cluster: 2-0x10198534a1d002e, quorum=127.0.0.1:60462, baseZNode=/hbase-test2 Unable to set watcher on znode (/hbase-test2/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:38,984 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2 {}] zookeeper.ZKWatcher(734): connection to cluster: 2-0x10198534a1d002e, quorum=127.0.0.1:60462, baseZNode=/hbase-test2 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:39,094 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 2-0x10198534a1d002e, quorum=127.0.0.1:60462, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:39,094 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2acf3e45 to 127.0.0.1:60462 2024-12-02T17:14:39,094 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:39,095 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(430): Done with the queue 2 2024-12-02T17:14:39,101 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-02T17:14:39,102 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/2/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:39,111 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/2/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:39,111 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/2 2024-12-02T17:14:39,111 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/2 2024-12-02T17:14:39,111 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-02T17:14:39,111 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=50 2024-12-02T17:14:39,112 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=50 2024-12-02T17:14:39,115 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:39,117 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=50, resume processing ppid=49 2024-12-02T17:14:39,118 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=50, ppid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-02T17:14:39,128 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-02T17:14:39,128 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 2 2024-12-02T17:14:39,130 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 345 msec 2024-12-02T17:14:39,260 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:39,411 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-02T17:14:39,411 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 2 completed 2024-12-02T17:14:39,412 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:39,412 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:39,414 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=51, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:39,415 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-02T17:14:39,416 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:39,417 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=51, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:39,419 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=51, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-02T17:14:39,419 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:39,521 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-02T17:14:39,522 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:39,522 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:39,523 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=52, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:39,524 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-02T17:14:39,525 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:39,526 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=52, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:39,528 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=52, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:39,528 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:39,631 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-02T17:14:39,631 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:39,645 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=220 (was 220), OpenFileDescriptor=444 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=230 (was 207) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=7512 (was 7559) 2024-12-02T17:14:39,656 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=230, ProcessCount=11, AvailableMemoryMB=7511 2024-12-02T17:14:39,657 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=whatever,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:39,658 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=53, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:39,659 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-02T17:14:39,660 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:291) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.lang.ClassNotFoundException: whatever at jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641) ~[?:?] at jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188) ~[?:?] at java.lang.ClassLoader.loadClass(ClassLoader.java:525) ~[?:?] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:288) ~[classes/:?] ... 12 more 2024-12-02T17:14:39,662 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=53, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:291) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.lang.ClassNotFoundException: whatever at jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641) ~[?:?] at jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188) ~[?:?] at java.lang.ClassLoader.loadClass(ClassLoader.java:525) ~[?:?] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:288) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:39,663 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=53, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=5 msec 2024-12-02T17:14:39,663 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:39,771 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-02T17:14:39,772 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Can not instantiate configured replication endpoint class=whatever 2024-12-02T17:14:39,777 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:39,778 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=54, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:39,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-02T17:14:39,779 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:39,780 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=54, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:39,782 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=54, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:39,782 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:39,891 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-02T17:14:39,892 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:39,893 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:39,894 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=55, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:39,895 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-02T17:14:39,895 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:39,896 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=55, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:39,898 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=55, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:39,898 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:40,002 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-02T17:14:40,002 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:40,020 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=220 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=230 (was 230), ProcessCount=11 (was 11), AvailableMemoryMB=7509 (was 7511) 2024-12-02T17:14:40,029 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=230, ProcessCount=11, AvailableMemoryMB=7509 2024-12-02T17:14:40,030 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=whatever,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:40,031 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=56, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:40,033 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-02T17:14:40,033 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.io.IOException: Cluster key passed whatever is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-12-02T17:14:40,035 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=56, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.io.IOException: Cluster key passed whatever is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:40,036 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=56, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=5 msec 2024-12-02T17:14:40,037 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:40,141 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-02T17:14:40,141 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Invalid cluster key: whatever 2024-12-02T17:14:40,142 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:40,143 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=57, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:40,144 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-02T17:14:40,144 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:40,146 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=57, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:40,147 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=57, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:40,147 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:40,251 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-02T17:14:40,251 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:40,252 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:40,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=58, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:40,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-02T17:14:40,254 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:40,255 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=58, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:40,256 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=58, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:40,257 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:40,362 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-02T17:14:40,364 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:40,381 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=220 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=230 (was 230), ProcessCount=11 (was 11), AvailableMemoryMB=7509 (was 7509) 2024-12-02T17:14:40,388 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=230, ProcessCount=11, AvailableMemoryMB=7509 2024-12-02T17:14:40,389 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:40,390 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=59, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:40,391 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-02T17:14:40,404 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:40,404 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:40,415 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:40,415 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d002f connected 2024-12-02T17:14:40,500 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-02T17:14:40,523 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d002f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:40,546 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=60, ppid=59, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:40,698 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:40,699 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=60 2024-12-02T17:14:40,699 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:40,711 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-02T17:14:40,720 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=60}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:40,741 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:40,786 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=60 2024-12-02T17:14:40,787 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=60 2024-12-02T17:14:40,789 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:40,792 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=60, resume processing ppid=59 2024-12-02T17:14:40,792 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:40,792 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=60, ppid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 244 msec 2024-12-02T17:14:40,794 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 403 msec 2024-12-02T17:14:40,834 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x07a68ab2 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5713c812 2024-12-02T17:14:40,861 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:40,861 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:40,862 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@746f204e, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:40,863 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:40,886 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:40,886 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:40,888 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0031 connected 2024-12-02T17:14:41,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-02T17:14:41,021 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:41,022 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:41,023 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=61, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:41,026 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-02T17:14:41,044 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:41,045 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:41,056 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:41,057 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0032 connected 2024-12-02T17:14:41,131 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-02T17:14:41,165 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0032, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:41,179 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=62, ppid=61, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:41,331 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:41,332 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=62 2024-12-02T17:14:41,332 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:41,334 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:41,334 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:41,335 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:41,335 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0031, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:41,336 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0031, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:41,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-02T17:14:41,567 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0031, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:41,568 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x07a68ab2 to 127.0.0.1:60462 2024-12-02T17:14:41,568 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:41,591 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:41,591 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:41,592 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=62 2024-12-02T17:14:41,592 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=62 2024-12-02T17:14:41,594 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:41,597 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=62, resume processing ppid=61 2024-12-02T17:14:41,597 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=62, ppid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 417 msec 2024-12-02T17:14:41,597 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:41,600 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 576 msec 2024-12-02T17:14:41,622 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7441085a to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2855de10 2024-12-02T17:14:41,632 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:41,632 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:41,633 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@30211f7, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:41,634 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:41,652 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-02T17:14:41,653 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:41,653 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:41,654 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-02T17:14:41,656 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=63, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:41,657 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-02T17:14:41,666 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:41,666 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:41,666 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0034 connected 2024-12-02T17:14:41,677 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:41,678 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:41,694 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:41,694 ERROR [PEWorker-1-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f6a848d4010@10d2acaf rejected from java.util.concurrent.ThreadPoolExecutor@14ed3a6d[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2065) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:833) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1365) ~[?:?] at java.util.concurrent.Executors$DelegatedExecutorService.execute(Executors.java:721) ~[?:?] at org.apache.hadoop.hbase.zookeeper.ZKWatcher.process(ZKWatcher.java:613) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:38) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:579) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-12-02T17:14:41,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-02T17:14:41,802 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:41,818 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=64, ppid=63, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:41,971 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-02T17:14:41,972 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:41,973 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=64 2024-12-02T17:14:41,973 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:41,975 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:41,975 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:41,975 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:41,975 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0034, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:41,975 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0034, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:42,086 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0034, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:42,086 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7441085a to 127.0.0.1:60462 2024-12-02T17:14:42,086 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:42,106 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:42,107 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:42,107 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=64 2024-12-02T17:14:42,108 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=64 2024-12-02T17:14:42,110 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:42,114 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=64, resume processing ppid=63 2024-12-02T17:14:42,114 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-02T17:14:42,114 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=64, ppid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 292 msec 2024-12-02T17:14:42,116 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 460 msec 2024-12-02T17:14:42,140 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6ddd6177 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@46c961a4 2024-12-02T17:14:42,153 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:42,154 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:42,154 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@79cb41e5, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:42,156 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:42,173 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:42,173 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:42,173 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0037 connected 2024-12-02T17:14:42,281 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-02T17:14:42,282 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:42,282 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:42,283 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:42,285 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-02T17:14:42,286 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=65, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:42,288 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-02T17:14:42,304 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:42,305 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:42,315 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:42,315 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0038 connected 2024-12-02T17:14:42,390 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-02T17:14:42,423 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0038, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:42,437 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=66, ppid=65, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:42,590 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:42,590 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=66 2024-12-02T17:14:42,591 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:42,592 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:42,592 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:42,592 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:42,593 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0037, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:42,593 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0037, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:42,601 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-02T17:14:42,703 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0037, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:42,703 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6ddd6177 to 127.0.0.1:60462 2024-12-02T17:14:42,703 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:42,726 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:42,726 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:42,726 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=66 2024-12-02T17:14:42,727 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=66 2024-12-02T17:14:42,735 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:42,739 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=66, resume processing ppid=65 2024-12-02T17:14:42,739 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-02T17:14:42,739 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=66, ppid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 298 msec 2024-12-02T17:14:42,742 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 454 msec 2024-12-02T17:14:42,778 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x42b55610 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2dc67824 2024-12-02T17:14:42,803 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:42,804 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:42,804 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7eaf75cf, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:42,805 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:42,815 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:42,815 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:42,815 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d003a connected 2024-12-02T17:14:42,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-02T17:14:42,912 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:42,912 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:42,915 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:42,917 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=67, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:42,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-02T17:14:42,922 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:42,931 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:42,931 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:42,931 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:42,932 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=68, ppid=67, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:43,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-02T17:14:43,085 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:43,086 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=68 2024-12-02T17:14:43,087 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:43,087 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:43,087 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:43,087 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:43,087 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d003a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:43,087 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d003a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:43,198 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d003a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:43,198 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x42b55610 to 127.0.0.1:60462 2024-12-02T17:14:43,198 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:43,199 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:43,207 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:43,214 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:43,215 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:43,215 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:43,216 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:43,216 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=68 2024-12-02T17:14:43,217 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=68 2024-12-02T17:14:43,219 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:43,222 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=68, resume processing ppid=67 2024-12-02T17:14:43,223 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=68, ppid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 287 msec 2024-12-02T17:14:43,231 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-02T17:14:43,232 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:43,233 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:43,235 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 318 msec 2024-12-02T17:14:43,541 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-02T17:14:43,542 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:43,542 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:43,543 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=69, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:43,545 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-02T17:14:43,545 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:43,547 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=69, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:43,549 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=69, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-02T17:14:43,549 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:43,651 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-02T17:14:43,652 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:43,653 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:43,654 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=70, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:43,655 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-02T17:14:43,656 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:43,657 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=70, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:43,659 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=70, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:43,659 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:43,766 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-02T17:14:43,767 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:43,780 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=219 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=252 (was 230) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=7472 (was 7509) 2024-12-02T17:14:43,790 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=219, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=252, ProcessCount=11, AvailableMemoryMB=7471 2024-12-02T17:14:43,791 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:43,792 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=71, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:43,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-02T17:14:43,814 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:43,815 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:43,852 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:43,853 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d003b connected 2024-12-02T17:14:43,901 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-02T17:14:43,934 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:14:43,961 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d003b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:43,983 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=72, ppid=71, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:44,111 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-02T17:14:44,139 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:44,140 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=72 2024-12-02T17:14:44,140 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:44,163 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=72}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:44,185 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:44,227 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=72 2024-12-02T17:14:44,228 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=72 2024-12-02T17:14:44,231 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:44,235 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=72, resume processing ppid=71 2024-12-02T17:14:44,235 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:44,235 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=72, ppid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 248 msec 2024-12-02T17:14:44,237 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 444 msec 2024-12-02T17:14:44,269 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x262a88cb to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6ae5dd39 2024-12-02T17:14:44,278 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:44,279 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:44,279 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@434758e, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:44,280 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:44,290 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:44,290 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:44,290 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d003d connected 2024-12-02T17:14:44,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-02T17:14:44,421 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:44,421 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:44,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=73, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:44,424 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-02T17:14:44,444 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:44,445 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:44,452 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:44,453 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d003e connected 2024-12-02T17:14:44,530 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-02T17:14:44,561 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d003e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:44,570 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=74, ppid=73, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:44,723 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:44,724 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=74 2024-12-02T17:14:44,724 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:44,725 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:44,725 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:44,725 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:44,725 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d003d, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:44,725 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d003d, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:44,740 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-02T17:14:44,836 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d003d, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:44,836 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x262a88cb to 127.0.0.1:60462 2024-12-02T17:14:44,836 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:44,851 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:44,852 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:44,852 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=74 2024-12-02T17:14:44,852 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=74 2024-12-02T17:14:44,854 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:44,856 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=74, resume processing ppid=73 2024-12-02T17:14:44,856 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:14:44,856 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=74, ppid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-12-02T17:14:44,858 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 435 msec 2024-12-02T17:14:44,884 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2400d6f5 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@d1fda90 2024-12-02T17:14:44,903 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:44,903 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:44,903 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@29340ff0, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:44,904 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:44,919 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:44,919 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:44,919 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0040 connected 2024-12-02T17:14:45,051 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-02T17:14:45,052 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:45,052 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:45,053 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-02T17:14:45,055 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=75, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:45,056 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-02T17:14:45,072 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:45,073 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:45,085 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:45,086 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0041 connected 2024-12-02T17:14:45,161 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-02T17:14:45,202 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0041, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:45,232 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=76, ppid=75, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:45,371 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-02T17:14:45,384 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:45,385 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=76 2024-12-02T17:14:45,385 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:45,387 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:45,388 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:45,388 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:45,388 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0040, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:45,389 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0040, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:45,506 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0040, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:45,506 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2400d6f5 to 127.0.0.1:60462 2024-12-02T17:14:45,507 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:45,524 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:45,524 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:45,524 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=76 2024-12-02T17:14:45,525 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=76 2024-12-02T17:14:45,527 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:45,529 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=76, resume processing ppid=75 2024-12-02T17:14:45,529 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-02T17:14:45,529 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=76, ppid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 296 msec 2024-12-02T17:14:45,530 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 476 msec 2024-12-02T17:14:45,552 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7c3cd9ae to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1985a464 2024-12-02T17:14:45,613 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:45,615 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:45,615 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1ec105e5, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:45,618 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:45,636 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:45,636 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:45,636 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0043 connected 2024-12-02T17:14:45,681 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-02T17:14:45,681 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:45,682 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:45,682 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:45,683 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-02T17:14:45,684 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=77, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:45,685 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-02T17:14:45,697 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:45,698 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:45,728 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:45,728 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0044 connected 2024-12-02T17:14:45,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-02T17:14:45,844 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0044, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:45,870 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=78, ppid=77, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:46,001 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-02T17:14:46,022 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:46,023 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=78 2024-12-02T17:14:46,023 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:46,024 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:46,025 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:46,025 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:46,025 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0043, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:46,025 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0043, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:46,140 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0043, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:46,140 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7c3cd9ae to 127.0.0.1:60462 2024-12-02T17:14:46,140 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:46,153 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:46,153 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:46,154 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=78 2024-12-02T17:14:46,154 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=78 2024-12-02T17:14:46,156 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:46,158 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=78, resume processing ppid=77 2024-12-02T17:14:46,158 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-02T17:14:46,158 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=78, ppid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-02T17:14:46,159 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 475 msec 2024-12-02T17:14:46,183 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1529708f to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3729deb1 2024-12-02T17:14:46,211 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:46,212 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:46,212 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@322bf92a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:46,213 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:46,277 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:46,277 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:46,278 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0046 connected 2024-12-02T17:14:46,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-02T17:14:46,311 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:46,311 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:46,312 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:46,313 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-02T17:14:46,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=79, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:46,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-02T17:14:46,334 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:46,335 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:46,380 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:46,380 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0047 connected 2024-12-02T17:14:46,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-02T17:14:46,554 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0047, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:46,619 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=80, ppid=79, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:46,631 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-02T17:14:46,772 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:46,773 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=80 2024-12-02T17:14:46,774 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:46,777 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:46,778 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:46,778 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:46,779 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0046, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:46,779 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0046, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:46,920 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0046, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:46,920 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1529708f to 127.0.0.1:60462 2024-12-02T17:14:46,921 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:46,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-02T17:14:46,941 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:46,941 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:46,941 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=80 2024-12-02T17:14:46,942 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=80 2024-12-02T17:14:46,943 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:46,945 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=80, resume processing ppid=79 2024-12-02T17:14:46,945 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-02T17:14:46,945 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=80, ppid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 324 msec 2024-12-02T17:14:46,946 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 632 msec 2024-12-02T17:14:46,972 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5e888464 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2d0921e8 2024-12-02T17:14:46,996 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:46,996 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:46,997 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4a66f2e3, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:46,998 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:47,062 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:47,063 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:47,063 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0049 connected 2024-12-02T17:14:47,451 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-02T17:14:47,451 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:47,452 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:47,453 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:47,454 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-02T17:14:47,455 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=81, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:47,456 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-02T17:14:47,469 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:47,470 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:47,491 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:47,492 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d004a connected 2024-12-02T17:14:47,561 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-02T17:14:47,606 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d004a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:47,632 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=82, ppid=81, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:47,771 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-02T17:14:47,783 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:47,784 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=82 2024-12-02T17:14:47,784 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:47,785 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:47,785 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:47,785 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:47,785 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0049, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:47,786 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0049, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:47,894 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0049, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:47,894 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5e888464 to 127.0.0.1:60462 2024-12-02T17:14:47,894 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:47,909 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:47,909 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:47,909 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=82 2024-12-02T17:14:47,910 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=82 2024-12-02T17:14:47,912 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:47,914 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=82, resume processing ppid=81 2024-12-02T17:14:47,914 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-02T17:14:47,914 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=82, ppid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 280 msec 2024-12-02T17:14:47,917 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 460 msec 2024-12-02T17:14:47,946 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x08c28a13 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7036994b 2024-12-02T17:14:47,961 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:47,961 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:47,962 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@72982460, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:47,963 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:47,977 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:47,978 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:47,978 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d004c connected 2024-12-02T17:14:48,080 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-02T17:14:48,081 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:48,082 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:48,083 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:48,084 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-02T17:14:48,085 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=83, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:48,087 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-02T17:14:48,111 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:48,112 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:48,123 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:48,126 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d004d connected 2024-12-02T17:14:48,190 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-02T17:14:48,244 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d004d, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:48,257 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=84, ppid=83, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:48,400 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-02T17:14:48,410 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:48,411 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=84 2024-12-02T17:14:48,411 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:48,412 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:48,412 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:48,412 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:48,412 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d004c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:48,413 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d004c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:48,523 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d004c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:48,523 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x08c28a13 to 127.0.0.1:60462 2024-12-02T17:14:48,523 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:48,536 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:48,536 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:48,537 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=84 2024-12-02T17:14:48,537 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=84 2024-12-02T17:14:48,539 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:48,541 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=84, resume processing ppid=83 2024-12-02T17:14:48,541 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=84, ppid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-02T17:14:48,541 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-02T17:14:48,542 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 457 msec 2024-12-02T17:14:48,563 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x58afb543 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6e283873 2024-12-02T17:14:48,573 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:48,574 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:48,574 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@797319ab, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:48,574 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:48,585 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:48,586 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:48,586 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d004f connected 2024-12-02T17:14:48,711 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-02T17:14:48,711 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:48,711 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:48,712 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-02T17:14:48,713 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=85, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:48,714 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-02T17:14:48,730 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:48,731 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:48,740 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:48,740 ERROR [PEWorker-4-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f6a848d4010@f07f39d rejected from java.util.concurrent.ThreadPoolExecutor@b3876a5[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2065) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:833) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1365) ~[?:?] at java.util.concurrent.Executors$DelegatedExecutorService.execute(Executors.java:721) ~[?:?] at org.apache.hadoop.hbase.zookeeper.ZKWatcher.process(ZKWatcher.java:613) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:38) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:579) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-12-02T17:14:48,820 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-02T17:14:48,852 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:48,861 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=86, ppid=85, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:49,014 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:49,015 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=86 2024-12-02T17:14:49,015 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:49,017 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=86 2024-12-02T17:14:49,017 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=86 2024-12-02T17:14:49,020 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:49,023 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=86, resume processing ppid=85 2024-12-02T17:14:49,024 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=86, ppid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 159 msec 2024-12-02T17:14:49,024 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-02T17:14:49,026 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 311 msec 2024-12-02T17:14:49,031 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-02T17:14:49,031 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:49,032 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:49,033 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:49,034 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-02T17:14:49,036 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=87, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:49,037 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-02T17:14:49,059 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:49,060 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:49,069 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:49,069 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0051 connected 2024-12-02T17:14:49,141 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-02T17:14:49,177 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0051, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:49,186 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=88, ppid=87, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:49,302 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:49,338 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:49,339 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=88 2024-12-02T17:14:49,339 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:49,341 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:49,341 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:49,341 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:49,342 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d004f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:49,342 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d004f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:49,351 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-02T17:14:49,369 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:14:49,452 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d004f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:49,452 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x58afb543 to 127.0.0.1:60462 2024-12-02T17:14:49,452 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:49,465 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:49,465 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:49,466 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=88 2024-12-02T17:14:49,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=88 2024-12-02T17:14:49,468 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:49,470 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=88, resume processing ppid=87 2024-12-02T17:14:49,470 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-02T17:14:49,470 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=88, ppid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-02T17:14:49,471 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 435 msec 2024-12-02T17:14:49,491 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x29ac3a68 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2abe1a98 2024-12-02T17:14:49,502 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:49,503 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:49,503 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@71d2aa8, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:49,504 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:49,514 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:49,515 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0053 connected 2024-12-02T17:14:49,515 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:49,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-02T17:14:49,661 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:49,661 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:49,662 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-02T17:14:49,664 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=89, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:49,665 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-02T17:14:49,680 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:49,681 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:49,689 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:49,690 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0054 connected 2024-12-02T17:14:49,771 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-02T17:14:49,798 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0054, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:49,852 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=90, ppid=89, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:49,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-02T17:14:50,003 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:50,004 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=90 2024-12-02T17:14:50,004 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:50,006 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:50,006 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:50,006 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:50,006 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0053, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:50,006 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0053, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:50,115 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0053, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:50,115 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x29ac3a68 to 127.0.0.1:60462 2024-12-02T17:14:50,115 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:50,129 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:50,130 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:50,130 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=90 2024-12-02T17:14:50,131 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=90 2024-12-02T17:14:50,133 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:50,136 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=90, resume processing ppid=89 2024-12-02T17:14:50,136 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-02T17:14:50,136 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=90, ppid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-12-02T17:14:50,139 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 473 msec 2024-12-02T17:14:50,165 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x56e9dc4a to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@40299b9d 2024-12-02T17:14:50,177 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:50,178 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:50,178 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1fc13a29, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:50,179 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:50,194 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:50,194 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:50,194 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0056 connected 2024-12-02T17:14:50,291 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-02T17:14:50,291 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:50,291 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:50,292 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:50,293 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=91, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:50,296 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:50,299 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-02T17:14:50,306 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:50,306 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:50,306 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:50,307 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=92, ppid=91, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:50,411 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-02T17:14:50,460 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:50,461 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=92 2024-12-02T17:14:50,461 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:50,461 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:50,461 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:50,461 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:50,461 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0056, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:50,462 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0056, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:50,569 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0056, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:50,569 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x56e9dc4a to 127.0.0.1:60462 2024-12-02T17:14:50,569 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:50,569 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:50,578 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:50,585 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:50,585 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:50,585 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:50,587 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:50,587 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=92 2024-12-02T17:14:50,587 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=92 2024-12-02T17:14:50,590 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:50,593 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=92, resume processing ppid=91 2024-12-02T17:14:50,593 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=92, ppid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 283 msec 2024-12-02T17:14:50,602 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:50,602 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:50,604 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 310 msec 2024-12-02T17:14:50,621 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-02T17:14:50,621 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:50,622 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:50,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=93, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:50,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-02T17:14:50,624 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:50,625 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=93, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:50,626 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=93, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-02T17:14:50,626 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:50,731 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-02T17:14:50,732 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:50,732 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:50,733 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=94, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:50,734 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-02T17:14:50,734 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:50,736 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=94, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:50,737 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=94, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:50,737 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:50,842 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-02T17:14:50,843 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:50,859 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=221 (was 219) - Thread LEAK? -, OpenFileDescriptor=446 (was 444) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=264 (was 252) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=7348 (was 7471) 2024-12-02T17:14:50,867 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=264, ProcessCount=11, AvailableMemoryMB=7348 2024-12-02T17:14:50,868 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:50,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=95, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:50,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-02T17:14:50,884 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:50,885 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:50,893 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:50,894 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0057 connected 2024-12-02T17:14:50,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-02T17:14:51,002 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0057, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:51,024 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=96, ppid=95, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:51,176 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:51,176 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=96 2024-12-02T17:14:51,177 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:51,191 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-02T17:14:51,198 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=96}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:51,216 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:51,260 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=96 2024-12-02T17:14:51,261 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=96 2024-12-02T17:14:51,262 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:51,265 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=96, resume processing ppid=95 2024-12-02T17:14:51,265 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:51,265 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=96, ppid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 238 msec 2024-12-02T17:14:51,266 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 397 msec 2024-12-02T17:14:51,291 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7be2e020 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5805e319 2024-12-02T17:14:51,303 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:51,304 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:51,304 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@39022c27, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:51,304 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:51,315 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:51,315 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:51,315 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0059 connected 2024-12-02T17:14:51,500 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-02T17:14:51,501 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:51,501 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:51,505 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3938): Client=jenkins//172.17.0.2 disable replication peer, id=1 2024-12-02T17:14:51,507 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=97, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure 2024-12-02T17:14:51,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-02T17:14:51,519 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=98, ppid=97, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:51,621 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-02T17:14:51,671 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:51,672 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=98 2024-12-02T17:14:51,672 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=DISABLE_PEER 2024-12-02T17:14:51,672 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:14:51,673 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:14:51,673 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:51,673 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0059, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:51,673 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0059, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:51,781 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0059, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:51,781 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7be2e020 to 127.0.0.1:60462 2024-12-02T17:14:51,781 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:51,797 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:51,797 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:14:51,798 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=98 2024-12-02T17:14:51,798 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=98 2024-12-02T17:14:51,801 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for DISABLE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:51,806 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=98, resume processing ppid=97 2024-12-02T17:14:51,807 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=98, ppid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-02T17:14:51,807 INFO [PEWorker-5 {}] replication.DisablePeerProcedure(67): Successfully disabled peer 1 2024-12-02T17:14:51,809 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure in 302 msec 2024-12-02T17:14:51,830 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-02T17:14:51,831 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: DISABLE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:51,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:51,832 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:51,833 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=99, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:51,835 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-02T17:14:51,835 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2ef1b1c9 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@775b54e1 2024-12-02T17:14:51,837 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:51,888 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:51,888 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:51,888 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:51,889 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=100, ppid=99, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:51,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-02T17:14:51,987 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:51,988 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:51,988 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@120a5de8, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:51,989 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:52,038 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:52,038 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:52,038 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d005b connected 2024-12-02T17:14:52,041 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:52,042 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=100 2024-12-02T17:14:52,042 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:52,042 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:52,042 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:52,042 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:52,043 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d005b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:52,043 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d005b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:52,151 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-02T17:14:52,160 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d005b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:52,160 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2ef1b1c9 to 127.0.0.1:60462 2024-12-02T17:14:52,160 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:52,161 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:52,169 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:52,177 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:52,177 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:52,177 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:52,177 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:52,177 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=100 2024-12-02T17:14:52,178 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=100 2024-12-02T17:14:52,179 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:52,181 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=100, resume processing ppid=99 2024-12-02T17:14:52,181 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=100, ppid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-02T17:14:52,190 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:52,190 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:52,191 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 358 msec 2024-12-02T17:14:52,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-02T17:14:52,461 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:52,461 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:52,462 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=101, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:52,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-02T17:14:52,463 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:52,467 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=101, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:52,469 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=101, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=7 msec 2024-12-02T17:14:52,469 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:52,570 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-02T17:14:52,571 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:52,572 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:52,573 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=102, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:52,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-02T17:14:52,574 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:52,575 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=102, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:52,576 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=102, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-02T17:14:52,577 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:52,681 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-02T17:14:52,682 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:52,697 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=264 (was 264), ProcessCount=11 (was 11), AvailableMemoryMB=7299 (was 7348) 2024-12-02T17:14:52,708 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=264, ProcessCount=11, AvailableMemoryMB=7298 2024-12-02T17:14:52,709 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=dummy_peer 2024-12-02T17:14:52,710 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=103, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:52,711 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-02T17:14:52,711 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer dummy_peer, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:52,715 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=103, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:52,716 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=103, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-02T17:14:52,716 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:52,820 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-02T17:14:52,821 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: dummy_peer failed with dummy_peer 2024-12-02T17:14:52,822 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:52,823 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=104, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:52,824 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-02T17:14:52,824 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:52,825 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=104, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:52,826 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=104, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-02T17:14:52,827 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:52,931 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-02T17:14:52,931 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:52,932 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:52,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=105, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:52,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-02T17:14:52,934 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:52,935 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=105, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:52,936 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=105, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-02T17:14:52,936 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:53,040 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-02T17:14:53,041 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:53,054 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=264 (was 264), ProcessCount=11 (was 11), AvailableMemoryMB=7297 (was 7298) 2024-12-02T17:14:53,064 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=264, ProcessCount=11, AvailableMemoryMB=7296 2024-12-02T17:14:53,066 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:53,067 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=106, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:53,068 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-02T17:14:53,090 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:53,091 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:53,102 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:53,102 ERROR [PEWorker-5-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f6a848d4010@56543b7e rejected from java.util.concurrent.ThreadPoolExecutor@526bb56c[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2065) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:833) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1365) ~[?:?] at java.util.concurrent.Executors$DelegatedExecutorService.execute(Executors.java:721) ~[?:?] at org.apache.hadoop.hbase.zookeeper.ZKWatcher.process(ZKWatcher.java:613) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:38) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:579) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-12-02T17:14:53,170 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-02T17:14:53,210 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:53,245 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=107, ppid=106, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:53,380 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-02T17:14:53,398 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:53,399 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=107 2024-12-02T17:14:53,399 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:53,422 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=107}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:53,445 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:53,523 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=107 2024-12-02T17:14:53,524 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=107 2024-12-02T17:14:53,525 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:53,527 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=107, resume processing ppid=106 2024-12-02T17:14:53,527 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:53,527 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=107, ppid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 280 msec 2024-12-02T17:14:53,528 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 461 msec 2024-12-02T17:14:53,550 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1d458533 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@53766052 2024-12-02T17:14:53,561 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:53,561 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:53,562 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@79a1af7, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:53,563 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:53,590 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:53,590 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:53,590 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d005e connected 2024-12-02T17:14:53,691 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-02T17:14:53,691 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:53,692 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-02T17:14:53,693 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:53,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=108, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:53,695 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-02T17:14:53,697 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:53,748 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:53,749 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:53,749 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:53,751 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=109, ppid=108, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:53,800 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-02T17:14:53,904 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:53,904 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=109 2024-12-02T17:14:53,905 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:53,905 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:53,905 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:53,905 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:53,905 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d005e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:53,905 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d005e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:54,010 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-02T17:14:54,019 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d005e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:54,019 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1d458533 to 127.0.0.1:60462 2024-12-02T17:14:54,019 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:54,019 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:54,058 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:54,108 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:54,108 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:54,108 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:54,109 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:54,109 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=109 2024-12-02T17:14:54,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=109 2024-12-02T17:14:54,113 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:54,116 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=109, resume processing ppid=108 2024-12-02T17:14:54,116 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=109, ppid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 363 msec 2024-12-02T17:14:54,167 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:54,167 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:54,169 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 474 msec 2024-12-02T17:14:54,321 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-02T17:14:54,321 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:54,321 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:54,322 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=110, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:54,323 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-02T17:14:54,323 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:54,324 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=110, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:54,325 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=110, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-02T17:14:54,325 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:54,431 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-02T17:14:54,431 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:54,432 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:54,432 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=111, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:54,433 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-02T17:14:54,433 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:54,434 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=111, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:54,434 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=111, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-02T17:14:54,434 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:54,541 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-02T17:14:54,541 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:54,550 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=223 (was 221) - Thread LEAK? -, OpenFileDescriptor=448 (was 446) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=243 (was 264), ProcessCount=11 (was 11), AvailableMemoryMB=7296 (was 7296) 2024-12-02T17:14:54,557 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=243, ProcessCount=11, AvailableMemoryMB=7295 2024-12-02T17:14:54,562 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:54,562 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] ipc.MetricsHBaseServer(152): Unknown exception type java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) ~[classes/:?] at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) ~[classes/:?] at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-12-02T17:14:54,562 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] ipc.CallRunner(138): callId: 356 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:56058 deadline: 1733159754562, exception=java.io.IOException: Replication peer modification disabled 2024-12-02T17:14:54,578 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 1, maxAttempts = 2, timeout = 120000 ms, time elapsed = 16 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.instantiateException(RemoteWithExtrasException.java:110) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.unwrapRemoteException(RemoteWithExtrasException.java:100) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionUtils.translateException(ConnectionUtils.java:245) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncRpcRetryingCaller.onError(AsyncRpcRetryingCaller.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncMasterRequestRpcRetryingCaller.lambda$doCall$4(AsyncMasterRequestRpcRetryingCaller.java:76) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.util.FutureUtils.lambda$addListener$0(FutureUtils.java:71) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:841) ~[?:?] at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:510) ~[?:?] at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2162) ~[?:?] at org.apache.hadoop.hbase.client.RawAsyncHBaseAdmin$1.run(RawAsyncHBaseAdmin.java:431) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:56) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:47) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:397) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.access$100(AbstractRpcClient.java:94) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:430) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.callComplete(Call.java:116) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.setException(Call.java:131) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcConnection.readResponse(RpcConnection.java:457) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.readResponse(NettyRpcDuplexHandler.java:125) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.channelRead(NettyRpcDuplexHandler.java:140) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:289) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1357) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:868) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[hbase-shaded-netty-4.1.9.jar:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-02T17:14:54,691 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:54,691 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] ipc.MetricsHBaseServer(152): Unknown exception type java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) ~[classes/:?] at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) ~[classes/:?] at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-12-02T17:14:54,692 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] ipc.CallRunner(138): callId: 357 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:56058 deadline: 1733159754691, exception=java.io.IOException: Replication peer modification disabled 2024-12-02T17:14:54,692 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 2, maxAttempts = 2, timeout = 120000 ms, time elapsed = 130 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.instantiateException(RemoteWithExtrasException.java:110) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.unwrapRemoteException(RemoteWithExtrasException.java:100) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionUtils.translateException(ConnectionUtils.java:245) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncRpcRetryingCaller.onError(AsyncRpcRetryingCaller.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncMasterRequestRpcRetryingCaller.lambda$doCall$4(AsyncMasterRequestRpcRetryingCaller.java:76) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.util.FutureUtils.lambda$addListener$0(FutureUtils.java:71) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:841) ~[?:?] at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:510) ~[?:?] at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2162) ~[?:?] at org.apache.hadoop.hbase.client.RawAsyncHBaseAdmin$1.run(RawAsyncHBaseAdmin.java:431) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:56) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:47) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:397) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.access$100(AbstractRpcClient.java:94) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:430) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.callComplete(Call.java:116) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.setException(Call.java:131) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcConnection.readResponse(RpcConnection.java:457) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.readResponse(NettyRpcDuplexHandler.java:125) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.channelRead(NettyRpcDuplexHandler.java:140) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:289) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1357) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:868) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[hbase-shaded-netty-4.1.9.jar:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-02T17:14:54,693 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Failed after attempts=2, exceptions: 2024-12-02T17:14:54.579Z, java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) 2024-12-02T17:14:54.693Z, java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) 2024-12-02T17:14:54,696 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:54,697 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=112, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:54,697 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-02T17:14:54,697 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:54,699 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=112, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:54,700 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=112, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-02T17:14:54,700 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:54,801 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-02T17:14:54,802 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:54,802 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:54,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=113, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:54,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-02T17:14:54,803 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:54,804 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=113, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:54,805 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=113, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-02T17:14:54,805 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:54,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-02T17:14:54,912 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:54,928 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=223 (was 223), OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=243 (was 243), ProcessCount=11 (was 11), AvailableMemoryMB=7287 (was 7295) 2024-12-02T17:14:54,938 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=243, ProcessCount=11, AvailableMemoryMB=7286 2024-12-02T17:14:54,939 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:54,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=114, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:54,941 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-02T17:14:54,960 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:54,961 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:55,007 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:55,008 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d005f connected 2024-12-02T17:14:55,051 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-02T17:14:55,150 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d005f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:55,260 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-02T17:14:55,269 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=115, ppid=114, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:55,421 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:55,421 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=115 2024-12-02T17:14:55,421 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:55,438 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=115}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:55,449 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:55,570 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-02T17:14:55,686 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=115 2024-12-02T17:14:55,688 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=115 2024-12-02T17:14:55,691 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:55,693 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=115, resume processing ppid=114 2024-12-02T17:14:55,693 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:55,693 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=115, ppid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 422 msec 2024-12-02T17:14:55,695 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 754 msec 2024-12-02T17:14:55,719 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1d276503 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@407c0a70 2024-12-02T17:14:55,779 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:55,780 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:55,780 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2c1ee188, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:55,781 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:55,828 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:55,829 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:55,829 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0061 connected 2024-12-02T17:14:56,081 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-02T17:14:56,081 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:56,082 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:56,083 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:56,083 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:14:56,085 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=116, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:56,087 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-02T17:14:56,090 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:56,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:56,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:56,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:56,103 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=117, ppid=116, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:56,191 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-02T17:14:56,254 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:56,255 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=117 2024-12-02T17:14:56,255 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:56,255 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:56,255 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:56,256 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:56,256 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0061, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:56,256 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0061, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:56,365 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0061, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:56,365 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1d276503 to 127.0.0.1:60462 2024-12-02T17:14:56,365 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:56,365 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:56,377 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:56,395 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:56,395 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:56,395 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:56,396 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:56,396 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=117 2024-12-02T17:14:56,397 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=117 2024-12-02T17:14:56,399 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:56,401 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-02T17:14:56,402 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=117, resume processing ppid=116 2024-12-02T17:14:56,402 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=117, ppid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 296 msec 2024-12-02T17:14:56,416 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:56,416 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:56,418 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 333 msec 2024-12-02T17:14:56,711 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-02T17:14:56,711 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:56,712 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:56,713 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=118, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:56,714 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-02T17:14:56,714 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:56,716 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=118, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:56,717 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=118, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:56,717 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:56,821 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-02T17:14:56,821 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:56,833 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=223 (was 223), OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=243 (was 243), ProcessCount=11 (was 11), AvailableMemoryMB=7248 (was 7286) 2024-12-02T17:14:56,840 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=243, ProcessCount=11, AvailableMemoryMB=7246 2024-12-02T17:14:56,841 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:56,842 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=119, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:56,843 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-02T17:14:56,855 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:56,855 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:56,865 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:56,865 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0062 connected 2024-12-02T17:14:56,951 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-02T17:14:56,977 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0062, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:57,078 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=120, ppid=119, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:57,161 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-02T17:14:57,231 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:57,232 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=120 2024-12-02T17:14:57,232 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:57,252 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=120}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:57,263 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:57,330 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=120 2024-12-02T17:14:57,331 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=120 2024-12-02T17:14:57,335 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:57,338 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=120, resume processing ppid=119 2024-12-02T17:14:57,338 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=120, ppid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 257 msec 2024-12-02T17:14:57,338 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:57,340 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 497 msec 2024-12-02T17:14:57,349 DEBUG [BootstrapNodeManager {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-02T17:14:57,350 INFO [RS-EventLoopGroup-1-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:57032, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-02T17:14:57,364 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x355a0b29 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3a5a9057 2024-12-02T17:14:57,382 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:14:57,382 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:14:57,382 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6c8593fa, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:14:57,383 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:57,393 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:57,394 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:14:57,394 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0064 connected 2024-12-02T17:14:57,471 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-02T17:14:57,471 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:57,472 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:57,473 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-02T17:14:57,475 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=121, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:14:57,476 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-02T17:14:57,494 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:14:57,494 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:14:57,502 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:14:57,502 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0065 connected 2024-12-02T17:14:57,581 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-02T17:14:57,610 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0065, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:57,619 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=122, ppid=121, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:57,771 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:57,772 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=122 2024-12-02T17:14:57,772 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:14:57,774 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=122 2024-12-02T17:14:57,775 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=122 2024-12-02T17:14:57,777 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:57,781 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=122, resume processing ppid=121 2024-12-02T17:14:57,781 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=122, ppid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 158 msec 2024-12-02T17:14:57,781 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-02T17:14:57,783 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 308 msec 2024-12-02T17:14:57,790 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-02T17:14:57,791 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:14:57,792 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:14:57,792 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:57,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=123, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:57,794 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-02T17:14:57,798 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:57,810 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:57,810 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:57,810 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:57,812 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=124, ppid=123, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:57,900 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-02T17:14:57,964 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:57,965 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=124 2024-12-02T17:14:57,966 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:57,966 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:57,966 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:57,966 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:14:57,966 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0064, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:57,967 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0064, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:14:58,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0064, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:14:58,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x355a0b29 to 127.0.0.1:60462 2024-12-02T17:14:58,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:14:58,078 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:14:58,094 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:58,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:14:58,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:58,102 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:14:58,102 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:58,102 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=124 2024-12-02T17:14:58,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=124 2024-12-02T17:14:58,104 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:58,106 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=124, resume processing ppid=123 2024-12-02T17:14:58,106 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=124, ppid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 293 msec 2024-12-02T17:14:58,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-02T17:14:58,115 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:14:58,115 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:14:58,117 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 323 msec 2024-12-02T17:14:58,421 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-02T17:14:58,421 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:58,422 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:58,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=125, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:58,425 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-02T17:14:58,425 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:58,428 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=125, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:58,429 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=125, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-02T17:14:58,430 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:58,531 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-02T17:14:58,531 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-02T17:14:58,533 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:14:58,534 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=126, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:58,535 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-02T17:14:58,535 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:14:58,537 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=126, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:58,538 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=126, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:14:58,538 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:58,641 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-02T17:14:58,642 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:14:58,656 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223 (was 223), OpenFileDescriptor=450 (was 448) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=223 (was 243), ProcessCount=11 (was 11), AvailableMemoryMB=7216 (was 7246) 2024-12-02T17:14:58,666 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=223, ProcessCount=11, AvailableMemoryMB=7215 2024-12-02T17:14:58,667 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:58,668 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=127, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:58,668 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-02T17:14:58,686 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=128, ppid=127, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:58,771 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-02T17:14:58,837 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:58,838 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=128 2024-12-02T17:14:58,838 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:14:58,871 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:14:58,910 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=128 2024-12-02T17:14:58,911 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(587): peerId=1, queueId=1 (queues=1) is replicating from cluster=a56154ea-b277-49c8-abc8-799bb07e4f77 to cluster=a56154ea-b277-49c8-abc8-799bb07e4f77 2024-12-02T17:14:58,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=128 2024-12-02T17:14:58,912 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(343): peerId=1, starting shipping worker for walGroupId=fa731d6f0321%2C40509%2C1733159661070 2024-12-02T17:14:58,913 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:14:58,915 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSourceWALReader(112): peerClusterZnode=1, ReplicationSourceWALReaderThread : 1 inited, replicationBatchSizeCapacity=67108864, replicationBatchCountCapacity=25000, replicationBatchQueueCapacity=1 2024-12-02T17:14:58,916 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=128, resume processing ppid=127 2024-12-02T17:14:58,916 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=128, ppid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 227 msec 2024-12-02T17:14:58,916 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:14:58,917 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.wal-reader.fa731d6f0321%2C40509%2C1733159661070,1 {}] regionserver.WALEntryStream(260): Creating new reader hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.1733159663631, startPosition=0, beingWritten=true 2024-12-02T17:14:58,917 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.shipperfa731d6f0321%2C40509%2C1733159661070,1 {}] regionserver.ReplicationSourceShipper(98): Running ReplicationSourceShipper Thread for wal group: fa731d6f0321%2C40509%2C1733159661070 2024-12-02T17:14:58,918 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 249 msec 2024-12-02T17:14:58,981 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-02T17:14:58,981 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:14:58,981 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:14:58,982 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=129, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:14:58,983 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-02T17:14:58,983 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.io.IOException: Cluster key passed is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-12-02T17:14:58,984 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=129, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: ; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.io.IOException: Cluster key passed is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:14:58,985 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=129, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: ; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=3 msec 2024-12-02T17:14:58,985 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:14:58,992 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.wal-reader.fa731d6f0321%2C40509%2C1733159661070,1 {}] regionserver.ReplicationSourceWALReader(181): Read 0 WAL entries eligible for replication 2024-12-02T17:14:58,992 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.wal-reader.fa731d6f0321%2C40509%2C1733159661070,1 {}] regionserver.WALEntryStream(223): Reset reader hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.1733159663631 to pos 589, reset compression=false 2024-12-02T17:14:58,992 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.shipperfa731d6f0321%2C40509%2C1733159661070,1 {}] regionserver.ReplicationSourceShipper(110): Shipper from source 1 got entry batch from reader: WALEntryBatch [walEntries=[], lastWalPath=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/WALs/fa731d6f0321,40509,1733159661070/fa731d6f0321%2C40509%2C1733159661070.1733159663631, lastWalPosition=589, nbRowKeys=0, nbHFiles=0, heapSize=0, lastSeqIds={}, endOfFile=false,usedBufferSize=0] 2024-12-02T17:14:59,092 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-02T17:14:59,094 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 2 failed with Invalid cluster key: 2024-12-02T17:14:59,095 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:14:59,096 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=130, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:14:59,097 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:14:59,099 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:59,110 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:14:59,110 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:59,110 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:14:59,111 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=131, ppid=130, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:14:59,200 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:14:59,264 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:14:59,264 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=131 2024-12-02T17:14:59,264 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:14:59,264 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:14:59,265 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:14:59,330 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:14:59,411 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:14:59,720 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:15:00,230 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:15:00,265 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.wal-reader.fa731d6f0321%2C40509%2C1733159661070,1 {}] util.Threads(127): sleep interrupted java.lang.InterruptedException: sleep interrupted at java.lang.Thread.sleep(Native Method) ~[?:?] at org.apache.hadoop.hbase.util.Threads.sleep(Threads.java:125) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.sleep(ReplicationSourceWALReader.java:131) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.run(ReplicationSourceWALReader.java:166) ~[classes/:?] 2024-12-02T17:15:00,265 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.shipperfa731d6f0321%2C40509%2C1733159661070,1 {}] regionserver.ReplicationSourceShipper(123): Interrupted while waiting for next replication entry batch java.lang.InterruptedException: null at java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1681) ~[?:?] at java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) ~[?:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.poll(ReplicationSourceWALReader.java:313) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceShipper.run(ReplicationSourceShipper.java:109) ~[classes/:?] 2024-12-02T17:15:01,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:15:01,265 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(711): peerId=1, ReplicationSourceWorker RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1.replicationSource.shipperfa731d6f0321%2C40509%2C1733159661070,1 terminated 2024-12-02T17:15:01,265 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:15:01,267 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:15:01,277 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:15:01,277 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:15:01,277 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:15:01,278 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:15:01,278 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=131 2024-12-02T17:15:01,279 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=131 2024-12-02T17:15:01,282 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:01,285 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=131, resume processing ppid=130 2024-12-02T17:15:01,285 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=131, ppid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 2.1710 sec 2024-12-02T17:15:01,294 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:15:01,294 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:15:01,296 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 2.1990 sec 2024-12-02T17:15:01,867 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:15:03,251 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-02T17:15:03,251 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:15:03,252 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-02T17:15:03,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=132, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:15:03,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-02T17:15:03,254 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-02T17:15:03,256 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=132, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-02T17:15:03,257 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=132, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-02T17:15:03,257 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-02T17:15:03,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-02T17:15:03,362 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-02T17:15:03,380 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=221 (was 223), OpenFileDescriptor=450 (was 450), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=229 (was 223) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=7176 (was 7215) 2024-12-02T17:15:03,389 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[1] Thread=221, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=229, ProcessCount=11, AvailableMemoryMB=7174 2024-12-02T17:15:03,390 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-02T17:15:03,391 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=133, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-02T17:15:03,392 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-02T17:15:03,405 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:03,406 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:03,451 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:03,452 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0066 connected 2024-12-02T17:15:03,501 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-02T17:15:03,574 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0066, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:03,594 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=134, ppid=133, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:03,710 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-02T17:15:03,745 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:03,746 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=134 2024-12-02T17:15:03,747 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-02T17:15:03,766 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=134}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:03,778 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:03,835 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=134 2024-12-02T17:15:03,836 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=134 2024-12-02T17:15:03,839 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:03,842 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=134, resume processing ppid=133 2024-12-02T17:15:03,842 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-02T17:15:03,842 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=134, ppid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 245 msec 2024-12-02T17:15:03,844 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 452 msec 2024-12-02T17:15:03,867 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x410a1309 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7a5c5db6 2024-12-02T17:15:03,877 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:03,877 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:03,877 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3f986bb7, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:03,878 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:03,893 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:03,893 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:03,893 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0068 connected 2024-12-02T17:15:04,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-02T17:15:04,021 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:15:04,022 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:15:04,022 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=135, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:15:04,023 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-02T17:15:04,035 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:04,035 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:04,066 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:04,066 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0069 connected 2024-12-02T17:15:04,131 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-02T17:15:04,181 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0069, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:04,194 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=136, ppid=135, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:04,341 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-02T17:15:04,346 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:04,346 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=136 2024-12-02T17:15:04,346 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:15:04,347 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:15:04,347 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:15:04,347 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:04,347 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0068, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:04,347 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0068, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:04,456 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0068, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:04,457 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x410a1309 to 127.0.0.1:60462 2024-12-02T17:15:04,457 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:04,476 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:04,476 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:15:04,477 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=136 2024-12-02T17:15:04,477 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=136 2024-12-02T17:15:04,479 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:04,480 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=136, resume processing ppid=135 2024-12-02T17:15:04,480 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:15:04,480 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=136, ppid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-02T17:15:04,481 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 458 msec 2024-12-02T17:15:04,516 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2cba3d7a to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@68ab12d3 2024-12-02T17:15:04,527 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:04,527 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:04,527 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2971d0ea, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:04,528 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:04,535 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:04,535 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:04,535 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d006b connected 2024-12-02T17:15:04,651 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-02T17:15:04,651 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:15:04,652 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:04,652 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:04,653 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:04,653 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-02T17:15:04,654 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=137, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:15:04,655 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-02T17:15:04,669 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:04,670 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:04,685 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:04,685 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d006c connected 2024-12-02T17:15:04,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-02T17:15:04,802 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d006c, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:04,810 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=138, ppid=137, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:04,962 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:04,963 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=138 2024-12-02T17:15:04,963 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:15:04,965 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:15:04,966 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:15:04,966 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:04,966 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d006b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:04,966 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d006b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:04,971 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-02T17:15:05,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d006b, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:05,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2cba3d7a to 127.0.0.1:60462 2024-12-02T17:15:05,077 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:05,091 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:05,091 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:15:05,091 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=138 2024-12-02T17:15:05,092 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=138 2024-12-02T17:15:05,093 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:05,095 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=138, resume processing ppid=137 2024-12-02T17:15:05,095 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-02T17:15:05,095 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=138, ppid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 283 msec 2024-12-02T17:15:05,096 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 442 msec 2024-12-02T17:15:05,120 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x63921ef6 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@99b437 2024-12-02T17:15:05,132 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:05,132 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:05,132 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@769bd27c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:05,133 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:05,148 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:05,148 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:05,149 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d006e connected 2024-12-02T17:15:05,281 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-02T17:15:05,281 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:15:05,281 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,282 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,282 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,283 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,284 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-02T17:15:05,285 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=139, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:15:05,285 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-02T17:15:05,304 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:05,305 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:05,315 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:05,315 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d006f connected 2024-12-02T17:15:05,392 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-02T17:15:05,432 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d006f, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:05,444 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=140, ppid=139, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:05,596 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:05,597 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=140 2024-12-02T17:15:05,598 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:15:05,601 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:15:05,601 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-02T17:15:05,601 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:15:05,601 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:05,601 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d006e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:05,601 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d006e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:05,710 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d006e, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:05,710 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x63921ef6 to 127.0.0.1:60462 2024-12-02T17:15:05,710 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:05,730 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:05,730 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:15:05,730 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=140 2024-12-02T17:15:05,730 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=140 2024-12-02T17:15:05,732 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:05,733 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=140, resume processing ppid=139 2024-12-02T17:15:05,733 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=140, ppid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-12-02T17:15:05,733 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-02T17:15:05,734 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 449 msec 2024-12-02T17:15:05,776 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6d48d82f to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3c0bbe29 2024-12-02T17:15:05,785 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:05,786 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:05,786 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@14aaabd7, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:05,787 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:05,794 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:05,794 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:05,794 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0071 connected 2024-12-02T17:15:05,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-02T17:15:05,912 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:15:05,912 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,913 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,915 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:05,916 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:15:05,917 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=141, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:15:05,918 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-02T17:15:05,935 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:05,936 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:05,951 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:05,952 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0072 connected 2024-12-02T17:15:06,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-02T17:15:06,068 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0072, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:06,082 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=142, ppid=141, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:06,231 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-02T17:15:06,234 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:06,235 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=142 2024-12-02T17:15:06,235 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:15:06,236 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:15:06,236 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:15:06,236 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:06,236 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0071, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:06,236 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0071, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:06,343 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0071, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:06,343 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6d48d82f to 127.0.0.1:60462 2024-12-02T17:15:06,343 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:06,360 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:06,360 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:15:06,360 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=142 2024-12-02T17:15:06,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=142 2024-12-02T17:15:06,362 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:06,364 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=142, resume processing ppid=141 2024-12-02T17:15:06,364 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:15:06,364 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=142, ppid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 280 msec 2024-12-02T17:15:06,365 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 448 msec 2024-12-02T17:15:06,386 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1b0bc5ed to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@34d6efba 2024-12-02T17:15:06,393 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:06,394 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:06,394 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1af924b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:06,394 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:06,401 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:06,401 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:06,401 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0074 connected 2024-12-02T17:15:06,456 INFO [master/fa731d6f0321:0.Chore.1 {}] migrate.RollingUpgradeChore(116): There is no table to migrate StoreFileTracker! 2024-12-02T17:15:06,456 INFO [master/fa731d6f0321:0.Chore.1 {}] migrate.RollingUpgradeChore(85): All Rolling-Upgrade tasks are complete, shutdown RollingUpgradeChore! 2024-12-02T17:15:06,541 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-02T17:15:06,542 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:15:06,542 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:06,544 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:06,545 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-02T17:15:06,547 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=143, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:15:06,547 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-02T17:15:06,564 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:06,564 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:06,573 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:06,573 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0075 connected 2024-12-02T17:15:06,650 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-02T17:15:06,681 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0075, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:06,690 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=144, ppid=143, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:06,766 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:15:06,842 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:06,843 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=144 2024-12-02T17:15:06,843 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:15:06,845 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:15:06,845 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:15:06,846 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:06,846 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0074, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:06,846 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0074, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:06,861 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-02T17:15:06,957 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0074, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:06,957 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1b0bc5ed to 127.0.0.1:60462 2024-12-02T17:15:06,957 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:06,975 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:06,975 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:15:06,975 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=144 2024-12-02T17:15:06,976 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=144 2024-12-02T17:15:06,977 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:06,978 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=144, resume processing ppid=143 2024-12-02T17:15:06,978 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-02T17:15:06,979 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=144, ppid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 287 msec 2024-12-02T17:15:06,980 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 434 msec 2024-12-02T17:15:07,002 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x63660195 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@171bb810 2024-12-02T17:15:07,010 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:07,010 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:07,010 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@13504630, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:07,011 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:07,018 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:07,018 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:07,018 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d0077 connected 2024-12-02T17:15:07,171 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-02T17:15:07,171 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:15:07,172 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:07,173 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:15:07,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=145, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-02T17:15:07,174 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-02T17:15:07,186 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-02T17:15:07,187 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:07,239 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id0x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:07,239 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0078 connected 2024-12-02T17:15:07,280 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-02T17:15:07,352 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@6985a838check-peer-cluster-id-0x10198534a1d0078, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:07,361 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=146, ppid=145, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:07,490 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-02T17:15:07,514 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:07,515 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=146 2024-12-02T17:15:07,515 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-02T17:15:07,515 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-02T17:15:07,515 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Peer 1 state or config changed. Will close the previous replication source and open a new one 2024-12-02T17:15:07,516 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:07,516 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d0077, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:07,516 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d0077, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:07,626 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d0077, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:07,626 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x63660195 to 127.0.0.1:60462 2024-12-02T17:15:07,627 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:07,639 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-02T17:15:07,639 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-02T17:15:07,639 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=146 2024-12-02T17:15:07,640 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=146 2024-12-02T17:15:07,641 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:07,643 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=146, resume processing ppid=145 2024-12-02T17:15:07,643 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:60462:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-02T17:15:07,643 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=146, ppid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 280 msec 2024-12-02T17:15:07,644 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 470 msec 2024-12-02T17:15:07,665 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x71f5ffb9 to 127.0.0.1:60462 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4c4cc648 2024-12-02T17:15:07,677 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-02T17:15:07,677 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-02T17:15:07,677 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1d08d992, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-02T17:15:07,678 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:60462 2024-12-02T17:15:07,685 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-02T17:15:07,685 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-02T17:15:07,685 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10198534a1d007a connected 2024-12-02T17:15:07,801 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-02T17:15:07,801 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-02T17:15:07,802 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-02T17:15:07,803 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:15:07,804 INFO [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-02T17:15:07,805 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=147, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:15:07,805 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] procedure2.ProcedureExecutor(1098): Stored pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:15:07,805 DEBUG [PEWorker-5 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=147 2024-12-02T17:15:07,805 DEBUG [PEWorker-5 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-02T17:15:07,806 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-02T17:15:07,806 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:07,809 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-02T17:15:07,818 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-02T17:15:07,818 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:15:07,818 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45999-0x10198534a1d0000, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-02T17:15:07,819 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=149, ppid=147, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-02T17:15:07,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-02T17:15:07,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:07,972 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to fa731d6f0321,40509,1733159661070 2024-12-02T17:15:07,973 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=149 2024-12-02T17:15:07,973 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-02T17:15:07,973 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-02T17:15:07,973 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-02T17:15:07,974 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-02T17:15:07,974 WARN [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10198534a1d007a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Unable to set watcher on znode (/hbase-test1/hbaseid) java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:07,975 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10198534a1d007a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received InterruptedException, will interrupt current thread and rethrow a SystemErrorException java.lang.InterruptedException: null at java.lang.Object.wait(Native Method) ~[?:?] at java.lang.Object.wait(Object.java:338) ~[?:?] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1604) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn.submitRequest(ClientCnxn.java:1576) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ZooKeeper.exists(ZooKeeper.java:1864) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.RecoverableZooKeeper.exists(RecoverableZooKeeper.java:250) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKUtil.checkExists(ZKUtil.java:158) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.readClusterIdZNode(ZKClusterId.java:59) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKClusterId.getUUIDForCluster(ZKClusterId.java:89) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.HBaseReplicationEndpoint.getPeerUUID(HBaseReplicationEndpoint.java:113) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:566) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-02T17:15:08,085 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10198534a1d007a, quorum=127.0.0.1:60462, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-02T17:15:08,085 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x71f5ffb9 to 127.0.0.1:60462 2024-12-02T17:15:08,086 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-02T17:15:08,086 INFO [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-02T17:15:08,095 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ZKUtil(111): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:15:08,106 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1/fa731d6f0321%2C40509%2C1733159661070.1733159663631 2024-12-02T17:15:08,106 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:15:08,106 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:40509-0x10198534a1d0001, quorum=127.0.0.1:60462, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/fa731d6f0321,40509,1733159661070/1 2024-12-02T17:15:08,106 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:15:08,107 DEBUG [RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=149 2024-12-02T17:15:08,107 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.HMaster(4106): Remote procedure done, pid=149 2024-12-02T17:15:08,108 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on fa731d6f0321,40509,1733159661070 suceeded 2024-12-02T17:15:08,109 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=149, resume processing ppid=147 2024-12-02T17:15:08,109 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=149, ppid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-02T17:15:08,118 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-02T17:15:08,118 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-02T17:15:08,120 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 314 msec 2024-12-02T17:15:08,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-02T17:15:08,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:08,120 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-02T17:15:08,430 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:08,941 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:09,371 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:15:09,960 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:11,971 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:13,588 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:15:15,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:19,370 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:15:19,440 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:15:24,953 DEBUG [master/fa731d6f0321:0.Chore.1 {}] balancer.RegionLocationFinder(172): Locality for region 75b753686f65c916787e2c95f48b987c changed from -1.0 to 0.0, refreshing cache 2024-12-02T17:15:25,991 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:36,071 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:39,590 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:15:46,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:49,370 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:15:56,171 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:15:59,601 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:16:16,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:16:19,371 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:16:19,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:16:36,411 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:16:39,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:16:49,371 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:16:56,450 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:16:59,871 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:17:16,481 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:17:19,371 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:17:19,891 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:17:36,521 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:17:39,961 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:17:49,372 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:17:56,650 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:18:00,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:18:16,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:18:19,372 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:18:20,191 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:18:36,860 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:18:40,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:18:49,373 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:18:57,061 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:19:00,390 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:19:17,071 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:19:19,373 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:19:20,591 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:19:21,087 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=660.99 KB, freeSize=879.35 MB, max=880 MB, blockCount=0, accesses=0, hits=0, hitRatio=0, cachingAccesses=0, cachingHits=0, cachingHitsRatio=0,evictions=29, evicted=0, evictedPerRun=0.0 2024-12-02T17:19:21,243 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=0, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-12-02T17:19:21,249 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-02T17:19:23,517 INFO [fa731d6f0321:40509Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-02T17:19:26,486 INFO [regionserver/fa731d6f0321:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:meta,,1.1588230740 because 1588230740/info has an old edit so flush to free WALs after random delay 89407 ms 2024-12-02T17:19:26,487 INFO [regionserver/fa731d6f0321:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c. because 75b753686f65c916787e2c95f48b987c/info has an old edit so flush to free WALs after random delay 108520 ms 2024-12-02T17:19:27,257 DEBUG [hconnection-0x4803368e-shared-pool-4 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:19:27,262 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:37284, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:19:27,268 DEBUG [master/fa731d6f0321:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-02T17:19:27,269 DEBUG [master/fa731d6f0321:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-02T17:19:27,270 DEBUG [master/fa731d6f0321:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-02T17:19:30,153 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:19:37,101 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:19:40,670 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:19:49,373 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:19:57,211 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:20:00,731 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:20:17,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:20:19,374 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:20:20,800 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:20:37,421 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:20:40,840 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:20:49,374 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:20:55,893 DEBUG [MemStoreFlusher.0 {}] regionserver.FlushAllLargeStoresPolicy(69): Since none of the CFs were above the size, flushing all. 2024-12-02T17:20:55,894 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 1588230740 3/3 column families, dataSize=1.23 KB heapSize=2.87 KB 2024-12-02T17:20:55,953 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/.tmp/info/b21672cbddce4939942627eb5573caf8 is 143, key is hbase:namespace,,1733159664963.75b753686f65c916787e2c95f48b987c./info:regioninfo/1733159666236/Put/seqid=0 2024-12-02T17:20:55,961 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741837_1013 (size=6595) 2024-12-02T17:20:56,364 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1.14 KB at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/.tmp/info/b21672cbddce4939942627eb5573caf8 2024-12-02T17:20:56,416 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/.tmp/table/ea4a6d0b60414c60b48ef9211bdd787e is 51, key is hbase:namespace/table:state/1733159666256/Put/seqid=0 2024-12-02T17:20:56,421 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741838_1014 (size=5242) 2024-12-02T17:20:56,822 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=94 B at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/.tmp/table/ea4a6d0b60414c60b48ef9211bdd787e 2024-12-02T17:20:56,836 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/.tmp/info/b21672cbddce4939942627eb5573caf8 as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/info/b21672cbddce4939942627eb5573caf8 2024-12-02T17:20:56,845 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/info/b21672cbddce4939942627eb5573caf8, entries=10, sequenceid=9, filesize=6.4 K 2024-12-02T17:20:56,849 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/.tmp/table/ea4a6d0b60414c60b48ef9211bdd787e as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/table/ea4a6d0b60414c60b48ef9211bdd787e 2024-12-02T17:20:56,859 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/meta/1588230740/table/ea4a6d0b60414c60b48ef9211bdd787e, entries=2, sequenceid=9, filesize=5.1 K 2024-12-02T17:20:56,861 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~1.23 KB/1264, heapSize ~2.59 KB/2648, currentSize=0 B/0 for 1588230740 in 967ms, sequenceid=9, compaction requested=false 2024-12-02T17:20:56,862 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 1588230740: 2024-12-02T17:20:57,490 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:21:00,850 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:21:09,635 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:21:15,007 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 75b753686f65c916787e2c95f48b987c 1/1 column families, dataSize=78 B heapSize=488 B 2024-12-02T17:21:15,024 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c/.tmp/info/cc9ed665266746e788f3b15a455606d5 is 45, key is default/info:d/1733159666323/Put/seqid=0 2024-12-02T17:21:15,028 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741839_1015 (size=5037) 2024-12-02T17:21:15,429 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=78 B at sequenceid=6 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c/.tmp/info/cc9ed665266746e788f3b15a455606d5 2024-12-02T17:21:15,437 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c/.tmp/info/cc9ed665266746e788f3b15a455606d5 as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c/info/cc9ed665266746e788f3b15a455606d5 2024-12-02T17:21:15,445 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/data/hbase/namespace/75b753686f65c916787e2c95f48b987c/info/cc9ed665266746e788f3b15a455606d5, entries=2, sequenceid=6, filesize=4.9 K 2024-12-02T17:21:15,446 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~78 B/78, heapSize ~472 B/472, currentSize=0 B/0 for 75b753686f65c916787e2c95f48b987c in 439ms, sequenceid=6, compaction requested=false 2024-12-02T17:21:15,446 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 75b753686f65c916787e2c95f48b987c: 2024-12-02T17:21:17,610 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:21:19,374 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:21:20,921 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:21:37,721 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:21:40,950 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:21:49,374 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:21:54,635 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:21:56,211 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:21:57,741 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:22:00,991 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:22:17,900 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:22:19,375 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:22:21,201 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:22:37,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:22:39,636 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:22:41,211 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:22:41,351 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:22:49,375 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:22:58,181 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:23:01,551 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:23:18,300 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:23:19,375 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:23:21,650 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:23:24,636 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:23:26,212 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:23:38,400 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:23:41,731 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:23:49,376 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:23:58,470 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:24:01,781 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:24:09,637 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:24:11,212 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:24:18,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:24:19,376 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:24:21,086 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=660.99 KB, freeSize=879.35 MB, max=880 MB, blockCount=0, accesses=0, hits=0, hitRatio=0, cachingAccesses=0, cachingHits=0, cachingHitsRatio=0,evictions=59, evicted=0, evictedPerRun=0.0 2024-12-02T17:24:21,243 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=3, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-12-02T17:24:21,249 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-02T17:24:21,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:24:23,517 INFO [fa731d6f0321:40509Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-02T17:24:24,729 DEBUG [master/fa731d6f0321:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-02T17:24:24,958 DEBUG [hconnection-0x4803368e-shared-pool-6 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:24:24,959 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:33630, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:24:24,975 DEBUG [master/fa731d6f0321:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-02T17:24:24,975 DEBUG [master/fa731d6f0321:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-02T17:24:24,979 DEBUG [master/fa731d6f0321:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-02T17:24:30,153 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:24:38,690 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:24:41,961 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:24:49,376 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:24:54,637 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:24:56,212 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:24:58,880 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:25:01,990 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:25:19,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:25:19,376 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:25:22,171 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:25:39,170 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:25:39,638 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:25:41,213 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:25:42,220 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:25:49,377 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:25:59,290 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:26:02,240 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:26:19,377 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:26:19,450 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:26:22,281 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:26:24,638 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:26:26,213 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:26:39,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:26:42,350 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:26:49,377 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:26:59,700 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:27:02,450 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:27:09,638 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:27:11,213 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:27:19,377 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:27:19,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:27:22,500 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:27:39,901 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:27:42,561 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:27:49,378 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:27:54,639 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:27:56,214 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:28:00,011 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:28:02,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:28:19,378 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:28:20,141 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:28:22,960 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:28:39,640 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:28:40,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:28:41,214 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:28:43,121 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:28:49,379 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:29:00,501 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:29:03,171 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:29:19,379 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:29:20,571 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:29:21,087 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=2, hits=0, hitRatio=0, cachingAccesses=2, cachingHits=0, cachingHitsRatio=0,evictions=89, evicted=0, evictedPerRun=0.0 2024-12-02T17:29:21,243 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=3, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-12-02T17:29:21,249 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-02T17:29:22,571 DEBUG [master:store-WAL-Roller {}] wal.AbstractWALRoller(200): WAL AsyncFSWAL fa731d6f0321%2C45999%2C1733159660197:(num 1733159662399) roll period 900000 ms elapsed 2024-12-02T17:29:22,588 DEBUG [master:store-WAL-Roller {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197/fa731d6f0321%2C45999%2C1733159660197.1733160562571, exclude list is [], retry=0 2024-12-02T17:29:22,592 DEBUG [RS-EventLoopGroup-3-3 {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(816): SASL client skipping handshake in unsecured configuration for addr = 127.0.0.1/127.0.0.1, datanodeId = DatanodeInfoWithStorage[127.0.0.1:44731,DS-9ba310a5-4506-4f12-8f97-b573b73f3f94,DISK] 2024-12-02T17:29:22,595 INFO [master:store-Flusher {}] regionserver.HRegion(2837): Flushing 1595e783b53d99cd5eef43b6debb2682 4/4 column families, dataSize=428.68 KB heapSize=530.64 KB 2024-12-02T17:29:22,595 INFO [master:store-WAL-Roller {}] wal.AbstractFSWAL(837): Rolled WAL /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197/fa731d6f0321%2C45999%2C1733159660197.1733159662399 with entries=1160, filesize=503.08 KB; new WAL /user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197/fa731d6f0321%2C45999%2C1733159660197.1733160562571 2024-12-02T17:29:22,596 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:36273:36273)] 2024-12-02T17:29:22,596 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(751): hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/WALs/fa731d6f0321,45999,1733159660197/fa731d6f0321%2C45999%2C1733159660197.1733159662399 is not closed yet, will try archiving it next time 2024-12-02T17:29:22,598 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741830_1006 (size=515161) 2024-12-02T17:29:22,611 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/96297aa62deb40a1bbfb2726a04c5ce8 is 82, key is hbase:meta,,1/info:regioninfo/1733159664679/Put/seqid=0 2024-12-02T17:29:22,615 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741841_1017 (size=5672) 2024-12-02T17:29:23,017 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=504 B at sequenceid=1163 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/96297aa62deb40a1bbfb2726a04c5ce8 2024-12-02T17:29:23,051 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/85384301c57244c8a268a4fe109e56f2 is 293, key is \x00\x00\x00\x00\x00\x00\x00\x94/proc:d/1733159707804/Put/seqid=0 2024-12-02T17:29:23,055 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741842_1018 (size=11538) 2024-12-02T17:29:23,280 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:29:23,457 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=427.13 KB at sequenceid=1163 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/85384301c57244c8a268a4fe109e56f2 2024-12-02T17:29:23,470 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for 85384301c57244c8a268a4fe109e56f2 2024-12-02T17:29:23,483 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/0505c7ca6f2e4b9f8b71d66bddffabf7 is 69, key is fa731d6f0321,40509,1733159661070/rs:state/1733159663406/Put/seqid=0 2024-12-02T17:29:23,487 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741843_1019 (size=5156) 2024-12-02T17:29:23,517 INFO [fa731d6f0321:40509Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-02T17:29:23,890 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=65 B at sequenceid=1163 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/0505c7ca6f2e4b9f8b71d66bddffabf7 2024-12-02T17:29:23,925 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/aab8590140f5413bbcabfd90b75705e0 is 68, key is replication_peer_modification_on/state:d/1733159703364/Put/seqid=0 2024-12-02T17:29:23,929 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:44731 is added to blk_1073741844_1020 (size=5154) 2024-12-02T17:29:24,332 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1 KB at sequenceid=1163 (bloomFilter=true), to=hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/aab8590140f5413bbcabfd90b75705e0 2024-12-02T17:29:24,347 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/96297aa62deb40a1bbfb2726a04c5ce8 as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/96297aa62deb40a1bbfb2726a04c5ce8 2024-12-02T17:29:24,355 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/96297aa62deb40a1bbfb2726a04c5ce8, entries=8, sequenceid=1163, filesize=5.5 K 2024-12-02T17:29:24,356 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/85384301c57244c8a268a4fe109e56f2 as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/85384301c57244c8a268a4fe109e56f2 2024-12-02T17:29:24,364 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for 85384301c57244c8a268a4fe109e56f2 2024-12-02T17:29:24,365 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/85384301c57244c8a268a4fe109e56f2, entries=149, sequenceid=1163, filesize=11.3 K 2024-12-02T17:29:24,366 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/0505c7ca6f2e4b9f8b71d66bddffabf7 as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/0505c7ca6f2e4b9f8b71d66bddffabf7 2024-12-02T17:29:24,373 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/0505c7ca6f2e4b9f8b71d66bddffabf7, entries=1, sequenceid=1163, filesize=5.0 K 2024-12-02T17:29:24,375 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/aab8590140f5413bbcabfd90b75705e0 as hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/aab8590140f5413bbcabfd90b75705e0 2024-12-02T17:29:24,381 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/aab8590140f5413bbcabfd90b75705e0, entries=1, sequenceid=1163, filesize=5.0 K 2024-12-02T17:29:24,382 INFO [master:store-Flusher {}] regionserver.HRegion(3040): Finished flush of dataSize ~428.68 KB/438973, heapSize ~530.58 KB/543312, currentSize=0 B/0 for 1595e783b53d99cd5eef43b6debb2682 in 1787ms, sequenceid=1163, compaction requested=false 2024-12-02T17:29:24,382 DEBUG [master:store-Flusher {}] regionserver.HRegion(2538): Flush status journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-02T17:29:24,640 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:29:26,215 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:29:26,471 DEBUG [master/fa731d6f0321:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-02T17:29:26,471 DEBUG [master/fa731d6f0321:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-02T17:29:26,471 DEBUG [hconnection-0x4803368e-shared-pool-8 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:29:26,472 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:54882, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:29:26,476 DEBUG [master/fa731d6f0321:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-02T17:29:30,152 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:29:40,610 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:29:43,291 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:29:49,379 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:30:00,631 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:30:03,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:30:09,641 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:30:11,216 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:30:19,380 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:30:20,751 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:30:23,540 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:30:40,801 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:30:43,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:30:49,380 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:30:54,641 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:30:56,216 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:31:00,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:31:03,820 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:31:19,381 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:31:20,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:31:23,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:31:39,642 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:31:41,001 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:31:41,216 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:31:44,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:31:49,381 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:32:01,200 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:32:04,061 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:32:19,381 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:32:21,370 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:32:24,181 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:32:24,643 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:32:26,217 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:32:41,540 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:32:44,351 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:32:49,382 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:33:01,731 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:33:04,410 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:33:09,643 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:33:11,217 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:33:19,382 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:33:21,821 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:33:24,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:33:41,921 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:33:44,520 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:33:49,383 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:33:54,644 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:33:56,218 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:34:02,060 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:34:04,681 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:34:19,383 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:34:21,087 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=4, hits=2, hitRatio=50.00%, , cachingAccesses=4, cachingHits=2, cachingHitsRatio=50.00%, evictions=119, evicted=0, evictedPerRun=0.0 2024-12-02T17:34:21,243 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=6, created chunk count=7, reused chunk count=1, reuseRatio=12.50% 2024-12-02T17:34:21,249 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-02T17:34:22,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:34:23,517 INFO [fa731d6f0321:40509Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-02T17:34:24,881 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:34:30,152 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:34:30,427 DEBUG [hconnection-0x4803368e-shared-pool-10 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:34:30,430 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:34110, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:34:30,432 DEBUG [master/fa731d6f0321:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-02T17:34:30,433 DEBUG [master/fa731d6f0321:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-02T17:34:30,440 DEBUG [master/fa731d6f0321:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-02T17:34:30,440 DEBUG [master/fa731d6f0321:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-02T17:34:39,644 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:34:41,219 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:34:42,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:34:44,891 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:34:49,384 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:35:02,281 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:35:05,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:35:19,384 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:35:22,430 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:35:24,645 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:35:25,260 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:35:26,219 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:35:42,561 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:35:45,371 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:35:49,385 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:36:02,671 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:36:05,560 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:36:09,645 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:36:11,220 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:36:19,385 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:36:22,690 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:36:25,731 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:36:42,811 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:36:45,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:36:49,385 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:36:54,646 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:36:56,220 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:37:02,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:37:05,820 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:37:19,386 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:37:23,021 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:37:25,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:37:39,647 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:37:41,221 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:37:43,050 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:37:46,041 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:37:49,386 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:38:03,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:38:06,251 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:38:19,386 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:38:23,291 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:38:24,647 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:38:26,221 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:38:26,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:38:43,331 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:38:46,651 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:38:49,387 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:39:03,431 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:39:06,710 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:39:09,648 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:39:11,221 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:39:19,387 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:39:21,087 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=6, hits=4, hitRatio=66.67%, , cachingAccesses=6, cachingHits=4, cachingHitsRatio=66.67%, evictions=149, evicted=0, evictedPerRun=0.0 2024-12-02T17:39:21,243 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=6, created chunk count=7, reused chunk count=1, reuseRatio=12.50% 2024-12-02T17:39:21,249 DEBUG [master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-02T17:39:23,517 INFO [fa731d6f0321:40509Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-02T17:39:23,590 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:39:25,265 DEBUG [master/fa731d6f0321:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-02T17:39:25,265 DEBUG [master/fa731d6f0321:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-02T17:39:25,267 DEBUG [hconnection-0x4803368e-shared-pool-12 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-02T17:39:25,269 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:52590, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-02T17:39:25,272 DEBUG [master/fa731d6f0321:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-02T17:39:26,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:39:30,152 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-02T17:39:43,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:39:46,991 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-02T17:39:49,388 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-02T17:39:54,648 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-02T17:39:56,222 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 75b753686f65c916787e2c95f48b987c, had cached 0 bytes from a total of 5037 2024-12-02T17:40:03,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-02T17:40:07,071 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 ====> TEST TIMED OUT. PRINTING THREAD DUMP. <==== Timestamp: 2024-12-02 05:40:16,349 "NIOWorkerThread-7" daemon prio=5 tid=163 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "MemStoreFlusher.0" daemon prio=5 tid=277 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:77) at app//org.apache.hadoop.hbase.regionserver.MemStoreFlusher$FlushHandler.run(MemStoreFlusher.java:322) "master:store-WAL-Roller" daemon prio=5 tid=225 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.wal.AbstractWALRoller.run(AbstractWALRoller.java:179) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=45999" daemon prio=5 tid=179 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "PEWorker-3" daemon prio=5 tid=247 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "RS-EventLoopGroup-1-2" daemon prio=10 tid=267 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/fa731d6f0321:0.leaseChecker" daemon prio=5 tid=274 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.regionserver.LeaseManager.run(LeaseManager.java:82) "qtp1360798187-88-acceptor-0@7f49f38e-ServerConnector@2ed72052{HTTP/1.1, (http/1.1)}{localhost:40785}" daemon prio=3 tid=88 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at app//org.eclipse.jetty.server.ServerConnector.accept(ServerConnector.java:388) at app//org.eclipse.jetty.server.AbstractConnector$Acceptor.run(AbstractConnector.java:704) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Timer for 'HBase' metrics system" daemon prio=5 tid=1013 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "PacketResponder: BP-283315478-172.17.0.2-1733159656995:blk_1073741834_1010, type=LAST_IN_PIPELINE" daemon prio=5 tid=296 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "fa731d6f0321:40509Replication Statistics #0" daemon prio=5 tid=279 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-4" daemon prio=5 tid=159 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "zk-event-processor-pool-0" daemon prio=5 tid=160 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp214549639-40" daemon prio=5 tid=40 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6a844252a8.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS_OPEN_META-regionserver/fa731d6f0321:0-0" daemon prio=5 tid=294 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "MarkedDeleteBlockScrubberThread" daemon prio=5 tid=48 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$MarkedDeleteBlockScrubber.run(BlockManager.java:5326) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server Responder" daemon prio=5 tid=97 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.ipc.Server$Responder.doRunLoop(Server.java:1733) at app//org.apache.hadoop.ipc.Server$Responder.run(Server.java:1716) "ReadOnlyZKClient-127.0.0.1:60462@0x047c7384" daemon prio=5 tid=325 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:370) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$$Lambda$760/0x00007f6a84b4cff8.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test.LruBlockCache.EvictionThread" daemon prio=5 tid=187 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.io.hfile.LruBlockCache$EvictionThread.run(LruBlockCache.java:957) "RedundancyMonitor" daemon prio=5 tid=47 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at java.base@17.0.11/java.lang.Thread.sleep(Thread.java:344) at java.base@17.0.11/java.util.concurrent.TimeUnit.sleep(TimeUnit.java:446) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$RedundancyMonitor.run(BlockManager.java:5352) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeResourceMonitor@40827a80" daemon prio=5 tid=72 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeResourceMonitor.run(FSNamesystem.java:4550) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=45999" daemon prio=5 tid=181 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Server listener on 0" daemon prio=5 tid=54 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener.run(Server.java:1559) "Async-Client-Retry-Timer-pool-0" daemon prio=5 tid=319 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "DataXceiver for client DFSClient_NONMAPREDUCE_-2053343619_22 at /127.0.0.1:55260 [Receiving block BP-283315478-172.17.0.2-1733159656995:blk_1073741840_1016]" daemon prio=5 tid=892 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics" daemon prio=5 tid=211 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-14" daemon prio=5 tid=170 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "main" prio=5 tid=1 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/java.lang.Thread.dumpThreads(Native Method) at java.base@17.0.11/java.lang.Thread.getAllStackTraces(Thread.java:1671) at app//org.apache.hadoop.hbase.TimedOutTestsListener.buildThreadDump(TimedOutTestsListener.java:92) at app//org.apache.hadoop.hbase.TimedOutTestsListener.buildThreadDiagnosticString(TimedOutTestsListener.java:78) at app//org.apache.hadoop.hbase.TimedOutTestsListener.testFailure(TimedOutTestsListener.java:65) at app//org.junit.runner.notification.SynchronizedRunListener.testFailure(SynchronizedRunListener.java:94) at app//org.junit.runner.notification.RunNotifier$6.notifyListener(RunNotifier.java:177) at app//org.junit.runner.notification.RunNotifier$SafeNotifier.run(RunNotifier.java:72) at app//org.junit.runner.notification.RunNotifier.fireTestFailures(RunNotifier.java:173) at app//org.junit.runner.notification.RunNotifier.fireTestFailure(RunNotifier.java:167) at app//org.apache.maven.surefire.common.junit4.Notifier.fireTestFailure(Notifier.java:100) at app//org.junit.internal.runners.model.EachTestNotifier.addFailure(EachTestNotifier.java:23) at app//org.junit.internal.runners.model.EachTestNotifier.addMultipleFailureException(EachTestNotifier.java:29) at app//org.junit.internal.runners.model.EachTestNotifier.addFailure(EachTestNotifier.java:21) at app//org.junit.runners.ParentRunner.run(ParentRunner.java:419) at app//org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:316) at app//org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:240) at app//org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:214) at app//org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:155) at app//org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:385) at app//org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:162) at app//org.apache.maven.surefire.booter.ForkedBooter.run(ForkedBooter.java:507) at app//org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:495) "HBase-Metrics2-1" daemon prio=5 tid=153 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-5" daemon prio=5 tid=249 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "NIOWorkerThread-11" daemon prio=5 tid=167 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.namenode.LeaseManager$Monitor@6701d9b6" daemon prio=5 tid=71 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.LeaseManager$Monitor.run(LeaseManager.java:537) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcClient-timer-pool-0" daemon prio=5 tid=241 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:60462)" daemon prio=5 tid=403 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "Reference Handler" daemon prio=10 tid=2 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/java.lang.ref.Reference.waitForReferencePendingList(Native Method) at java.base@17.0.11/java.lang.ref.Reference.processPendingReferences(Reference.java:253) at java.base@17.0.11/java.lang.ref.Reference$ReferenceHandler.run(Reference.java:215) "GcTimeMonitor obsWindow = 60000, sleepInterval = 5000, maxGcTimePerc = 100" daemon prio=5 tid=35 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.GcTimeMonitor.run(GcTimeMonitor.java:161) "RS-EventLoopGroup-1-1" daemon prio=10 tid=154 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-2" daemon prio=5 tid=157 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-8" daemon prio=5 tid=164 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:60462)" daemon prio=5 tid=155 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "RegionServerTracker-0" daemon prio=5 tid=268 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "JvmPauseMonitor" daemon prio=5 tid=271 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:148) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45999" daemon prio=5 tid=173 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "RS-EventLoopGroup-3-2" daemon prio=10 tid=234 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait0(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:193) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWait(EpollEventLoop.java:304) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:368) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Hadoop-Metrics-Updater-0" daemon prio=5 tid=98 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS_REFRESH_PEER-regionserver/fa731d6f0321:0-0" daemon prio=5 tid=334 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 3 on default port 45201" daemon prio=5 tid=67 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "NIOWorkerThread-12" daemon prio=5 tid=168 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "M:0;fa731d6f0321:45999" daemon prio=5 tid=184 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:81) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:64) at app//org.apache.hadoop.hbase.master.HMaster.waitForMasterActive(HMaster.java:702) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.initializeZooKeeper(HRegionServer.java:1014) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.preRegistrationInitialization(HRegionServer.java:954) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.run(HRegionServer.java:1075) at app//org.apache.hadoop.hbase.master.HMaster.run(HMaster.java:603) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ProcedureDispatcherTimeoutThread" daemon prio=5 tid=250 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.RemoteProcedureDispatcher$TimeoutExecutorThread.run(RemoteProcedureDispatcher.java:328) "pool-1-thread-1" daemon prio=5 tid=14 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.run(EPollPort.java:275) at java.base@17.0.11/sun.nio.ch.AsynchronousChannelGroupImpl$1.run(AsynchronousChannelGroupImpl.java:113) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SSL Certificates Store Monitor" daemon prio=5 tid=25 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:537) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/dfs/data/data1)" daemon prio=5 tid=117 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.VolumeScanner.run(VolumeScanner.java:656) "org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor@169fbdd9" daemon prio=5 tid=49 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor.run(HeartbeatManager.java:563) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-9" daemon prio=5 tid=165 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=40509" daemon prio=5 tid=202 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "pool-11-thread-1" prio=5 tid=69 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-EventThread" daemon prio=5 tid=156 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "DataXceiver for client DFSClient_NONMAPREDUCE_857854957_22 at /127.0.0.1:34226 [Receiving block BP-283315478-172.17.0.2-1733159656995:blk_1073741832_1008]" daemon prio=5 tid=281 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Client (600310644) connection to localhost/127.0.0.1:45201 from jenkins" daemon prio=5 tid=109 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.ipc.Client$Connection.waitForWork(Client.java:1042) at app//org.apache.hadoop.ipc.Client$Connection.run(Client.java:1093) "AsyncFSWAL-0-hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6-prefix:fa731d6f0321,40509,1733159661070" daemon prio=5 tid=284 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp214549639-38" daemon prio=5 tid=38 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6a844252a8.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 3 on default port 43317" daemon prio=5 tid=107 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "region-location-0" daemon prio=5 tid=317 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=40509" daemon prio=5 tid=204 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "AsyncFSWAL-0-hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6/MasterData-prefix:fa731d6f0321,45999,1733159660197" daemon prio=5 tid=237 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Block report processor" daemon prio=5 tid=51 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$BlockReportProcessingThread.processQueue(BlockManager.java:5627) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$BlockReportProcessingThread.run(BlockManager.java:5614) "Signal Dispatcher" daemon prio=9 tid=4 runnable java.lang.Thread.State: RUNNABLE "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=45999" daemon prio=5 tid=176 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "pool-5-thread-1" prio=5 tid=36 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RPCClient-NioEventLoopGroup-4-1" daemon prio=5 tid=324 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:68) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:879) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-10" daemon prio=5 tid=166 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-EventThread" daemon prio=5 tid=404 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "surefire-forkedjvm-stream-flusher" daemon prio=5 tid=16 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Session-HouseKeeper-3e504af5-1" prio=5 tid=45 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-EventLoopGroup-3-1" daemon prio=10 tid=186 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait0(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:193) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWait(EpollEventLoop.java:304) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:368) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp214549639-39" daemon prio=5 tid=39 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6a844252a8.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server idle connection scanner for port 45201" daemon prio=5 tid=56 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "nioEventLoopGroup-2-1" prio=10 tid=92 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:68) at app//io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:879) at app//io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) at app//io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:994) at app//io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RPCClient-NioEventLoopGroup-4-2" daemon prio=5 tid=328 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.SelectedSelectionKeySetSelector.select(SelectedSelectionKeySetSelector.java:62) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.select(NioEventLoop.java:883) at app//org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:526) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RequestThrottler" daemon prio=5 tid=144 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.RequestThrottler.run(RequestThrottler.java:147) "Monitor thread for TaskMonitor" daemon prio=5 tid=209 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.monitoring.TaskMonitor$MonitorRunnable.run(TaskMonitor.java:325) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-2" daemon prio=5 tid=751 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SyncThread:0" daemon prio=5 tid=142 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.SyncRequestProcessor.run(SyncRequestProcessor.java:170) "pool-1-thread-2" daemon prio=5 tid=15 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.poll(EPollPort.java:200) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.run(EPollPort.java:281) at java.base@17.0.11/sun.nio.ch.AsynchronousChannelGroupImpl$1.run(AsynchronousChannelGroupImpl.java:113) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/fa731d6f0321:0:becomeActiveMaster-MemStoreChunkPool Statistics" daemon prio=5 tid=213 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master:store-Flusher" daemon prio=5 tid=240 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1759) at app//org.apache.hadoop.hbase.master.region.MasterRegionFlusherAndCompactor.flushLoop(MasterRegionFlusherAndCompactor.java:200) at app//org.apache.hadoop.hbase.master.region.MasterRegionFlusherAndCompactor$$Lambda$481/0x00007f6a849ba0f0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-6" daemon prio=5 tid=162 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@37a14715" daemon prio=5 tid=34 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-14-thread-1" daemon prio=5 tid=132 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.PeerCache@2c7b3802" daemon prio=5 tid=215 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.PeerCache.run(PeerCache.java:253) at app//org.apache.hadoop.hdfs.PeerCache.access$000(PeerCache.java:46) at app//org.apache.hadoop.hdfs.PeerCache$1.run(PeerCache.java:124) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=40509" daemon prio=5 tid=197 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "Session-HouseKeeper-766db3cd-1" prio=5 tid=91 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "zk-event-processor-pool-0" daemon prio=5 tid=194 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=45999" daemon prio=5 tid=178 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "Time-limited test" daemon prio=5 tid=22 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.CompletableFuture$Signaller.block(CompletableFuture.java:1864) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.CompletableFuture.waitingGet(CompletableFuture.java:1898) at java.base@17.0.11/java.util.concurrent.CompletableFuture.join(CompletableFuture.java:2117) at app//org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi.clearPeerAndQueues(TestAsyncReplicationAdminApi.java:96) at java.base@17.0.11/jdk.internal.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at java.base@17.0.11/jdk.internal.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:77) at java.base@17.0.11/jdk.internal.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.base@17.0.11/java.lang.reflect.Method.invoke(Method.java:568) at app//org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:59) at app//org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) at app//org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:56) at app//org.junit.internal.runners.statements.RunAfters.invokeMethod(RunAfters.java:46) at app//org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:33) at app//org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:61) at app//org.junit.runners.ParentRunner$3.evaluate(ParentRunner.java:306) at app//org.junit.runners.BlockJUnit4ClassRunner$1.evaluate(BlockJUnit4ClassRunner.java:100) at app//org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:366) at app//org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:103) at app//org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:63) at app//org.junit.runners.ParentRunner$4.run(ParentRunner.java:331) at app//org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79) at app//org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329) at app//org.junit.runners.ParentRunner.access$100(ParentRunner.java:66) at app//org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293) at app//org.junit.runners.ParentRunner.run(ParentRunner.java:413) at app//org.junit.runners.Suite.runChild(Suite.java:128) at app//org.junit.runners.Suite.runChild(Suite.java:27) at app//org.junit.runners.ParentRunner$4.run(ParentRunner.java:331) at app//org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:79) at app//org.junit.runners.ParentRunner.runChildren(ParentRunner.java:329) at app//org.junit.runners.ParentRunner.access$100(ParentRunner.java:66) at app//org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:293) at app//org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26) at app//org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27) at app//org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:299) at app//org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:293) at java.base@17.0.11/java.util.concurrent.FutureTask.run(FutureTask.java:264) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "CacheReplicationMonitor(1726012937)" daemon prio=5 tid=75 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1759) at app//org.apache.hadoop.hdfs.server.blockmanagement.CacheReplicationMonitor.run(CacheReplicationMonitor.java:186) "IPC Server handler 2 on default port 43317" daemon prio=5 tid=106 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "LeaseRenewer:jenkins.hfs.0@localhost:45201" daemon prio=5 tid=283 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.run(LeaseRenewer.java:441) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.access$800(LeaseRenewer.java:77) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server listener on 0" daemon prio=5 tid=94 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener.run(Server.java:1559) "FSEditLogAsync" daemon prio=5 tid=53 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at app//org.apache.hadoop.hdfs.server.namenode.FSEditLogAsync.dequeueEdit(FSEditLogAsync.java:241) at app//org.apache.hadoop.hdfs.server.namenode.FSEditLogAsync.run(FSEditLogAsync.java:250) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test.named-queue-events-pool-0" daemon prio=5 tid=152 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//com.lmax.disruptor.BlockingWaitStrategy.waitFor(BlockingWaitStrategy.java:47) at app//com.lmax.disruptor.ProcessingSequenceBarrier.waitFor(ProcessingSequenceBarrier.java:56) at app//com.lmax.disruptor.BatchEventProcessor.processEvents(BatchEventProcessor.java:159) at app//com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:125) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/fa731d6f0321:0:becomeActiveMaster-HFileCleaner.small.0-1733159663257" daemon prio=5 tid=265 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.PriorityBlockingQueue.take(PriorityBlockingQueue.java:535) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner.consumerLoop(HFileCleaner.java:285) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner$2.run(HFileCleaner.java:269) "IPC Server idle connection scanner for port 43317" daemon prio=5 tid=96 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "qtp214549639-41-acceptor-0@63c55de2-ServerConnector@da70730{HTTP/1.1, (http/1.1)}{localhost:38267}" daemon prio=3 tid=41 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at app//org.eclipse.jetty.server.ServerConnector.accept(ServerConnector.java:388) at app//org.eclipse.jetty.server.AbstractConnector$Acceptor.run(AbstractConnector.java:704) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1360798187-89" daemon prio=5 tid=89 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-3" daemon prio=5 tid=158 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "normalizer-worker-0" daemon prio=5 tid=252 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.master.normalizer.RegionNormalizerWorkQueue.take(RegionNormalizerWorkQueue.java:146) at app//org.apache.hadoop.hbase.master.normalizer.RegionNormalizerWorker.run(RegionNormalizerWorker.java:191) at java.base@17.0.11/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:539) at java.base@17.0.11/java.util.concurrent.FutureTask.run(FutureTask.java:264) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-1" daemon prio=5 tid=245 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "OldWALsCleaner-0" daemon prio=5 tid=256 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.master.cleaner.LogCleaner.deleteFile(LogCleaner.java:172) at app//org.apache.hadoop.hbase.master.cleaner.LogCleaner.lambda$createOldWalsCleaner$1(LogCleaner.java:152) at app//org.apache.hadoop.hbase.master.cleaner.LogCleaner$$Lambda$588/0x00007f6a84a55c78.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "java.util.concurrent.ThreadPoolExecutor$Worker@72606656[State = -1, empty queue]" daemon prio=5 tid=135 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "BP-283315478-172.17.0.2-1733159656995 heartbeating to localhost/127.0.0.1:45201" daemon prio=5 tid=102 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.IncrementalBlockReportManager.waitTillNextIBR(IncrementalBlockReportManager.java:158) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor.offerService(BPServiceActor.java:771) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:914) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS_COMPACTED_FILES_DISCHARGER-regionserver/fa731d6f0321:0-0" daemon prio=5 tid=758 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Common-Cleaner" daemon prio=8 tid=12 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/jdk.internal.ref.CleanerImpl.run(CleanerImpl.java:140) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) at java.base@17.0.11/jdk.internal.misc.InnocuousThread.run(InnocuousThread.java:162) "NIOWorkerThread-5" daemon prio=5 tid=161 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "MobFileCache #0" daemon prio=5 tid=191 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-EventThread" daemon prio=5 tid=193 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "Time-limited test-SendThread(127.0.0.1:60462)" daemon prio=5 tid=192 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "PEWorker-2" daemon prio=5 tid=246 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "PEWorker-4" daemon prio=5 tid=248 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:167) at app//org.apache.hadoop.hbase.procedure2.AbstractProcedureScheduler.poll(AbstractProcedureScheduler.java:149) at app//org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2128) "Finalizer" daemon prio=8 tid=3 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:176) at java.base@17.0.11/java.lang.ref.Finalizer$FinalizerThread.run(Finalizer.java:172) "master/fa731d6f0321:0:becomeActiveMaster-HFileCleaner.large.0-1733159663256" daemon prio=5 tid=264 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.util.StealJobQueue.take(StealJobQueue.java:101) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner.consumerLoop(HFileCleaner.java:285) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner$1.run(HFileCleaner.java:254) "IPC Server handler 0 on default port 45201" daemon prio=5 tid=64 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=40509" daemon prio=5 tid=201 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "qtp1360798187-87" daemon prio=5 tid=87 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6a844252a8.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/fa731d6f0321:0.Chore.1" daemon prio=5 tid=257 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$LazyPersistFileScrubber@18703272" daemon prio=5 tid=74 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$LazyPersistFileScrubber.run(FSNamesystem.java:4689) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=45999" daemon prio=5 tid=180 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "pool-6-thread-1" prio=5 tid=46 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-17-thread-1" prio=5 tid=86 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/dfs/data/data1/current/BP-283315478-172.17.0.2-1733159656995" daemon prio=5 tid=124 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=45999" daemon prio=5 tid=177 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "region-location-1" daemon prio=5 tid=318 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "DataXceiver for client DFSClient_NONMAPREDUCE_857854957_22 at /127.0.0.1:34252 [Receiving block BP-283315478-172.17.0.2-1733159656995:blk_1073741834_1010]" daemon prio=5 tid=295 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "surefire-forkedjvm-command-thread" daemon prio=5 tid=18 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.CountDownLatch.await(CountDownLatch.java:230) at java.base@17.0.11/sun.nio.ch.PendingFuture.get(PendingFuture.java:178) at app//org.apache.maven.surefire.api.util.internal.Channels$2.read(Channels.java:127) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at app//org.apache.maven.surefire.api.util.internal.Channels$3.readImpl(Channels.java:169) at app//org.apache.maven.surefire.api.util.internal.AbstractNoninterruptibleReadableChannel.read(AbstractNoninterruptibleReadableChannel.java:50) at app//org.apache.maven.surefire.api.stream.AbstractStreamDecoder.read(AbstractStreamDecoder.java:430) at app//org.apache.maven.surefire.api.stream.AbstractStreamDecoder.read(AbstractStreamDecoder.java:419) at app//org.apache.maven.surefire.api.stream.AbstractStreamDecoder.readMessageType(AbstractStreamDecoder.java:116) at app//org.apache.maven.surefire.booter.stream.CommandDecoder.decode(CommandDecoder.java:77) at app//org.apache.maven.surefire.booter.spi.CommandChannelDecoder.decode(CommandChannelDecoder.java:60) at app//org.apache.maven.surefire.booter.CommandReader$CommandRunnable.run(CommandReader.java:290) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Hadoop-Metrics-Updater-0" daemon prio=5 tid=58 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-16" daemon prio=5 tid=172 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SnapshotHandlerChoreCleaner" daemon prio=5 tid=253 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "LruBlockCacheStatsExecutor" daemon prio=5 tid=189 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PacketResponder: BP-283315478-172.17.0.2-1733159656995:blk_1073741840_1016, type=LAST_IN_PIPELINE" daemon prio=5 tid=893 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "snapshot-hfile-cleaner-cache-refresher" daemon prio=5 tid=261 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=40509" daemon prio=5 tid=203 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/dfs/data/data2)" daemon prio=5 tid=118 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.VolumeScanner.run(VolumeScanner.java:656) "AsyncFSWAL-0-hdfs://localhost:45201/user/jenkins/test-data/336980f5-9bda-9914-5cff-67fe2988a9b6-prefix:fa731d6f0321,40509,1733159661070.meta" daemon prio=5 tid=297 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/fa731d6f0321:0.procedureResultReporter" daemon prio=5 tid=276 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.regionserver.RemoteProcedureResultReporter.run(RemoteProcedureResultReporter.java:75) "NIOWorkerThread-13" daemon prio=5 tid=169 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ProcessThread(sid:0 cport:60462):" daemon prio=5 tid=143 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.PrepRequestProcessor.run(PrepRequestProcessor.java:142) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=40509" daemon prio=5 tid=198 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "ReadOnlyZKClient-127.0.0.1:60462@0x706227a7" daemon prio=5 tid=320 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:265) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:370) at app//org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$$Lambda$760/0x00007f6a84b4cff8.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45999" daemon prio=5 tid=174 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "qtp214549639-37" daemon prio=5 tid=37 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.select(ManagedSelector.java:606) at app//org.eclipse.jetty.io.ManagedSelector$SelectorProducer.produce(ManagedSelector.java:543) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produceTask(EatWhatYouKill.java:362) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.doProduce(EatWhatYouKill.java:186) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.tryProduce(EatWhatYouKill.java:173) at app//org.eclipse.jetty.util.thread.strategy.EatWhatYouKill.produce(EatWhatYouKill.java:137) at app//org.eclipse.jetty.io.ManagedSelector$$Lambda$257/0x00007f6a844252a8.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Socket Reader #1 for port 0" daemon prio=5 tid=55 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener$Reader.doRunLoop(Server.java:1497) at app//org.apache.hadoop.ipc.Server$Listener$Reader.run(Server.java:1476) "fa731d6f0321:45999" daemon prio=5 tid=251 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager.waitOnAssignQueue(AssignmentManager.java:2370) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager.processAssignQueue(AssignmentManager.java:2392) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager.access$600(AssignmentManager.java:112) at app//org.apache.hadoop.hbase.master.assignment.AssignmentManager$1.run(AssignmentManager.java:2332) "qtp214549639-42" daemon prio=5 tid=42 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 1 on default port 45201" daemon prio=5 tid=65 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "Idle-Rpc-Conn-Sweeper-pool-0" daemon prio=5 tid=242 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 2 on default port 45201" daemon prio=5 tid=66 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "NIOServerCxnFactory.AcceptThread:localhost/127.0.0.1:60462" daemon prio=5 tid=140 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$AcceptThread.select(NIOServerCnxnFactory.java:205) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$AcceptThread.run(NIOServerCnxnFactory.java:181) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeEditLogRoller@109c718e" daemon prio=5 tid=73 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeEditLogRoller.run(FSNamesystem.java:4592) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 4 on default port 43317" daemon prio=5 tid=108 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "NIOWorkerThread-1" daemon prio=5 tid=145 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 1 on default port 43317" daemon prio=5 tid=105 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "LeaseRenewer:jenkins@localhost:45201" daemon prio=5 tid=147 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.run(LeaseRenewer.java:441) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.access$800(LeaseRenewer.java:77) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "FsDatasetAsyncDiskServiceFixer" daemon prio=5 tid=136 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer.run(HBaseTestingUtility.java:599) "qtp214549639-43" daemon prio=5 tid=43 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ConnnectionExpirer" daemon prio=5 tid=137 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$ConnectionExpirerThread.run(NIOServerCnxnFactory.java:554) "RS:0;fa731d6f0321:40509-longCompactions-0" daemon prio=5 tid=272 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.util.StealJobQueue.take(StealJobQueue.java:101) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 4 on default port 45201" daemon prio=5 tid=68 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@46f644ae" daemon prio=5 tid=93 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/fa731d6f0321:0.logRoller" daemon prio=5 tid=275 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.wal.AbstractWALRoller.run(AbstractWALRoller.java:179) "RS-EventLoopGroup-1-3" daemon prio=10 tid=329 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp214549639-44" daemon prio=5 tid=44 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS:0;fa731d6f0321:40509" daemon prio=5 tid=206 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:81) at app//org.apache.hadoop.hbase.util.Sleeper.sleep(Sleeper.java:64) at app//org.apache.hadoop.hbase.regionserver.HRegionServer.run(HRegionServer.java:1164) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer.runRegionServer(MiniHBaseCluster.java:176) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer.access$000(MiniHBaseCluster.java:124) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer$1.run(MiniHBaseCluster.java:160) at java.base@17.0.11/java.security.AccessController.executePrivileged(AccessController.java:776) at java.base@17.0.11/java.security.AccessController.doPrivileged(AccessController.java:399) at java.base@17.0.11/javax.security.auth.Subject.doAs(Subject.java:376) at app//org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1930) at app//org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:322) at app//org.apache.hadoop.hbase.MiniHBaseCluster$MiniHBaseClusterRegionServer.run(MiniHBaseCluster.java:157) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1360798187-90" daemon prio=5 tid=90 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/9db60e85-2026-9b86-6af9-f31f85fae612/cluster_cfec3779-8610-a88f-2bc1-57ab6029efc2/dfs/data/data2/current/BP-283315478-172.17.0.2-1733159656995" daemon prio=5 tid=123 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "zk-event-processor-pool-0" daemon prio=5 tid=405 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Notification Thread" daemon prio=9 tid=13 runnable java.lang.Thread.State: RUNNABLE "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=40509" daemon prio=5 tid=199 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=40509" daemon prio=5 tid=200 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "WorkerMonitor" daemon prio=5 tid=244 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "RS_OPEN_PRIORITY_REGION-regionserver/fa731d6f0321:0-0" daemon prio=5 tid=312 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-15" daemon prio=5 tid=171 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=45999" daemon prio=5 tid=182 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Parameter Sending Thread for localhost/127.0.0.1:45201" daemon prio=5 tid=110 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.SynchronousQueue$TransferQueue.transfer(SynchronousQueue.java:704) at java.base@17.0.11/java.util.concurrent.SynchronousQueue.poll(SynchronousQueue.java:903) at app//org.apache.hadoop.ipc.Client$Connection$RpcRequestSender.run(Client.java:1121) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-19-thread-1" prio=5 tid=103 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=40509" daemon prio=5 tid=195 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "ProcExecTimeout" daemon prio=5 tid=243 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "org.apache.hadoop.hdfs.server.datanode.DataXceiverServer@45627e2e" daemon prio=5 tid=85 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at java.base@17.0.11/sun.nio.ch.ServerSocketAdaptor.accept(ServerSocketAdaptor.java:126) at app//org.apache.hadoop.hdfs.net.TcpPeerServer.accept(TcpPeerServer.java:85) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiverServer.run(DataXceiverServer.java:242) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Command processor" daemon prio=5 tid=101 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor$CommandProcessingThread.processQueue(BPServiceActor.java:1411) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor$CommandProcessingThread.run(BPServiceActor.java:1395) "SessionTracker" daemon prio=5 tid=141 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.zookeeper.server.SessionTrackerImpl.run(SessionTrackerImpl.java:163) "BootstrapNodeManager" daemon prio=5 tid=266 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOServerCxnFactory.SelectorThread-0" daemon prio=5 tid=138 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.select(NIOServerCnxnFactory.java:403) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.run(NIOServerCnxnFactory.java:368) "Socket Reader #1 for port 0" daemon prio=5 tid=95 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener$Reader.doRunLoop(Server.java:1497) at app//org.apache.hadoop.ipc.Server$Listener$Reader.run(Server.java:1476) "regionserver/fa731d6f0321:0.Chore.1" daemon prio=5 tid=273 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PacketResponder: BP-283315478-172.17.0.2-1733159656995:blk_1073741832_1008, type=LAST_IN_PIPELINE" daemon prio=5 tid=282 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-EventLoopGroup-3-3" daemon prio=10 tid=293 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait0(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:193) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWait(EpollEventLoop.java:304) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:368) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=40509" daemon prio=5 tid=196 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "NIOServerCxnFactory.SelectorThread-1" daemon prio=5 tid=139 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.select(NIOServerCnxnFactory.java:403) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$SelectorThread.run(NIOServerCnxnFactory.java:368) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45999" daemon prio=5 tid=175 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Server handler 0 on default port 43317" daemon prio=5 tid=104 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "DatanodeAdminMonitor-0" daemon prio=5 tid=62 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server Responder" daemon prio=5 tid=57 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.ipc.Server$Responder.doRunLoop(Server.java:1733) at app//org.apache.hadoop.ipc.Server$Responder.run(Server.java:1716) "org.apache.hadoop.fs.FileSystem$Statistics$StatisticsDataReferenceCleaner" daemon prio=5 tid=23 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:176) at app//org.apache.hadoop.fs.FileSystem$Statistics$StatisticsDataReferenceCleaner.run(FileSystem.java:4171) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.blockmanagement.PendingReconstructionBlocks$PendingReconstructionMonitor@51e76336" daemon prio=5 tid=61 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.PendingReconstructionBlocks$PendingReconstructionMonitor.run(PendingReconstructionBlocks.java:267) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840)