2024-12-14 20:21:28,007 main DEBUG Apache Log4j Core 2.17.2 initializing configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@231f98ef 2024-12-14 20:21:28,020 main DEBUG Took 0.011644 seconds to load 1 plugins from package org.apache.hadoop.hbase.logging 2024-12-14 20:21:28,020 main DEBUG PluginManager 'Core' found 129 plugins 2024-12-14 20:21:28,021 main DEBUG PluginManager 'Level' found 0 plugins 2024-12-14 20:21:28,022 main DEBUG PluginManager 'Lookup' found 16 plugins 2024-12-14 20:21:28,023 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,031 main DEBUG PluginManager 'TypeConverter' found 26 plugins 2024-12-14 20:21:28,045 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.util.MBeans", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,047 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,048 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.logging.TestJul2Slf4j", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,048 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,049 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.zookeeper", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,050 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,051 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSinkAdapter", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,051 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,052 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSystemImpl", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,053 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,054 main DEBUG LoggerConfig$Builder(additivity="false", level="WARN", levelAndRefs="null", name="org.apache.directory", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,055 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,056 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.ipc.FailedServers", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,057 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,058 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsConfig", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,058 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,059 main DEBUG LoggerConfig$Builder(additivity="null", level="INFO", levelAndRefs="null", name="org.apache.hadoop.hbase.ScheduledChore", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,059 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,060 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.regionserver.RSRpcServices", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,061 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,061 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,062 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,063 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,063 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-14 20:21:28,064 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hbase.thirdparty.io.netty.channel", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,065 main DEBUG Building Plugin[name=root, class=org.apache.logging.log4j.core.config.LoggerConfig$RootLogger]. 2024-12-14 20:21:28,067 main DEBUG LoggerConfig$RootLogger$Builder(additivity="null", level="null", levelAndRefs="INFO,Console", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-14 20:21:28,069 main DEBUG Building Plugin[name=loggers, class=org.apache.logging.log4j.core.config.LoggersPlugin]. 2024-12-14 20:21:28,072 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}) 2024-12-14 20:21:28,073 main DEBUG Building Plugin[name=layout, class=org.apache.logging.log4j.core.layout.PatternLayout]. 2024-12-14 20:21:28,074 main DEBUG PatternLayout$Builder(pattern="%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n", PatternSelector=null, Configuration(PropertiesConfig), Replace=null, charset="null", alwaysWriteExceptions="null", disableAnsi="null", noConsoleNoAnsi="null", header="null", footer="null") 2024-12-14 20:21:28,075 main DEBUG PluginManager 'Converter' found 47 plugins 2024-12-14 20:21:28,087 main DEBUG Building Plugin[name=appender, class=org.apache.hadoop.hbase.logging.HBaseTestAppender]. 2024-12-14 20:21:28,090 main DEBUG HBaseTestAppender$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, ={}) 2024-12-14 20:21:28,092 main DEBUG Starting HBaseTestOutputStreamManager SYSTEM_ERR 2024-12-14 20:21:28,092 main DEBUG Building Plugin[name=appenders, class=org.apache.logging.log4j.core.config.AppendersPlugin]. 2024-12-14 20:21:28,093 main DEBUG createAppenders(={Console}) 2024-12-14 20:21:28,094 main DEBUG Configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@231f98ef initialized 2024-12-14 20:21:28,094 main DEBUG Starting configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@231f98ef 2024-12-14 20:21:28,094 main DEBUG Started configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@231f98ef OK. 2024-12-14 20:21:28,095 main DEBUG Shutting down OutputStreamManager SYSTEM_OUT.false.false-1 2024-12-14 20:21:28,095 main DEBUG OutputStream closed 2024-12-14 20:21:28,096 main DEBUG Shut down OutputStreamManager SYSTEM_OUT.false.false-1, all resources released: true 2024-12-14 20:21:28,096 main DEBUG Appender DefaultConsole-1 stopped with status true 2024-12-14 20:21:28,096 main DEBUG Stopped org.apache.logging.log4j.core.config.DefaultConfiguration@1e683a3e OK 2024-12-14 20:21:28,194 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6 2024-12-14 20:21:28,198 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=StatusLogger 2024-12-14 20:21:28,200 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=ContextSelector 2024-12-14 20:21:28,202 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name= 2024-12-14 20:21:28,203 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.directory 2024-12-14 20:21:28,203 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSinkAdapter 2024-12-14 20:21:28,204 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.zookeeper 2024-12-14 20:21:28,204 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.logging.TestJul2Slf4j 2024-12-14 20:21:28,205 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSystemImpl 2024-12-14 20:21:28,205 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.util.MBeans 2024-12-14 20:21:28,205 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase 2024-12-14 20:21:28,206 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop 2024-12-14 20:21:28,206 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ipc.FailedServers 2024-12-14 20:21:28,206 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.regionserver.RSRpcServices 2024-12-14 20:21:28,207 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsConfig 2024-12-14 20:21:28,207 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hbase.thirdparty.io.netty.channel 2024-12-14 20:21:28,207 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ScheduledChore 2024-12-14 20:21:28,208 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Appenders,name=Console 2024-12-14 20:21:28,211 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-14 20:21:28,211 main DEBUG Reconfiguration complete for context[name=1dbd16a6] at URI jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-logging/target/hbase-logging-2.7.0-SNAPSHOT-tests.jar!/log4j2.properties (org.apache.logging.log4j.core.LoggerContext@1458ed9c) with optional ClassLoader: null 2024-12-14 20:21:28,211 main DEBUG Shutdown hook enabled. Registering a new one. 2024-12-14 20:21:28,212 main DEBUG LoggerContext[name=1dbd16a6, org.apache.logging.log4j.core.LoggerContext@1458ed9c] started OK. 2024-12-14T20:21:28,495 DEBUG [main {}] hbase.HBaseTestingUtility(348): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568 2024-12-14 20:21:28,499 main DEBUG AsyncLogger.ThreadNameStrategy=UNCACHED (user specified null, default is UNCACHED) 2024-12-14 20:21:28,500 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-14T20:21:28,526 INFO [main {}] hbase.HBaseClassTestRule(94): Test class org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi timeout: 26 mins 2024-12-14T20:21:28,545 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} 2024-12-14T20:21:28,547 INFO [Time-limited test {}] hbase.HBaseZKTestingUtility(82): Created new mini-cluster data directory: /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64, deleteOnExit=true 2024-12-14T20:21:28,548 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1140): STARTING DFS 2024-12-14T20:21:28,548 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting test.cache.data to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/test.cache.data in system properties and HBase conf 2024-12-14T20:21:28,549 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.tmp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/hadoop.tmp.dir in system properties and HBase conf 2024-12-14T20:21:28,550 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.log.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/hadoop.log.dir in system properties and HBase conf 2024-12-14T20:21:28,551 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.local.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/mapreduce.cluster.local.dir in system properties and HBase conf 2024-12-14T20:21:28,551 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.temp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/mapreduce.cluster.temp.dir in system properties and HBase conf 2024-12-14T20:21:28,551 INFO [Time-limited test {}] hbase.HBaseTestingUtility(811): read short circuit is OFF 2024-12-14T20:21:28,657 WARN [Time-limited test {}] util.NativeCodeLoader(60): Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2024-12-14T20:21:28,753 DEBUG [Time-limited test {}] fs.HFileSystem(310): The file system is not a DistributedFileSystem. Skipping on block location reordering 2024-12-14T20:21:28,757 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.node-labels.fs-store.root-dir in system properties and HBase conf 2024-12-14T20:21:28,757 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.node-attribute.fs-store.root-dir in system properties and HBase conf 2024-12-14T20:21:28,758 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.log-dirs to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.nodemanager.log-dirs in system properties and HBase conf 2024-12-14T20:21:28,758 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-14T20:21:28,758 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.timeline-service.entity-group-fs-store.active-dir in system properties and HBase conf 2024-12-14T20:21:28,759 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.timeline-service.entity-group-fs-store.done-dir in system properties and HBase conf 2024-12-14T20:21:28,759 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-14T20:21:28,759 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-14T20:21:28,760 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/dfs.datanode.shared.file.descriptor.paths in system properties and HBase conf 2024-12-14T20:21:28,760 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting nfs.dump.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/nfs.dump.dir in system properties and HBase conf 2024-12-14T20:21:28,761 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting java.io.tmpdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/java.io.tmpdir in system properties and HBase conf 2024-12-14T20:21:28,761 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-14T20:21:28,761 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/dfs.provided.aliasmap.inmemory.leveldb.dir in system properties and HBase conf 2024-12-14T20:21:28,761 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@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/fs.s3a.committer.staging.tmp.path in system properties and HBase conf 2024-12-14T20:21:29,755 WARN [Time-limited test {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-namenode.properties,hadoop-metrics2.properties 2024-12-14T20:21:29,839 INFO [Time-limited test {}] log.Log(170): Logging initialized @2524ms to org.eclipse.jetty.util.log.Slf4jLog 2024-12-14T20:21:29,954 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 2024-12-14T20:21:30,048 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 2024-12-14T20:21:30,096 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-14T20:21:30,097 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-14T20:21:30,099 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 660000ms 2024-12-14T20:21:30,126 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 2024-12-14T20:21:30,134 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@5926db06{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/hadoop.log.dir/,AVAILABLE} 2024-12-14T20:21:30,136 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@1bad608b{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-12-14T20:21:30,366 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@630af856{hdfs,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/java.io.tmpdir/jetty-localhost-44281-hadoop-hdfs-3_4_1-tests_jar-_-any-10072433738565269727/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/hdfs} 2024-12-14T20:21:30,377 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@83f158{HTTP/1.1, (http/1.1)}{localhost:44281} 2024-12-14T20:21:30,377 INFO [Time-limited test {}] server.Server(415): Started @3063ms 2024-12-14T20:21:30,954 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 2024-12-14T20:21:30,961 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 2024-12-14T20:21:30,963 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-14T20:21:30,964 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-14T20:21:30,964 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 660000ms 2024-12-14T20:21:30,965 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@784cfa59{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/hadoop.log.dir/,AVAILABLE} 2024-12-14T20:21:30,966 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@7eb8c9a3{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-12-14T20:21:31,077 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@79cb91e2{datanode,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/java.io.tmpdir/jetty-localhost-35949-hadoop-hdfs-3_4_1-tests_jar-_-any-382837539353440037/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/datanode} 2024-12-14T20:21:31,078 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@791f695a{HTTP/1.1, (http/1.1)}{localhost:35949} 2024-12-14T20:21:31,078 INFO [Time-limited test {}] server.Server(415): Started @3764ms 2024-12-14T20:21:31,141 WARN [Time-limited test {}] web.RestCsrfPreventionFilterHandler(75): Got null for restCsrfPreventionFilter - will not do any filtering. 2024-12-14T20:21:32,030 WARN [Thread-72 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/dfs/data/data1/current/BP-1348547021-172.17.0.3-1734207689317/current, will proceed with Du for space computation calculation, 2024-12-14T20:21:32,032 WARN [Thread-73 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/dfs/data/data2/current/BP-1348547021-172.17.0.3-1734207689317/current, will proceed with Du for space computation calculation, 2024-12-14T20:21:32,068 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 2024-12-14T20:21:32,121 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x5545fdccdc51e479 with lease ID 0xae080714fc834965: Processing first storage report for DS-1d94624a-9c90-4feb-9a82-e0022ad33e5a from datanode DatanodeRegistration(127.0.0.1:38879, datanodeUuid=4bec27ce-ed8a-4eb7-b820-1af9d215a128, infoPort=37495, infoSecurePort=0, ipcPort=37747, storageInfo=lv=-57;cid=testClusterID;nsid=373656894;c=1734207689317) 2024-12-14T20:21:32,122 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x5545fdccdc51e479 with lease ID 0xae080714fc834965: from storage DS-1d94624a-9c90-4feb-9a82-e0022ad33e5a node DatanodeRegistration(127.0.0.1:38879, datanodeUuid=4bec27ce-ed8a-4eb7-b820-1af9d215a128, infoPort=37495, infoSecurePort=0, ipcPort=37747, storageInfo=lv=-57;cid=testClusterID;nsid=373656894;c=1734207689317), blocks: 0, hasStaleStorage: true, processing time: 1 msecs, invalidatedBlocks: 0 2024-12-14T20:21:32,122 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x5545fdccdc51e479 with lease ID 0xae080714fc834965: Processing first storage report for DS-51929e7b-1895-45e2-b7f8-368e0a0221b1 from datanode DatanodeRegistration(127.0.0.1:38879, datanodeUuid=4bec27ce-ed8a-4eb7-b820-1af9d215a128, infoPort=37495, infoSecurePort=0, ipcPort=37747, storageInfo=lv=-57;cid=testClusterID;nsid=373656894;c=1734207689317) 2024-12-14T20:21:32,123 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x5545fdccdc51e479 with lease ID 0xae080714fc834965: from storage DS-51929e7b-1895-45e2-b7f8-368e0a0221b1 node DatanodeRegistration(127.0.0.1:38879, datanodeUuid=4bec27ce-ed8a-4eb7-b820-1af9d215a128, infoPort=37495, infoSecurePort=0, ipcPort=37747, storageInfo=lv=-57;cid=testClusterID;nsid=373656894;c=1734207689317), blocks: 0, hasStaleStorage: false, processing time: 0 msecs, invalidatedBlocks: 0 2024-12-14T20:21:32,163 DEBUG [Time-limited test {}] hbase.HBaseTestingUtility(703): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568 2024-12-14T20:21:32,286 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(259): Started connectionTimeout=30000, dir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/zookeeper_0, clientPort=64264, secureClientPort=-1, dataDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/zookeeper_0/version-2, dataDirSize=457 dataLogDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/zookeeper_0/version-2, dataLogSize=457 tickTime=2000, maxClientCnxns=300, minSessionTimeout=4000, maxSessionTimeout=40000, clientPortListenBacklog=-1, serverId=0 2024-12-14T20:21:32,310 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(284): Started MiniZooKeeperCluster and ran 'stat' on client port=64264 2024-12-14T20:21:32,326 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$ReorderWALBlocks 2024-12-14T20:21:32,329 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-14T20:21:32,632 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741825_1001 (size=7) 2024-12-14T20:21:33,049 INFO [Time-limited test {}] util.FSUtils(490): Created version file at hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05 with version=8 2024-12-14T20:21:33,050 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1460): Setting hbase.fs.tmp.dir to hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/hbase-staging 2024-12-14T20:21:33,162 DEBUG [Time-limited test {}] channel.MultithreadEventLoopGroup(44): -Dio.netty.eventLoopThreads: 16 2024-12-14T20:21:33,458 INFO [Time-limited test {}] client.ConnectionUtils(129): master/26a9feeac337:0 server-side Connection retries=6 2024-12-14T20:21:33,474 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-14T20:21:33,474 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-14T20:21:33,475 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-14T20:21:33,475 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-14T20:21:33,475 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-14T20:21:33,609 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 2024-12-14T20:21:33,665 INFO [Time-limited test {}] metrics.MetricRegistriesLoader(60): Loaded MetricRegistries class org.apache.hadoop.hbase.metrics.impl.MetricRegistriesImpl 2024-12-14T20:21:33,673 DEBUG [Time-limited test {}] util.ClassSize(228): Using Unsafe to estimate memory layout 2024-12-14T20:21:33,676 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-14T20:21:33,698 DEBUG [Time-limited test {}] channel.DefaultChannelId(84): -Dio.netty.processId: 27416 (auto-detected) 2024-12-14T20:21:33,699 DEBUG [Time-limited test {}] channel.DefaultChannelId(106): -Dio.netty.machineId: 02:42:ac:ff:fe:11:00:03 (auto-detected) 2024-12-14T20:21:33,717 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.3:45141 2024-12-14T20:21:33,727 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$ReorderWALBlocks 2024-12-14T20:21:33,730 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-14T20:21:33,744 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=master:45141 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:33,855 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:451410x0, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:33,857 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): master:45141-0x10026347a580000 connected 2024-12-14T20:21:33,963 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-14T20:21:33,966 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-14T20:21:33,969 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-14T20:21:33,974 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=45141 2024-12-14T20:21:33,974 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=45141 2024-12-14T20:21:33,974 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=45141 2024-12-14T20:21:33,975 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=45141 2024-12-14T20:21:33,975 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=45141 2024-12-14T20:21:33,981 INFO [Time-limited test {}] master.HMaster(488): hbase.rootdir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05, hbase.cluster.distributed=false 2024-12-14T20:21:34,051 INFO [Time-limited test {}] client.ConnectionUtils(129): regionserver/26a9feeac337:0 server-side Connection retries=6 2024-12-14T20:21:34,051 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-14T20:21:34,052 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-14T20:21:34,052 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-14T20:21:34,052 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-14T20:21:34,052 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-14T20:21:34,054 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 2024-12-14T20:21:34,056 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-14T20:21:34,057 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.3:33199 2024-12-14T20:21:34,059 INFO [Time-limited test {}] hfile.BlockCacheFactory(123): Allocating BlockCache size=880 MB, blockSize=64 KB 2024-12-14T20:21:34,063 DEBUG [Time-limited test {}] mob.MobFileCache(124): MobFileCache enabled with cacheSize=1000, evictPeriods=3600sec, evictRemainRatio=0.5 2024-12-14T20:21:34,065 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$ReorderWALBlocks 2024-12-14T20:21:34,068 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-14T20:21:34,072 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=regionserver:33199 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:34,086 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:331990x0, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:34,087 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): regionserver:33199-0x10026347a580001 connected 2024-12-14T20:21:34,087 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-14T20:21:34,088 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-14T20:21:34,089 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-14T20:21:34,090 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=33199 2024-12-14T20:21:34,091 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=33199 2024-12-14T20:21:34,091 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=33199 2024-12-14T20:21:34,092 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=33199 2024-12-14T20:21:34,092 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=33199 2024-12-14T20:21:34,094 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.HMaster(2445): Adding backup master ZNode /hbase/backup-masters/26a9feeac337,45141,1734207693156 2024-12-14T20:21:34,108 DEBUG [M:0;26a9feeac337:45141 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:M:0;26a9feeac337:45141 2024-12-14T20:21:34,122 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-14T20:21:34,122 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-14T20:21:34,124 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/backup-masters/26a9feeac337,45141,1734207693156 2024-12-14T20:21:34,161 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-14T20:21:34,161 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-14T20:21:34,161 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:34,161 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:34,162 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-14T20:21:34,163 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-14T20:21:34,163 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.ActiveMasterManager(245): Deleting ZNode for /hbase/backup-masters/26a9feeac337,45141,1734207693156 from backup master directory 2024-12-14T20:21:34,221 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/backup-masters/26a9feeac337,45141,1734207693156 2024-12-14T20:21:34,221 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-14T20:21:34,222 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-14T20:21:34,222 WARN [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-14T20:21:34,222 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.ActiveMasterManager(255): Registered as active master=26a9feeac337,45141,1734207693156 2024-12-14T20:21:34,225 INFO [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating data MemStoreChunkPool with chunk size 2 MB, max count 396, initial count 0 2024-12-14T20:21:34,226 INFO [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating index MemStoreChunkPool with chunk size 204.80 KB, max count 440, initial count 0 2024-12-14T20:21:34,287 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741826_1002 (size=42) 2024-12-14T20:21:34,691 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] util.FSUtils(639): Created cluster ID file at hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/hbase.id with ID: 59f0e019-1d42-4023-a8f2-0bc1cde5e5d1 2024-12-14T20:21:34,735 INFO [master/26a9feeac337:0:becomeActiveMaster {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-14T20:21:34,804 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:34,804 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:34,824 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741827_1003 (size=196) 2024-12-14T20:21:35,246 INFO [master/26a9feeac337:0: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)'} 2024-12-14T20:21:35,249 INFO [master/26a9feeac337:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(132): Injected flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000 2024-12-14T20:21:35,266 DEBUG [master/26a9feeac337:0: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$0(HMaster.java:590) ~[classes/:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:187) ~[classes/:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:177) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.lambda$run$1(HMaster.java:587) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-14T20:21:35,269 INFO [master/26a9feeac337:0:becomeActiveMaster {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-14T20:21:35,294 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741828_1004 (size=1189) 2024-12-14T20:21:35,718 INFO [master/26a9feeac337:0: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:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store 2024-12-14T20:21:35,732 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741829_1005 (size=34) 2024-12-14T20:21:36,142 INFO [master/26a9feeac337:0: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. 2024-12-14T20:21:36,143 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-14T20:21:36,144 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1681): Closing 1595e783b53d99cd5eef43b6debb2682, disabling compactions & flushes 2024-12-14T20:21:36,144 INFO [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1703): Closing region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-14T20:21:36,144 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1724): Waiting without time limit for close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-14T20:21:36,144 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1791): Acquired close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. after waiting 0 ms 2024-12-14T20:21:36,144 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1801): Updates disabled for region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-14T20:21:36,145 INFO [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1922): Closed master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-14T20:21:36,145 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1635): Region close journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-14T20:21:36,147 WARN [master/26a9feeac337:0:becomeActiveMaster {}] region.MasterRegion(249): failed to clean up initializing flag: hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/.initializing 2024-12-14T20:21:36,147 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] region.MasterRegion(219): WALDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156 2024-12-14T20:21:36,153 INFO [master/26a9feeac337:0:becomeActiveMaster {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-14T20:21:36,163 INFO [master/26a9feeac337:0:becomeActiveMaster {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=26a9feeac337%2C45141%2C1734207693156, suffix=, logDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156, archiveDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/oldWALs, maxLogs=10 2024-12-14T20:21:36,181 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156/26a9feeac337%2C45141%2C1734207693156.1734207696168, exclude list is [], retry=0 2024-12-14T20:21:36,195 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[127.0.0.1:38879,DS-1d94624a-9c90-4feb-9a82-e0022ad33e5a,DISK] 2024-12-14T20:21:36,198 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.ProtobufDecoder(117): Hadoop 3.3 and above shades protobuf. 2024-12-14T20:21:36,228 INFO [master/26a9feeac337:0:becomeActiveMaster {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156/26a9feeac337%2C45141%2C1734207693156.1734207696168 2024-12-14T20:21:36,229 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37495:37495)] 2024-12-14T20:21:36,229 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(7285): Opening region: {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''} 2024-12-14T20:21:36,229 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-14T20:21:36,232 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(7327): checking encryption for 1595e783b53d99cd5eef43b6debb2682 2024-12-14T20:21:36,233 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(7330): checking classloading for 1595e783b53d99cd5eef43b6debb2682 2024-12-14T20:21:36,266 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 2024-12-14T20:21:36,284 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 2024-12-14T20:21:36,288 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:36,290 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 2024-12-14T20:21:36,291 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 2024-12-14T20:21:36,294 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 2024-12-14T20:21:36,294 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:36,295 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/proc, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-14T20:21:36,295 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 2024-12-14T20:21:36,297 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 2024-12-14T20:21:36,298 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:36,299 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/rs, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-14T20:21:36,299 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 2024-12-14T20:21:36,302 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 2024-12-14T20:21:36,302 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:36,303 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/state, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-14T20:21:36,307 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-14T20:21:36,308 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-14T20:21:36,317 DEBUG [master/26a9feeac337:0: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. 2024-12-14T20:21:36,322 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1085): writing seq id for 1595e783b53d99cd5eef43b6debb2682 2024-12-14T20:21:36,327 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-14T20:21:36,328 INFO [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1102): Opened 1595e783b53d99cd5eef43b6debb2682; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=59044606, jitterRate=-0.12016680836677551}}}, FlushLargeStoresPolicy{flushSizeLowerBound=33554432} 2024-12-14T20:21:36,332 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] regionserver.HRegion(1001): Region open journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-14T20:21:36,333 INFO [master/26a9feeac337:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(122): Constructor flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000, compactMin=4 2024-12-14T20:21:36,358 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@2de8f584, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:36,385 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.HMaster(882): No meta location available on zookeeper, skip migrating... 2024-12-14T20:21:36,394 INFO [master/26a9feeac337:0:becomeActiveMaster {}] region.RegionProcedureStore(104): Starting the Region Procedure Store, number threads=5 2024-12-14T20:21:36,394 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(633): Starting 5 core workers (bigger of cpus/4 or 16) with max (burst) worker count=50 2024-12-14T20:21:36,396 INFO [master/26a9feeac337:0:becomeActiveMaster {}] region.RegionProcedureStore(255): Starting Region Procedure Store lease recovery... 2024-12-14T20:21:36,397 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(653): Recovered RegionProcedureStore lease in 1 msec 2024-12-14T20:21:36,401 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(667): Loaded RegionProcedureStore in 4 msec 2024-12-14T20:21:36,402 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.RemoteProcedureDispatcher(96): Instantiated, coreThreads=3 (allowCoreThreadTimeOut=true), queueMaxSize=32, operationDelay=150 2024-12-14T20:21:36,423 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.RegionServerTracker(127): Upgrading RegionServerTracker to active master mode; 0 have existingServerCrashProcedures, 0 possibly 'live' servers, and 0 'splitting'. 2024-12-14T20:21:36,433 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Unable to get data of znode /hbase/balancer because node does not exist (not necessarily an error) 2024-12-14T20:21:36,444 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/balancer already deleted, retry=false 2024-12-14T20:21:36,446 INFO [master/26a9feeac337:0:becomeActiveMaster {}] normalizer.SimpleRegionNormalizer(163): Updated configuration for key 'hbase.normalizer.merge.min_region_size.mb' from 0 to 1 2024-12-14T20:21:36,447 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Unable to get data of znode /hbase/normalizer because node does not exist (not necessarily an error) 2024-12-14T20:21:36,452 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/normalizer already deleted, retry=false 2024-12-14T20:21:36,454 INFO [master/26a9feeac337:0:becomeActiveMaster {}] normalizer.RegionNormalizerWorker(137): Normalizer rate limit set to unlimited 2024-12-14T20:21:36,457 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Unable to get data of znode /hbase/switch/split because node does not exist (not necessarily an error) 2024-12-14T20:21:36,460 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/split already deleted, retry=false 2024-12-14T20:21:36,462 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Unable to get data of znode /hbase/switch/merge because node does not exist (not necessarily an error) 2024-12-14T20:21:36,469 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/merge already deleted, retry=false 2024-12-14T20:21:36,478 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Unable to get data of znode /hbase/snapshot-cleanup because node does not exist (not necessarily an error) 2024-12-14T20:21:36,486 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/snapshot-cleanup already deleted, retry=false 2024-12-14T20:21:36,502 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-14T20:21:36,502 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-14T20:21:36,502 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:36,502 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:36,503 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.HMaster(826): Active/primary master=26a9feeac337,45141,1734207693156, sessionid=0x10026347a580000, setting cluster-up flag (Was=false) 2024-12-14T20:21:36,544 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:36,544 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:36,577 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/flush-table-proc/acquired, /hbase/flush-table-proc/reached, /hbase/flush-table-proc/abort 2024-12-14T20:21:36,579 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=26a9feeac337,45141,1734207693156 2024-12-14T20:21:36,611 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:36,611 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:36,635 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/online-snapshot/acquired, /hbase/online-snapshot/reached, /hbase/online-snapshot/abort 2024-12-14T20:21:36,637 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=26a9feeac337,45141,1734207693156 2024-12-14T20:21:36,707 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT; InitMetaProcedure table=hbase:meta 2024-12-14T20:21:36,711 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:RS:0;26a9feeac337:33199 2024-12-14T20:21:36,712 INFO [master/26a9feeac337:0:becomeActiveMaster {}] balancer.BaseLoadBalancer(575): slop=0.2 2024-12-14T20:21:36,713 INFO [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(1008): ClusterId : 59f0e019-1d42-4023-a8f2-0bc1cde5e5d1 2024-12-14T20:21:36,715 INFO [master/26a9feeac337:0: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. 2024-12-14T20:21:36,716 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(43): Procedure flush-table-proc initializing 2024-12-14T20:21:36,719 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] balancer.RegionLocationFinder(146): Skipping locality-based refresh due to oldStatus=null, newStatus=Master: 26a9feeac337,45141,1734207693156 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 2024-12-14T20:21:36,722 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_OPEN_REGION-master/26a9feeac337:0, corePoolSize=5, maxPoolSize=5 2024-12-14T20:21:36,722 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_CLOSE_REGION-master/26a9feeac337:0, corePoolSize=5, maxPoolSize=5 2024-12-14T20:21:36,722 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SERVER_OPERATIONS-master/26a9feeac337:0, corePoolSize=5, maxPoolSize=5 2024-12-14T20:21:36,722 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_META_SERVER_OPERATIONS-master/26a9feeac337:0, corePoolSize=5, maxPoolSize=5 2024-12-14T20:21:36,723 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=M_LOG_REPLAY_OPS-master/26a9feeac337:0, corePoolSize=10, maxPoolSize=10 2024-12-14T20:21:36,723 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SNAPSHOT_OPERATIONS-master/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,723 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_MERGE_OPERATIONS-master/26a9feeac337:0, corePoolSize=2, maxPoolSize=2 2024-12-14T20:21:36,723 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_TABLE_OPERATIONS-master/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,724 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.procedure2.CompletedProcedureCleaner; timeout=30000, timestamp=1734207726724 2024-12-14T20:21:36,725 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.DirScanPool(74): log_cleaner Cleaner pool size is 1 2024-12-14T20:21:36,726 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveLogCleaner 2024-12-14T20:21:36,728 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT, locked=true; InitMetaProcedure table=hbase:meta 2024-12-14T20:21:36,728 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(75): BOOTSTRAP: creating hbase:meta region 2024-12-14T20:21:36,729 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(45): Procedure flush-table-proc initialized 2024-12-14T20:21:36,729 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(43): Procedure online-snapshot initializing 2024-12-14T20:21:36,730 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.replication.master.ReplicationLogCleaner 2024-12-14T20:21:36,730 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreWALCleaner 2024-12-14T20:21:36,730 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveProcedureWALCleaner 2024-12-14T20:21:36,731 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.LogCleaner(148): Creating 1 old WALs cleaner threads 2024-12-14T20:21:36,731 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=LogsCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,732 DEBUG [PEWorker-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:36,732 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)'} 2024-12-14T20:21:36,733 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.DirScanPool(74): hfile_cleaner Cleaner pool size is 2 2024-12-14T20:21:36,734 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreHFileCleaner 2024-12-14T20:21:36,735 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.HFileLinkCleaner 2024-12-14T20:21:36,738 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.snapshot.SnapshotHFileCleaner 2024-12-14T20:21:36,739 INFO [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveHFileCleaner 2024-12-14T20:21:36,740 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(45): Procedure online-snapshot initialized 2024-12-14T20:21:36,740 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.HFileCleaner(260): Starting for large file=Thread[master/26a9feeac337:0:becomeActiveMaster-HFileCleaner.large.0-1734207696740,5,FailOnTimeoutGroup] 2024-12-14T20:21:36,741 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] cleaner.HFileCleaner(275): Starting for small files=Thread[master/26a9feeac337:0:becomeActiveMaster-HFileCleaner.small.0-1734207696740,5,FailOnTimeoutGroup] 2024-12-14T20:21:36,741 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HFileCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,741 DEBUG [RS:0;26a9feeac337:33199 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@60e1e5de, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:36,741 INFO [master/26a9feeac337:0: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. 2024-12-14T20:21:36,742 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=ReplicationBarrierCleaner, period=43200000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,742 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741831_1007 (size=1039) 2024-12-14T20:21:36,742 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=SnapshotCleaner, period=1800000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,743 DEBUG [RS:0;26a9feeac337:33199 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@1a9e4657, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=26a9feeac337/172.17.0.3:0 2024-12-14T20:21:36,745 INFO [RS:0;26a9feeac337:33199 {}] regionserver.RegionServerCoprocessorHost(67): System coprocessor loading is enabled 2024-12-14T20:21:36,746 INFO [RS:0;26a9feeac337:33199 {}] regionserver.RegionServerCoprocessorHost(68): Table coprocessor loading is enabled 2024-12-14T20:21:36,746 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(1090): About to register with Master. 2024-12-14T20:21:36,748 INFO [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(3073): reportForDuty to master=26a9feeac337,45141,1734207693156 with isa=26a9feeac337/172.17.0.3:33199, startcode=1734207694050 2024-12-14T20:21:36,758 DEBUG [RS:0;26a9feeac337:33199 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-14T20:21:36,784 INFO [RS-EventLoopGroup-1-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:42365, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-14T20:21:36,790 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=45141 {}] master.ServerManager(332): Checking decommissioned status of RegionServer 26a9feeac337,33199,1734207694050 2024-12-14T20:21:36,792 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=45141 {}] master.ServerManager(486): Registering regionserver=26a9feeac337,33199,1734207694050 2024-12-14T20:21:36,808 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(1725): Config from master: hbase.rootdir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05 2024-12-14T20:21:36,808 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(1725): Config from master: fs.defaultFS=hdfs://localhost:42601 2024-12-14T20:21:36,808 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(1725): Config from master: hbase.master.info.port=-1 2024-12-14T20:21:36,819 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/rs 2024-12-14T20:21:36,819 DEBUG [RS:0;26a9feeac337:33199 {}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/rs/26a9feeac337,33199,1734207694050 2024-12-14T20:21:36,819 WARN [RS:0;26a9feeac337:33199 {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-14T20:21:36,820 INFO [RS:0;26a9feeac337:33199 {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-14T20:21:36,820 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(2100): logDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050 2024-12-14T20:21:36,822 INFO [RegionServerTracker-0 {}] master.RegionServerTracker(179): RegionServer ephemeral node created, adding [26a9feeac337,33199,1734207694050] 2024-12-14T20:21:36,831 DEBUG [RS:0;26a9feeac337:33199 {}] regionserver.Replication(140): Replication stats-in-log period=300 seconds 2024-12-14T20:21:36,840 INFO [RS:0;26a9feeac337:33199 {}] regionserver.MetricsRegionServerWrapperImpl(120): Computing regionserver metrics every 5000 milliseconds 2024-12-14T20:21:36,850 INFO [RS:0;26a9feeac337:33199 {}] regionserver.MemStoreFlusher(130): globalMemStoreLimit=880 M, globalMemStoreLimitLowMark=836 M, Offheap=false 2024-12-14T20:21:36,853 INFO [RS:0;26a9feeac337:33199 {}] 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 2024-12-14T20:21:36,853 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionThroughputTuner, period=60000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,853 INFO [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer$CompactionChecker(1988): CompactionChecker runs every PT1S 2024-12-14T20:21:36,859 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactedHFilesCleaner, period=120000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,859 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_REGION-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_META-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_REGION-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_META-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_LOG_REPLAY_OPS-regionserver/26a9feeac337:0, corePoolSize=2, maxPoolSize=2 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_COMPACTED_FILES_DISCHARGER-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_REGION_REPLICA_FLUSH_OPS-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,860 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_REFRESH_PEER-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,861 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_SWITCH_RPC_THROTTLE-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,861 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_CLAIM_REPLICATION_QUEUE-regionserver/26a9feeac337:0, corePoolSize=1, maxPoolSize=1 2024-12-14T20:21:36,861 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_SNAPSHOT_OPERATIONS-regionserver/26a9feeac337:0, corePoolSize=3, maxPoolSize=3 2024-12-14T20:21:36,861 DEBUG [RS:0;26a9feeac337:33199 {}] executor.ExecutorService(95): Starting executor service name=RS_FLUSH_OPERATIONS-regionserver/26a9feeac337:0, corePoolSize=3, maxPoolSize=3 2024-12-14T20:21:36,862 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionChecker, period=1000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,862 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=MemstoreFlusherChore, period=1000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,862 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=nonceCleaner, period=360000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,862 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=BrokenStoreFileCleaner, period=21600000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,862 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,33199,1734207694050-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-14T20:21:36,879 INFO [RS:0;26a9feeac337:33199 {}] regionserver.HeapMemoryManager(209): Starting, tuneOn=false 2024-12-14T20:21:36,880 INFO [RS:0;26a9feeac337:33199 {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,33199,1734207694050-HeapMemoryTunerChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:36,897 INFO [RS:0;26a9feeac337:33199 {}] regionserver.Replication(204): 26a9feeac337,33199,1734207694050 started 2024-12-14T20:21:36,897 INFO [RS:0;26a9feeac337:33199 {}] regionserver.HRegionServer(1767): Serving as 26a9feeac337,33199,1734207694050, RpcServer on 26a9feeac337/172.17.0.3:33199, sessionid=0x10026347a580001 2024-12-14T20:21:36,898 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(51): Procedure flush-table-proc starting 2024-12-14T20:21:36,898 DEBUG [RS:0;26a9feeac337:33199 {}] flush.RegionServerFlushTableProcedureManager(108): Start region server flush procedure manager 26a9feeac337,33199,1734207694050 2024-12-14T20:21:36,898 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '26a9feeac337,33199,1734207694050' 2024-12-14T20:21:36,898 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/flush-table-proc/abort' 2024-12-14T20:21:36,899 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/flush-table-proc/acquired' 2024-12-14T20:21:36,899 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(53): Procedure flush-table-proc started 2024-12-14T20:21:36,899 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(51): Procedure online-snapshot starting 2024-12-14T20:21:36,900 DEBUG [RS:0;26a9feeac337:33199 {}] snapshot.RegionServerSnapshotManager(126): Start Snapshot Manager 26a9feeac337,33199,1734207694050 2024-12-14T20:21:36,900 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '26a9feeac337,33199,1734207694050' 2024-12-14T20:21:36,900 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/online-snapshot/abort' 2024-12-14T20:21:36,900 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/online-snapshot/acquired' 2024-12-14T20:21:36,901 DEBUG [RS:0;26a9feeac337:33199 {}] procedure.RegionServerProcedureManagerHost(53): Procedure online-snapshot started 2024-12-14T20:21:36,901 INFO [RS:0;26a9feeac337:33199 {}] quotas.RegionServerRpcQuotaManager(64): Quota support disabled 2024-12-14T20:21:36,901 INFO [RS:0;26a9feeac337:33199 {}] quotas.RegionServerSpaceQuotaManager(80): Quota support disabled, not starting space quota manager. 2024-12-14T20:21:37,010 INFO [RS:0;26a9feeac337:33199 {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-14T20:21:37,014 INFO [RS:0;26a9feeac337:33199 {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=26a9feeac337%2C33199%2C1734207694050, suffix=, logDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050, archiveDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/oldWALs, maxLogs=32 2024-12-14T20:21:37,029 DEBUG [RS:0;26a9feeac337:33199 {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.1734207697017, exclude list is [], retry=0 2024-12-14T20:21:37,033 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[127.0.0.1:38879,DS-1d94624a-9c90-4feb-9a82-e0022ad33e5a,DISK] 2024-12-14T20:21:37,036 INFO [RS:0;26a9feeac337:33199 {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:37,037 DEBUG [RS:0;26a9feeac337:33199 {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37495:37495)] 2024-12-14T20:21:37,149 INFO [PEWorker-1 {}] util.FSTableDescriptors(140): Updated hbase:meta table descriptor to hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/.tabledesc/.tableinfo.0000000001.1039 2024-12-14T20:21:37,150 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:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05 2024-12-14T20:21:37,161 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741833_1009 (size=32) 2024-12-14T20:21:37,565 DEBUG [PEWorker-1 {}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-14T20:21:37,569 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 2024-12-14T20:21:37,572 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 2024-12-14T20:21:37,572 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:37,573 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 2024-12-14T20:21:37,573 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 2024-12-14T20:21:37,576 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 2024-12-14T20:21:37,576 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:37,577 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 2024-12-14T20:21:37,577 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 2024-12-14T20:21:37,580 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 2024-12-14T20:21:37,580 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:37,581 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 2024-12-14T20:21:37,582 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740 2024-12-14T20:21:37,583 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740 2024-12-14T20:21:37,585 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. 2024-12-14T20:21:37,588 DEBUG [PEWorker-1 {}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-14T20:21:37,591 DEBUG [PEWorker-1 {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-14T20:21:37,592 INFO [PEWorker-1 {}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=66908593, jitterRate=-0.002984270453453064}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-14T20:21:37,595 DEBUG [PEWorker-1 {}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-14T20:21:37,595 DEBUG [PEWorker-1 {}] regionserver.HRegion(1681): Closing 1588230740, disabling compactions & flushes 2024-12-14T20:21:37,595 INFO [PEWorker-1 {}] regionserver.HRegion(1703): Closing region hbase:meta,,1.1588230740 2024-12-14T20:21:37,595 DEBUG [PEWorker-1 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:meta,,1.1588230740 2024-12-14T20:21:37,595 DEBUG [PEWorker-1 {}] regionserver.HRegion(1791): Acquired close lock on hbase:meta,,1.1588230740 after waiting 0 ms 2024-12-14T20:21:37,595 DEBUG [PEWorker-1 {}] regionserver.HRegion(1801): Updates disabled for region hbase:meta,,1.1588230740 2024-12-14T20:21:37,596 INFO [PEWorker-1 {}] regionserver.HRegion(1922): Closed hbase:meta,,1.1588230740 2024-12-14T20:21:37,596 DEBUG [PEWorker-1 {}] regionserver.HRegion(1635): Region close journal for 1588230740: 2024-12-14T20:21:37,598 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_ASSIGN_META, locked=true; InitMetaProcedure table=hbase:meta 2024-12-14T20:21:37,599 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(107): Going to assign meta 2024-12-14T20:21:37,603 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}] 2024-12-14T20:21:37,610 INFO [PEWorker-2 {}] 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 2024-12-14T20:21:37,612 INFO [PEWorker-2 {}] 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 2024-12-14T20:21:37,765 DEBUG [26a9feeac337:45141 {}] assignment.AssignmentManager(2444): Processing assignQueue; systemServersCount=1, allServersCount=1 2024-12-14T20:21:37,773 INFO [PEWorker-3 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPENING, regionLocation=26a9feeac337,33199,1734207694050 2024-12-14T20:21:37,805 INFO [PEWorker-3 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 26a9feeac337,33199,1734207694050, state=OPENING 2024-12-14T20:21:38,037 DEBUG [PEWorker-3 {}] zookeeper.MetaTableLocator(183): hbase:meta region location doesn't exist, create it 2024-12-14T20:21:38,045 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:38,045 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:38,046 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-14T20:21:38,046 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-14T20:21:38,048 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=3, ppid=2, state=RUNNABLE; OpenRegionProcedure 1588230740, server=26a9feeac337,33199,1734207694050}] 2024-12-14T20:21:38,228 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:38,231 DEBUG [RSProcedureDispatcher-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=AdminService, sasl=false 2024-12-14T20:21:38,234 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:56500, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=AdminService 2024-12-14T20:21:38,245 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(135): Open hbase:meta,,1.1588230740 2024-12-14T20:21:38,246 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-14T20:21:38,246 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] monitor.StreamSlowMonitor(122): New stream slow monitor .meta 2024-12-14T20:21:38,249 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=26a9feeac337%2C33199%2C1734207694050.meta, suffix=.meta, logDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050, archiveDir=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/oldWALs, maxLogs=32 2024-12-14T20:21:38,263 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.meta.1734207698250.meta, exclude list is [], retry=0 2024-12-14T20:21:38,266 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[127.0.0.1:38879,DS-1d94624a-9c90-4feb-9a82-e0022ad33e5a,DISK] 2024-12-14T20:21:38,270 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.meta.1734207698250.meta 2024-12-14T20:21:38,270 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37495:37495)] 2024-12-14T20:21:38,271 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7285): Opening region: {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''} 2024-12-14T20:21:38,272 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:38,335 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7999): Registered coprocessor service: region=hbase:meta,,1 service=MultiRowMutationService 2024-12-14T20:21:38,340 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {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. 2024-12-14T20:21:38,345 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table meta 1588230740 2024-12-14T20:21:38,345 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:38,345 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7327): checking encryption for 1588230740 2024-12-14T20:21:38,345 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7330): checking classloading for 1588230740 2024-12-14T20:21:38,349 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 2024-12-14T20:21:38,351 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 2024-12-14T20:21:38,352 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:38,353 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 2024-12-14T20:21:38,353 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 2024-12-14T20:21:38,355 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 2024-12-14T20:21:38,356 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:38,357 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 2024-12-14T20:21:38,357 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 2024-12-14T20:21:38,359 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 2024-12-14T20:21:38,359 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:38,360 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 2024-12-14T20:21:38,361 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740 2024-12-14T20:21:38,365 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740 2024-12-14T20:21:38,368 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {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. 2024-12-14T20:21:38,371 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-14T20:21:38,374 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=70917973, jitterRate=0.05676014721393585}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-14T20:21:38,376 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-14T20:21:38,383 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:meta,,1.1588230740, pid=3, masterSystemTime=1734207698221 2024-12-14T20:21:38,397 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPEN, openSeqNum=2, regionLocation=26a9feeac337,33199,1734207694050 2024-12-14T20:21:38,399 DEBUG [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:meta,,1.1588230740 2024-12-14T20:21:38,400 INFO [PEWorker-5 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 26a9feeac337,33199,1734207694050, state=OPEN 2024-12-14T20:21:38,400 INFO [RS_OPEN_META-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(164): Opened hbase:meta,,1.1588230740 2024-12-14T20:21:38,437 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-14T20:21:38,437 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-14T20:21:38,438 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-14T20:21:38,438 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-14T20:21:38,443 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=3, resume processing ppid=2 2024-12-14T20:21:38,443 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=3, ppid=2, state=SUCCESS; OpenRegionProcedure 1588230740, server=26a9feeac337,33199,1734207694050 in 389 msec 2024-12-14T20:21:38,453 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=2, resume processing ppid=1 2024-12-14T20:21:38,453 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=2, ppid=1, state=SUCCESS; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN in 841 msec 2024-12-14T20:21:38,460 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=1, state=SUCCESS; InitMetaProcedure table=hbase:meta in 1.7870 sec 2024-12-14T20:21:38,460 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.HMaster(1088): Wait for region servers to report in: status=status unset, state=RUNNING, startTime=1734207698460, completionTime=-1 2024-12-14T20:21:38,461 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.ServerManager(907): Finished waiting on RegionServer count=1; waited=0ms, expected min=1 server(s), max=1 server(s), master is running 2024-12-14T20:21:38,461 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] assignment.AssignmentManager(1747): Joining cluster... 2024-12-14T20:21:38,501 DEBUG [hconnection-0x2c7784c7-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:21:38,504 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:56506, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:21:38,516 INFO [master/26a9feeac337:0:becomeActiveMaster {}] assignment.AssignmentManager(1759): Number of RegionServers=1 2024-12-14T20:21:38,516 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$RegionInTransitionChore; timeout=60000, timestamp=1734207758516 2024-12-14T20:21:38,516 INFO [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$DeadServerMetricRegionChore; timeout=120000, timestamp=1734207818516 2024-12-14T20:21:38,516 INFO [master/26a9feeac337:0:becomeActiveMaster {}] assignment.AssignmentManager(1766): Joined the cluster in 55 msec 2024-12-14T20:21:38,546 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,45141,1734207693156-ClusterStatusChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:38,546 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,45141,1734207693156-BalancerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:38,546 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,45141,1734207693156-RegionNormalizerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:38,547 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=CatalogJanitor-26a9feeac337:45141, period=300000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:38,548 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HbckChore-, period=3600000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:38,554 DEBUG [master/26a9feeac337:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-14T20:21:38,556 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.TableNamespaceManager(92): Namespace table not found. Creating... 2024-12-14T20:21:38,557 INFO [master/26a9feeac337:0: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)'} 2024-12-14T20:21:38,563 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION; CreateTableProcedure table=hbase:namespace 2024-12-14T20:21:38,567 INFO [PEWorker-3 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_PRE_OPERATION 2024-12-14T20:21:38,568 DEBUG [PEWorker-3 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:38,571 INFO [PEWorker-3 {}] 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 2024-12-14T20:21:38,582 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741835_1011 (size=358) 2024-12-14T20:21:38,988 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(7106): creating {ENCODED => 057fa4c987c40e584d6d33b443bf0875, NAME => 'hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875.', 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:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05 2024-12-14T20:21:39,000 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741836_1012 (size=42) 2024-12-14T20:21:39,402 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(894): Instantiated hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-14T20:21:39,402 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1681): Closing 057fa4c987c40e584d6d33b443bf0875, disabling compactions & flushes 2024-12-14T20:21:39,402 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1703): Closing region hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,402 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,402 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1791): Acquired close lock on hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. after waiting 0 ms 2024-12-14T20:21:39,403 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1801): Updates disabled for region hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,403 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1922): Closed hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,403 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1635): Region close journal for 057fa4c987c40e584d6d33b443bf0875: 2024-12-14T20:21:39,405 INFO [PEWorker-3 {}] 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 2024-12-14T20:21:39,412 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":2,"row":"hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875.","families":{"info":[{"qualifier":"regioninfo","vlen":41,"tag":[],"timestamp":"1734207699406"},{"qualifier":"state","vlen":6,"tag":[],"timestamp":"1734207699406"}]},"ts":"1734207699406"} 2024-12-14T20:21:39,458 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1516): Added 1 regions to meta. 2024-12-14T20:21:39,460 INFO [PEWorker-3 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_ASSIGN_REGIONS, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_ASSIGN_REGIONS 2024-12-14T20:21:39,463 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1734207699460"}]},"ts":"1734207699460"} 2024-12-14T20:21:39,470 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLING in hbase:meta 2024-12-14T20:21:39,520 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:namespace, region=057fa4c987c40e584d6d33b443bf0875, ASSIGN}] 2024-12-14T20:21:39,523 INFO [PEWorker-4 {}] procedure.MasterProcedureScheduler(786): Took xlock for pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE; TransitRegionStateProcedure table=hbase:namespace, region=057fa4c987c40e584d6d33b443bf0875, ASSIGN 2024-12-14T20:21:39,525 INFO [PEWorker-4 {}] assignment.TransitRegionStateProcedure(264): Starting pid=5, ppid=4, state=RUNNABLE:REGION_STATE_TRANSITION_GET_ASSIGN_CANDIDATE, locked=true; TransitRegionStateProcedure table=hbase:namespace, region=057fa4c987c40e584d6d33b443bf0875, ASSIGN; state=OFFLINE, location=26a9feeac337,33199,1734207694050; forceNewPlan=false, retain=false 2024-12-14T20:21:39,676 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=057fa4c987c40e584d6d33b443bf0875, regionState=OPENING, regionLocation=26a9feeac337,33199,1734207694050 2024-12-14T20:21:39,683 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=6, ppid=5, state=RUNNABLE; OpenRegionProcedure 057fa4c987c40e584d6d33b443bf0875, server=26a9feeac337,33199,1734207694050}] 2024-12-14T20:21:39,838 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:39,846 INFO [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(135): Open hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,846 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7285): Opening region: {ENCODED => 057fa4c987c40e584d6d33b443bf0875, NAME => 'hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875.', STARTKEY => '', ENDKEY => ''} 2024-12-14T20:21:39,847 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table namespace 057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,847 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(894): Instantiated hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-14T20:21:39,847 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7327): checking encryption for 057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,847 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7330): checking classloading for 057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,849 INFO [StoreOpener-057fa4c987c40e584d6d33b443bf0875-1 {}] 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 057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,851 INFO [StoreOpener-057fa4c987c40e584d6d33b443bf0875-1 {}] 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 057fa4c987c40e584d6d33b443bf0875 columnFamilyName info 2024-12-14T20:21:39,851 DEBUG [StoreOpener-057fa4c987c40e584d6d33b443bf0875-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-14T20:21:39,852 INFO [StoreOpener-057fa4c987c40e584d6d33b443bf0875-1 {}] regionserver.HStore(327): Store=057fa4c987c40e584d6d33b443bf0875/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-14T20:21:39,853 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,854 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,858 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1085): writing seq id for 057fa4c987c40e584d6d33b443bf0875 2024-12-14T20:21:39,861 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-14T20:21:39,863 INFO [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1102): Opened 057fa4c987c40e584d6d33b443bf0875; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=65765162, jitterRate=-0.020022720098495483}}}, FlushLargeStoresPolicy{flushSizeLowerBound=-1} 2024-12-14T20:21:39,864 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1001): Region open journal for 057fa4c987c40e584d6d33b443bf0875: 2024-12-14T20:21:39,866 INFO [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875., pid=6, masterSystemTime=1734207699838 2024-12-14T20:21:39,869 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,869 INFO [RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(164): Opened hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. 2024-12-14T20:21:39,870 INFO [PEWorker-2 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=057fa4c987c40e584d6d33b443bf0875, regionState=OPEN, openSeqNum=2, regionLocation=26a9feeac337,33199,1734207694050 2024-12-14T20:21:39,877 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=6, resume processing ppid=5 2024-12-14T20:21:39,878 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=6, ppid=5, state=SUCCESS; OpenRegionProcedure 057fa4c987c40e584d6d33b443bf0875, server=26a9feeac337,33199,1734207694050 in 190 msec 2024-12-14T20:21:39,881 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=5, resume processing ppid=4 2024-12-14T20:21:39,881 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=5, ppid=4, state=SUCCESS; TransitRegionStateProcedure table=hbase:namespace, region=057fa4c987c40e584d6d33b443bf0875, ASSIGN in 357 msec 2024-12-14T20:21:39,882 INFO [PEWorker-4 {}] 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 2024-12-14T20:21:39,883 DEBUG [PEWorker-4 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1734207699882"}]},"ts":"1734207699882"} 2024-12-14T20:21:39,885 INFO [PEWorker-4 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLED in hbase:meta 2024-12-14T20:21:39,933 INFO [PEWorker-4 {}] procedure.CreateTableProcedure(89): pid=4, state=RUNNABLE:CREATE_TABLE_POST_OPERATION, locked=true; CreateTableProcedure table=hbase:namespace execute state=CREATE_TABLE_POST_OPERATION 2024-12-14T20:21:39,938 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=4, state=SUCCESS; CreateTableProcedure table=hbase:namespace in 1.3760 sec 2024-12-14T20:21:39,968 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKUtil(113): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/namespace 2024-12-14T20:21:39,977 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/namespace 2024-12-14T20:21:39,977 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:39,977 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:40,012 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=7, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=default 2024-12-14T20:21:40,035 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-14T20:21:40,051 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=7, state=SUCCESS; CreateNamespaceProcedure, namespace=default in 40 msec 2024-12-14T20:21:40,057 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=8, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=hbase 2024-12-14T20:21:40,076 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-14T20:21:40,090 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=8, state=SUCCESS; CreateNamespaceProcedure, namespace=hbase in 31 msec 2024-12-14T20:21:40,119 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/default 2024-12-14T20:21:40,135 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/hbase 2024-12-14T20:21:40,135 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.HMaster(1218): Master has completed initialization 5.912sec 2024-12-14T20:21:40,136 INFO [master/26a9feeac337:0:becomeActiveMaster {}] quotas.MasterQuotaManager(97): Quota support disabled 2024-12-14T20:21:40,137 INFO [master/26a9feeac337:0:becomeActiveMaster {}] slowlog.SlowLogMasterService(57): Slow/Large requests logging to system table hbase:slowlog is disabled. Quitting. 2024-12-14T20:21:40,138 INFO [master/26a9feeac337:0:becomeActiveMaster {}] waleventtracker.WALEventTrackerTableCreator(75): wal event tracker requests logging to table REPLICATION.WALEVENTTRACKER is disabled. Quitting. 2024-12-14T20:21:40,139 INFO [master/26a9feeac337:0:becomeActiveMaster {}] master.ReplicationSinkTrackerTableCreator(90): replication sink tracker requests logging to table REPLICATION.SINK_TRACKER is disabled. Quitting. 2024-12-14T20:21:40,139 INFO [master/26a9feeac337:0:becomeActiveMaster {}] zookeeper.ZKWatcher(271): not a secure deployment, proceeding 2024-12-14T20:21:40,139 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,45141,1734207693156-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-14T20:21:40,140 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,45141,1734207693156-MobFileCompactionChore, period=604800, unit=SECONDS is enabled. 2024-12-14T20:21:40,146 DEBUG [master/26a9feeac337:0:becomeActiveMaster {}] master.HMaster(1321): Balancer post startup initialization complete, took 0 seconds 2024-12-14T20:21:40,147 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=RollingUpgradeChore, period=10, unit=SECONDS is enabled. 2024-12-14T20:21:40,147 INFO [master/26a9feeac337:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=26a9feeac337,45141,1734207693156-OldWALsDirSizeChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-14T20:21:40,219 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x797ad262 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@46697499 2024-12-14T20:21:40,219 WARN [Time-limited test {}] client.ZKConnectionRegistry(90): ZKConnectionRegistry is deprecated. See https://hbase.apache.org/book.html#client.rpcconnectionregistry 2024-12-14T20:21:40,229 DEBUG [Time-limited test {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@59542893, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:40,232 DEBUG [Time-limited test {}] nio.NioEventLoop(110): -Dio.netty.noKeySetOptimization: false 2024-12-14T20:21:40,232 DEBUG [Time-limited test {}] nio.NioEventLoop(111): -Dio.netty.selectorAutoRebuildThreshold: 512 2024-12-14T20:21:40,240 DEBUG [hconnection-0x2acfda6e-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:21:40,248 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:38702, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:21:40,256 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1199): Minicluster is up; activeMaster=26a9feeac337,45141,1734207693156 2024-12-14T20:21:40,257 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3c605cf9 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@67899e46 2024-12-14T20:21:40,271 DEBUG [ReadOnlyZKClient-127.0.0.1:64264@0x3c605cf9 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@3f28493f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:40,285 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=222, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=367, ProcessCount=11, AvailableMemoryMB=5956 2024-12-14T20:21:40,311 DEBUG [Time-limited test {}] client.ConnectionUtils(573): Start fetching master stub from registry 2024-12-14T20:21:40,312 DEBUG [ReadOnlyZKClient-127.0.0.1:64264@0x3c605cf9 {}] client.AsyncConnectionImpl(310): The fetched master address is 26a9feeac337,45141,1734207693156 2024-12-14T20:21:40,314 DEBUG [ReadOnlyZKClient-127.0.0.1:64264@0x3c605cf9 {}] client.ConnectionUtils(581): The fetched master stub is org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$Stub@34776684 2024-12-14T20:21:40,315 DEBUG [ReadOnlyZKClient-127.0.0.1:64264@0x3c605cf9 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=MasterService, sasl=false 2024-12-14T20:21:40,317 INFO [RS-EventLoopGroup-1-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:50860, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=MasterService 2024-12-14T20:21:40,318 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:40,324 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=9, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:40,328 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-14T20:21:40,340 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:40,341 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:40,352 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:40,353 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580004 connected 2024-12-14T20:21:40,434 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-14T20:21:40,461 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580004, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:40,485 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:40,485 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-14T20:21:40,507 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=10, ppid=9, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:40,644 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-14T20:21:40,676 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:40,677 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=10 2024-12-14T20:21:40,678 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:21:40,692 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=10}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:40,709 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:40,773 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=10 2024-12-14T20:21:40,776 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=10 2024-12-14T20:21:40,780 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:40,786 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=10, resume processing ppid=9 2024-12-14T20:21:40,786 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:21:40,786 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=10, ppid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 273 msec 2024-12-14T20:21:40,790 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 467 msec 2024-12-14T20:21:40,810 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x398c4b9d to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5c2bdd62 2024-12-14T20:21:40,819 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:40,820 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:40,820 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4acc097c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:40,822 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:40,827 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:40,827 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:40,827 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580006 connected 2024-12-14T20:21:40,954 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-14T20:21:40,955 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:40,958 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:40,963 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=11, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:40,965 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-14T20:21:40,981 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:40,982 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:40,985 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:40,986 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580007 connected 2024-12-14T20:21:41,074 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-14T20:21:41,094 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580007, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:41,104 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=12, ppid=11, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:41,257 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:41,258 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=12 2024-12-14T20:21:41,258 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:41,260 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:41,260 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:41,261 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:41,261 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580006, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:41,261 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580006, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:41,284 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-14T20:21:41,369 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580006, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:41,369 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x398c4b9d to 127.0.0.1:64264 2024-12-14T20:21:41,370 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:41,385 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:41,386 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:41,386 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=12 2024-12-14T20:21:41,387 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=12 2024-12-14T20:21:41,390 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:41,394 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=12, resume processing ppid=11 2024-12-14T20:21:41,394 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:41,394 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=12, ppid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-14T20:21:41,397 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 435 msec 2024-12-14T20:21:41,419 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x783e3a40 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@dfd4096 2024-12-14T20:21:41,428 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:41,428 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:41,429 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4949c144, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:41,431 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:41,435 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:41,436 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:41,436 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580009 connected 2024-12-14T20:21:41,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-14T20:21:41,595 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:41,601 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:41,603 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:41,605 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:41,609 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-14T20:21:41,611 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=13, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:41,612 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-14T20:21:41,625 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:41,626 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:41,635 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:41,636 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58000a connected 2024-12-14T20:21:41,724 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-14T20:21:41,744 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58000a, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:41,798 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=14, ppid=13, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:41,935 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-14T20:21:41,953 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:41,955 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=14 2024-12-14T20:21:41,955 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:41,959 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:41,959 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:41,959 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:41,959 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580009, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:41,960 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580009, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:42,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580009, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:42,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x783e3a40 to 127.0.0.1:64264 2024-12-14T20:21:42,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:42,098 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:42,099 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:42,099 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=14 2024-12-14T20:21:42,100 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=14 2024-12-14T20:21:42,103 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:42,108 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=14, resume processing ppid=13 2024-12-14T20:21:42,108 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-14T20:21:42,108 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=14, ppid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 305 msec 2024-12-14T20:21:42,111 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 499 msec 2024-12-14T20:21:42,129 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x428c1965 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2ab843fe 2024-12-14T20:21:42,136 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:42,136 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:42,136 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7e5add09, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:42,138 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:42,144 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:42,144 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:42,144 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58000c connected 2024-12-14T20:21:42,244 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-14T20:21:42,245 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:42,246 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,248 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,250 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,252 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,253 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-14T20:21:42,255 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=15, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:42,256 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-14T20:21:42,270 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:42,270 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:42,277 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:42,277 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58000d connected 2024-12-14T20:21:42,364 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-14T20:21:42,386 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58000d, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:42,396 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=16, ppid=15, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:42,551 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:42,552 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=16 2024-12-14T20:21:42,552 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:42,554 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:42,554 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:42,554 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:42,554 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58000c, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:42,554 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58000c, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:42,573 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-14T20:21:42,660 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58000c, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:42,660 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x428c1965 to 127.0.0.1:64264 2024-12-14T20:21:42,661 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:42,674 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:42,674 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:42,675 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=16 2024-12-14T20:21:42,675 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=16 2024-12-14T20:21:42,678 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:42,681 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=16, resume processing ppid=15 2024-12-14T20:21:42,681 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-14T20:21:42,681 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=16, ppid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-14T20:21:42,683 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 428 msec 2024-12-14T20:21:42,700 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3e5557f5 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@14df6d3 2024-12-14T20:21:42,711 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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 2024-12-14T20:21:42,711 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:42,712 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@b8d5e74, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:42,713 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:42,719 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:42,719 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:42,719 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58000f connected 2024-12-14T20:21:42,837 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:meta' 2024-12-14T20:21:42,839 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:namespace' 2024-12-14T20:21:42,884 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-14T20:21:42,885 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:42,886 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,888 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,890 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:42,891 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:42,893 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=17, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:42,894 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-14T20:21:42,907 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:42,908 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:42,919 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:42,919 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580010 connected 2024-12-14T20:21:43,004 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-14T20:21:43,027 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580010, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:43,056 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=18, ppid=17, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:43,210 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:43,211 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=18 2024-12-14T20:21:43,211 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:43,212 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:43,212 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:43,212 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:43,212 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58000f, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:43,213 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58000f, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:43,213 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-14T20:21:43,319 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58000f, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:43,319 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3e5557f5 to 127.0.0.1:64264 2024-12-14T20:21:43,319 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:43,331 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:43,331 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:43,331 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=18 2024-12-14T20:21:43,332 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=18 2024-12-14T20:21:43,335 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:43,337 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=18, resume processing ppid=17 2024-12-14T20:21:43,337 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=18, ppid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 279 msec 2024-12-14T20:21:43,337 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:43,339 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 445 msec 2024-12-14T20:21:43,362 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x090af573 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@65296f66 2024-12-14T20:21:43,369 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:43,370 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:43,370 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@539c6d24, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:43,371 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:43,377 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:43,377 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:43,377 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580012 connected 2024-12-14T20:21:43,524 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-14T20:21:43,525 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:43,525 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:43,526 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:43,527 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-14T20:21:43,528 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=19, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:43,529 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-14T20:21:43,541 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:43,542 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:43,552 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:43,552 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580013 connected 2024-12-14T20:21:43,634 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-14T20:21:43,660 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580013, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:43,671 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=20, ppid=19, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:43,825 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:43,826 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=20 2024-12-14T20:21:43,827 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:43,830 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:43,830 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:43,831 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:43,831 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580012, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:43,831 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580012, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:43,843 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-14T20:21:43,853 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:21:43,894 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_meta 2024-12-14T20:21:43,894 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_meta Metrics about Tables on a single HBase RegionServer 2024-12-14T20:21:43,896 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_namespace 2024-12-14T20:21:43,896 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_namespace Metrics about Tables on a single HBase RegionServer 2024-12-14T20:21:43,897 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint 2024-12-14T20:21:43,897 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint Metrics about HBase RegionObservers 2024-12-14T20:21:43,897 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_master_table_store 2024-12-14T20:21:43,897 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_master_table_store Metrics about Tables on a single HBase RegionServer 2024-12-14T20:21:43,935 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580012, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:43,935 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x090af573 to 127.0.0.1:64264 2024-12-14T20:21:43,935 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:43,953 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:43,953 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:43,953 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=20 2024-12-14T20:21:43,954 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=20 2024-12-14T20:21:43,956 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:43,959 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=20, resume processing ppid=19 2024-12-14T20:21:43,959 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-14T20:21:43,959 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=20, ppid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-14T20:21:43,961 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 432 msec 2024-12-14T20:21:43,980 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3b3c61b8 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1bf0947c 2024-12-14T20:21:43,986 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:43,986 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:43,986 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6109fd7c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:43,987 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:43,993 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:43,994 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:43,994 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580015 connected 2024-12-14T20:21:44,154 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-14T20:21:44,155 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:44,155 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:44,156 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:44,157 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=21, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:44,158 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-14T20:21:44,176 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:44,177 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:44,185 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:44,186 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580016 connected 2024-12-14T20:21:44,264 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-14T20:21:44,294 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580016, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:44,305 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=22, ppid=21, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:44,458 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:44,459 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=22 2024-12-14T20:21:44,459 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:44,461 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:44,461 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:44,461 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:44,461 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580015, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:44,461 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580015, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:44,473 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-14T20:21:44,569 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580015, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:44,569 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3b3c61b8 to 127.0.0.1:64264 2024-12-14T20:21:44,569 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:44,582 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:44,582 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:44,583 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=22 2024-12-14T20:21:44,583 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=22 2024-12-14T20:21:44,586 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:44,589 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=22, resume processing ppid=21 2024-12-14T20:21:44,589 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=22, ppid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-14T20:21:44,589 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:44,592 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 433 msec 2024-12-14T20:21:44,610 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x27cf6ee2 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@35ce9775 2024-12-14T20:21:44,619 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:44,620 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:44,620 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6728a77a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:44,621 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:44,627 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:44,627 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:44,628 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580018 connected 2024-12-14T20:21:44,784 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-14T20:21:44,785 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:44,785 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:44,788 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:44,788 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:44,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:44,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=24, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:44,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-14T20:21:44,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-14T20:21:44,795 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:44,802 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:44,802 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:44,802 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:44,804 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=25, ppid=23, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:44,904 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-14T20:21:44,904 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-14T20:21:44,957 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:44,958 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=25 2024-12-14T20:21:44,958 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:21:44,958 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:21:44,958 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:21:44,958 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:44,958 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580018, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:44,959 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580018, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:45,069 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580018, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:45,069 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x27cf6ee2 to 127.0.0.1:64264 2024-12-14T20:21:45,069 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:45,070 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:21:45,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:45,085 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:45,085 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:45,085 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:45,086 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:45,086 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=25 2024-12-14T20:21:45,087 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=25 2024-12-14T20:21:45,089 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:45,093 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=25, resume processing ppid=23 2024-12-14T20:21:45,093 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=25, ppid=23, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-14T20:21:45,102 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:45,102 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:21:45,105 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=23, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 315 msec 2024-12-14T20:21:45,106 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:45,112 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=24, 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:45,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-14T20:21:45,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-14T20:21:45,114 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=24, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=325 msec 2024-12-14T20:21:45,114 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:45,114 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:45,115 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:45,116 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=26, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:45,117 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-14T20:21:45,118 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:45,119 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:45,121 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=26, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-14T20:21:45,121 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:45,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-14T20:21:45,225 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:45,226 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=testing utility connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:45,235 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): testing utility0x0, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:45,236 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): testing utility-0x10026347a580019 connected 2024-12-14T20:21:45,261 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=223 (was 222) 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: 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$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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: 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) 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: 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) - Thread LEAK? -, OpenFileDescriptor=450 (was 446) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=370 (was 367) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=5917 (was 5956) 2024-12-14T20:21:45,269 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=370, ProcessCount=11, AvailableMemoryMB=5916 2024-12-14T20:21:45,271 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:45,272 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=27, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:45,273 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-14T20:21:45,286 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:45,287 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:45,294 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:45,294 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58001a connected 2024-12-14T20:21:45,384 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-14T20:21:45,402 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58001a, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:45,420 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=28, ppid=27, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:45,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-14T20:21:45,424 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:21:45,573 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:45,574 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=28 2024-12-14T20:21:45,574 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:21:45,587 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=28}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:45,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-14T20:21:45,598 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:45,660 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=28 2024-12-14T20:21:45,661 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=28 2024-12-14T20:21:45,664 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:45,666 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=28, resume processing ppid=27 2024-12-14T20:21:45,666 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:21:45,666 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=28, ppid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 244 msec 2024-12-14T20:21:45,668 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 395 msec 2024-12-14T20:21:45,685 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x27d56460 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@51a5810d 2024-12-14T20:21:45,694 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:45,694 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:45,695 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@400d6920, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:45,696 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:45,702 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:45,702 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:45,702 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58001c connected 2024-12-14T20:21:45,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-14T20:21:45,904 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:45,904 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:45,906 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=29, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:45,906 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-14T20:21:45,920 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:45,921 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:45,927 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:45,927 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58001d connected 2024-12-14T20:21:46,014 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-14T20:21:46,035 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58001d, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:46,045 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=30, ppid=29, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:46,198 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:46,199 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=30 2024-12-14T20:21:46,199 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:46,202 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:46,202 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:46,205 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:46,205 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58001c, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:46,205 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58001c, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:46,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-14T20:21:46,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58001c, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:46,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x27d56460 to 127.0.0.1:64264 2024-12-14T20:21:46,311 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:46,325 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:46,325 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:46,326 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=30 2024-12-14T20:21:46,327 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=30 2024-12-14T20:21:46,331 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:46,334 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=30, resume processing ppid=29 2024-12-14T20:21:46,334 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:46,334 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=30, ppid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-14T20:21:46,337 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 431 msec 2024-12-14T20:21:46,358 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1995be79 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@30cff12d 2024-12-14T20:21:46,377 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:46,378 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:46,378 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5350d47f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:46,379 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:46,410 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:46,411 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58001f connected 2024-12-14T20:21:46,412 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:46,534 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-14T20:21:46,535 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:46,535 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:46,536 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-14T20:21:46,538 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=31, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:46,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-14T20:21:46,556 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:46,557 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:46,602 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:46,602 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580020 connected 2024-12-14T20:21:46,644 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-14T20:21:46,710 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580020, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:46,720 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=32, ppid=31, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:46,854 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-14T20:21:46,872 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:46,873 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=32 2024-12-14T20:21:46,874 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:46,875 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:46,875 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:46,875 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:46,875 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58001f, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:46,876 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58001f, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:46,985 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58001f, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:46,985 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1995be79 to 127.0.0.1:64264 2024-12-14T20:21:46,986 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:47,001 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:47,001 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:47,001 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=32 2024-12-14T20:21:47,002 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=32 2024-12-14T20:21:47,005 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:47,008 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=32, resume processing ppid=31 2024-12-14T20:21:47,008 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-14T20:21:47,008 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=32, ppid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-14T20:21:47,010 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 472 msec 2024-12-14T20:21:47,027 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4905d5ae to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@17a8b7f2 2024-12-14T20:21:47,035 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:47,036 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:47,036 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@37de58b1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:47,037 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:47,044 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:47,044 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:47,044 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580022 connected 2024-12-14T20:21:47,164 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-14T20:21:47,164 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:47,165 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:47,166 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns1:testNamespacesAndTableCfsConfigConflict1=null},bandwidth=0,serial=false 2024-12-14T20:21:47,168 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=33, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:47,169 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-14T20:21:47,189 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:47,190 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:47,202 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:47,202 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580023 connected 2024-12-14T20:21:47,274 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-14T20:21:47,310 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580023, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:47,311 WARN [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:47,312 ERROR [PEWorker-3 {}] 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) ~[classes/:?] 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 2024-12-14T20:21:47,314 INFO [PEWorker-3 {}] 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=147 msec 2024-12-14T20:21:47,314 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. 2024-12-14T20:21:47,483 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-14T20:21:47,484 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 2024-12-14T20:21:47,485 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:47,486 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-14T20:21:47,487 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=34, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:47,488 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-14T20:21:47,503 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:47,504 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:47,510 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:47,510 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580024 connected 2024-12-14T20:21:47,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-14T20:21:47,619 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580024, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:47,628 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=35, ppid=34, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:47,781 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:47,782 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=35 2024-12-14T20:21:47,782 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:47,784 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:47,784 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:47,784 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:47,784 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580022, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:47,784 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580022, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:47,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-14T20:21:47,894 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580022, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:47,894 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4905d5ae to 127.0.0.1:64264 2024-12-14T20:21:47,894 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:47,909 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:47,909 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:47,909 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=35 2024-12-14T20:21:47,910 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=35 2024-12-14T20:21:47,913 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:47,915 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=35, resume processing ppid=34 2024-12-14T20:21:47,915 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-14T20:21:47,916 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=35, ppid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-14T20:21:47,917 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 430 msec 2024-12-14T20:21:47,936 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3dff7875 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@431c0fa0 2024-12-14T20:21:48,015 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:48,016 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:48,016 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@31158df0, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:48,018 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:48,039 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:48,039 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:48,039 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580026 connected 2024-12-14T20:21:48,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-14T20:21:48,115 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:48,115 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:48,117 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-14T20:21:48,118 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=36, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:48,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-14T20:21:48,136 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:48,137 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:48,143 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:48,144 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580027 connected 2024-12-14T20:21:48,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-14T20:21:48,252 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580027, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:48,252 WARN [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:48,254 ERROR [PEWorker-3 {}] 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) ~[classes/:?] 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 2024-12-14T20:21:48,256 INFO [PEWorker-3 {}] 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 2024-12-14T20:21:48,256 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. 2024-12-14T20:21:48,434 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-14T20:21:48,435 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 2024-12-14T20:21:48,435 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:48,436 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=37, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:48,437 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-14T20:21:48,440 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:48,485 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:48,485 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:48,485 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:48,487 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=38, ppid=37, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:48,544 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-14T20:21:48,640 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:48,641 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=38 2024-12-14T20:21:48,642 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:21:48,642 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:21:48,642 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:21:48,642 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:48,643 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580026, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:48,643 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580026, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:48,753 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-14T20:21:48,760 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580026, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:48,760 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3dff7875 to 127.0.0.1:64264 2024-12-14T20:21:48,760 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:48,760 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:21:48,769 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:48,777 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:48,777 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:48,777 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:48,777 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:48,777 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=38 2024-12-14T20:21:48,778 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=38 2024-12-14T20:21:48,780 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:48,782 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=38, resume processing ppid=37 2024-12-14T20:21:48,782 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=38, ppid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 293 msec 2024-12-14T20:21:48,794 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:48,794 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:21:48,796 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 359 msec 2024-12-14T20:21:49,064 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-14T20:21:49,064 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:49,065 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:49,066 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=39, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:49,067 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-14T20:21:49,067 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:49,069 ERROR [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:49,070 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=39, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-14T20:21:49,070 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:49,174 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-14T20:21:49,175 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:21:49,175 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:49,177 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=40, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:49,178 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-14T20:21:49,178 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:49,179 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:49,180 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=40, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:21:49,180 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:49,284 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-14T20:21:49,284 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:49,296 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223 (was 223), OpenFileDescriptor=448 (was 450), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=380 (was 370) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=5987 (was 5916) - AvailableMemoryMB LEAK? - 2024-12-14T20:21:49,305 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=380, ProcessCount=11, AvailableMemoryMB=5986 2024-12-14T20:21:49,306 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:49,307 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=41, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:49,308 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-14T20:21:49,320 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:49,321 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:49,360 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:49,361 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580028 connected 2024-12-14T20:21:49,414 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-14T20:21:49,468 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580028, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:49,486 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=42, ppid=41, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:49,624 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-14T20:21:49,638 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:49,639 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=42 2024-12-14T20:21:49,639 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:21:49,652 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=42}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:49,666 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:49,710 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=42 2024-12-14T20:21:49,711 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=42 2024-12-14T20:21:49,713 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:49,716 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=42, resume processing ppid=41 2024-12-14T20:21:49,716 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:21:49,716 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=42, ppid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 227 msec 2024-12-14T20:21:49,718 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 410 msec 2024-12-14T20:21:49,738 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5035e1e7 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@122ef456 2024-12-14T20:21:49,744 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:49,744 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:49,744 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@36e6a7dd, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:49,746 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:49,768 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:49,768 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:49,769 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58002a connected 2024-12-14T20:21:49,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-14T20:21:49,934 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:49,934 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:49,935 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=43, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:49,936 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-14T20:21:49,948 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:49,948 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:49,960 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:49,960 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58002b connected 2024-12-14T20:21:50,044 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-14T20:21:50,068 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58002b, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:50,068 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:50,070 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:50,071 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=43, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=136 msec 2024-12-14T20:21:50,071 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:50,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-14T20:21:50,254 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Replication peer 1 already exists 2024-12-14T20:21:50,258 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:21:50,260 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:50,261 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=44, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:50,262 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-14T20:21:50,262 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:50,264 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:50,265 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=44, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-14T20:21:50,265 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:50,373 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-14T20:21:50,374 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:50,374 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:21:50,375 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=2, config=clusterKey=127.0.0.1:64264:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:50,376 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=45, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:50,377 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-14T20:21:50,394 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:50,395 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:50,435 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:50,436 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58002c connected 2024-12-14T20:21:50,483 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-14T20:21:50,543 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58002c, quorum=127.0.0.1:64264, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:50,561 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=46, ppid=45, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:50,571 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:21:50,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-14T20:21:50,714 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:50,715 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=46 2024-12-14T20:21:50,715 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=ADD_PEER 2024-12-14T20:21:50,727 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=46}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:50,738 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.ReplicationSource(229): queueId=2, ReplicationSource: 2, currentBandwidth=0 2024-12-14T20:21:50,760 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=46 2024-12-14T20:21:50,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=46 2024-12-14T20:21:50,763 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:50,765 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=46, resume processing ppid=45 2024-12-14T20:21:50,765 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 2, config clusterKey=127.0.0.1:64264:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:21:50,765 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=46, ppid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 202 msec 2024-12-14T20:21:50,766 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 390 msec 2024-12-14T20:21:50,769 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 2000 millis 2024-12-14T20:21:50,786 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x71c9ccea to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5f9b0781 2024-12-14T20:21:50,794 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:50,794 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:50,794 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@25790fe1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:50,796 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 2 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:50,802 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 20x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:50,802 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] regionserver.ReplicationSource(569): peerId=2, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:50,802 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 2-0x10026347a58002e connected 2024-12-14T20:21:51,004 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-14T20:21:51,004 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 2 completed 2024-12-14T20:21:51,005 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:21:51,005 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:51,007 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=47, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:51,008 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-14T20:21:51,010 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:51,018 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:51,018 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:51,018 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:51,020 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=48, ppid=47, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:51,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-14T20:21:51,172 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:51,173 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=48 2024-12-14T20:21:51,173 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:21:51,173 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:21:51,173 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:21:51,173 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:51,173 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58002a, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:51,173 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58002a, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:51,277 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58002a, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:51,277 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5035e1e7 to 127.0.0.1:64264 2024-12-14T20:21:51,277 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:51,277 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:21:51,286 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:51,293 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:51,294 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:51,294 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:51,295 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:51,295 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=48 2024-12-14T20:21:51,296 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=48 2024-12-14T20:21:51,301 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:51,304 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=48, resume processing ppid=47 2024-12-14T20:21:51,304 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=48, ppid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-14T20:21:51,319 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:51,319 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:21:51,321 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 314 msec 2024-12-14T20:21:51,324 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-14T20:21:51,324 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:51,324 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:21:51,325 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:51,327 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=49, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:51,328 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-14T20:21:51,331 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/2/peer-state 2024-12-14T20:21:51,343 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2/peer-state 2024-12-14T20:21:51,343 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-14T20:21:51,343 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-14T20:21:51,344 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=50, ppid=49, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:51,435 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-14T20:21:51,496 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:51,497 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=50 2024-12-14T20:21:51,497 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=REMOVE_PEER 2024-12-14T20:21:51,497 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 2: 0 2024-12-14T20:21:51,497 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSource(657): peerId=2, Closing source 2 because: Replication stream was removed by a user 2024-12-14T20:21:51,497 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] regionserver.ReplicationSource(508): peerId=2, Interrupted while sleeping between retries 2024-12-14T20:21:51,497 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] zookeeper.ZKUtil(165): connection to cluster: 2-0x10026347a58002e, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:51,498 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2 {}] zookeeper.ZKWatcher(734): connection to cluster: 2-0x10026347a58002e, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:51,602 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 2-0x10026347a58002e, quorum=127.0.0.1:64264, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:51,602 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x71c9ccea to 127.0.0.1:64264 2024-12-14T20:21:51,602 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:51,602 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(430): Done with the queue 2 2024-12-14T20:21:51,610 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/2/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:51,618 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/2/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:51,618 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/2 2024-12-14T20:21:51,618 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/2 2024-12-14T20:21:51,619 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-14T20:21:51,619 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=50 2024-12-14T20:21:51,619 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=50 2024-12-14T20:21:51,621 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:51,623 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=50, resume processing ppid=49 2024-12-14T20:21:51,623 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=50, ppid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-14T20:21:51,627 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-14T20:21:51,627 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 2 2024-12-14T20:21:51,629 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 302 msec 2024-12-14T20:21:51,644 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-14T20:21:51,644 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 2 completed 2024-12-14T20:21:51,644 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:21:51,645 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:51,646 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=51, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:51,647 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-14T20:21:51,647 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:51,648 ERROR [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:51,649 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=51, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:21:51,649 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:51,755 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-14T20:21:51,757 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:21:51,758 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:51,760 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=52, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:51,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-14T20:21:51,762 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:51,764 ERROR [PEWorker-4 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:51,766 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=52, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-14T20:21:51,766 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:51,864 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-14T20:21:51,866 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:51,881 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=220 (was 223), OpenFileDescriptor=442 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=350 (was 380), ProcessCount=11 (was 11), AvailableMemoryMB=5897 (was 5986) 2024-12-14T20:21:51,888 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=220, OpenFileDescriptor=442, MaxFileDescriptor=1048576, SystemLoadAverage=350, ProcessCount=11, AvailableMemoryMB=5897 2024-12-14T20:21:51,889 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=whatever,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:51,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=53, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:51,891 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-14T20:21:51,892 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: 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) ~[classes/:?] 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 2024-12-14T20:21:51,893 ERROR [PEWorker-1 {}] 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) ~[classes/:?] 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 2024-12-14T20:21:51,894 INFO [PEWorker-1 {}] 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=4 msec 2024-12-14T20:21:51,894 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. 2024-12-14T20:21:51,994 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-14T20:21:51,996 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 2024-12-14T20:21:52,004 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:52,005 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=54, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:52,006 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-14T20:21:52,006 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:52,007 ERROR [PEWorker-5 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:52,008 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=54, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-14T20:21:52,008 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:52,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-14T20:21:52,116 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:21:52,117 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:52,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=55, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:52,121 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-14T20:21:52,122 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:52,125 ERROR [PEWorker-2 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:52,127 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=55, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=8 msec 2024-12-14T20:21:52,127 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:52,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-14T20:21:52,225 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:52,240 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=220 (was 220), OpenFileDescriptor=442 (was 442), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=350 (was 350), ProcessCount=11 (was 11), AvailableMemoryMB=5897 (was 5897) 2024-12-14T20:21:52,248 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=220, OpenFileDescriptor=442, MaxFileDescriptor=1048576, SystemLoadAverage=350, ProcessCount=11, AvailableMemoryMB=5896 2024-12-14T20:21:52,249 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=whatever,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:52,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=56, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:52,251 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-14T20:21:52,251 WARN [PEWorker-3 {}] 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) ~[classes/:?] 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) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-12-14T20:21:52,252 ERROR [PEWorker-3 {}] 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) ~[classes/:?] 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) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[classes/: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 2024-12-14T20:21:52,253 INFO [PEWorker-3 {}] 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=3 msec 2024-12-14T20:21:52,253 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. 2024-12-14T20:21:52,354 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-14T20:21:52,356 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Invalid cluster key: whatever 2024-12-14T20:21:52,356 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:52,358 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=57, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:52,360 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-14T20:21:52,361 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:52,363 ERROR [PEWorker-4 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:52,365 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=57, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-14T20:21:52,365 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:52,464 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-14T20:21:52,465 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:21:52,465 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:52,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=58, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:52,467 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-14T20:21:52,468 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:52,469 ERROR [PEWorker-1 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:52,470 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=58, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-14T20:21:52,470 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:52,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-14T20:21:52,576 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:52,592 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=220 (was 220), OpenFileDescriptor=442 (was 442), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=350 (was 350), ProcessCount=11 (was 11), AvailableMemoryMB=5905 (was 5896) - AvailableMemoryMB LEAK? - 2024-12-14T20:21:52,601 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=220, OpenFileDescriptor=442, MaxFileDescriptor=1048576, SystemLoadAverage=350, ProcessCount=11, AvailableMemoryMB=5902 2024-12-14T20:21:52,602 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:52,603 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=59, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:52,604 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-14T20:21:52,617 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:52,617 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:52,660 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:52,661 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58002f connected 2024-12-14T20:21:52,715 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-14T20:21:52,769 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58002f, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:52,794 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=60, ppid=59, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:52,923 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-14T20:21:52,946 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:52,947 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=60 2024-12-14T20:21:52,947 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:21:52,959 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=60}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:52,970 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:53,010 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=60 2024-12-14T20:21:53,011 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=60 2024-12-14T20:21:53,014 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:53,017 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=60, resume processing ppid=59 2024-12-14T20:21:53,017 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:21:53,018 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=60, ppid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 221 msec 2024-12-14T20:21:53,020 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 416 msec 2024-12-14T20:21:53,041 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4b27eced to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3de47cf5 2024-12-14T20:21:53,052 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:53,052 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:53,053 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1426b700, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:53,054 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:53,103 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:53,104 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:53,104 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580031 connected 2024-12-14T20:21:53,234 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-14T20:21:53,235 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:53,236 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:53,238 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=61, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:53,240 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-14T20:21:53,259 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:53,259 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:53,268 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:53,269 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580032 connected 2024-12-14T20:21:53,344 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-14T20:21:53,377 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580032, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:53,386 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=62, ppid=61, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:53,538 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:53,539 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=62 2024-12-14T20:21:53,540 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:53,542 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:53,542 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:53,542 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:53,543 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580031, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:53,543 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580031, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:53,554 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-14T20:21:53,652 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580031, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:53,652 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4b27eced to 127.0.0.1:64264 2024-12-14T20:21:53,653 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:53,671 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:53,672 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:53,672 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=62 2024-12-14T20:21:53,673 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=62 2024-12-14T20:21:53,674 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:53,676 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=62, resume processing ppid=61 2024-12-14T20:21:53,676 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=62, ppid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-12-14T20:21:53,676 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:53,678 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 440 msec 2024-12-14T20:21:53,700 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0f3f54c3 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4414a90b 2024-12-14T20:21:53,710 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:53,710 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:53,711 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@78635bcb, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:53,712 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:53,759 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:53,760 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:53,760 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580034 connected 2024-12-14T20:21:53,864 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-14T20:21:53,865 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:53,866 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:53,868 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-14T20:21:53,871 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=63, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:53,873 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-14T20:21:53,889 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:53,890 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:53,902 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:53,902 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580035 connected 2024-12-14T20:21:53,984 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-14T20:21:54,010 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580035, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:54,019 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=64, ppid=63, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:54,171 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:54,172 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=64 2024-12-14T20:21:54,172 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:54,174 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:54,174 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:54,174 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:54,174 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580034, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:54,174 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580034, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:54,193 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-14T20:21:54,285 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580034, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:54,285 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0f3f54c3 to 127.0.0.1:64264 2024-12-14T20:21:54,285 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:54,298 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:54,298 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:54,299 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=64 2024-12-14T20:21:54,299 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=64 2024-12-14T20:21:54,301 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:54,303 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=64, resume processing ppid=63 2024-12-14T20:21:54,303 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-14T20:21:54,303 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=64, ppid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-14T20:21:54,305 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 435 msec 2024-12-14T20:21:54,325 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x68bd0963 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@d166222 2024-12-14T20:21:54,335 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:54,336 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:54,336 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4aa2b085, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:54,337 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:54,343 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:54,344 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:54,344 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580037 connected 2024-12-14T20:21:54,504 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-14T20:21:54,504 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:54,505 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:54,505 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:54,506 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-14T20:21:54,507 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=65, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:54,508 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-14T20:21:54,520 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:54,520 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:54,527 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:54,527 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580038 connected 2024-12-14T20:21:54,614 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-14T20:21:54,635 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580038, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:54,644 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=66, ppid=65, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:54,797 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:54,798 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=66 2024-12-14T20:21:54,798 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:54,799 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:54,799 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:54,799 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:54,799 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580037, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:54,799 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580037, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:54,824 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-14T20:21:54,910 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580037, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:54,910 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x68bd0963 to 127.0.0.1:64264 2024-12-14T20:21:54,910 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:54,922 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:54,923 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:54,923 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=66 2024-12-14T20:21:54,923 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=66 2024-12-14T20:21:54,925 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:54,928 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=66, resume processing ppid=65 2024-12-14T20:21:54,928 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-14T20:21:54,928 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=66, ppid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-12-14T20:21:54,929 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 422 msec 2024-12-14T20:21:54,948 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x59d1cf25 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6210bd5c 2024-12-14T20:21:54,960 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:54,961 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:54,961 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@644919e6, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:54,962 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:54,968 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:54,968 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:54,968 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58003a connected 2024-12-14T20:21:55,135 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-14T20:21:55,136 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:55,137 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:55,140 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:55,142 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=67, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:55,143 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-14T20:21:55,147 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:55,151 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:21:55,152 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:55,152 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:21:55,153 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=68, ppid=67, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:55,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-14T20:21:55,305 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:55,306 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=68 2024-12-14T20:21:55,306 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:21:55,306 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:21:55,306 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:21:55,306 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:55,307 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58003a, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:55,307 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58003a, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:55,410 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58003a, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:55,410 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x59d1cf25 to 127.0.0.1:64264 2024-12-14T20:21:55,410 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:55,410 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:21:55,419 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:55,426 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:21:55,427 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:55,427 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:21:55,427 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:55,427 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=68 2024-12-14T20:21:55,427 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=68 2024-12-14T20:21:55,429 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:55,431 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=68, resume processing ppid=67 2024-12-14T20:21:55,431 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=68, ppid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 276 msec 2024-12-14T20:21:55,435 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:21:55,435 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:21:55,437 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 295 msec 2024-12-14T20:21:55,464 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-14T20:21:55,464 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:55,465 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:21:55,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=69, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:55,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-14T20:21:55,466 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:55,467 ERROR [PEWorker-2 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:55,468 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=69, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-14T20:21:55,468 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:55,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-14T20:21:55,576 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:21:55,577 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:21:55,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=70, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:21:55,581 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-14T20:21:55,582 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:21:55,584 ERROR [PEWorker-5 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:21:55,586 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=70, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=7 msec 2024-12-14T20:21:55,586 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:21:55,684 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-14T20:21:55,684 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:21:55,694 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=220 (was 220), OpenFileDescriptor=442 (was 442), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=350 (was 350), ProcessCount=11 (was 11), AvailableMemoryMB=5872 (was 5902) 2024-12-14T20:21:55,702 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=220, OpenFileDescriptor=442, MaxFileDescriptor=1048576, SystemLoadAverage=350, ProcessCount=11, AvailableMemoryMB=5871 2024-12-14T20:21:55,703 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:21:55,704 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=71, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:21:55,705 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-14T20:21:55,717 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:55,718 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:55,727 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:55,727 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58003b connected 2024-12-14T20:21:55,814 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-14T20:21:55,835 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58003b, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:55,854 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=72, ppid=71, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:56,008 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:56,008 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=72 2024-12-14T20:21:56,009 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:21:56,021 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=72}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:56,024 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-14T20:21:56,033 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:56,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=72 2024-12-14T20:21:56,077 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=72 2024-12-14T20:21:56,079 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:56,082 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=72, resume processing ppid=71 2024-12-14T20:21:56,082 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:21:56,082 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=72, ppid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 225 msec 2024-12-14T20:21:56,083 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 379 msec 2024-12-14T20:21:56,102 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x73b59983 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7b131916 2024-12-14T20:21:56,110 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:56,111 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:56,111 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@abd49b9, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:56,112 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:56,118 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:56,119 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:56,119 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58003d connected 2024-12-14T20:21:56,334 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-14T20:21:56,335 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:21:56,336 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:56,338 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=73, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:56,339 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-14T20:21:56,363 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:56,364 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:56,368 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:56,369 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58003e connected 2024-12-14T20:21:56,445 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-14T20:21:56,477 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58003e, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:56,520 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=74, ppid=73, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:56,653 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-14T20:21:56,674 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:56,675 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=74 2024-12-14T20:21:56,675 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:56,676 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:56,676 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:56,676 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:56,676 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58003d, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:56,677 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58003d, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:56,781 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:21:56,785 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58003d, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:56,785 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x73b59983 to 127.0.0.1:64264 2024-12-14T20:21:56,785 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:56,800 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:56,800 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:56,801 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=74 2024-12-14T20:21:56,801 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=74 2024-12-14T20:21:56,803 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:56,806 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=74, resume processing ppid=73 2024-12-14T20:21:56,806 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=74, ppid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 283 msec 2024-12-14T20:21:56,806 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:21:56,808 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 470 msec 2024-12-14T20:21:56,843 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x01c3820d to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@49d098 2024-12-14T20:21:56,852 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:56,853 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:56,853 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@70533e44, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:56,855 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:56,868 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:56,868 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:56,868 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580040 connected 2024-12-14T20:21:56,964 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-14T20:21:56,964 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:56,965 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:56,965 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-14T20:21:56,967 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=75, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:56,968 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-14T20:21:56,983 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:56,983 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:56,993 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:56,994 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580041 connected 2024-12-14T20:21:57,074 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-14T20:21:57,102 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580041, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:57,111 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=76, ppid=75, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:57,262 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:57,263 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=76 2024-12-14T20:21:57,263 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:57,264 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:57,264 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:57,264 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:57,265 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580040, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:57,265 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580040, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:57,283 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-14T20:21:57,368 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580040, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:57,368 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x01c3820d to 127.0.0.1:64264 2024-12-14T20:21:57,369 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:57,382 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:57,382 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:57,382 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=76 2024-12-14T20:21:57,383 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=76 2024-12-14T20:21:57,385 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:57,387 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=76, resume processing ppid=75 2024-12-14T20:21:57,387 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-14T20:21:57,387 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=76, ppid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 275 msec 2024-12-14T20:21:57,388 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 421 msec 2024-12-14T20:21:57,409 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x53466a4a to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5ef2ff85 2024-12-14T20:21:57,419 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:57,419 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:57,419 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@11565f01, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:57,420 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:57,426 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:57,427 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:57,427 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580043 connected 2024-12-14T20:21:57,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-14T20:21:57,594 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:57,595 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:57,596 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:57,597 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-14T20:21:57,598 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=77, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:57,599 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-14T20:21:57,610 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:57,611 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:57,636 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:57,636 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580044 connected 2024-12-14T20:21:57,704 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-14T20:21:57,743 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580044, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:57,752 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=78, ppid=77, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:57,904 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:57,905 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=78 2024-12-14T20:21:57,905 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:57,906 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:57,906 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:57,906 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:57,906 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580043, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:57,907 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580043, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:57,914 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-14T20:21:58,010 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580043, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:58,010 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x53466a4a to 127.0.0.1:64264 2024-12-14T20:21:58,010 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:58,022 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:58,022 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:58,022 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=78 2024-12-14T20:21:58,023 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=78 2024-12-14T20:21:58,025 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:58,027 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=78, resume processing ppid=77 2024-12-14T20:21:58,027 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-14T20:21:58,027 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=78, ppid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 273 msec 2024-12-14T20:21:58,029 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 430 msec 2024-12-14T20:21:58,063 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x035b74e8 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@24592f87 2024-12-14T20:21:58,069 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:58,070 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:58,070 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@9ec468d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:58,071 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:58,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:58,077 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:58,077 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580046 connected 2024-12-14T20:21:58,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-14T20:21:58,225 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:58,225 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:58,226 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:58,227 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-14T20:21:58,228 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=79, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:58,228 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-14T20:21:58,241 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:58,241 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:58,260 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:58,260 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580047 connected 2024-12-14T20:21:58,333 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-14T20:21:58,368 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580047, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:58,378 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=80, ppid=79, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:58,529 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:58,530 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=80 2024-12-14T20:21:58,530 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:58,531 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:58,531 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:58,531 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:58,531 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580046, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:58,532 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580046, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:58,544 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-14T20:21:58,635 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580046, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:58,635 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x035b74e8 to 127.0.0.1:64264 2024-12-14T20:21:58,635 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:58,653 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:58,654 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:58,654 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=80 2024-12-14T20:21:58,655 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=80 2024-12-14T20:21:58,656 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:58,658 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=80, resume processing ppid=79 2024-12-14T20:21:58,658 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=80, ppid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 279 msec 2024-12-14T20:21:58,658 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-14T20:21:58,659 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 431 msec 2024-12-14T20:21:58,680 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2dac1fda to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@46943924 2024-12-14T20:21:58,685 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:58,686 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:58,686 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3bba176f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:58,687 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:58,693 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:58,694 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:58,694 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580049 connected 2024-12-14T20:21:58,853 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-14T20:21:58,854 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:58,854 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:58,855 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:58,856 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-14T20:21:58,857 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=81, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:58,857 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-14T20:21:58,871 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:58,871 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:58,877 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:58,877 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58004a connected 2024-12-14T20:21:58,963 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-14T20:21:58,985 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58004a, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:58,994 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=82, ppid=81, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:59,146 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:59,147 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=82 2024-12-14T20:21:59,147 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:59,148 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:59,148 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:59,148 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:59,148 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580049, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:59,148 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580049, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:59,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-14T20:21:59,252 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580049, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:59,252 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2dac1fda to 127.0.0.1:64264 2024-12-14T20:21:59,252 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:59,267 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:59,267 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:59,267 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=82 2024-12-14T20:21:59,268 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=82 2024-12-14T20:21:59,269 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:59,271 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=82, resume processing ppid=81 2024-12-14T20:21:59,272 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-14T20:21:59,272 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=82, ppid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 276 msec 2024-12-14T20:21:59,273 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 416 msec 2024-12-14T20:21:59,293 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x14a4aff8 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@383200df 2024-12-14T20:21:59,302 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:59,303 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:59,303 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@480c450b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:59,303 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:59,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:59,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:59,310 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58004c connected 2024-12-14T20:21:59,484 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-14T20:21:59,484 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:21:59,485 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:59,485 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:21:59,486 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-14T20:21:59,488 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=83, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:21:59,488 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-14T20:21:59,501 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:21:59,501 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:59,510 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:59,510 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58004d connected 2024-12-14T20:21:59,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-14T20:21:59,618 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58004d, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:59,627 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=84, ppid=83, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:21:59,779 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:21:59,780 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=84 2024-12-14T20:21:59,780 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:21:59,781 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:21:59,781 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:21:59,781 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:21:59,782 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58004c, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:59,782 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58004c, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:21:59,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-14T20:21:59,885 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58004c, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:21:59,885 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x14a4aff8 to 127.0.0.1:64264 2024-12-14T20:21:59,885 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:21:59,898 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:21:59,898 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:21:59,898 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=84 2024-12-14T20:21:59,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=84 2024-12-14T20:21:59,901 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:21:59,902 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=84, resume processing ppid=83 2024-12-14T20:21:59,902 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-14T20:21:59,902 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=84, ppid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 274 msec 2024-12-14T20:21:59,904 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 415 msec 2024-12-14T20:21:59,924 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x66e3e5ca to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@68d8426 2024-12-14T20:21:59,936 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:21:59,936 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:21:59,936 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@25ebb37, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:21:59,937 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:21:59,943 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:21:59,944 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:21:59,944 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58004f connected 2024-12-14T20:22:00,114 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-14T20:22:00,114 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:00,115 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:00,116 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-14T20:22:00,116 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=85, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:00,117 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-14T20:22:00,130 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:00,130 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:00,135 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:00,136 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580050 connected 2024-12-14T20:22:00,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-14T20:22:00,243 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580050, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:00,253 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=86, ppid=85, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:00,405 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:00,405 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=86 2024-12-14T20:22:00,405 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:00,407 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=86 2024-12-14T20:22:00,407 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=86 2024-12-14T20:22:00,409 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:00,410 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=86, resume processing ppid=85 2024-12-14T20:22:00,410 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-14T20:22:00,411 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=86, ppid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 156 msec 2024-12-14T20:22:00,412 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 294 msec 2024-12-14T20:22:00,433 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-14T20:22:00,434 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:00,434 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:00,435 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:00,436 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-14T20:22:00,437 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=87, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:00,438 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-14T20:22:00,450 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:00,451 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:00,460 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:00,460 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580051 connected 2024-12-14T20:22:00,543 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-14T20:22:00,568 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580051, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:00,577 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=88, ppid=87, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:00,729 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:00,730 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=88 2024-12-14T20:22:00,730 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:00,731 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:00,731 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:00,731 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:00,732 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58004f, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:00,732 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58004f, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:00,753 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-14T20:22:00,835 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58004f, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:00,835 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x66e3e5ca to 127.0.0.1:64264 2024-12-14T20:22:00,835 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:00,847 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:00,848 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:00,848 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=88 2024-12-14T20:22:00,848 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=88 2024-12-14T20:22:00,850 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:00,852 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=88, resume processing ppid=87 2024-12-14T20:22:00,852 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-14T20:22:00,852 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=88, ppid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 273 msec 2024-12-14T20:22:00,853 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 416 msec 2024-12-14T20:22:00,876 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1736f11e to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2933ac22 2024-12-14T20:22:00,886 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:00,886 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:00,886 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5622d195, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:00,887 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:00,893 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:00,893 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:00,894 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580053 connected 2024-12-14T20:22:01,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-14T20:22:01,064 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:01,064 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:01,065 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-14T20:22:01,066 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=89, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:01,067 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-14T20:22:01,079 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:01,079 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:01,085 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:01,085 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580054 connected 2024-12-14T20:22:01,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-14T20:22:01,193 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580054, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:01,244 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=90, ppid=89, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:01,383 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-14T20:22:01,396 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:01,397 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=90 2024-12-14T20:22:01,397 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:01,398 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:01,398 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:01,398 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:01,398 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580053, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:01,399 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580053, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:01,518 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580053, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:01,518 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1736f11e to 127.0.0.1:64264 2024-12-14T20:22:01,518 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:01,532 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:01,532 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:01,533 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=90 2024-12-14T20:22:01,533 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=90 2024-12-14T20:22:01,535 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:01,537 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=90, resume processing ppid=89 2024-12-14T20:22:01,537 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-14T20:22:01,537 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=90, ppid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 291 msec 2024-12-14T20:22:01,539 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 472 msec 2024-12-14T20:22:01,559 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x73e8dd28 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@34195453 2024-12-14T20:22:01,569 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:01,569 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:01,569 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4421b417, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:01,570 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:01,577 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:01,577 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:01,577 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580056 connected 2024-12-14T20:22:01,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-14T20:22:01,694 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:01,695 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:01,696 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:01,697 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=91, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:01,697 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-14T20:22:01,699 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:01,709 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:01,710 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:01,710 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:01,711 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=92, ppid=91, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:01,804 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-14T20:22:01,862 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:01,863 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=92 2024-12-14T20:22:01,863 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:01,863 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:01,863 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:01,863 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:01,864 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580056, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:01,864 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580056, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:01,968 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580056, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:01,968 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x73e8dd28 to 127.0.0.1:64264 2024-12-14T20:22:01,969 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:01,969 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:01,977 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:01,985 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:01,985 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:01,985 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:01,985 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:01,985 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=92 2024-12-14T20:22:01,986 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=92 2024-12-14T20:22:01,987 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:01,989 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=92, resume processing ppid=91 2024-12-14T20:22:01,989 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=92, ppid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-14T20:22:01,994 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:01,994 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:01,996 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 298 msec 2024-12-14T20:22:02,013 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-14T20:22:02,014 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:02,014 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:02,015 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=93, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:02,016 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-14T20:22:02,016 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:02,017 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:02,018 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=93, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:02,018 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:02,123 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-14T20:22:02,124 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:22:02,124 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:02,125 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=94, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:02,126 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-14T20:22:02,126 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:02,127 ERROR [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:02,127 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=94, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:02,127 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:02,167 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:22:02,233 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-14T20:22:02,234 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:02,244 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=219 (was 220), OpenFileDescriptor=442 (was 442), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=312 (was 350), ProcessCount=11 (was 11), AvailableMemoryMB=5759 (was 5871) 2024-12-14T20:22:02,251 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=219, OpenFileDescriptor=442, MaxFileDescriptor=1048576, SystemLoadAverage=312, ProcessCount=11, AvailableMemoryMB=5759 2024-12-14T20:22:02,252 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:02,253 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=95, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:02,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-14T20:22:02,273 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:02,273 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:02,284 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:02,285 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580057 connected 2024-12-14T20:22:02,363 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-14T20:22:02,393 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580057, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:02,444 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=96, ppid=95, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:02,573 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-14T20:22:02,595 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:02,596 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=96 2024-12-14T20:22:02,596 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:22:02,609 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=96}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:02,621 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:02,660 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=96 2024-12-14T20:22:02,661 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=96 2024-12-14T20:22:02,662 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:02,663 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=96, resume processing ppid=95 2024-12-14T20:22:02,663 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:22:02,663 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=96, ppid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 218 msec 2024-12-14T20:22:02,665 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 411 msec 2024-12-14T20:22:02,685 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1c92bef9 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@40803bd9 2024-12-14T20:22:02,694 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:02,694 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:02,694 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4fbecd06, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:02,695 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:02,702 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:02,702 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:02,702 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580059 connected 2024-12-14T20:22:02,884 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-14T20:22:02,884 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:02,885 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:22:02,887 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3938): Client=jenkins//172.17.0.3 disable replication peer, id=1 2024-12-14T20:22:02,889 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=97, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure 2024-12-14T20:22:02,891 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-14T20:22:02,902 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=98, ppid=97, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:02,994 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-14T20:22:03,054 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:03,054 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=98 2024-12-14T20:22:03,054 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=DISABLE_PEER 2024-12-14T20:22:03,055 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:03,055 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:03,055 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:03,055 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580059, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:03,056 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580059, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:03,161 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580059, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:03,161 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1c92bef9 to 127.0.0.1:64264 2024-12-14T20:22:03,162 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:03,175 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:03,175 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:03,175 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=98 2024-12-14T20:22:03,176 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=98 2024-12-14T20:22:03,177 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for DISABLE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:03,179 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=98, resume processing ppid=97 2024-12-14T20:22:03,179 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=98, ppid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 275 msec 2024-12-14T20:22:03,179 INFO [PEWorker-4 {}] replication.DisablePeerProcedure(67): Successfully disabled peer 1 2024-12-14T20:22:03,180 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure in 291 msec 2024-12-14T20:22:03,200 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2e2df139 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@72620f55 2024-12-14T20:22:03,204 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-14T20:22:03,204 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: DISABLE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:03,204 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:22:03,205 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:03,206 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=99, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:03,206 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-14T20:22:03,210 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:03,210 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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 2024-12-14T20:22:03,211 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:03,211 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1e5b251d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:03,212 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:03,218 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:03,218 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:03,218 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:03,219 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=100, ppid=99, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:03,227 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:03,227 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:03,227 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58005b connected 2024-12-14T20:22:03,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-14T20:22:03,371 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:03,371 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=100 2024-12-14T20:22:03,371 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:03,371 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:03,372 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:03,372 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:03,372 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58005b, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:03,372 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58005b, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:03,524 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-14T20:22:03,632 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58005b, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:03,632 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2e2df139 to 127.0.0.1:64264 2024-12-14T20:22:03,632 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:03,632 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:03,644 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:03,651 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:03,652 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:03,652 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:03,652 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:03,652 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=100 2024-12-14T20:22:03,652 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=100 2024-12-14T20:22:03,654 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:03,655 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=100, resume processing ppid=99 2024-12-14T20:22:03,655 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=100, ppid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 435 msec 2024-12-14T20:22:03,661 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:03,661 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:03,662 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 456 msec 2024-12-14T20:22:03,834 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-14T20:22:03,835 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:03,836 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:03,838 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=101, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:03,840 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-14T20:22:03,841 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:03,842 ERROR [PEWorker-4 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:03,843 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=101, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-14T20:22:03,843 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:03,944 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-14T20:22:03,944 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:22:03,945 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:03,945 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=102, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:03,946 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-14T20:22:03,946 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:03,947 ERROR [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:03,948 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=102, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:03,948 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:04,054 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-14T20:22:04,054 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:04,064 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221 (was 219) - Thread LEAK? -, OpenFileDescriptor=444 (was 442) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=312 (was 312), ProcessCount=11 (was 11), AvailableMemoryMB=5741 (was 5759) 2024-12-14T20:22:04,072 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=312, ProcessCount=11, AvailableMemoryMB=5741 2024-12-14T20:22:04,073 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=dummy_peer 2024-12-14T20:22:04,073 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=103, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:04,074 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-14T20:22:04,074 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 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:04,075 ERROR [PEWorker-2 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:04,076 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=103, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:04,077 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:04,184 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-14T20:22:04,184 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: dummy_peer failed with dummy_peer 2024-12-14T20:22:04,185 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:04,186 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=104, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:04,187 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-14T20:22:04,187 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:04,188 ERROR [PEWorker-1 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:04,189 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=104, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:04,189 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:04,294 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-14T20:22:04,295 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:22:04,295 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:04,296 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=105, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:04,297 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-14T20:22:04,297 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:04,298 ERROR [PEWorker-5 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:04,299 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=105, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:04,299 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:04,404 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-14T20:22:04,405 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:04,416 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221 (was 221), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=312 (was 312), ProcessCount=11 (was 11), AvailableMemoryMB=5738 (was 5741) 2024-12-14T20:22:04,424 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=312, ProcessCount=11, AvailableMemoryMB=5737 2024-12-14T20:22:04,425 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:04,426 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=106, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:04,427 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-14T20:22:04,440 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:04,440 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:04,452 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:04,452 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58005c connected 2024-12-14T20:22:04,534 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-14T20:22:04,568 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58005c, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:04,586 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=107, ppid=106, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:04,737 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:04,738 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=107 2024-12-14T20:22:04,738 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:22:04,743 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-14T20:22:04,753 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=107}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:04,766 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:04,827 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=107 2024-12-14T20:22:04,827 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=107 2024-12-14T20:22:04,829 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:04,831 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=107, resume processing ppid=106 2024-12-14T20:22:04,831 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:22:04,831 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=107, ppid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 243 msec 2024-12-14T20:22:04,832 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 406 msec 2024-12-14T20:22:04,855 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x73d7f99a to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@41378ac1 2024-12-14T20:22:04,860 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:04,861 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:04,861 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@38f63783, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:04,863 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:04,868 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:04,869 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:04,869 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58005e connected 2024-12-14T20:22:05,054 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-14T20:22:05,055 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:05,055 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3971): Client=jenkins//172.17.0.3 list replication peers, regex=null 2024-12-14T20:22:05,056 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:05,056 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=108, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:05,057 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-14T20:22:05,059 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:05,068 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:05,068 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:05,068 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:05,069 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=109, ppid=108, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:05,164 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-14T20:22:05,221 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:05,221 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=109 2024-12-14T20:22:05,221 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:05,221 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:05,221 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:05,222 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:05,222 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58005e, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:05,222 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58005e, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:05,327 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58005e, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:05,327 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x73d7f99a to 127.0.0.1:64264 2024-12-14T20:22:05,327 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:05,327 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:05,335 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:05,343 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:05,343 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:05,343 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:05,343 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:05,343 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=109 2024-12-14T20:22:05,344 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=109 2024-12-14T20:22:05,345 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:05,347 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=109, resume processing ppid=108 2024-12-14T20:22:05,347 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=109, ppid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 276 msec 2024-12-14T20:22:05,352 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:05,352 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:05,354 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 296 msec 2024-12-14T20:22:05,374 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-14T20:22:05,374 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:05,375 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:05,376 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=110, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:05,377 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-14T20:22:05,377 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:05,378 ERROR [PEWorker-1 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:05,379 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=110, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:05,379 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:05,484 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-14T20:22:05,485 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:22:05,485 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:05,486 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=111, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:05,486 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-14T20:22:05,486 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:05,487 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:05,488 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=111, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-14T20:22:05,488 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:05,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-14T20:22:05,594 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:05,604 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221 (was 221), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=312 (was 312), ProcessCount=11 (was 11), AvailableMemoryMB=5700 (was 5737) 2024-12-14T20:22:05,611 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=312, ProcessCount=11, AvailableMemoryMB=5698 2024-12-14T20:22:05,617 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:05,617 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] 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$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-12-14T20:22:05,617 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] ipc.CallRunner(138): callId: 344 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.3:50860 deadline: 1734207785617, exception=java.io.IOException: Replication peer modification disabled 2024-12-14T20:22:05,636 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 1, maxAttempts = 2, timeout = 120000 ms, time elapsed = 19 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$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$0(FutureUtils.java:71) ~[classes/:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$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$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-14T20:22:05,744 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:05,744 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] ipc.MetricsHBaseServer(152): Unknown exception type java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) ~[classes/:?] at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) ~[classes/:?] at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-12-14T20:22:05,745 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] ipc.CallRunner(138): callId: 345 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.3:50860 deadline: 1734207785744, exception=java.io.IOException: Replication peer modification disabled 2024-12-14T20:22:05,745 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 2, maxAttempts = 2, timeout = 120000 ms, time elapsed = 128 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$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$0(FutureUtils.java:71) ~[classes/:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$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$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-14T20:22:05,746 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Failed after attempts=2, exceptions: 2024-12-14T20:22:05.638Z, 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$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) 2024-12-14T20:22:05.746Z, java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$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) 2024-12-14T20:22:05,749 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:05,750 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=112, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:05,750 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-14T20:22:05,751 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:05,752 ERROR [PEWorker-4 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:05,753 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=112, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:05,753 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:05,854 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-14T20:22:05,855 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:22:05,855 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:05,856 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=113, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:05,857 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-14T20:22:05,857 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:05,858 ERROR [PEWorker-3 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:05,859 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=113, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:05,859 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:05,964 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-14T20:22:05,965 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:05,975 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=221 (was 221), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=312 (was 312), ProcessCount=11 (was 11), AvailableMemoryMB=5688 (was 5698) 2024-12-14T20:22:05,982 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=312, ProcessCount=11, AvailableMemoryMB=5688 2024-12-14T20:22:05,983 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:05,984 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=114, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:05,985 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-14T20:22:06,004 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:06,005 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:06,018 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:06,018 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58005f connected 2024-12-14T20:22:06,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-14T20:22:06,127 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58005f, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:06,144 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=115, ppid=114, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:06,296 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:06,297 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=115 2024-12-14T20:22:06,297 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:22:06,304 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-14T20:22:06,311 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=115}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:06,322 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:06,360 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=115 2024-12-14T20:22:06,361 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=115 2024-12-14T20:22:06,362 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:06,364 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=115, resume processing ppid=114 2024-12-14T20:22:06,364 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=115, ppid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 218 msec 2024-12-14T20:22:06,364 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:22:06,365 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 381 msec 2024-12-14T20:22:06,386 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x11ffc818 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@40955c71 2024-12-14T20:22:06,394 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:06,394 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:06,394 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@74d3c628, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:06,395 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:06,402 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:06,402 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:06,402 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580061 connected 2024-12-14T20:22:06,613 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-14T20:22:06,614 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:06,614 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:06,615 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:06,616 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=116, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:06,616 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-14T20:22:06,618 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:06,627 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:06,627 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:06,627 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:06,628 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=117, ppid=116, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:06,723 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-14T20:22:06,744 DEBUG [BootstrapNodeManager {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-14T20:22:06,746 INFO [RS-EventLoopGroup-1-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:46854, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-14T20:22:06,779 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:06,780 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=117 2024-12-14T20:22:06,780 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:06,780 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:06,780 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:06,780 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:06,780 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580061, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:06,781 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580061, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:06,885 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580061, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:06,885 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x11ffc818 to 127.0.0.1:64264 2024-12-14T20:22:06,885 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:06,885 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:06,894 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:06,902 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:06,902 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:06,902 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:06,902 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:06,902 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=117 2024-12-14T20:22:06,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=117 2024-12-14T20:22:06,904 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:06,905 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=117, resume processing ppid=116 2024-12-14T20:22:06,905 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=117, ppid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-14T20:22:06,911 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:06,911 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:06,912 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 296 msec 2024-12-14T20:22:06,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-14T20:22:06,933 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:06,934 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:06,934 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=118, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:06,935 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-14T20:22:06,935 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:06,936 ERROR [PEWorker-4 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:06,937 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=118, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-14T20:22:06,937 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:07,043 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-14T20:22:07,044 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:07,054 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=222 (was 221) - Thread LEAK? -, OpenFileDescriptor=448 (was 444) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=295 (was 312), ProcessCount=11 (was 11), AvailableMemoryMB=5671 (was 5688) 2024-12-14T20:22:07,061 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=222, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=295, ProcessCount=11, AvailableMemoryMB=5670 2024-12-14T20:22:07,062 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:07,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=119, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:07,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-14T20:22:07,075 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:07,076 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:07,085 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:07,085 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580062 connected 2024-12-14T20:22:07,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-14T20:22:07,193 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580062, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:07,219 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=120, ppid=119, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:07,370 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:07,371 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=120 2024-12-14T20:22:07,371 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:22:07,384 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-14T20:22:07,384 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=120}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:07,396 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:07,449 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=120 2024-12-14T20:22:07,450 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=120 2024-12-14T20:22:07,451 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:07,453 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=120, resume processing ppid=119 2024-12-14T20:22:07,453 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:22:07,453 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=120, ppid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 232 msec 2024-12-14T20:22:07,454 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 391 msec 2024-12-14T20:22:07,473 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1154bc9c to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2d40c3ed 2024-12-14T20:22:07,482 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:22:07,485 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:07,486 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:07,486 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@c903204, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:07,487 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:07,502 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:07,502 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:07,502 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580064 connected 2024-12-14T20:22:07,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-14T20:22:07,694 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:07,694 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:07,695 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-14T20:22:07,695 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=121, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:07,696 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-14T20:22:07,709 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:07,709 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:07,718 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:07,719 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580065 connected 2024-12-14T20:22:07,803 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-14T20:22:07,827 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580065, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:07,836 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=122, ppid=121, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:07,987 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:07,988 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=122 2024-12-14T20:22:07,988 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:07,989 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=122 2024-12-14T20:22:07,990 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=122 2024-12-14T20:22:07,991 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:07,992 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=122, resume processing ppid=121 2024-12-14T20:22:07,992 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-14T20:22:07,992 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=122, ppid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 155 msec 2024-12-14T20:22:07,993 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 297 msec 2024-12-14T20:22:08,013 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-14T20:22:08,014 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:08,014 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:08,015 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:08,016 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=123, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:08,017 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-14T20:22:08,018 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:08,027 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:08,027 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:08,027 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:08,028 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=124, ppid=123, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:08,123 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-14T20:22:08,179 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:08,180 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=124 2024-12-14T20:22:08,180 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:08,180 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:08,180 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:08,180 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:08,180 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580064, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:08,181 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580064, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:08,285 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580064, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:08,285 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1154bc9c to 127.0.0.1:64264 2024-12-14T20:22:08,285 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:08,285 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:08,294 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:08,302 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:08,302 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:08,302 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:08,302 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:08,302 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=124 2024-12-14T20:22:08,303 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=124 2024-12-14T20:22:08,304 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:08,306 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=124, resume processing ppid=123 2024-12-14T20:22:08,306 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=124, ppid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 276 msec 2024-12-14T20:22:08,311 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:08,311 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:08,312 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 296 msec 2024-12-14T20:22:08,334 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-14T20:22:08,334 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:08,334 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:08,335 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=125, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:08,336 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-14T20:22:08,336 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:08,337 ERROR [PEWorker-1 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:08,337 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=125, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:08,337 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:08,444 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-14T20:22:08,444 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-14T20:22:08,445 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:08,446 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=126, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:08,446 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-14T20:22:08,446 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:08,447 ERROR [PEWorker-5 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:08,448 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=126, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:08,448 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:08,554 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-14T20:22:08,554 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:08,565 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223 (was 222) - Thread LEAK? -, OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=295 (was 295), ProcessCount=11 (was 11), AvailableMemoryMB=5656 (was 5670) 2024-12-14T20:22:08,572 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=295, ProcessCount=11, AvailableMemoryMB=5655 2024-12-14T20:22:08,574 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:08,575 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=127, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:08,575 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-14T20:22:08,684 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-14T20:22:08,868 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=128, ppid=127, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:08,894 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-14T20:22:09,022 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:09,023 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=128 2024-12-14T20:22:09,023 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:22:09,056 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:09,102 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=128 2024-12-14T20:22:09,102 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(587): peerId=1, queueId=1 (queues=1) is replicating from cluster=59f0e019-1d42-4023-a8f2-0bc1cde5e5d1 to cluster=59f0e019-1d42-4023-a8f2-0bc1cde5e5d1 2024-12-14T20:22:09,102 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=128 2024-12-14T20:22:09,103 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(343): peerId=1, starting shipping worker for walGroupId=26a9feeac337%2C33199%2C1734207694050 2024-12-14T20:22:09,104 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:09,105 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=128, resume processing ppid=127 2024-12-14T20:22:09,105 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:22:09,105 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=128, ppid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 236 msec 2024-12-14T20:22:09,105 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSourceWALReader(112): peerClusterZnode=1, ReplicationSourceWALReaderThread : 1 inited, replicationBatchSizeCapacity=67108864, replicationBatchCountCapacity=25000, replicationBatchQueueCapacity=1 2024-12-14T20:22:09,106 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 531 msec 2024-12-14T20:22:09,107 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.shipper26a9feeac337%2C33199%2C1734207694050,1 {}] regionserver.ReplicationSourceShipper(98): Running ReplicationSourceShipper Thread for wal group: 26a9feeac337%2C33199%2C1734207694050 2024-12-14T20:22:09,107 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.wal-reader.26a9feeac337%2C33199%2C1734207694050,1 {}] regionserver.WALEntryStream(260): Creating new reader hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.1734207697017, startPosition=0, beingWritten=true 2024-12-14T20:22:09,159 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.wal-reader.26a9feeac337%2C33199%2C1734207694050,1 {}] regionserver.ReplicationSourceWALReader(181): Read 0 WAL entries eligible for replication 2024-12-14T20:22:09,159 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.wal-reader.26a9feeac337%2C33199%2C1734207694050,1 {}] regionserver.WALEntryStream(223): Reset reader hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.1734207697017 to pos 589, reset compression=false 2024-12-14T20:22:09,159 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.shipper26a9feeac337%2C33199%2C1734207694050,1 {}] regionserver.ReplicationSourceShipper(110): Shipper from source 1 got entry batch from reader: WALEntryBatch [walEntries=[], lastWalPath=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/WALs/26a9feeac337,33199,1734207694050/26a9feeac337%2C33199%2C1734207694050.1734207697017, lastWalPosition=589, nbRowKeys=0, nbHFiles=0, heapSize=0, lastSeqIds={}, endOfFile=false,usedBufferSize=0] 2024-12-14T20:22:09,204 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-14T20:22:09,204 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:09,205 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=2, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:09,206 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=129, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:09,206 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-14T20:22:09,207 WARN [PEWorker-5 {}] 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) ~[classes/:?] 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) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-12-14T20:22:09,208 ERROR [PEWorker-5 {}] 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) ~[classes/:?] 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) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[classes/: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 2024-12-14T20:22:09,208 INFO [PEWorker-5 {}] 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 2024-12-14T20:22:09,208 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. 2024-12-14T20:22:09,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-14T20:22:09,316 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 2 failed with Invalid cluster key: 2024-12-14T20:22:09,316 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:09,318 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=130, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:09,319 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:09,321 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:09,326 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:09,327 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:09,327 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:09,327 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=131, ppid=130, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:09,424 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:09,479 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:09,480 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=131 2024-12-14T20:22:09,480 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:09,480 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:09,481 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:09,634 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:09,944 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:10,453 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:10,481 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.wal-reader.26a9feeac337%2C33199%2C1734207694050,1 {}] 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) ~[classes/:?] 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/:?] 2024-12-14T20:22:10,481 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.shipper26a9feeac337%2C33199%2C1734207694050,1 {}] 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/:?] 2024-12-14T20:22:11,464 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:11,481 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(711): peerId=1, ReplicationSourceWorker RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1.replicationSource.shipper26a9feeac337%2C33199%2C1734207694050,1 terminated 2024-12-14T20:22:11,481 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:11,483 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:11,527 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:11,527 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:11,527 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:11,527 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:11,528 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=131 2024-12-14T20:22:11,528 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=131 2024-12-14T20:22:11,530 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:11,532 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=131, resume processing ppid=130 2024-12-14T20:22:11,532 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=131, ppid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 2.2030 sec 2024-12-14T20:22:11,544 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:11,544 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:11,545 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 2.2280 sec 2024-12-14T20:22:12,388 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:22:13,484 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-14T20:22:13,484 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:13,485 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=2 2024-12-14T20:22:13,485 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=132, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:13,486 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-14T20:22:13,487 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-14T20:22:13,488 ERROR [PEWorker-5 {}] 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) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-14T20:22:13,489 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=132, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-14T20:22:13,489 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-14T20:22:13,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-14T20:22:13,595 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-14T20:22:13,606 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=221 (was 223), OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=279 (was 295), ProcessCount=11 (was 11), AvailableMemoryMB=5644 (was 5655) 2024-12-14T20:22:13,615 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[1] Thread=221, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=279, ProcessCount=11, AvailableMemoryMB=5641 2024-12-14T20:22:13,616 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3919): Client=jenkins//172.17.0.3 creating replication peer, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-14T20:22:13,617 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=133, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-14T20:22:13,618 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-14T20:22:13,630 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:13,630 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:13,677 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:13,678 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580066 connected 2024-12-14T20:22:13,724 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-14T20:22:13,785 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580066, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:13,802 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=134, ppid=133, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:13,934 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-14T20:22:13,953 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:13,954 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=134 2024-12-14T20:22:13,954 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-14T20:22:13,967 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=134}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:13,978 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:14,019 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=134 2024-12-14T20:22:14,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=134 2024-12-14T20:22:14,022 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:14,025 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=134, resume processing ppid=133 2024-12-14T20:22:14,025 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=134, ppid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 220 msec 2024-12-14T20:22:14,025 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-14T20:22:14,028 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 410 msec 2024-12-14T20:22:14,053 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6edae38c to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@d6f8a6d 2024-12-14T20:22:14,101 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:14,102 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:14,102 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4a810ea5, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:14,103 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:14,110 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:14,110 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:14,110 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580068 connected 2024-12-14T20:22:14,243 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-14T20:22:14,244 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:14,245 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:22:14,246 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=135, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:14,247 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-14T20:22:14,262 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:14,262 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:14,287 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:14,287 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580069 connected 2024-12-14T20:22:14,354 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-14T20:22:14,393 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580069, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:14,403 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=136, ppid=135, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:14,555 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:14,556 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=136 2024-12-14T20:22:14,556 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:14,559 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:14,559 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:14,559 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:14,560 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580068, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:14,560 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580068, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:14,564 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-14T20:22:14,669 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580068, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:14,669 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6edae38c to 127.0.0.1:64264 2024-12-14T20:22:14,669 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:14,685 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:14,685 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:14,685 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=136 2024-12-14T20:22:14,686 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=136 2024-12-14T20:22:14,688 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:14,689 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=136, resume processing ppid=135 2024-12-14T20:22:14,689 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:22:14,689 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=136, ppid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-14T20:22:14,690 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 444 msec 2024-12-14T20:22:14,712 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x102b7843 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4da9388a 2024-12-14T20:22:14,719 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:14,719 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:14,719 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@22ee6ce6, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:14,720 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:14,726 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:14,727 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:14,727 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58006b connected 2024-12-14T20:22:14,874 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-14T20:22:14,875 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:14,876 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:14,878 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:14,880 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:14,882 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-14T20:22:14,884 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=137, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:14,885 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-14T20:22:14,897 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:14,898 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:14,909 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:14,910 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58006c connected 2024-12-14T20:22:14,993 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-14T20:22:15,018 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58006c, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:15,027 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=138, ppid=137, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:15,179 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:15,180 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=138 2024-12-14T20:22:15,181 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:15,183 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:15,184 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:15,184 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:15,184 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58006b, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:15,185 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58006b, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:15,204 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-14T20:22:15,294 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58006b, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:15,294 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x102b7843 to 127.0.0.1:64264 2024-12-14T20:22:15,294 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:15,311 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:15,312 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:15,312 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=138 2024-12-14T20:22:15,312 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=138 2024-12-14T20:22:15,314 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:15,315 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=138, resume processing ppid=137 2024-12-14T20:22:15,315 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-14T20:22:15,315 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=138, ppid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 287 msec 2024-12-14T20:22:15,316 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 432 msec 2024-12-14T20:22:15,337 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1d092dd8 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@75308feb 2024-12-14T20:22:15,344 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:15,344 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:15,344 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@35ffd783, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:15,345 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:15,352 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:15,352 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:15,352 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58006e connected 2024-12-14T20:22:15,514 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-14T20:22:15,514 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:15,515 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:15,516 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:15,516 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:15,517 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:15,517 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-14T20:22:15,518 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=139, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:15,519 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-14T20:22:15,534 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:15,535 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:15,543 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:15,544 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58006f connected 2024-12-14T20:22:15,624 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-14T20:22:15,652 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a58006f, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:15,662 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=140, ppid=139, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:15,814 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:15,815 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=140 2024-12-14T20:22:15,815 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:15,816 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:15,816 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:15,816 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:15,816 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58006e, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:15,817 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58006e, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:15,834 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-14T20:22:15,927 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58006e, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:15,927 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1d092dd8 to 127.0.0.1:64264 2024-12-14T20:22:15,927 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:15,966 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:15,966 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:15,966 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=140 2024-12-14T20:22:15,967 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=140 2024-12-14T20:22:15,968 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:15,969 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=140, resume processing ppid=139 2024-12-14T20:22:15,969 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-14T20:22:15,969 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=140, ppid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 307 msec 2024-12-14T20:22:15,970 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 451 msec 2024-12-14T20:22:15,990 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x18a36a8b to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@a0191ba 2024-12-14T20:22:16,001 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:16,002 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:16,002 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@63870041, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:16,003 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:16,010 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:16,010 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:16,010 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580071 connected 2024-12-14T20:22:16,143 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-14T20:22:16,144 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:16,144 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:16,145 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:16,145 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:16,146 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:22:16,146 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=141, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:16,147 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-14T20:22:16,158 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:16,158 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:16,168 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:16,169 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580072 connected 2024-12-14T20:22:16,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-14T20:22:16,277 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580072, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:16,286 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=142, ppid=141, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:16,437 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:16,438 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=142 2024-12-14T20:22:16,438 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:16,439 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:16,439 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:16,439 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:16,439 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580071, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:16,440 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580071, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:16,464 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-14T20:22:16,543 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580071, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:16,544 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x18a36a8b to 127.0.0.1:64264 2024-12-14T20:22:16,544 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:16,558 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:16,558 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:16,559 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=142 2024-12-14T20:22:16,559 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=142 2024-12-14T20:22:16,561 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:16,562 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=142, resume processing ppid=141 2024-12-14T20:22:16,562 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:22:16,562 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=142, ppid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 275 msec 2024-12-14T20:22:16,563 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 416 msec 2024-12-14T20:22:16,582 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x44083775 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@59793f47 2024-12-14T20:22:16,594 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:16,594 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:16,594 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@59d29a62, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:16,595 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:16,602 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:16,602 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:16,602 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580074 connected 2024-12-14T20:22:16,774 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-14T20:22:16,774 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:16,775 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:16,775 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:16,776 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-14T20:22:16,776 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=143, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:16,777 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-14T20:22:16,788 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:16,788 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:16,793 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:16,794 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580075 connected 2024-12-14T20:22:16,884 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-14T20:22:16,902 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580075, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:16,910 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=144, ppid=143, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:17,062 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:17,062 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=144 2024-12-14T20:22:17,062 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:17,064 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:17,064 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:17,064 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:17,064 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580074, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:17,064 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580074, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:17,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-14T20:22:17,168 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580074, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:17,169 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x44083775 to 127.0.0.1:64264 2024-12-14T20:22:17,169 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:17,181 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:17,181 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:17,181 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=144 2024-12-14T20:22:17,181 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=144 2024-12-14T20:22:17,183 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:17,184 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=144, resume processing ppid=143 2024-12-14T20:22:17,184 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-14T20:22:17,184 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=144, ppid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 273 msec 2024-12-14T20:22:17,185 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 408 msec 2024-12-14T20:22:17,206 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x57c514e9 to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4540d1c8 2024-12-14T20:22:17,218 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:17,218 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:17,218 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@36328a8f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:17,219 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:17,227 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:17,227 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:17,227 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a580077 connected 2024-12-14T20:22:17,404 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-14T20:22:17,404 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:17,405 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:17,405 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3960): Client=jenkins//172.17.0.3 update replication peer config, id=1, config=clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:22:17,406 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=145, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-14T20:22:17,406 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-14T20:22:17,417 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-14T20:22:17,418 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:17,427 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id0x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:17,427 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580078 connected 2024-12-14T20:22:17,514 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-14T20:22:17,535 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@2a2fc03acheck-peer-cluster-id-0x10026347a580078, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:17,544 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=146, ppid=145, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:17,695 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:17,696 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=146 2024-12-14T20:22:17,696 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-14T20:22:17,697 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-14T20:22:17,697 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {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 2024-12-14T20:22:17,697 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:17,697 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a580077, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:17,697 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a580077, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:17,724 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-14T20:22:17,802 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a580077, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:17,802 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x57c514e9 to 127.0.0.1:64264 2024-12-14T20:22:17,802 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:17,819 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-14T20:22:17,820 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-14T20:22:17,820 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=146 2024-12-14T20:22:17,820 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=146 2024-12-14T20:22:17,822 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:17,823 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=146, resume processing ppid=145 2024-12-14T20:22:17,823 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:64264:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-14T20:22:17,823 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=146, ppid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 278 msec 2024-12-14T20:22:17,824 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 418 msec 2024-12-14T20:22:17,843 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x20d02b4f to 127.0.0.1:64264 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3ff62e83 2024-12-14T20:22:17,852 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.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) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[classes/:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-14T20:22:17,852 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-14T20:22:17,853 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2ba6d516, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-14T20:22:17,853 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:64264 2024-12-14T20:22:17,860 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-14T20:22:17,860 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x10026347a58007a connected 2024-12-14T20:22:17,860 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-14T20:22:18,034 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-14T20:22:18,034 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-14T20:22:18,035 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3948): Client=jenkins//172.17.0.3 get replication peer config, id=1 2024-12-14T20:22:18,036 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:18,036 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.HMaster(3926): Client=jenkins//172.17.0.3 removing replication peer, id=1 2024-12-14T20:22:18,037 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=147, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:18,037 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] procedure2.ProcedureExecutor(1098): Stored pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:18,038 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:18,038 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-14T20:22:18,041 DEBUG [PEWorker-5 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=147 2024-12-14T20:22:18,041 DEBUG [PEWorker-5 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-14T20:22:18,042 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:18,051 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-14T20:22:18,052 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:18,052 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:45141-0x10026347a580000, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-14T20:22:18,052 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=149, ppid=147, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-14T20:22:18,144 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:18,144 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-14T20:22:18,203 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 26a9feeac337,33199,1734207694050 2024-12-14T20:22:18,204 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=149 2024-12-14T20:22:18,204 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-14T20:22:18,204 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-14T20:22:18,204 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-14T20:22:18,204 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-14T20:22:18,204 WARN [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x10026347a58007a, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:18,204 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x10026347a58007a, quorum=127.0.0.1:64264, 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) ~[?:?] 2024-12-14T20:22:18,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x10026347a58007a, quorum=127.0.0.1:64264, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-14T20:22:18,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x20d02b4f to 127.0.0.1:64264 2024-12-14T20:22:18,310 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-14T20:22:18,310 INFO [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-14T20:22:18,319 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ZKUtil(111): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:18,327 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1/26a9feeac337%2C33199%2C1734207694050.1734207697017 2024-12-14T20:22:18,327 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:18,327 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:33199-0x10026347a580001, quorum=127.0.0.1:64264, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/26a9feeac337,33199,1734207694050/1 2024-12-14T20:22:18,327 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:18,327 DEBUG [RS_REFRESH_PEER-regionserver/26a9feeac337:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=149 2024-12-14T20:22:18,327 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.HMaster(4106): Remote procedure done, pid=149 2024-12-14T20:22:18,328 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 26a9feeac337,33199,1734207694050 suceeded 2024-12-14T20:22:18,330 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=149, resume processing ppid=147 2024-12-14T20:22:18,330 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=149, ppid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-14T20:22:18,351 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-14T20:22:18,351 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-14T20:22:18,353 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 315 msec 2024-12-14T20:22:18,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:18,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-14T20:22:18,354 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-14T20:22:18,663 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:19,174 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:20,184 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:20,569 INFO [master/26a9feeac337:0.Chore.1 {}] migrate.RollingUpgradeChore(116): There is no table to migrate StoreFileTracker! 2024-12-14T20:22:20,569 INFO [master/26a9feeac337:0.Chore.1 {}] migrate.RollingUpgradeChore(85): All Rolling-Upgrade tasks are complete, shutdown RollingUpgradeChore! 2024-12-14T20:22:22,193 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:23,829 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:22:26,203 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:32,168 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:22:36,234 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:38,676 DEBUG [master/26a9feeac337:0.Chore.1 {}] balancer.RegionLocationFinder(172): Locality for region 057fa4c987c40e584d6d33b443bf0875 changed from -1.0 to 0.0, refreshing cache 2024-12-14T20:22:46,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:22:56,394 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:23:02,168 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:23:06,454 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:23:26,514 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:23:32,168 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:23:46,613 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:24:02,169 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:24:06,664 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:24:26,764 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:24:32,169 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:24:46,934 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:25:02,169 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:25:06,964 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:25:27,124 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:25:32,170 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:25:47,264 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:26:02,170 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:26:07,344 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:26:27,484 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:26:32,170 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:26:34,063 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 2024-12-14T20:26:34,227 DEBUG [master/26a9feeac337:0: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% 2024-12-14T20:26:34,227 DEBUG [master/26a9feeac337:0: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 2024-12-14T20:26:36,897 INFO [26a9feeac337:33199Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-14T20:26:38,831 DEBUG [hconnection-0x2c7784c7-shared-pool-4 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:26:38,834 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:54346, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:26:38,842 DEBUG [master/26a9feeac337:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-14T20:26:38,844 DEBUG [master/26a9feeac337:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-14T20:26:38,844 DEBUG [master/26a9feeac337:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-14T20:26:39,865 INFO [regionserver/26a9feeac337:0.Chore.1 {}] regionserver.HRegionServer$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 161887 ms 2024-12-14T20:26:40,864 INFO [regionserver/26a9feeac337:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875. because 057fa4c987c40e584d6d33b443bf0875/info has an old edit so flush to free WALs after random delay 280522 ms 2024-12-14T20:26:43,858 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:26:47,604 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:27:02,171 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:27:07,694 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:27:27,894 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:27:32,171 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:27:48,094 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:28:02,172 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:28:08,174 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:28:28,274 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:28:32,172 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:28:48,294 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:29:02,172 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:29:08,404 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:29:21,753 DEBUG [MemStoreFlusher.0 {}] regionserver.FlushAllLargeStoresPolicy(69): Since none of the CFs were above the size, flushing all. 2024-12-14T20:29:21,754 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 1588230740 3/3 column families, dataSize=1.23 KB heapSize=2.87 KB 2024-12-14T20:29:21,815 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/.tmp/info/3c60502fcd834ddf81165de4fdb3f842 is 143, key is hbase:namespace,,1734207698556.057fa4c987c40e584d6d33b443bf0875./info:regioninfo/1734207699870/Put/seqid=0 2024-12-14T20:29:21,823 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741837_1013 (size=6595) 2024-12-14T20:29:22,226 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1.14 KB at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/.tmp/info/3c60502fcd834ddf81165de4fdb3f842 2024-12-14T20:29:22,279 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/.tmp/table/750d58ba1b7e48bdb799502c2a3114bd is 51, key is hbase:namespace/table:state/1734207699882/Put/seqid=0 2024-12-14T20:29:22,283 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741838_1014 (size=5242) 2024-12-14T20:29:22,685 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=94 B at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/.tmp/table/750d58ba1b7e48bdb799502c2a3114bd 2024-12-14T20:29:22,702 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/.tmp/info/3c60502fcd834ddf81165de4fdb3f842 as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/info/3c60502fcd834ddf81165de4fdb3f842 2024-12-14T20:29:22,710 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/info/3c60502fcd834ddf81165de4fdb3f842, entries=10, sequenceid=9, filesize=6.4 K 2024-12-14T20:29:22,712 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/.tmp/table/750d58ba1b7e48bdb799502c2a3114bd as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/table/750d58ba1b7e48bdb799502c2a3114bd 2024-12-14T20:29:22,719 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/meta/1588230740/table/750d58ba1b7e48bdb799502c2a3114bd, entries=2, sequenceid=9, filesize=5.1 K 2024-12-14T20:29:22,720 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 2024-12-14T20:29:22,721 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 1588230740: 2024-12-14T20:29:28,564 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:29:32,173 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:29:48,584 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:29:53,852 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:30:02,173 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:30:08,644 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:30:28,664 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:30:32,173 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:30:38,852 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:30:48,744 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:31:02,174 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:31:08,934 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:31:21,386 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 057fa4c987c40e584d6d33b443bf0875 1/1 column families, dataSize=78 B heapSize=488 B 2024-12-14T20:31:21,410 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875/.tmp/info/a1111f0430fe477485a0b01afc8fdab6 is 45, key is default/info:d/1734207700023/Put/seqid=0 2024-12-14T20:31:21,415 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741839_1015 (size=5037) 2024-12-14T20:31:21,818 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=78 B at sequenceid=6 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875/.tmp/info/a1111f0430fe477485a0b01afc8fdab6 2024-12-14T20:31:21,834 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875/.tmp/info/a1111f0430fe477485a0b01afc8fdab6 as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875/info/a1111f0430fe477485a0b01afc8fdab6 2024-12-14T20:31:21,843 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/data/hbase/namespace/057fa4c987c40e584d6d33b443bf0875/info/a1111f0430fe477485a0b01afc8fdab6, entries=2, sequenceid=6, filesize=4.9 K 2024-12-14T20:31:21,844 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~78 B/78, heapSize ~472 B/472, currentSize=0 B/0 for 057fa4c987c40e584d6d33b443bf0875 in 458ms, sequenceid=6, compaction requested=false 2024-12-14T20:31:21,844 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 057fa4c987c40e584d6d33b443bf0875: 2024-12-14T20:31:23,853 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:31:24,850 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:31:29,034 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:31:32,174 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:31:34,062 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 2024-12-14T20:31:34,226 DEBUG [master/26a9feeac337:0: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% 2024-12-14T20:31:34,227 DEBUG [master/26a9feeac337:0: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 2024-12-14T20:31:36,897 INFO [26a9feeac337:33199Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-14T20:31:38,597 DEBUG [hconnection-0x2c7784c7-shared-pool-6 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:31:38,598 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:60672, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:31:38,611 DEBUG [master/26a9feeac337:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-14T20:31:38,613 DEBUG [master/26a9feeac337:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-14T20:31:38,613 DEBUG [master/26a9feeac337:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-14T20:31:38,617 DEBUG [master/26a9feeac337:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-14T20:31:43,864 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:31:49,094 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:32:02,174 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:32:08,853 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:32:09,293 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:32:09,850 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:32:29,344 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:32:32,175 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:32:49,464 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:32:53,854 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:32:54,851 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:33:02,175 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:33:09,484 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:33:29,614 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:33:32,175 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:33:38,854 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:33:39,851 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:33:49,683 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:34:02,176 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:34:09,754 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:34:23,855 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:34:24,851 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:34:29,853 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:34:32,176 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:34:49,975 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:35:02,176 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:35:08,856 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:35:09,852 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:35:10,154 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:35:30,284 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:35:32,177 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:35:50,324 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:35:53,856 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:35:54,852 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:36:02,177 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:36:10,474 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:36:30,494 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:36:32,178 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:36:34,062 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=2, hits=0, hitRatio=0, cachingAccesses=2, cachingHits=0, cachingHitsRatio=0,evictions=89, evicted=0, evictedPerRun=0.0 2024-12-14T20:36:34,226 DEBUG [master/26a9feeac337:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=3, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-12-14T20:36:34,227 DEBUG [master/26a9feeac337:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-14T20:36:36,277 DEBUG [master:store-WAL-Roller {}] wal.AbstractWALRoller(200): WAL AsyncFSWAL 26a9feeac337%2C45141%2C1734207693156:(num 1734207696168) roll period 900000 ms elapsed 2024-12-14T20:36:36,298 DEBUG [master:store-WAL-Roller {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156/26a9feeac337%2C45141%2C1734207693156.1734208596278, exclude list is [], retry=0 2024-12-14T20:36:36,302 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[127.0.0.1:38879,DS-1d94624a-9c90-4feb-9a82-e0022ad33e5a,DISK] 2024-12-14T20:36:36,304 INFO [master:store-WAL-Roller {}] wal.AbstractFSWAL(837): Rolled WAL /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156/26a9feeac337%2C45141%2C1734207693156.1734207696168 with entries=1165, filesize=507.09 KB; new WAL /user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156/26a9feeac337%2C45141%2C1734207693156.1734208596278 2024-12-14T20:36:36,304 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37495:37495)] 2024-12-14T20:36:36,304 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(751): hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/WALs/26a9feeac337,45141,1734207693156/26a9feeac337%2C45141%2C1734207693156.1734207696168 is not closed yet, will try archiving it next time 2024-12-14T20:36:36,307 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741830_1006 (size=519270) 2024-12-14T20:36:36,334 INFO [master:store-Flusher {}] regionserver.HRegion(2837): Flushing 1595e783b53d99cd5eef43b6debb2682 4/4 column families, dataSize=432.38 KB heapSize=534.71 KB 2024-12-14T20:36:36,348 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/8bf62b70c22048458a4b8030d8947863 is 82, key is hbase:meta,,1/info:regioninfo/1734207698397/Put/seqid=0 2024-12-14T20:36:36,353 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741841_1017 (size=5672) 2024-12-14T20:36:36,756 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=504 B at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/8bf62b70c22048458a4b8030d8947863 2024-12-14T20:36:36,788 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/c9a91762fcf149fead9696fa41f1b8de is 293, key is \x00\x00\x00\x00\x00\x00\x00\x94/proc:d/1734207738036/Put/seqid=0 2024-12-14T20:36:36,793 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741842_1018 (size=11283) 2024-12-14T20:36:36,897 INFO [26a9feeac337:33199Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-14T20:36:37,196 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=430.82 KB at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/c9a91762fcf149fead9696fa41f1b8de 2024-12-14T20:36:37,207 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for c9a91762fcf149fead9696fa41f1b8de 2024-12-14T20:36:37,222 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/63596340e58b46a392d8f421664ee4f1 is 69, key is 26a9feeac337,33199,1734207694050/rs:state/1734207696795/Put/seqid=0 2024-12-14T20:36:37,226 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741843_1019 (size=5156) 2024-12-14T20:36:37,641 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=65 B at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/63596340e58b46a392d8f421664ee4f1 2024-12-14T20:36:37,664 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/0c4ca6510755468ebdc19436b4b57c7f is 68, key is replication_peer_modification_on/state:d/1734207733595/Put/seqid=0 2024-12-14T20:36:37,667 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38879 is added to blk_1073741844_1020 (size=5154) 2024-12-14T20:36:38,069 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1 KB at sequenceid=1168 (bloomFilter=true), to=hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/0c4ca6510755468ebdc19436b4b57c7f 2024-12-14T20:36:38,085 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/8bf62b70c22048458a4b8030d8947863 as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/8bf62b70c22048458a4b8030d8947863 2024-12-14T20:36:38,092 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/8bf62b70c22048458a4b8030d8947863, entries=8, sequenceid=1168, filesize=5.5 K 2024-12-14T20:36:38,093 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/c9a91762fcf149fead9696fa41f1b8de as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/c9a91762fcf149fead9696fa41f1b8de 2024-12-14T20:36:38,099 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for c9a91762fcf149fead9696fa41f1b8de 2024-12-14T20:36:38,099 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/c9a91762fcf149fead9696fa41f1b8de, entries=149, sequenceid=1168, filesize=11.0 K 2024-12-14T20:36:38,100 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/63596340e58b46a392d8f421664ee4f1 as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/63596340e58b46a392d8f421664ee4f1 2024-12-14T20:36:38,106 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/63596340e58b46a392d8f421664ee4f1, entries=1, sequenceid=1168, filesize=5.0 K 2024-12-14T20:36:38,107 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/0c4ca6510755468ebdc19436b4b57c7f as hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/0c4ca6510755468ebdc19436b4b57c7f 2024-12-14T20:36:38,114 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/0c4ca6510755468ebdc19436b4b57c7f, entries=1, sequenceid=1168, filesize=5.0 K 2024-12-14T20:36:38,115 INFO [master:store-Flusher {}] regionserver.HRegion(3040): Finished flush of dataSize ~432.38 KB/442757, heapSize ~534.65 KB/547480, currentSize=0 B/0 for 1595e783b53d99cd5eef43b6debb2682 in 1781ms, sequenceid=1168, compaction requested=false 2024-12-14T20:36:38,115 DEBUG [master:store-Flusher {}] regionserver.HRegion(2538): Flush status journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-14T20:36:38,857 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:36:39,853 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:36:41,132 DEBUG [master/26a9feeac337:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-14T20:36:41,133 DEBUG [master/26a9feeac337:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-14T20:36:41,135 DEBUG [hconnection-0x2c7784c7-shared-pool-8 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:36:41,137 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:53106, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:36:41,144 DEBUG [master/26a9feeac337:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-14T20:36:43,857 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:36:50,684 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:37:02,178 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:37:10,864 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:37:23,857 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:37:24,853 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:37:31,013 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:37:32,178 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:37:51,184 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:38:02,179 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:38:08,858 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:38:09,854 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:38:11,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:38:31,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:38:32,179 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:38:51,664 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:38:53,858 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:38:54,854 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:39:02,179 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:39:11,854 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:39:32,043 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:39:32,180 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:39:38,859 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:39:39,854 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:39:52,224 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:40:02,180 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:40:12,233 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:40:23,859 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:40:24,855 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:40:32,180 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:40:32,343 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:40:52,394 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:41:02,180 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:41:08,859 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:41:09,855 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:41:12,433 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:41:32,181 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:41:32,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:41:34,062 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 2024-12-14T20:41:34,226 DEBUG [master/26a9feeac337:0: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% 2024-12-14T20:41:34,226 DEBUG [master/26a9feeac337:0: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 2024-12-14T20:41:36,897 INFO [26a9feeac337:33199Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-14T20:41:39,355 DEBUG [master/26a9feeac337:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-14T20:41:39,355 DEBUG [master/26a9feeac337:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-14T20:41:39,362 DEBUG [hconnection-0x2c7784c7-shared-pool-10 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:41:39,364 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:33236, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:41:39,366 DEBUG [master/26a9feeac337:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-14T20:41:39,368 DEBUG [master/26a9feeac337:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-14T20:41:43,862 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:41:52,693 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:41:53,860 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:41:54,855 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:42:02,181 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:42:12,844 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:42:32,181 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:42:32,893 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:42:38,860 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:42:39,856 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:42:53,083 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:43:02,181 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:43:13,094 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:43:23,861 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:43:24,856 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:43:32,182 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:43:33,194 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:43:53,254 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:44:02,182 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:44:08,861 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:44:09,857 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:44:13,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:44:32,183 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:44:33,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:44:53,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:44:53,862 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:44:54,857 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:45:02,183 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:45:13,723 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:45:32,184 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:45:33,744 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:45:38,862 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:45:39,858 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:45:53,834 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:46:02,184 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:46:13,853 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:46:23,863 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:46:24,858 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:46:32,184 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:46:33,963 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:46:34,062 INFO [LruBlockCacheStatsExecutor {}] hfile.LruBlockCache(1020): totalSize=880 MB, usedSize=663.48 KB, freeSize=879.35 MB, max=880 MB, blockCount=2, accesses=6, hits=4, hitRatio=66.67%, , cachingAccesses=6, cachingHits=4, cachingHitsRatio=66.67%, evictions=149, evicted=0, evictedPerRun=0.0 2024-12-14T20:46:34,226 DEBUG [master/26a9feeac337:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=6, created chunk count=7, reused chunk count=1, reuseRatio=12.50% 2024-12-14T20:46:34,227 DEBUG [master/26a9feeac337:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): index stats (chunk size=209715): current pool size=0, created chunk count=0, reused chunk count=0, reuseRatio=0 2024-12-14T20:46:36,897 INFO [26a9feeac337:33199Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-14T20:46:39,046 DEBUG [master/26a9feeac337:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-14T20:46:39,046 DEBUG [master/26a9feeac337:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-14T20:46:39,047 DEBUG [hconnection-0x2c7784c7-shared-pool-12 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-14T20:46:39,050 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.3:39894, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-14T20:46:39,058 DEBUG [master/26a9feeac337:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-14T20:46:43,856 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-14T20:46:54,013 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-14T20:47:02,185 DEBUG [FsDatasetAsyncDiskServiceFixer {}] hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer(620): NoSuchFieldException: threadGroup; It might because your Hadoop version > 3.2.3 or 3.3.4, See HBASE-27595 for details. 2024-12-14T20:47:08,864 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-14T20:47:09,859 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 057fa4c987c40e584d6d33b443bf0875, had cached 0 bytes from a total of 5037 2024-12-14T20:47:14,153 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 ====> TEST TIMED OUT. PRINTING THREAD DUMP. <==== Timestamp: 2024-12-14 08:47:28,558 "NIOWorkerThread-13" daemon prio=5 tid=169 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "DataXceiver for client DFSClient_NONMAPREDUCE_-737504833_22 at /127.0.0.1:56062 [Receiving block BP-1348547021-172.17.0.3-1734207689317:blk_1073741840_1016]" daemon prio=5 tid=895 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 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$Responder.run(Server.java:1716) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=45141" daemon prio=5 tid=182 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "NIOWorkerThread-5" daemon prio=5 tid=161 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$RedundancyMonitor.run(BlockManager.java:5352) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "LruBlockCacheStatsExecutor" daemon prio=5 tid=189 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp642875574-39" daemon prio=5 tid=39 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$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$257/0x00007ff47c4273d0.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) "PacketResponder: BP-1348547021-172.17.0.3-1734207689317: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) "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) "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) "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) "AsyncFSWAL-0-hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05-prefix:26a9feeac337,33199,1734207694050.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) "Timer for 'HBase' metrics system" daemon prio=5 tid=1016 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) "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) "LeaseRenewer:jenkins@localhost:42601" 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) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=45141" 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) "ReadOnlyZKClient-127.0.0.1:64264@0x797ad262" 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$760/0x00007ff47cb6e298.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 0 on default port 42601" daemon prio=5 tid=64 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Handler.run(Server.java:3165) "SSL Certificates Store Monitor" daemon prio=5 tid=25 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:537) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "pool-1-thread-1" daemon prio=5 tid=14 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollPort$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) "NIOServerCxnFactory.AcceptThread:localhost/127.0.0.1:64264" 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) "M:0;26a9feeac337:45141" 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) "org.apache.hadoop.hdfs.server.datanode.DataXceiverServer@14141e4" 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) "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) "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$EvictionThread.run(LruBlockCache.java:957) "Signal Dispatcher" daemon prio=9 tid=4 runnable java.lang.Thread.State: RUNNABLE "qtp642875574-43" daemon prio=5 tid=43 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/dfs/data/data1/current/BP-1348547021-172.17.0.3-1734207689317" 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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "FsDatasetAsyncDiskServiceFixer" daemon prio=5 tid=136 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer.run(HBaseTestingUtility.java:599) "BP-1348547021-172.17.0.3-1734207689317 heartbeating to localhost/127.0.0.1:42601" 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) "Time-limited test-SendThread(127.0.0.1:64264)" 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$SendThread.run(ClientCnxn.java:1289) "NIOWorkerThread-14" daemon prio=5 tid=170 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=45141" 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) "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) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@1a19aca8" daemon prio=5 tid=93 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "OldWALsCleaner-0" daemon prio=5 tid=257 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$588/0x00007ff47ca78508.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 2 on default port 42601" 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) "IPC Server handler 1 on default port 37747" 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) "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) "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) "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) "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) "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) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=33199" 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) "RS_REFRESH_PEER-regionserver/26a9feeac337:0-0" 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) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/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) "qtp642875574-44" 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) "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) "IPC Server handler 4 on default port 37747" 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) "IPC Server idle connection scanner for port 42601" 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) "RS_COMPACTED_FILES_DISCHARGER-regionserver/26a9feeac337:0-0" daemon prio=5 tid=757 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.FSNamesystem$LazyPersistFileScrubber@48f951d7" 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) "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) "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) "IPC Server handler 1 on default port 42601" 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) "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) "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) "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) "qtp642875574-41-acceptor-0@37ffddf-ServerConnector@83f158{HTTP/1.1, (http/1.1)}{localhost:44281}" 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) "org.apache.hadoop.hdfs.server.blockmanagement.PendingReconstructionBlocks$PendingReconstructionMonitor@54ef6f29" 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) "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) "ReadOnlyZKClient-127.0.0.1:64264@0x3c605cf9" 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$760/0x00007ff47cb6e298.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-8" daemon prio=5 tid=164 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp642875574-37" daemon prio=5 tid=37 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$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$257/0x00007ff47c4273d0.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) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeResourceMonitor@63a94202" 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) "master/26a9feeac337:0: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) "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) "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) "IPC Server handler 2 on default port 37747" 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) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=45141" 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) "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) "master/26a9feeac337:0:becomeActiveMaster-HFileCleaner.large.0-1734207696740" daemon prio=5 tid=263 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) "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) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=45141" 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) "26a9feeac337:45141" 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) "Notification Thread" daemon prio=9 tid=13 runnable java.lang.Thread.State: RUNNABLE "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) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=33199" 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) "org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor@317c4abf" 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) "DataXceiver for client DFSClient_NONMAPREDUCE_258589514_22 at /127.0.0.1:38552 [Receiving block BP-1348547021-172.17.0.3-1734207689317: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) "CacheReplicationMonitor(949164640)" 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) "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) "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) "RS:0;26a9feeac337:33199" 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) "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) "RS_OPEN_META-regionserver/26a9feeac337:0-0" 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) "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) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/dfs/data/data2/current/BP-1348547021-172.17.0.3-1734207689317" 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) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=33199" 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) "Session-HouseKeeper-3a57a7a3-1" 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) "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) "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) "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) "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-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) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=45141" 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) "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.priority.RWQ.Fifo.read.handler=2,queue=1,port=33199" 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) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@1b31c5ba" 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) "LeaseRenewer:jenkins.hfs.0@localhost:42601" 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) "regionserver/26a9feeac337:0.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) "IPC Server handler 4 on default port 42601" 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) "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) "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) "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) "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) "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) "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) "regionserver/26a9feeac337:0.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) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33199" 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) "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) "IPC Server idle connection scanner for port 37747" 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) "RS:0;26a9feeac337:33199-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 Parameter Sending Thread for localhost/127.0.0.1:42601" 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) "qtp932934172-88-acceptor-0@130b12b5-ServerConnector@791f695a{HTTP/1.1, (http/1.1)}{localhost:35949}" 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) "AsyncFSWAL-0-hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05-prefix:26a9feeac337,33199,1734207694050" 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) "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) "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) "org.apache.hadoop.hdfs.server.namenode.LeaseManager$Monitor@3afaea7b" 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) "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) "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) "26a9feeac337:33199Replication 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) "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) "master/26a9feeac337:0: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) "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) "pool-1-thread-2" daemon prio=5 tid=15 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) "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) "qtp642875574-42" 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) "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) "region-location-2" daemon prio=5 tid=750 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.default.FPBQ.Fifo.handler=0,queue=0,port=33199" 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) "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) "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) "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) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=45141" 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) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeEditLogRoller@28e1e0dc" 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) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=45141" 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) "master/26a9feeac337:0.Chore.1" daemon prio=5 tid=258 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) "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) "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) "ProcessThread(sid:0 cport:64264):" 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) "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) "qtp932934172-90" 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) "PacketResponder: BP-1348547021-172.17.0.3-1734207689317: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) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=45141" 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) "snapshot-hfile-cleaner-cache-refresher" daemon prio=5 tid=260 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) "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) "IPC Server handler 3 on default port 37747" 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) "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) "qtp932934172-87" 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$257/0x00007ff47c4273d0.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "process reaper" daemon prio=10 tid=1014 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$TransferStack.transfer(SynchronousQueue.java:401) at java.base@17.0.11/java.util.concurrent.SynchronousQueue.poll(SynchronousQueue.java:903) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1061) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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$ReferenceHandler.run(Reference.java:215) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=33199" daemon prio=5 tid=198 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Server Responder" daemon prio=5 tid=97 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.ipc.Server$Responder.doRunLoop(Server.java:1733) at app//org.apache.hadoop.ipc.Server$Responder.run(Server.java:1716) "regionserver/26a9feeac337:0.logRoller" daemon prio=5 tid=275 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.wal.AbstractWALRoller.run(AbstractWALRoller.java:179) "qtp642875574-40" daemon prio=5 tid=40 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$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$257/0x00007ff47c4273d0.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) "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) "AsyncFSWAL-0-hdfs://localhost:42601/user/jenkins/test-data/1ef25059-72c9-641e-9c6d-c03437354e05/MasterData-prefix:26a9feeac337,45141,1734207693156" 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) "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) "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) "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) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33199" 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) "qtp642875574-38" 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$257/0x00007ff47c4273d0.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "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) "IPC Server handler 3 on default port 42601" 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) "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$481/0x00007ff47c9da0f0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SessionTracker" daemon prio=5 tid=141 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.zookeeper.server.SessionTrackerImpl.run(SessionTrackerImpl.java:163) "qtp932934172-89" daemon prio=5 tid=89 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "IPC Server handler 0 on default port 37747" 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) "PacketResponder: BP-1348547021-172.17.0.3-1734207689317:blk_1073741840_1016, type=LAST_IN_PIPELINE" daemon prio=5 tid=896 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) "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$MarkedDeleteBlockScrubber.run(BlockManager.java:5326) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Session-HouseKeeper-44752a25-1" prio=5 tid=91 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "HBase-Metrics2-1" daemon prio=5 tid=153 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2@2/hbase-server/target/test-data/97e5dee5-74a6-4b83-751e-3a4e810e6568/cluster_3b721da7-9c7a-20db-f41f-cfc7a2115d64/dfs/data/data1)" daemon prio=5 tid=117 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.VolumeScanner.run(VolumeScanner.java:656) "pool-14-thread-1" daemon prio=5 tid=132 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Monitor thread for TaskMonitor" daemon prio=5 tid=209 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.monitoring.TaskMonitor$MonitorRunnable.run(TaskMonitor.java:325) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "DataXceiver for client DFSClient_NONMAPREDUCE_258589514_22 at /127.0.0.1:38548 [Receiving block BP-1348547021-172.17.0.3-1734207689317: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$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Async-Client-Retry-Timer-pool-0" daemon prio=5 tid=319 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/26a9feeac337:0.procedureResultReporter" daemon prio=5 tid=276 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.regionserver.RemoteProcedureResultReporter.run(RemoteProcedureResultReporter.java:75) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33199" daemon prio=5 tid=197 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "Time-limited test-SendThread(127.0.0.1:64264)" daemon prio=5 tid=403 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "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) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=45141" 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) "org.apache.hadoop.hdfs.PeerCache@486b0e43" 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$1.run(PeerCache.java:124) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=33199" daemon prio=5 tid=202 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "java.util.concurrent.ThreadPoolExecutor$Worker@e81097e[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) "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$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "RS_OPEN_PRIORITY_REGION-regionserver/26a9feeac337:0-0" daemon prio=5 tid=312 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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) "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) "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) "IPC Client (1609210180) connection to localhost/127.0.0.1:42601 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) "master/26a9feeac337:0:becomeActiveMaster-HFileCleaner.small.0-1734207696740" 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$2.run(HFileCleaner.java:269) "Time-limited test-SendThread(127.0.0.1:64264)" daemon prio=5 tid=155 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289)