2024-12-04 01:16:23,327 main DEBUG Apache Log4j Core 2.17.2 initializing configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-12-04 01:16:23,342 main DEBUG Took 0.012691 seconds to load 1 plugins from package org.apache.hadoop.hbase.logging 2024-12-04 01:16:23,342 main DEBUG PluginManager 'Core' found 129 plugins 2024-12-04 01:16:23,343 main DEBUG PluginManager 'Level' found 0 plugins 2024-12-04 01:16:23,344 main DEBUG PluginManager 'Lookup' found 16 plugins 2024-12-04 01:16:23,345 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,354 main DEBUG PluginManager 'TypeConverter' found 26 plugins 2024-12-04 01:16:23,371 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.util.MBeans", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,373 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,374 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.logging.TestJul2Slf4j", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,374 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,375 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.zookeeper", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,376 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,377 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSinkAdapter", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,377 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,378 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSystemImpl", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,378 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,379 main DEBUG LoggerConfig$Builder(additivity="false", level="WARN", levelAndRefs="null", name="org.apache.directory", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,379 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,380 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.ipc.FailedServers", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,381 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,381 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsConfig", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,382 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,382 main DEBUG LoggerConfig$Builder(additivity="null", level="INFO", levelAndRefs="null", name="org.apache.hadoop.hbase.ScheduledChore", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,383 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,383 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.regionserver.RSRpcServices", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,384 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,384 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,385 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,385 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,386 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-04 01:16:23,386 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hbase.thirdparty.io.netty.channel", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,387 main DEBUG Building Plugin[name=root, class=org.apache.logging.log4j.core.config.LoggerConfig$RootLogger]. 2024-12-04 01:16:23,389 main DEBUG LoggerConfig$RootLogger$Builder(additivity="null", level="null", levelAndRefs="INFO,Console", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-04 01:16:23,391 main DEBUG Building Plugin[name=loggers, class=org.apache.logging.log4j.core.config.LoggersPlugin]. 2024-12-04 01:16:23,393 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}) 2024-12-04 01:16:23,394 main DEBUG Building Plugin[name=layout, class=org.apache.logging.log4j.core.layout.PatternLayout]. 2024-12-04 01:16:23,395 main DEBUG PatternLayout$Builder(pattern="%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n", PatternSelector=null, Configuration(PropertiesConfig), Replace=null, charset="null", alwaysWriteExceptions="null", disableAnsi="null", noConsoleNoAnsi="null", header="null", footer="null") 2024-12-04 01:16:23,396 main DEBUG PluginManager 'Converter' found 47 plugins 2024-12-04 01:16:23,408 main DEBUG Building Plugin[name=appender, class=org.apache.hadoop.hbase.logging.HBaseTestAppender]. 2024-12-04 01:16:23,411 main DEBUG HBaseTestAppender$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, ={}) 2024-12-04 01:16:23,413 main DEBUG Starting HBaseTestOutputStreamManager SYSTEM_ERR 2024-12-04 01:16:23,413 main DEBUG Building Plugin[name=appenders, class=org.apache.logging.log4j.core.config.AppendersPlugin]. 2024-12-04 01:16:23,414 main DEBUG createAppenders(={Console}) 2024-12-04 01:16:23,415 main DEBUG Configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f initialized 2024-12-04 01:16:23,415 main DEBUG Starting configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-12-04 01:16:23,415 main DEBUG Started configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f OK. 2024-12-04 01:16:23,416 main DEBUG Shutting down OutputStreamManager SYSTEM_OUT.false.false-1 2024-12-04 01:16:23,416 main DEBUG OutputStream closed 2024-12-04 01:16:23,416 main DEBUG Shut down OutputStreamManager SYSTEM_OUT.false.false-1, all resources released: true 2024-12-04 01:16:23,417 main DEBUG Appender DefaultConsole-1 stopped with status true 2024-12-04 01:16:23,417 main DEBUG Stopped org.apache.logging.log4j.core.config.DefaultConfiguration@505fc5a4 OK 2024-12-04 01:16:23,489 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6 2024-12-04 01:16:23,492 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=StatusLogger 2024-12-04 01:16:23,494 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=ContextSelector 2024-12-04 01:16:23,495 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name= 2024-12-04 01:16:23,496 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.directory 2024-12-04 01:16:23,496 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSinkAdapter 2024-12-04 01:16:23,497 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.zookeeper 2024-12-04 01:16:23,497 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.logging.TestJul2Slf4j 2024-12-04 01:16:23,498 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSystemImpl 2024-12-04 01:16:23,498 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.util.MBeans 2024-12-04 01:16:23,498 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase 2024-12-04 01:16:23,499 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop 2024-12-04 01:16:23,499 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ipc.FailedServers 2024-12-04 01:16:23,499 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.regionserver.RSRpcServices 2024-12-04 01:16:23,500 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsConfig 2024-12-04 01:16:23,500 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hbase.thirdparty.io.netty.channel 2024-12-04 01:16:23,500 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ScheduledChore 2024-12-04 01:16:23,501 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Appenders,name=Console 2024-12-04 01:16:23,503 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-04 01:16:23,504 main DEBUG Reconfiguration complete for context[name=1dbd16a6] at URI jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-logging/target/hbase-logging-2.7.0-SNAPSHOT-tests.jar!/log4j2.properties (org.apache.logging.log4j.core.LoggerContext@39de3d36) with optional ClassLoader: null 2024-12-04 01:16:23,504 main DEBUG Shutdown hook enabled. Registering a new one. 2024-12-04 01:16:23,505 main DEBUG LoggerContext[name=1dbd16a6, org.apache.logging.log4j.core.LoggerContext@39de3d36] started OK. 2024-12-04T01:16:23,689 DEBUG [main {}] hbase.HBaseTestingUtility(348): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48 2024-12-04 01:16:23,692 main DEBUG AsyncLogger.ThreadNameStrategy=UNCACHED (user specified null, default is UNCACHED) 2024-12-04 01:16:23,692 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-04T01:16:23,715 INFO [main {}] hbase.HBaseClassTestRule(94): Test class org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi timeout: 26 mins 2024-12-04T01:16:23,735 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} 2024-12-04T01:16:23,737 INFO [Time-limited test {}] hbase.HBaseZKTestingUtility(82): Created new mini-cluster data directory: /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf, deleteOnExit=true 2024-12-04T01:16:23,738 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1140): STARTING DFS 2024-12-04T01:16:23,738 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting test.cache.data to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/test.cache.data in system properties and HBase conf 2024-12-04T01:16:23,739 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.tmp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/hadoop.tmp.dir in system properties and HBase conf 2024-12-04T01:16:23,739 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting hadoop.log.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/hadoop.log.dir in system properties and HBase conf 2024-12-04T01:16:23,740 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.local.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/mapreduce.cluster.local.dir in system properties and HBase conf 2024-12-04T01:16:23,740 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting mapreduce.cluster.temp.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/mapreduce.cluster.temp.dir in system properties and HBase conf 2024-12-04T01:16:23,741 INFO [Time-limited test {}] hbase.HBaseTestingUtility(811): read short circuit is OFF 2024-12-04T01:16:23,821 WARN [Time-limited test {}] util.NativeCodeLoader(60): Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2024-12-04T01:16:23,912 DEBUG [Time-limited test {}] fs.HFileSystem(310): The file system is not a DistributedFileSystem. Skipping on block location reordering 2024-12-04T01:16:23,917 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.node-labels.fs-store.root-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.node-labels.fs-store.root-dir in system properties and HBase conf 2024-12-04T01:16:23,918 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.node-attribute.fs-store.root-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.node-attribute.fs-store.root-dir in system properties and HBase conf 2024-12-04T01:16:23,919 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.log-dirs to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.nodemanager.log-dirs in system properties and HBase conf 2024-12-04T01:16:23,919 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.remote-app-log-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-04T01:16:23,920 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.timeline-service.entity-group-fs-store.active-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.timeline-service.entity-group-fs-store.active-dir in system properties and HBase conf 2024-12-04T01:16:23,921 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.timeline-service.entity-group-fs-store.done-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.timeline-service.entity-group-fs-store.done-dir in system properties and HBase conf 2024-12-04T01:16:23,921 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting yarn.nodemanager.remote-app-log-dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-04T01:16:23,922 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-04T01:16:23,922 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.datanode.shared.file.descriptor.paths to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/dfs.datanode.shared.file.descriptor.paths in system properties and HBase conf 2024-12-04T01:16:23,923 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting nfs.dump.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/nfs.dump.dir in system properties and HBase conf 2024-12-04T01:16:23,923 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting java.io.tmpdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/java.io.tmpdir in system properties and HBase conf 2024-12-04T01:16:23,924 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.journalnode.edits.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-04T01:16:23,924 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting dfs.provided.aliasmap.inmemory.leveldb.dir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/dfs.provided.aliasmap.inmemory.leveldb.dir in system properties and HBase conf 2024-12-04T01:16:23,924 INFO [Time-limited test {}] hbase.HBaseTestingUtility(824): Setting fs.s3a.committer.staging.tmp.path to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/fs.s3a.committer.staging.tmp.path in system properties and HBase conf 2024-12-04T01:16:24,875 WARN [Time-limited test {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-namenode.properties,hadoop-metrics2.properties 2024-12-04T01:16:24,940 INFO [Time-limited test {}] log.Log(170): Logging initialized @2258ms to org.eclipse.jetty.util.log.Slf4jLog 2024-12-04T01:16:25,017 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 2024-12-04T01:16:25,111 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 2024-12-04T01:16:25,134 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-04T01:16:25,134 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-04T01:16:25,136 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 600000ms 2024-12-04T01:16:25,151 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 2024-12-04T01:16:25,156 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@842d13f{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/hadoop.log.dir/,AVAILABLE} 2024-12-04T01:16:25,157 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@201ce359{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-12-04T01:16:25,394 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@2490b214{hdfs,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/java.io.tmpdir/jetty-localhost-33597-hadoop-hdfs-3_4_1-tests_jar-_-any-14549641936923960714/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/hdfs} 2024-12-04T01:16:25,407 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@1f7e2804{HTTP/1.1, (http/1.1)}{localhost:33597} 2024-12-04T01:16:25,407 INFO [Time-limited test {}] server.Server(415): Started @2726ms 2024-12-04T01:16:26,033 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 2024-12-04T01:16:26,041 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 2024-12-04T01:16:26,042 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-04T01:16:26,043 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-04T01:16:26,043 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 600000ms 2024-12-04T01:16:26,043 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@5b9056db{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/hadoop.log.dir/,AVAILABLE} 2024-12-04T01:16:26,044 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@50244d8f{static,/static,jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/static,AVAILABLE} 2024-12-04T01:16:26,139 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@19f1b88e{datanode,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/java.io.tmpdir/jetty-localhost-40595-hadoop-hdfs-3_4_1-tests_jar-_-any-5342314255315230890/webapp/,AVAILABLE}{jar:file:/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/local-repository/org/apache/hadoop/hadoop-hdfs/3.4.1/hadoop-hdfs-3.4.1-tests.jar!/webapps/datanode} 2024-12-04T01:16:26,140 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@2117487{HTTP/1.1, (http/1.1)}{localhost:40595} 2024-12-04T01:16:26,140 INFO [Time-limited test {}] server.Server(415): Started @3459ms 2024-12-04T01:16:26,187 WARN [Time-limited test {}] web.RestCsrfPreventionFilterHandler(75): Got null for restCsrfPreventionFilter - will not do any filtering. 2024-12-04T01:16:26,978 WARN [Thread-73 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/dfs/data/data2/current/BP-304627035-172.17.0.2-1733274984478/current, will proceed with Du for space computation calculation, 2024-12-04T01:16:26,978 WARN [Thread-72 {}] impl.BlockPoolSlice(347): dfsUsed file missing in /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/dfs/data/data1/current/BP-304627035-172.17.0.2-1733274984478/current, will proceed with Du for space computation calculation, 2024-12-04T01:16:27,002 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 2024-12-04T01:16:27,042 DEBUG [Time-limited test {}] hbase.HBaseTestingUtility(703): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48 2024-12-04T01:16:27,046 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x66f1766fd2645bc5 with lease ID 0xd800ea0db1fd38c6: Processing first storage report for DS-6f395c98-e2e9-4ed4-958d-1a21efae397b from datanode DatanodeRegistration(127.0.0.1:41679, datanodeUuid=e501d226-7912-4f10-b99e-60676be64d72, infoPort=42895, infoSecurePort=0, ipcPort=44411, storageInfo=lv=-57;cid=testClusterID;nsid=1504099570;c=1733274984478) 2024-12-04T01:16:27,047 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x66f1766fd2645bc5 with lease ID 0xd800ea0db1fd38c6: from storage DS-6f395c98-e2e9-4ed4-958d-1a21efae397b node DatanodeRegistration(127.0.0.1:41679, datanodeUuid=e501d226-7912-4f10-b99e-60676be64d72, infoPort=42895, infoSecurePort=0, ipcPort=44411, storageInfo=lv=-57;cid=testClusterID;nsid=1504099570;c=1733274984478), blocks: 0, hasStaleStorage: true, processing time: 1 msecs, invalidatedBlocks: 0 2024-12-04T01:16:27,047 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x66f1766fd2645bc5 with lease ID 0xd800ea0db1fd38c6: Processing first storage report for DS-886a7da4-2ca9-415d-b920-51b16834bd00 from datanode DatanodeRegistration(127.0.0.1:41679, datanodeUuid=e501d226-7912-4f10-b99e-60676be64d72, infoPort=42895, infoSecurePort=0, ipcPort=44411, storageInfo=lv=-57;cid=testClusterID;nsid=1504099570;c=1733274984478) 2024-12-04T01:16:27,047 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x66f1766fd2645bc5 with lease ID 0xd800ea0db1fd38c6: from storage DS-886a7da4-2ca9-415d-b920-51b16834bd00 node DatanodeRegistration(127.0.0.1:41679, datanodeUuid=e501d226-7912-4f10-b99e-60676be64d72, infoPort=42895, infoSecurePort=0, ipcPort=44411, storageInfo=lv=-57;cid=testClusterID;nsid=1504099570;c=1733274984478), blocks: 0, hasStaleStorage: false, processing time: 1 msecs, invalidatedBlocks: 0 2024-12-04T01:16:27,124 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(259): Started connectionTimeout=30000, dir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/zookeeper_0, clientPort=53444, secureClientPort=-1, dataDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/zookeeper_0/version-2, dataDirSize=457 dataLogDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/zookeeper_0/version-2, dataLogSize=457 tickTime=2000, maxClientCnxns=300, minSessionTimeout=4000, maxSessionTimeout=40000, clientPortListenBacklog=-1, serverId=0 2024-12-04T01:16:27,156 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(284): Started MiniZooKeeperCluster and ran 'stat' on client port=53444 2024-12-04T01:16:27,170 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$ReorderWALBlocks 2024-12-04T01:16:27,175 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-04T01:16:27,497 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741825_1001 (size=7) 2024-12-04T01:16:27,900 INFO [Time-limited test {}] util.FSUtils(490): Created version file at hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49 with version=8 2024-12-04T01:16:27,901 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1460): Setting hbase.fs.tmp.dir to hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/hbase-staging 2024-12-04T01:16:28,009 DEBUG [Time-limited test {}] channel.MultithreadEventLoopGroup(44): -Dio.netty.eventLoopThreads: 16 2024-12-04T01:16:28,251 INFO [Time-limited test {}] client.ConnectionUtils(129): master/93574c9bec15:0 server-side Connection retries=6 2024-12-04T01:16:28,266 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-04T01:16:28,267 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-04T01:16:28,267 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-04T01:16:28,267 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-04T01:16:28,267 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-04T01:16:28,374 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 2024-12-04T01:16:28,421 INFO [Time-limited test {}] metrics.MetricRegistriesLoader(60): Loaded MetricRegistries class org.apache.hadoop.hbase.metrics.impl.MetricRegistriesImpl 2024-12-04T01:16:28,429 DEBUG [Time-limited test {}] util.ClassSize(228): Using Unsafe to estimate memory layout 2024-12-04T01:16:28,432 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-04T01:16:28,454 DEBUG [Time-limited test {}] channel.DefaultChannelId(84): -Dio.netty.processId: 23386 (auto-detected) 2024-12-04T01:16:28,455 DEBUG [Time-limited test {}] channel.DefaultChannelId(106): -Dio.netty.machineId: 02:42:ac:ff:fe:11:00:02 (auto-detected) 2024-12-04T01:16:28,472 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:43769 2024-12-04T01:16:28,481 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$ReorderWALBlocks 2024-12-04T01:16:28,484 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-04T01:16:28,500 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=master:43769 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:28,684 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:437690x0, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:28,686 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): master:43769-0x1019f330cd30000 connected 2024-12-04T01:16:28,771 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-04T01:16:28,774 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-04T01:16:28,776 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-04T01:16:28,780 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=43769 2024-12-04T01:16:28,780 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=43769 2024-12-04T01:16:28,781 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=43769 2024-12-04T01:16:28,781 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=43769 2024-12-04T01:16:28,782 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=43769 2024-12-04T01:16:28,788 INFO [Time-limited test {}] master.HMaster(488): hbase.rootdir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49, hbase.cluster.distributed=false 2024-12-04T01:16:28,846 INFO [Time-limited test {}] client.ConnectionUtils(129): regionserver/93574c9bec15:0 server-side Connection retries=6 2024-12-04T01:16:28,847 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-04T01:16:28,847 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-04T01:16:28,847 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-04T01:16:28,848 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-04T01:16:28,848 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-04T01:16:28,851 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 2024-12-04T01:16:28,854 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-04T01:16:28,855 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:41969 2024-12-04T01:16:28,858 INFO [Time-limited test {}] hfile.BlockCacheFactory(123): Allocating BlockCache size=880 MB, blockSize=64 KB 2024-12-04T01:16:28,866 DEBUG [Time-limited test {}] mob.MobFileCache(124): MobFileCache enabled with cacheSize=1000, evictPeriods=3600sec, evictRemainRatio=0.5 2024-12-04T01:16:28,868 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$ReorderWALBlocks 2024-12-04T01:16:28,871 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-04T01:16:28,875 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=regionserver:41969 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:28,892 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:419690x0, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:28,892 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:419690x0, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-04T01:16:28,892 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): regionserver:41969-0x1019f330cd30001 connected 2024-12-04T01:16:28,894 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-04T01:16:28,895 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-04T01:16:28,895 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=41969 2024-12-04T01:16:28,896 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=41969 2024-12-04T01:16:28,901 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=41969 2024-12-04T01:16:28,902 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=41969 2024-12-04T01:16:28,906 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=41969 2024-12-04T01:16:28,909 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.HMaster(2445): Adding backup master ZNode /hbase/backup-masters/93574c9bec15,43769,1733274988003 2024-12-04T01:16:28,920 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-04T01:16:28,920 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-04T01:16:28,922 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/backup-masters/93574c9bec15,43769,1733274988003 2024-12-04T01:16:28,924 DEBUG [M:0;93574c9bec15:43769 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:M:0;93574c9bec15:43769 2024-12-04T01:16:28,949 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-04T01:16:28,949 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-04T01:16:28,950 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:28,950 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:28,950 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-04T01:16:28,951 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.ActiveMasterManager(245): Deleting ZNode for /hbase/backup-masters/93574c9bec15,43769,1733274988003 from backup master directory 2024-12-04T01:16:28,951 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-04T01:16:28,961 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/backup-masters/93574c9bec15,43769,1733274988003 2024-12-04T01:16:28,961 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-04T01:16:28,961 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-04T01:16:28,962 WARN [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-04T01:16:28,962 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.ActiveMasterManager(255): Registered as active master=93574c9bec15,43769,1733274988003 2024-12-04T01:16:28,965 INFO [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating data MemStoreChunkPool with chunk size 2 MB, max count 396, initial count 0 2024-12-04T01:16:28,966 INFO [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating index MemStoreChunkPool with chunk size 204.80 KB, max count 440, initial count 0 2024-12-04T01:16:29,033 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741826_1002 (size=42) 2024-12-04T01:16:29,437 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] util.FSUtils(639): Created cluster ID file at hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/hbase.id with ID: eebc8d6e-7cd5-45b7-ba9a-bccacb7458ca 2024-12-04T01:16:29,491 INFO [master/93574c9bec15:0:becomeActiveMaster {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-04T01:16:29,594 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:29,594 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:29,615 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741827_1003 (size=196) 2024-12-04T01:16:30,034 INFO [master/93574c9bec15:0: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)'} 2024-12-04T01:16:30,036 INFO [master/93574c9bec15:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(132): Injected flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000 2024-12-04T01:16:30,060 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper(244): No decryptEncryptedDataEncryptionKey method in DFSClient, should be hadoop version with HDFS-12396 java.lang.NoSuchMethodException: org.apache.hadoop.hdfs.DFSClient.decryptEncryptedDataEncryptionKey(org.apache.hadoop.fs.FileEncryptionInfo) at java.lang.Class.getDeclaredMethod(Class.java:2675) ~[?:?] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.createTransparentCryptoHelperWithoutHDFS12396(FanOutOneBlockAsyncDFSOutputSaslHelper.java:183) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.createTransparentCryptoHelper(FanOutOneBlockAsyncDFSOutputSaslHelper.java:242) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.io.asyncfs.FanOutOneBlockAsyncDFSOutputSaslHelper.(FanOutOneBlockAsyncDFSOutputSaslHelper.java:253) ~[hbase-asyncfs-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.wal.AsyncFSWALProvider.load(AsyncFSWALProvider.java:147) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.getProviderClass(WALFactory.java:160) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.getProvider(WALFactory.java:200) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.(WALFactory.java:232) ~[classes/:?] at org.apache.hadoop.hbase.wal.WALFactory.(WALFactory.java:207) ~[classes/:?] at org.apache.hadoop.hbase.master.region.MasterRegion.create(MasterRegion.java:402) ~[classes/:?] at org.apache.hadoop.hbase.master.region.MasterRegionFactory.create(MasterRegionFactory.java:135) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.finishActiveMasterInitialization(HMaster.java:973) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.startActiveMasterManager(HMaster.java:2470) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.lambda$run$0(HMaster.java:590) ~[classes/:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:187) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:177) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.HMaster.lambda$run$1(HMaster.java:587) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] 2024-12-04T01:16:30,066 INFO [master/93574c9bec15:0:becomeActiveMaster {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-04T01:16:30,103 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741828_1004 (size=1189) 2024-12-04T01:16:30,530 INFO [master/93574c9bec15:0: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:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store 2024-12-04T01:16:30,555 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741829_1005 (size=34) 2024-12-04T01:16:30,998 INFO [master/93574c9bec15:0: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. 2024-12-04T01:16:30,999 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-04T01:16:31,000 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1681): Closing 1595e783b53d99cd5eef43b6debb2682, disabling compactions & flushes 2024-12-04T01:16:31,000 INFO [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1703): Closing region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-04T01:16:31,000 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1724): Waiting without time limit for close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-04T01:16:31,000 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1791): Acquired close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. after waiting 0 ms 2024-12-04T01:16:31,000 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1801): Updates disabled for region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-04T01:16:31,000 INFO [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1922): Closed master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-04T01:16:31,000 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1635): Region close journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-04T01:16:31,003 WARN [master/93574c9bec15:0:becomeActiveMaster {}] region.MasterRegion(249): failed to clean up initializing flag: hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/.initializing 2024-12-04T01:16:31,003 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] region.MasterRegion(219): WALDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003 2024-12-04T01:16:31,012 INFO [master/93574c9bec15:0:becomeActiveMaster {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-04T01:16:31,033 INFO [master/93574c9bec15:0:becomeActiveMaster {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=93574c9bec15%2C43769%2C1733274988003, suffix=, logDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003, archiveDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/oldWALs, maxLogs=10 2024-12-04T01:16:31,064 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003/93574c9bec15%2C43769%2C1733274988003.1733274991041, exclude list is [], retry=0 2024-12-04T01:16:31,082 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[127.0.0.1:41679,DS-6f395c98-e2e9-4ed4-958d-1a21efae397b,DISK] 2024-12-04T01:16:31,085 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.ProtobufDecoder(117): Hadoop 3.3 and above shades protobuf. 2024-12-04T01:16:31,125 INFO [master/93574c9bec15:0:becomeActiveMaster {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003/93574c9bec15%2C43769%2C1733274988003.1733274991041 2024-12-04T01:16:31,126 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:42895:42895)] 2024-12-04T01:16:31,127 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(7285): Opening region: {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''} 2024-12-04T01:16:31,128 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-04T01:16:31,132 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(7327): checking encryption for 1595e783b53d99cd5eef43b6debb2682 2024-12-04T01:16:31,134 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(7330): checking classloading for 1595e783b53d99cd5eef43b6debb2682 2024-12-04T01:16:31,174 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 2024-12-04T01:16:31,207 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 2024-12-04T01:16:31,212 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:31,215 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 2024-12-04T01:16:31,216 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 2024-12-04T01:16:31,220 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 2024-12-04T01:16:31,220 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:31,222 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/proc, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-04T01:16:31,222 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 2024-12-04T01:16:31,227 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 2024-12-04T01:16:31,227 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:31,229 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/rs, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-04T01:16:31,230 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 2024-12-04T01:16:31,234 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 2024-12-04T01:16:31,235 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:31,236 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/state, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-04T01:16:31,241 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-04T01:16:31,243 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-04T01:16:31,255 DEBUG [master/93574c9bec15:0: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. 2024-12-04T01:16:31,260 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1085): writing seq id for 1595e783b53d99cd5eef43b6debb2682 2024-12-04T01:16:31,265 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-04T01:16:31,267 INFO [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1102): Opened 1595e783b53d99cd5eef43b6debb2682; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=60508519, jitterRate=-0.09835280478000641}}}, FlushLargeStoresPolicy{flushSizeLowerBound=33554432} 2024-12-04T01:16:31,270 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] regionserver.HRegion(1001): Region open journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-04T01:16:31,271 INFO [master/93574c9bec15:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(122): Constructor flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000, compactMin=4 2024-12-04T01:16:31,298 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@7166b76, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:31,330 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.HMaster(882): No meta location available on zookeeper, skip migrating... 2024-12-04T01:16:31,342 INFO [master/93574c9bec15:0:becomeActiveMaster {}] region.RegionProcedureStore(104): Starting the Region Procedure Store, number threads=5 2024-12-04T01:16:31,342 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(633): Starting 5 core workers (bigger of cpus/4 or 16) with max (burst) worker count=50 2024-12-04T01:16:31,344 INFO [master/93574c9bec15:0:becomeActiveMaster {}] region.RegionProcedureStore(255): Starting Region Procedure Store lease recovery... 2024-12-04T01:16:31,346 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(653): Recovered RegionProcedureStore lease in 1 msec 2024-12-04T01:16:31,352 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(667): Loaded RegionProcedureStore in 5 msec 2024-12-04T01:16:31,352 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.RemoteProcedureDispatcher(96): Instantiated, coreThreads=3 (allowCoreThreadTimeOut=true), queueMaxSize=32, operationDelay=150 2024-12-04T01:16:31,382 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.RegionServerTracker(127): Upgrading RegionServerTracker to active master mode; 0 have existingServerCrashProcedures, 0 possibly 'live' servers, and 0 'splitting'. 2024-12-04T01:16:31,399 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Unable to get data of znode /hbase/balancer because node does not exist (not necessarily an error) 2024-12-04T01:16:31,407 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/balancer already deleted, retry=false 2024-12-04T01:16:31,410 INFO [master/93574c9bec15:0:becomeActiveMaster {}] normalizer.SimpleRegionNormalizer(163): Updated configuration for key 'hbase.normalizer.merge.min_region_size.mb' from 0 to 1 2024-12-04T01:16:31,411 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Unable to get data of znode /hbase/normalizer because node does not exist (not necessarily an error) 2024-12-04T01:16:31,419 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/normalizer already deleted, retry=false 2024-12-04T01:16:31,421 INFO [master/93574c9bec15:0:becomeActiveMaster {}] normalizer.RegionNormalizerWorker(137): Normalizer rate limit set to unlimited 2024-12-04T01:16:31,425 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Unable to get data of znode /hbase/switch/split because node does not exist (not necessarily an error) 2024-12-04T01:16:31,432 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/split already deleted, retry=false 2024-12-04T01:16:31,434 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Unable to get data of znode /hbase/switch/merge because node does not exist (not necessarily an error) 2024-12-04T01:16:31,441 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/merge already deleted, retry=false 2024-12-04T01:16:31,451 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Unable to get data of znode /hbase/snapshot-cleanup because node does not exist (not necessarily an error) 2024-12-04T01:16:31,461 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/snapshot-cleanup already deleted, retry=false 2024-12-04T01:16:31,474 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-04T01:16:31,474 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-04T01:16:31,474 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:31,474 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:31,475 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.HMaster(826): Active/primary master=93574c9bec15,43769,1733274988003, sessionid=0x1019f330cd30000, setting cluster-up flag (Was=false) 2024-12-04T01:16:31,499 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:31,499 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:31,524 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/flush-table-proc/acquired, /hbase/flush-table-proc/reached, /hbase/flush-table-proc/abort 2024-12-04T01:16:31,527 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=93574c9bec15,43769,1733274988003 2024-12-04T01:16:31,544 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:31,544 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:31,570 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/online-snapshot/acquired, /hbase/online-snapshot/reached, /hbase/online-snapshot/abort 2024-12-04T01:16:31,571 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=93574c9bec15,43769,1733274988003 2024-12-04T01:16:31,621 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:RS:0;93574c9bec15:41969 2024-12-04T01:16:31,622 INFO [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(1008): ClusterId : eebc8d6e-7cd5-45b7-ba9a-bccacb7458ca 2024-12-04T01:16:31,625 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(43): Procedure flush-table-proc initializing 2024-12-04T01:16:31,638 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(45): Procedure flush-table-proc initialized 2024-12-04T01:16:31,638 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(43): Procedure online-snapshot initializing 2024-12-04T01:16:31,650 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(45): Procedure online-snapshot initialized 2024-12-04T01:16:31,651 DEBUG [RS:0;93574c9bec15:41969 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@2edc0086, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:31,652 DEBUG [RS:0;93574c9bec15:41969 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@dcbd531, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=93574c9bec15/172.17.0.2:0 2024-12-04T01:16:31,655 INFO [RS:0;93574c9bec15:41969 {}] regionserver.RegionServerCoprocessorHost(67): System coprocessor loading is enabled 2024-12-04T01:16:31,655 INFO [RS:0;93574c9bec15:41969 {}] regionserver.RegionServerCoprocessorHost(68): Table coprocessor loading is enabled 2024-12-04T01:16:31,655 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(1090): About to register with Master. 2024-12-04T01:16:31,657 INFO [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(3073): reportForDuty to master=93574c9bec15,43769,1733274988003 with isa=93574c9bec15/172.17.0.2:41969, startcode=1733274988845 2024-12-04T01:16:31,666 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT; InitMetaProcedure table=hbase:meta 2024-12-04T01:16:31,672 INFO [master/93574c9bec15:0:becomeActiveMaster {}] balancer.BaseLoadBalancer(575): slop=0.2 2024-12-04T01:16:31,673 DEBUG [RS:0;93574c9bec15:41969 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-04T01:16:31,676 INFO [master/93574c9bec15:0: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. 2024-12-04T01:16:31,683 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] balancer.RegionLocationFinder(146): Skipping locality-based refresh due to oldStatus=null, newStatus=Master: 93574c9bec15,43769,1733274988003 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 2024-12-04T01:16:31,687 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_OPEN_REGION-master/93574c9bec15:0, corePoolSize=5, maxPoolSize=5 2024-12-04T01:16:31,687 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_CLOSE_REGION-master/93574c9bec15:0, corePoolSize=5, maxPoolSize=5 2024-12-04T01:16:31,687 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SERVER_OPERATIONS-master/93574c9bec15:0, corePoolSize=5, maxPoolSize=5 2024-12-04T01:16:31,687 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_META_SERVER_OPERATIONS-master/93574c9bec15:0, corePoolSize=5, maxPoolSize=5 2024-12-04T01:16:31,688 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=M_LOG_REPLAY_OPS-master/93574c9bec15:0, corePoolSize=10, maxPoolSize=10 2024-12-04T01:16:31,688 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SNAPSHOT_OPERATIONS-master/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,688 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_MERGE_OPERATIONS-master/93574c9bec15:0, corePoolSize=2, maxPoolSize=2 2024-12-04T01:16:31,688 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_TABLE_OPERATIONS-master/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,691 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.procedure2.CompletedProcedureCleaner; timeout=30000, timestamp=1733275021691 2024-12-04T01:16:31,693 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.DirScanPool(74): log_cleaner Cleaner pool size is 1 2024-12-04T01:16:31,693 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT, locked=true; InitMetaProcedure table=hbase:meta 2024-12-04T01:16:31,694 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(75): BOOTSTRAP: creating hbase:meta region 2024-12-04T01:16:31,694 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveLogCleaner 2024-12-04T01:16:31,698 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.replication.master.ReplicationLogCleaner 2024-12-04T01:16:31,698 DEBUG [PEWorker-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:31,698 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)'} 2024-12-04T01:16:31,699 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreWALCleaner 2024-12-04T01:16:31,700 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveProcedureWALCleaner 2024-12-04T01:16:31,701 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.LogCleaner(148): Creating 1 old WALs cleaner threads 2024-12-04T01:16:31,701 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=LogsCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,703 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.DirScanPool(74): hfile_cleaner Cleaner pool size is 2 2024-12-04T01:16:31,704 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreHFileCleaner 2024-12-04T01:16:31,705 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.HFileLinkCleaner 2024-12-04T01:16:31,707 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.snapshot.SnapshotHFileCleaner 2024-12-04T01:16:31,707 INFO [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveHFileCleaner 2024-12-04T01:16:31,708 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741831_1007 (size=1039) 2024-12-04T01:16:31,709 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.HFileCleaner(260): Starting for large file=Thread[master/93574c9bec15:0:becomeActiveMaster-HFileCleaner.large.0-1733274991708,5,FailOnTimeoutGroup] 2024-12-04T01:16:31,709 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] cleaner.HFileCleaner(275): Starting for small files=Thread[master/93574c9bec15:0:becomeActiveMaster-HFileCleaner.small.0-1733274991709,5,FailOnTimeoutGroup] 2024-12-04T01:16:31,709 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HFileCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,710 INFO [master/93574c9bec15:0: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. 2024-12-04T01:16:31,711 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=ReplicationBarrierCleaner, period=43200000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,711 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=SnapshotCleaner, period=1800000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,712 INFO [RS-EventLoopGroup-1-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:45689, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-04T01:16:31,717 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=43769 {}] master.ServerManager(332): Checking decommissioned status of RegionServer 93574c9bec15,41969,1733274988845 2024-12-04T01:16:31,719 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=43769 {}] master.ServerManager(486): Registering regionserver=93574c9bec15,41969,1733274988845 2024-12-04T01:16:31,732 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(1725): Config from master: hbase.rootdir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49 2024-12-04T01:16:31,732 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(1725): Config from master: fs.defaultFS=hdfs://localhost:36667 2024-12-04T01:16:31,732 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(1725): Config from master: hbase.master.info.port=-1 2024-12-04T01:16:31,744 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/rs 2024-12-04T01:16:31,745 DEBUG [RS:0;93574c9bec15:41969 {}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/rs/93574c9bec15,41969,1733274988845 2024-12-04T01:16:31,745 WARN [RS:0;93574c9bec15:41969 {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-04T01:16:31,745 INFO [RS:0;93574c9bec15:41969 {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-04T01:16:31,746 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(2100): logDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845 2024-12-04T01:16:31,747 INFO [RegionServerTracker-0 {}] master.RegionServerTracker(179): RegionServer ephemeral node created, adding [93574c9bec15,41969,1733274988845] 2024-12-04T01:16:31,758 DEBUG [RS:0;93574c9bec15:41969 {}] regionserver.Replication(140): Replication stats-in-log period=300 seconds 2024-12-04T01:16:31,770 INFO [RS:0;93574c9bec15:41969 {}] regionserver.MetricsRegionServerWrapperImpl(120): Computing regionserver metrics every 5000 milliseconds 2024-12-04T01:16:31,782 INFO [RS:0;93574c9bec15:41969 {}] regionserver.MemStoreFlusher(130): globalMemStoreLimit=880 M, globalMemStoreLimitLowMark=836 M, Offheap=false 2024-12-04T01:16:31,785 INFO [RS:0;93574c9bec15:41969 {}] 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 2024-12-04T01:16:31,786 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionThroughputTuner, period=60000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,786 INFO [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer$CompactionChecker(1988): CompactionChecker runs every PT1S 2024-12-04T01:16:31,793 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactedHFilesCleaner, period=120000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,793 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_REGION-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,793 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_META-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,793 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,793 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_REGION-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_META-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_LOG_REPLAY_OPS-regionserver/93574c9bec15:0, corePoolSize=2, maxPoolSize=2 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_COMPACTED_FILES_DISCHARGER-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_REGION_REPLICA_FLUSH_OPS-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_REFRESH_PEER-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_SWITCH_RPC_THROTTLE-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,794 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_CLAIM_REPLICATION_QUEUE-regionserver/93574c9bec15:0, corePoolSize=1, maxPoolSize=1 2024-12-04T01:16:31,795 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_SNAPSHOT_OPERATIONS-regionserver/93574c9bec15:0, corePoolSize=3, maxPoolSize=3 2024-12-04T01:16:31,795 DEBUG [RS:0;93574c9bec15:41969 {}] executor.ExecutorService(95): Starting executor service name=RS_FLUSH_OPERATIONS-regionserver/93574c9bec15:0, corePoolSize=3, maxPoolSize=3 2024-12-04T01:16:31,795 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionChecker, period=1000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,796 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=MemstoreFlusherChore, period=1000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,796 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=nonceCleaner, period=360000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,796 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=BrokenStoreFileCleaner, period=21600000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,796 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,41969,1733274988845-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-04T01:16:31,812 INFO [RS:0;93574c9bec15:41969 {}] regionserver.HeapMemoryManager(209): Starting, tuneOn=false 2024-12-04T01:16:31,813 INFO [RS:0;93574c9bec15:41969 {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,41969,1733274988845-HeapMemoryTunerChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:31,834 INFO [RS:0;93574c9bec15:41969 {}] regionserver.Replication(204): 93574c9bec15,41969,1733274988845 started 2024-12-04T01:16:31,834 INFO [RS:0;93574c9bec15:41969 {}] regionserver.HRegionServer(1767): Serving as 93574c9bec15,41969,1733274988845, RpcServer on 93574c9bec15/172.17.0.2:41969, sessionid=0x1019f330cd30001 2024-12-04T01:16:31,835 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(51): Procedure flush-table-proc starting 2024-12-04T01:16:31,835 DEBUG [RS:0;93574c9bec15:41969 {}] flush.RegionServerFlushTableProcedureManager(108): Start region server flush procedure manager 93574c9bec15,41969,1733274988845 2024-12-04T01:16:31,835 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '93574c9bec15,41969,1733274988845' 2024-12-04T01:16:31,836 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/flush-table-proc/abort' 2024-12-04T01:16:31,836 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/flush-table-proc/acquired' 2024-12-04T01:16:31,837 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(53): Procedure flush-table-proc started 2024-12-04T01:16:31,837 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(51): Procedure online-snapshot starting 2024-12-04T01:16:31,837 DEBUG [RS:0;93574c9bec15:41969 {}] snapshot.RegionServerSnapshotManager(126): Start Snapshot Manager 93574c9bec15,41969,1733274988845 2024-12-04T01:16:31,837 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '93574c9bec15,41969,1733274988845' 2024-12-04T01:16:31,838 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/online-snapshot/abort' 2024-12-04T01:16:31,838 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/online-snapshot/acquired' 2024-12-04T01:16:31,839 DEBUG [RS:0;93574c9bec15:41969 {}] procedure.RegionServerProcedureManagerHost(53): Procedure online-snapshot started 2024-12-04T01:16:31,839 INFO [RS:0;93574c9bec15:41969 {}] quotas.RegionServerRpcQuotaManager(64): Quota support disabled 2024-12-04T01:16:31,839 INFO [RS:0;93574c9bec15:41969 {}] quotas.RegionServerSpaceQuotaManager(80): Quota support disabled, not starting space quota manager. 2024-12-04T01:16:31,944 INFO [RS:0;93574c9bec15:41969 {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-04T01:16:31,948 INFO [RS:0;93574c9bec15:41969 {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=93574c9bec15%2C41969%2C1733274988845, suffix=, logDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845, archiveDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/oldWALs, maxLogs=32 2024-12-04T01:16:31,961 DEBUG [RS:0;93574c9bec15:41969 {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.1733274991949, exclude list is [], retry=0 2024-12-04T01:16:31,966 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[127.0.0.1:41679,DS-6f395c98-e2e9-4ed4-958d-1a21efae397b,DISK] 2024-12-04T01:16:31,970 INFO [RS:0;93574c9bec15:41969 {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:31,971 DEBUG [RS:0;93574c9bec15:41969 {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:42895:42895)] 2024-12-04T01:16:32,111 INFO [PEWorker-1 {}] util.FSTableDescriptors(140): Updated hbase:meta table descriptor to hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/.tabledesc/.tableinfo.0000000001.1039 2024-12-04T01:16:32,111 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:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49 2024-12-04T01:16:32,122 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741833_1009 (size=32) 2024-12-04T01:16:32,525 DEBUG [PEWorker-1 {}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-04T01:16:32,528 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 2024-12-04T01:16:32,531 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 2024-12-04T01:16:32,532 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:32,533 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 2024-12-04T01:16:32,533 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 2024-12-04T01:16:32,536 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 2024-12-04T01:16:32,536 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:32,538 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 2024-12-04T01:16:32,538 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 2024-12-04T01:16:32,541 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 2024-12-04T01:16:32,541 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:32,542 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 2024-12-04T01:16:32,544 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740 2024-12-04T01:16:32,545 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740 2024-12-04T01:16:32,548 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. 2024-12-04T01:16:32,550 DEBUG [PEWorker-1 {}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-04T01:16:32,553 DEBUG [PEWorker-1 {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-04T01:16:32,554 INFO [PEWorker-1 {}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=60901413, jitterRate=-0.09249822795391083}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-04T01:16:32,556 DEBUG [PEWorker-1 {}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-04T01:16:32,556 DEBUG [PEWorker-1 {}] regionserver.HRegion(1681): Closing 1588230740, disabling compactions & flushes 2024-12-04T01:16:32,556 INFO [PEWorker-1 {}] regionserver.HRegion(1703): Closing region hbase:meta,,1.1588230740 2024-12-04T01:16:32,557 DEBUG [PEWorker-1 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:meta,,1.1588230740 2024-12-04T01:16:32,557 DEBUG [PEWorker-1 {}] regionserver.HRegion(1791): Acquired close lock on hbase:meta,,1.1588230740 after waiting 0 ms 2024-12-04T01:16:32,557 DEBUG [PEWorker-1 {}] regionserver.HRegion(1801): Updates disabled for region hbase:meta,,1.1588230740 2024-12-04T01:16:32,558 INFO [PEWorker-1 {}] regionserver.HRegion(1922): Closed hbase:meta,,1.1588230740 2024-12-04T01:16:32,558 DEBUG [PEWorker-1 {}] regionserver.HRegion(1635): Region close journal for 1588230740: 2024-12-04T01:16:32,560 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_ASSIGN_META, locked=true; InitMetaProcedure table=hbase:meta 2024-12-04T01:16:32,560 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(107): Going to assign meta 2024-12-04T01:16:32,564 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}] 2024-12-04T01:16:32,571 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 2024-12-04T01:16:32,573 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 2024-12-04T01:16:32,725 DEBUG [93574c9bec15:43769 {}] assignment.AssignmentManager(2444): Processing assignQueue; systemServersCount=1, allServersCount=1 2024-12-04T01:16:32,732 INFO [PEWorker-3 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPENING, regionLocation=93574c9bec15,41969,1733274988845 2024-12-04T01:16:32,739 INFO [PEWorker-3 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 93574c9bec15,41969,1733274988845, state=OPENING 2024-12-04T01:16:32,783 DEBUG [PEWorker-3 {}] zookeeper.MetaTableLocator(183): hbase:meta region location doesn't exist, create it 2024-12-04T01:16:32,791 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:32,791 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:32,793 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-04T01:16:32,793 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-04T01:16:32,797 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=3, ppid=2, state=RUNNABLE; OpenRegionProcedure 1588230740, server=93574c9bec15,41969,1733274988845}] 2024-12-04T01:16:32,974 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:32,976 DEBUG [RSProcedureDispatcher-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=AdminService, sasl=false 2024-12-04T01:16:32,979 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:55510, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=AdminService 2024-12-04T01:16:32,988 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(135): Open hbase:meta,,1.1588230740 2024-12-04T01:16:32,988 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-04T01:16:32,989 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] monitor.StreamSlowMonitor(122): New stream slow monitor .meta 2024-12-04T01:16:32,992 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=93574c9bec15%2C41969%2C1733274988845.meta, suffix=.meta, logDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845, archiveDir=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/oldWALs, maxLogs=32 2024-12-04T01:16:33,009 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.meta.1733274992994.meta, exclude list is [], retry=0 2024-12-04T01:16:33,013 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[127.0.0.1:41679,DS-6f395c98-e2e9-4ed4-958d-1a21efae397b,DISK] 2024-12-04T01:16:33,016 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.meta.1733274992994.meta 2024-12-04T01:16:33,016 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:42895:42895)] 2024-12-04T01:16:33,017 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7285): Opening region: {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''} 2024-12-04T01:16:33,019 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:33,079 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7999): Registered coprocessor service: region=hbase:meta,,1 service=MultiRowMutationService 2024-12-04T01:16:33,083 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {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. 2024-12-04T01:16:33,086 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table meta 1588230740 2024-12-04T01:16:33,087 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:33,087 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7327): checking encryption for 1588230740 2024-12-04T01:16:33,087 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7330): checking classloading for 1588230740 2024-12-04T01:16:33,090 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 2024-12-04T01:16:33,091 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 2024-12-04T01:16:33,091 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:33,092 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 2024-12-04T01:16:33,093 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 2024-12-04T01:16:33,094 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 2024-12-04T01:16:33,094 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:33,095 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 2024-12-04T01:16:33,096 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 2024-12-04T01:16:33,097 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 2024-12-04T01:16:33,097 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:33,098 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 2024-12-04T01:16:33,099 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740 2024-12-04T01:16:33,102 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740 2024-12-04T01:16:33,104 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {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. 2024-12-04T01:16:33,107 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-04T01:16:33,108 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=71864176, jitterRate=0.07085967063903809}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-04T01:16:33,110 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-04T01:16:33,116 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:meta,,1.1588230740, pid=3, masterSystemTime=1733274992970 2024-12-04T01:16:33,126 DEBUG [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:meta,,1.1588230740 2024-12-04T01:16:33,127 INFO [RS_OPEN_META-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(164): Opened hbase:meta,,1.1588230740 2024-12-04T01:16:33,127 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPEN, openSeqNum=2, regionLocation=93574c9bec15,41969,1733274988845 2024-12-04T01:16:33,129 INFO [PEWorker-5 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 93574c9bec15,41969,1733274988845, state=OPEN 2024-12-04T01:16:33,159 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-04T01:16:33,159 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-04T01:16:33,159 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-04T01:16:33,159 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-04T01:16:33,165 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=3, resume processing ppid=2 2024-12-04T01:16:33,165 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=3, ppid=2, state=SUCCESS; OpenRegionProcedure 1588230740, server=93574c9bec15,41969,1733274988845 in 362 msec 2024-12-04T01:16:33,174 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=2, resume processing ppid=1 2024-12-04T01:16:33,174 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=2, ppid=1, state=SUCCESS; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN in 602 msec 2024-12-04T01:16:33,179 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=1, state=SUCCESS; InitMetaProcedure table=hbase:meta in 1.5620 sec 2024-12-04T01:16:33,179 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.HMaster(1088): Wait for region servers to report in: status=status unset, state=RUNNING, startTime=1733274993179, completionTime=-1 2024-12-04T01:16:33,179 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.ServerManager(907): Finished waiting on RegionServer count=1; waited=0ms, expected min=1 server(s), max=1 server(s), master is running 2024-12-04T01:16:33,179 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] assignment.AssignmentManager(1747): Joining cluster... 2024-12-04T01:16:33,213 DEBUG [hconnection-0x71b91111-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:16:33,215 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:55526, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:16:33,225 INFO [master/93574c9bec15:0:becomeActiveMaster {}] assignment.AssignmentManager(1759): Number of RegionServers=1 2024-12-04T01:16:33,225 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$RegionInTransitionChore; timeout=60000, timestamp=1733275053225 2024-12-04T01:16:33,225 INFO [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$DeadServerMetricRegionChore; timeout=120000, timestamp=1733275113225 2024-12-04T01:16:33,225 INFO [master/93574c9bec15:0:becomeActiveMaster {}] assignment.AssignmentManager(1766): Joined the cluster in 45 msec 2024-12-04T01:16:33,264 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,43769,1733274988003-ClusterStatusChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:33,264 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,43769,1733274988003-BalancerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:33,264 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,43769,1733274988003-RegionNormalizerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:33,266 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=CatalogJanitor-93574c9bec15:43769, period=300000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:33,267 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HbckChore-, period=3600000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:33,273 DEBUG [master/93574c9bec15:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-04T01:16:33,275 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.TableNamespaceManager(92): Namespace table not found. Creating... 2024-12-04T01:16:33,277 INFO [master/93574c9bec15:0: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)'} 2024-12-04T01:16:33,282 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION; CreateTableProcedure table=hbase:namespace 2024-12-04T01:16:33,285 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 2024-12-04T01:16:33,286 DEBUG [PEWorker-3 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:33,288 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 2024-12-04T01:16:33,299 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741835_1011 (size=358) 2024-12-04T01:16:33,709 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(7106): creating {ENCODED => be568d21e6f4779021608a7d7c9d641c, NAME => 'hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c.', 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:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49 2024-12-04T01:16:33,718 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741836_1012 (size=42) 2024-12-04T01:16:34,120 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(894): Instantiated hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-04T01:16:34,120 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1681): Closing be568d21e6f4779021608a7d7c9d641c, disabling compactions & flushes 2024-12-04T01:16:34,120 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1703): Closing region hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,120 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,120 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1791): Acquired close lock on hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. after waiting 0 ms 2024-12-04T01:16:34,121 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1801): Updates disabled for region hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,121 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1922): Closed hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,121 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1635): Region close journal for be568d21e6f4779021608a7d7c9d641c: 2024-12-04T01:16:34,123 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 2024-12-04T01:16:34,130 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":2,"row":"hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c.","families":{"info":[{"qualifier":"regioninfo","vlen":41,"tag":[],"timestamp":"1733274994124"},{"qualifier":"state","vlen":6,"tag":[],"timestamp":"1733274994124"}]},"ts":"1733274994124"} 2024-12-04T01:16:34,149 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1516): Added 1 regions to meta. 2024-12-04T01:16:34,150 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 2024-12-04T01:16:34,153 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1733274994151"}]},"ts":"1733274994151"} 2024-12-04T01:16:34,157 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLING in hbase:meta 2024-12-04T01:16:34,210 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=be568d21e6f4779021608a7d7c9d641c, ASSIGN}] 2024-12-04T01:16:34,213 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=be568d21e6f4779021608a7d7c9d641c, ASSIGN 2024-12-04T01:16:34,215 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=be568d21e6f4779021608a7d7c9d641c, ASSIGN; state=OFFLINE, location=93574c9bec15,41969,1733274988845; forceNewPlan=false, retain=false 2024-12-04T01:16:34,366 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=be568d21e6f4779021608a7d7c9d641c, regionState=OPENING, regionLocation=93574c9bec15,41969,1733274988845 2024-12-04T01:16:34,370 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=6, ppid=5, state=RUNNABLE; OpenRegionProcedure be568d21e6f4779021608a7d7c9d641c, server=93574c9bec15,41969,1733274988845}] 2024-12-04T01:16:34,525 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:34,531 INFO [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(135): Open hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,531 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7285): Opening region: {ENCODED => be568d21e6f4779021608a7d7c9d641c, NAME => 'hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c.', STARTKEY => '', ENDKEY => ''} 2024-12-04T01:16:34,531 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table namespace be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,531 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(894): Instantiated hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-04T01:16:34,532 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7327): checking encryption for be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,532 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7330): checking classloading for be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,534 INFO [StoreOpener-be568d21e6f4779021608a7d7c9d641c-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 be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,536 INFO [StoreOpener-be568d21e6f4779021608a7d7c9d641c-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 be568d21e6f4779021608a7d7c9d641c columnFamilyName info 2024-12-04T01:16:34,536 DEBUG [StoreOpener-be568d21e6f4779021608a7d7c9d641c-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-04T01:16:34,537 INFO [StoreOpener-be568d21e6f4779021608a7d7c9d641c-1 {}] regionserver.HStore(327): Store=be568d21e6f4779021608a7d7c9d641c/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-04T01:16:34,539 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,540 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,544 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1085): writing seq id for be568d21e6f4779021608a7d7c9d641c 2024-12-04T01:16:34,547 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-04T01:16:34,548 INFO [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1102): Opened be568d21e6f4779021608a7d7c9d641c; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=73316628, jitterRate=0.0925028920173645}}}, FlushLargeStoresPolicy{flushSizeLowerBound=-1} 2024-12-04T01:16:34,549 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1001): Region open journal for be568d21e6f4779021608a7d7c9d641c: 2024-12-04T01:16:34,552 INFO [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c., pid=6, masterSystemTime=1733274994525 2024-12-04T01:16:34,555 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,555 INFO [RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(164): Opened hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. 2024-12-04T01:16:34,556 INFO [PEWorker-2 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=be568d21e6f4779021608a7d7c9d641c, regionState=OPEN, openSeqNum=2, regionLocation=93574c9bec15,41969,1733274988845 2024-12-04T01:16:34,563 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=6, resume processing ppid=5 2024-12-04T01:16:34,563 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=6, ppid=5, state=SUCCESS; OpenRegionProcedure be568d21e6f4779021608a7d7c9d641c, server=93574c9bec15,41969,1733274988845 in 189 msec 2024-12-04T01:16:34,566 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=5, resume processing ppid=4 2024-12-04T01:16:34,567 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=5, ppid=4, state=SUCCESS; TransitRegionStateProcedure table=hbase:namespace, region=be568d21e6f4779021608a7d7c9d641c, ASSIGN in 353 msec 2024-12-04T01:16:34,568 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 2024-12-04T01:16:34,568 DEBUG [PEWorker-4 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1733274994568"}]},"ts":"1733274994568"} 2024-12-04T01:16:34,570 INFO [PEWorker-4 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLED in hbase:meta 2024-12-04T01:16:34,580 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 2024-12-04T01:16:34,583 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=4, state=SUCCESS; CreateTableProcedure table=hbase:namespace in 1.3030 sec 2024-12-04T01:16:34,586 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKUtil(113): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/namespace 2024-12-04T01:16:34,594 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/namespace 2024-12-04T01:16:34,594 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:34,595 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:34,620 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=7, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=default 2024-12-04T01:16:34,644 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-04T01:16:34,659 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=7, state=SUCCESS; CreateNamespaceProcedure, namespace=default in 39 msec 2024-12-04T01:16:34,665 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=8, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=hbase 2024-12-04T01:16:34,682 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-04T01:16:34,695 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=8, state=SUCCESS; CreateNamespaceProcedure, namespace=hbase in 29 msec 2024-12-04T01:16:34,716 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/default 2024-12-04T01:16:34,732 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/hbase 2024-12-04T01:16:34,733 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.HMaster(1218): Master has completed initialization 5.770sec 2024-12-04T01:16:34,734 INFO [master/93574c9bec15:0:becomeActiveMaster {}] quotas.MasterQuotaManager(97): Quota support disabled 2024-12-04T01:16:34,735 INFO [master/93574c9bec15:0:becomeActiveMaster {}] slowlog.SlowLogMasterService(57): Slow/Large requests logging to system table hbase:slowlog is disabled. Quitting. 2024-12-04T01:16:34,736 INFO [master/93574c9bec15:0:becomeActiveMaster {}] waleventtracker.WALEventTrackerTableCreator(75): wal event tracker requests logging to table REPLICATION.WALEVENTTRACKER is disabled. Quitting. 2024-12-04T01:16:34,736 INFO [master/93574c9bec15:0:becomeActiveMaster {}] master.ReplicationSinkTrackerTableCreator(90): replication sink tracker requests logging to table REPLICATION.SINK_TRACKER is disabled. Quitting. 2024-12-04T01:16:34,737 INFO [master/93574c9bec15:0:becomeActiveMaster {}] zookeeper.ZKWatcher(271): not a secure deployment, proceeding 2024-12-04T01:16:34,737 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,43769,1733274988003-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-04T01:16:34,738 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,43769,1733274988003-MobFileCompactionChore, period=604800, unit=SECONDS is enabled. 2024-12-04T01:16:34,743 DEBUG [master/93574c9bec15:0:becomeActiveMaster {}] master.HMaster(1321): Balancer post startup initialization complete, took 0 seconds 2024-12-04T01:16:34,744 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=RollingUpgradeChore, period=10, unit=SECONDS is enabled. 2024-12-04T01:16:34,744 INFO [master/93574c9bec15:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=93574c9bec15,43769,1733274988003-OldWALsDirSizeChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-04T01:16:34,834 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x53d9c032 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7c2a5090 2024-12-04T01:16:34,835 WARN [Time-limited test {}] client.ZKConnectionRegistry(90): ZKConnectionRegistry is deprecated. See https://hbase.apache.org/book.html#client.rpcconnectionregistry 2024-12-04T01:16:34,846 DEBUG [Time-limited test {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@47ab1946, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:34,849 DEBUG [Time-limited test {}] nio.NioEventLoop(110): -Dio.netty.noKeySetOptimization: false 2024-12-04T01:16:34,849 DEBUG [Time-limited test {}] nio.NioEventLoop(111): -Dio.netty.selectorAutoRebuildThreshold: 512 2024-12-04T01:16:34,858 DEBUG [hconnection-0x485c112f-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:16:34,865 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:55532, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:16:34,873 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1199): Minicluster is up; activeMaster=93574c9bec15,43769,1733274988003 2024-12-04T01:16:34,874 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x502fe4e9 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@74e5f234 2024-12-04T01:16:34,884 DEBUG [ReadOnlyZKClient-127.0.0.1:53444@0x502fe4e9 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@6fc7906f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:34,900 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=222, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=270, ProcessCount=11, AvailableMemoryMB=9564 2024-12-04T01:16:34,961 DEBUG [Time-limited test {}] client.ConnectionUtils(573): Start fetching master stub from registry 2024-12-04T01:16:34,962 DEBUG [ReadOnlyZKClient-127.0.0.1:53444@0x502fe4e9 {}] client.AsyncConnectionImpl(310): The fetched master address is 93574c9bec15,43769,1733274988003 2024-12-04T01:16:34,965 DEBUG [ReadOnlyZKClient-127.0.0.1:53444@0x502fe4e9 {}] client.ConnectionUtils(581): The fetched master stub is org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$Stub@4fd994e2 2024-12-04T01:16:34,966 DEBUG [ReadOnlyZKClient-127.0.0.1:53444@0x502fe4e9 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=MasterService, sasl=false 2024-12-04T01:16:34,975 INFO [RS-EventLoopGroup-1-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:52622, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=MasterService 2024-12-04T01:16:34,976 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:34,982 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=9, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:34,987 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-04T01:16:34,998 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:34,999 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:35,007 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:35,008 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30004 connected 2024-12-04T01:16:35,100 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-04T01:16:35,117 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30004, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:35,144 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:35,144 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-04T01:16:35,169 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=10, ppid=9, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:35,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-04T01:16:35,338 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:35,341 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=10 2024-12-04T01:16:35,342 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:16:35,357 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=10}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:35,378 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:35,439 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=10 2024-12-04T01:16:35,444 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=10 2024-12-04T01:16:35,447 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:35,451 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=10, resume processing ppid=9 2024-12-04T01:16:35,451 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=10, ppid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 278 msec 2024-12-04T01:16:35,451 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:35,455 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 473 msec 2024-12-04T01:16:35,475 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x76ddb2b4 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@715dc734 2024-12-04T01:16:35,487 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:35,488 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:35,488 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5e63f1a9, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:35,491 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:35,503 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:35,504 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30006 connected 2024-12-04T01:16:35,504 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:35,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-04T01:16:35,621 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:35,624 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:35,630 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=11, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:35,633 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-04T01:16:35,647 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:35,648 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:35,657 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:35,658 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30007 connected 2024-12-04T01:16:35,739 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-04T01:16:35,766 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30007, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:35,779 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=12, ppid=11, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:35,934 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:35,936 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=12 2024-12-04T01:16:35,937 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:35,941 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:35,941 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:35,941 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:35,942 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30006, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:35,943 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30006, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:35,950 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-04T01:16:36,053 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30006, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:36,053 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x76ddb2b4 to 127.0.0.1:53444 2024-12-04T01:16:36,054 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:36,073 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:36,073 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:36,074 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=12 2024-12-04T01:16:36,074 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=12 2024-12-04T01:16:36,077 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:36,083 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=12, resume processing ppid=11 2024-12-04T01:16:36,083 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:36,084 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=12, ppid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 298 msec 2024-12-04T01:16:36,087 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 459 msec 2024-12-04T01:16:36,111 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x47cfd110 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@784f3fac 2024-12-04T01:16:36,125 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:36,125 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:36,126 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@493ab354, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:36,128 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:36,136 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:36,137 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:36,139 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30009 connected 2024-12-04T01:16:36,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-04T01:16:36,260 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:36,264 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,265 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,267 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,270 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-04T01:16:36,272 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=13, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:36,274 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-04T01:16:36,288 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:36,289 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:36,299 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:36,300 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3000a connected 2024-12-04T01:16:36,380 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-04T01:16:36,407 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3000a, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:36,442 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=14, ppid=13, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:36,590 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-04T01:16:36,597 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:36,598 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=14 2024-12-04T01:16:36,598 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:36,600 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:36,600 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:36,600 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:36,600 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30009, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:36,601 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30009, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:36,711 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30009, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:36,711 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x47cfd110 to 127.0.0.1:53444 2024-12-04T01:16:36,712 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:36,724 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:36,725 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:36,725 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=14 2024-12-04T01:16:36,726 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=14 2024-12-04T01:16:36,728 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:36,731 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=14, resume processing ppid=13 2024-12-04T01:16:36,731 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=14, ppid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-04T01:16:36,731 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-04T01:16:36,734 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 461 msec 2024-12-04T01:16:36,751 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x16569ddb to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@54e12007 2024-12-04T01:16:36,762 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:36,762 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:36,762 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2059787f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:36,765 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:36,774 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:36,774 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:36,775 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3000c connected 2024-12-04T01:16:36,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-04T01:16:36,900 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:36,901 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,903 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,904 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,906 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:36,907 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-04T01:16:36,909 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=15, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:36,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-04T01:16:36,928 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:36,929 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:36,941 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:36,942 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3000d connected 2024-12-04T01:16:37,019 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-04T01:16:37,049 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3000d, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:37,063 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=16, ppid=15, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:37,218 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:37,219 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=16 2024-12-04T01:16:37,219 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:37,221 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:37,221 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:37,221 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:37,221 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3000c, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:37,222 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3000c, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:37,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-04T01:16:37,333 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3000c, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:37,333 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x16569ddb to 127.0.0.1:53444 2024-12-04T01:16:37,333 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:37,353 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:37,353 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:37,353 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=16 2024-12-04T01:16:37,354 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=16 2024-12-04T01:16:37,356 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:37,360 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=16, resume processing ppid=15 2024-12-04T01:16:37,360 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-04T01:16:37,360 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=16, ppid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 293 msec 2024-12-04T01:16:37,362 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 453 msec 2024-12-04T01:16:37,379 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7eb934da to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6b3d3ece 2024-12-04T01:16:37,391 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:37,392 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:37,392 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@70b59cde, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:37,393 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:37,403 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:37,403 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:37,403 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3000f connected 2024-12-04T01:16:37,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-04T01:16:37,540 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:37,541 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:37,543 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:37,545 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:37,547 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:37,549 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=17, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:37,551 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-04T01:16:37,562 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:37,563 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:37,574 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:37,574 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30010 connected 2024-12-04T01:16:37,659 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-04T01:16:37,682 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30010, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:37,696 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=18, ppid=17, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:37,764 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:meta' 2024-12-04T01:16:37,766 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:namespace' 2024-12-04T01:16:37,848 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:37,849 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=18 2024-12-04T01:16:37,849 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:37,851 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:37,851 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:37,852 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:37,852 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3000f, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:37,852 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3000f, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:37,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-04T01:16:37,961 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3000f, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:37,961 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7eb934da to 127.0.0.1:53444 2024-12-04T01:16:37,962 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:37,977 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:37,977 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:37,977 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=18 2024-12-04T01:16:37,978 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=18 2024-12-04T01:16:37,980 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:37,984 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=18, resume processing ppid=17 2024-12-04T01:16:37,984 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:37,984 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=18, ppid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-04T01:16:37,986 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 437 msec 2024-12-04T01:16:38,005 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x17ab34b6 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@797cdc69 2024-12-04T01:16:38,016 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:38,017 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:38,017 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@165e2abf, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:38,018 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:38,028 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:38,028 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30012 connected 2024-12-04T01:16:38,028 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:38,180 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-04T01:16:38,181 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:38,182 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:38,183 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:38,185 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-04T01:16:38,188 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=19, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:38,189 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-04T01:16:38,203 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:38,203 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:38,211 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:38,212 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30013 connected 2024-12-04T01:16:38,300 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-04T01:16:38,320 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30013, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:38,335 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=20, ppid=19, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:38,489 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:38,490 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=20 2024-12-04T01:16:38,490 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:38,493 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:38,493 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:38,493 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:38,493 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30012, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:38,494 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30012, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:38,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-04T01:16:38,597 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:16:38,603 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30012, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:38,603 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x17ab34b6 to 127.0.0.1:53444 2024-12-04T01:16:38,603 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:38,625 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:38,625 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:38,626 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=20 2024-12-04T01:16:38,626 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=20 2024-12-04T01:16:38,630 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:38,636 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=20, resume processing ppid=19 2024-12-04T01:16:38,636 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=20, ppid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 296 msec 2024-12-04T01:16:38,636 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-04T01:16:38,640 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 451 msec 2024-12-04T01:16:38,663 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_meta 2024-12-04T01:16:38,663 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_meta Metrics about Tables on a single HBase RegionServer 2024-12-04T01:16:38,666 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_namespace 2024-12-04T01:16:38,667 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_namespace Metrics about Tables on a single HBase RegionServer 2024-12-04T01:16:38,668 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint 2024-12-04T01:16:38,668 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint Metrics about HBase RegionObservers 2024-12-04T01:16:38,669 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_master_table_store 2024-12-04T01:16:38,669 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_master_table_store Metrics about Tables on a single HBase RegionServer 2024-12-04T01:16:38,680 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1e22f564 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@9224ca9 2024-12-04T01:16:38,691 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:38,692 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:38,692 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6702e662, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:38,694 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:38,703 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:38,703 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:38,704 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30015 connected 2024-12-04T01:16:38,819 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-04T01:16:38,820 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:38,820 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:38,821 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:38,822 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=21, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:38,823 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-04T01:16:38,842 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:38,843 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:38,853 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:38,854 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30016 connected 2024-12-04T01:16:38,929 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-04T01:16:38,961 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30016, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:38,975 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=22, ppid=21, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:39,128 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:39,129 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=22 2024-12-04T01:16:39,129 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:39,131 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:39,131 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:39,131 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:39,132 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30015, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:39,132 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30015, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:39,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-04T01:16:39,241 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30015, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:39,241 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1e22f564 to 127.0.0.1:53444 2024-12-04T01:16:39,241 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:39,260 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:39,260 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:39,261 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=22 2024-12-04T01:16:39,262 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=22 2024-12-04T01:16:39,265 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:39,269 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=22, resume processing ppid=21 2024-12-04T01:16:39,269 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:39,269 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=22, ppid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-04T01:16:39,271 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 448 msec 2024-12-04T01:16:39,293 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3699cd67 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3d8b90d7 2024-12-04T01:16:39,303 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:39,304 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:39,304 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@32fd86ef, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:39,305 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:39,316 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:39,316 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:39,316 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30018 connected 2024-12-04T01:16:39,449 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-04T01:16:39,450 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:39,450 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:39,455 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:39,455 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:39,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:39,461 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=24, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:39,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-04T01:16:39,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-04T01:16:39,468 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:39,478 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:39,478 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:39,478 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:39,480 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=25, ppid=23, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:39,569 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-04T01:16:39,570 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-04T01:16:39,634 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:39,635 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=25 2024-12-04T01:16:39,635 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:16:39,635 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:16:39,635 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:16:39,635 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:39,636 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30018, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:39,636 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30018, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:39,745 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30018, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:39,745 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3699cd67 to 127.0.0.1:53444 2024-12-04T01:16:39,745 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:39,746 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:16:39,754 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:39,766 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:39,766 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:39,766 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:39,768 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:39,768 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=25 2024-12-04T01:16:39,770 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=25 2024-12-04T01:16:39,775 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:39,777 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=25, resume processing ppid=23 2024-12-04T01:16:39,777 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=25, ppid=23, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 295 msec 2024-12-04T01:16:39,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-04T01:16:39,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-04T01:16:39,787 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:39,787 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:16:39,789 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=23, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 332 msec 2024-12-04T01:16:39,790 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:39,797 ERROR [PEWorker-5 {}] 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:39,799 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=24, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=342 msec 2024-12-04T01:16:39,799 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:40,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-04T01:16:40,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-04T01:16:40,090 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:40,091 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:40,092 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:40,095 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=26, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:40,096 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-04T01:16:40,096 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:40,101 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=26, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:40,103 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=26, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=9 msec 2024-12-04T01:16:40,103 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:40,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-04T01:16:40,209 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:40,211 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=testing utility connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:40,257 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): testing utility0x0, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:40,258 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): testing utility-0x1019f330cd30019 connected 2024-12-04T01:16:40,281 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=223 (was 222) 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$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RSProcedureDispatcher-pool-2 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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: ForkJoinPool.commonPool-worker-1 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkUntil(LockSupport.java:410) java.base@17.0.11/java.util.concurrent.ForkJoinPool.awaitWork(ForkJoinPool.java:1726) java.base@17.0.11/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1623) java.base@17.0.11/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:165) Potentially hanging thread: RS-EventLoopGroup-1-3 app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) - Thread LEAK? -, OpenFileDescriptor=452 (was 448) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=248 (was 270), ProcessCount=11 (was 11), AvailableMemoryMB=9438 (was 9564) 2024-12-04T01:16:40,289 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223, OpenFileDescriptor=452, MaxFileDescriptor=1048576, SystemLoadAverage=248, ProcessCount=11, AvailableMemoryMB=9438 2024-12-04T01:16:40,290 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:40,291 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=27, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:40,292 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-04T01:16:40,305 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:40,305 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:40,315 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:40,316 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3001a connected 2024-12-04T01:16:40,400 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-04T01:16:40,424 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3001a, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:40,451 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=28, ppid=27, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:40,604 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:40,605 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=28 2024-12-04T01:16:40,605 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:16:40,609 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-04T01:16:40,622 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=28}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:40,634 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:40,699 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=28 2024-12-04T01:16:40,700 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=28 2024-12-04T01:16:40,702 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:40,705 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=28, resume processing ppid=27 2024-12-04T01:16:40,705 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:40,705 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=28, ppid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 251 msec 2024-12-04T01:16:40,708 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 415 msec 2024-12-04T01:16:40,739 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x777f35ab to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@24382163 2024-12-04T01:16:40,750 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:40,750 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:40,751 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3993ba99, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:40,752 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:40,761 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:40,762 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:40,762 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3001c connected 2024-12-04T01:16:40,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-04T01:16:40,920 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:40,920 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:40,922 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=29, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:40,923 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-04T01:16:40,936 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:40,936 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:40,944 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:40,945 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3001d connected 2024-12-04T01:16:41,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-04T01:16:41,053 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3001d, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:41,068 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=30, ppid=29, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:41,222 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:41,223 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=30 2024-12-04T01:16:41,223 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:41,225 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:41,225 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:41,225 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:41,225 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3001c, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:41,225 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3001c, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:41,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-04T01:16:41,434 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3001c, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:41,434 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x777f35ab to 127.0.0.1:53444 2024-12-04T01:16:41,434 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:41,455 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:41,455 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:41,455 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=30 2024-12-04T01:16:41,456 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=30 2024-12-04T01:16:41,459 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:41,463 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=30, resume processing ppid=29 2024-12-04T01:16:41,463 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:41,463 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=30, ppid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 392 msec 2024-12-04T01:16:41,466 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 543 msec 2024-12-04T01:16:41,491 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0b0e0c53 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@26ca9a3a 2024-12-04T01:16:41,508 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:41,508 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:41,508 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1aca1af3, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:41,509 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:41,519 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:41,520 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:41,520 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3001f connected 2024-12-04T01:16:41,550 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-04T01:16:41,550 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:41,551 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:41,552 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-04T01:16:41,553 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=31, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:41,554 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-04T01:16:41,570 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:41,571 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:41,582 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:41,583 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30020 connected 2024-12-04T01:16:41,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-04T01:16:41,691 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30020, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:41,705 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=32, ppid=31, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:41,860 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:41,861 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=32 2024-12-04T01:16:41,861 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:41,863 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:41,863 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:41,864 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:41,864 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3001f, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:41,864 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3001f, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:41,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-04T01:16:41,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3001f, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:41,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0b0e0c53 to 127.0.0.1:53444 2024-12-04T01:16:41,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:41,990 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:41,991 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:41,991 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=32 2024-12-04T01:16:41,992 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=32 2024-12-04T01:16:41,995 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:41,998 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=32, resume processing ppid=31 2024-12-04T01:16:41,998 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-04T01:16:41,999 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=32, ppid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-04T01:16:42,001 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 447 msec 2024-12-04T01:16:42,028 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0f21ace1 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5c2894c2 2024-12-04T01:16:42,037 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:42,037 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:42,037 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4f3f18b1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:42,038 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:42,049 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:42,049 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:42,049 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30022 connected 2024-12-04T01:16:42,180 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-04T01:16:42,182 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:42,183 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:42,186 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns1:testNamespacesAndTableCfsConfigConflict1=null},bandwidth=0,serial=false 2024-12-04T01:16:42,187 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=33, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:42,189 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-04T01:16:42,203 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:42,204 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:42,211 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:42,211 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30023 connected 2024-12-04T01:16:42,299 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-04T01:16:42,319 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30023, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:42,320 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:42,322 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=33, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:42,324 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=33, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns1:testNamespacesAndTableCfsConfigConflict1 is conflict with namespaces ns1 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure exec-time=136 msec 2024-12-04T01:16:42,324 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. 2024-12-04T01:16:42,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-04T01:16:42,510 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 2024-12-04T01:16:42,511 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:42,512 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-04T01:16:42,514 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=34, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:42,515 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-04T01:16:42,531 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:42,532 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:42,540 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:42,541 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30024 connected 2024-12-04T01:16:42,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-04T01:16:42,649 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30024, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:42,663 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=35, ppid=34, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:42,816 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:42,817 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=35 2024-12-04T01:16:42,817 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:42,820 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:42,820 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:42,820 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:42,821 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30022, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:42,821 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30022, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:42,830 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-04T01:16:42,932 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30022, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:42,932 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0f21ace1 to 127.0.0.1:53444 2024-12-04T01:16:42,933 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:42,946 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:42,946 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:42,946 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=35 2024-12-04T01:16:42,947 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=35 2024-12-04T01:16:42,949 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:42,952 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=35, resume processing ppid=34 2024-12-04T01:16:42,952 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-04T01:16:42,952 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=35, ppid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-04T01:16:42,954 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 440 msec 2024-12-04T01:16:42,971 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7c4b3a58 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@e53b919 2024-12-04T01:16:42,982 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:42,983 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:42,983 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@18dc11d5, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:42,984 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:42,994 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:42,995 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:42,995 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30026 connected 2024-12-04T01:16:43,139 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-04T01:16:43,139 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:43,140 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:43,142 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-04T01:16:43,145 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=36, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:43,146 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-04T01:16:43,164 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:43,164 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:43,174 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:43,174 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30027 connected 2024-12-04T01:16:43,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-04T01:16:43,282 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30027, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:43,283 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:43,287 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=36, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkNamespacesAndTableCfsConfigConflict(ReplicationPeerManager.java:369) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:331) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preUpdatePeerConfig(ReplicationPeerManager.java:161) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure.prePeerModification(UpdatePeerConfigProcedure.java:176) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:43,291 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=36, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-update_config-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Table-cfs ns2:testNamespacesAndTableCfsConfigConflict2 is conflict with namespaces ns2 in peer config; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure exec-time=145 msec 2024-12-04T01:16:43,291 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. 2024-12-04T01:16:43,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-04T01:16:43,462 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 2024-12-04T01:16:43,464 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:43,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=37, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:43,467 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-04T01:16:43,470 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:43,478 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:43,478 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:43,478 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:43,479 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=38, ppid=37, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:43,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-04T01:16:43,631 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:43,632 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=38 2024-12-04T01:16:43,632 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:16:43,632 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:16:43,633 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:16:43,633 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:43,633 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30026, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:43,633 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30026, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:43,741 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30026, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:43,741 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7c4b3a58 to 127.0.0.1:53444 2024-12-04T01:16:43,741 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:43,741 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:16:43,749 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:43,761 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:43,761 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:43,762 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:43,762 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:43,763 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=38 2024-12-04T01:16:43,764 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=38 2024-12-04T01:16:43,768 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:43,772 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=38, resume processing ppid=37 2024-12-04T01:16:43,772 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=38, ppid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-04T01:16:43,783 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:43,783 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:16:43,786 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 319 msec 2024-12-04T01:16:43,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-04T01:16:43,790 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:43,790 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:43,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=39, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:43,792 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-04T01:16:43,792 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:43,793 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=39, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:43,794 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=39, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-04T01:16:43,794 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:43,900 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-04T01:16:43,902 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:43,903 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:43,906 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=40, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:43,908 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-04T01:16:43,909 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:43,911 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=40, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:43,912 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=40, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=8 msec 2024-12-04T01:16:43,912 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:44,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-04T01:16:44,021 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:44,036 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223 (was 223), OpenFileDescriptor=450 (was 452), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=236 (was 248), ProcessCount=11 (was 11), AvailableMemoryMB=9465 (was 9438) - AvailableMemoryMB LEAK? - 2024-12-04T01:16:44,046 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=236, ProcessCount=11, AvailableMemoryMB=9464 2024-12-04T01:16:44,047 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:44,049 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=41, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:44,050 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-04T01:16:44,065 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:44,066 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:44,074 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:44,074 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30028 connected 2024-12-04T01:16:44,160 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-04T01:16:44,182 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30028, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:44,210 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=42, ppid=41, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:44,365 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:44,367 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=42 2024-12-04T01:16:44,367 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:16:44,369 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-04T01:16:44,386 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=42}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:44,396 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:44,441 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=42 2024-12-04T01:16:44,441 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=42 2024-12-04T01:16:44,443 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:44,446 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=42, resume processing ppid=41 2024-12-04T01:16:44,446 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=42, ppid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 233 msec 2024-12-04T01:16:44,446 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:44,448 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 399 msec 2024-12-04T01:16:44,466 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3a0d7153 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@20bf0692 2024-12-04T01:16:44,478 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:44,479 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:44,479 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5e488b1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:44,480 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:44,491 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:44,491 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:44,491 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3002a connected 2024-12-04T01:16:44,680 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-04T01:16:44,680 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:44,681 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:44,682 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=43, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:44,683 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-04T01:16:44,696 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:44,697 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:44,730 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:44,730 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3002b connected 2024-12-04T01:16:44,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-04T01:16:44,845 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3002b, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:44,845 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 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:44,847 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=43, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:44,849 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=43, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=167 msec 2024-12-04T01:16:44,850 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:44,999 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-04T01:16:45,000 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Replication peer 1 already exists 2024-12-04T01:16:45,004 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:45,006 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:45,007 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=44, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:45,008 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-04T01:16:45,008 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:45,009 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=44, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:45,011 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=44, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:16:45,011 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:45,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-04T01:16:45,121 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:45,121 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:45,123 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=127.0.0.1:53444:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:45,124 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=45, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:45,125 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-04T01:16:45,140 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:45,141 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:45,191 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:45,191 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3002c connected 2024-12-04T01:16:45,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-04T01:16:45,248 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:16:45,299 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3002c, quorum=127.0.0.1:53444, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:45,321 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=46, ppid=45, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:45,439 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-04T01:16:45,474 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:45,475 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=46 2024-12-04T01:16:45,475 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=ADD_PEER 2024-12-04T01:16:45,492 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 2000 millis 2024-12-04T01:16:45,496 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=46}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:45,507 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.ReplicationSource(229): queueId=2, ReplicationSource: 2, currentBandwidth=0 2024-12-04T01:16:45,532 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=46 2024-12-04T01:16:45,533 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=46 2024-12-04T01:16:45,536 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:45,540 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=46, resume processing ppid=45 2024-12-04T01:16:45,540 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 2, config clusterKey=127.0.0.1:53444:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:45,540 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=46, ppid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 215 msec 2024-12-04T01:16:45,543 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 417 msec 2024-12-04T01:16:45,566 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7e7a4ce1 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2d8f9ee 2024-12-04T01:16:45,578 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test2/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test2/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:45,579 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:45,579 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4620bb62, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:45,581 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 2 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:45,590 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 20x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:45,591 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] regionserver.ReplicationSource(569): peerId=2, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:45,591 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 2-0x1019f330cd3002e connected 2024-12-04T01:16:45,749 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-04T01:16:45,750 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 2 completed 2024-12-04T01:16:45,751 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:45,753 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:45,756 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=47, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:45,757 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-04T01:16:45,760 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:45,769 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:45,769 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:45,769 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:45,770 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=48, ppid=47, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:45,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-04T01:16:45,923 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:45,924 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=48 2024-12-04T01:16:45,924 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:16:45,924 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:16:45,924 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:16:45,925 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:45,925 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3002a, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:45,925 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3002a, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:46,036 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3002a, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:46,036 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3a0d7153 to 127.0.0.1:53444 2024-12-04T01:16:46,037 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:46,037 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:16:46,045 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:46,057 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:46,057 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:46,057 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:46,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:46,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=48 2024-12-04T01:16:46,059 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=48 2024-12-04T01:16:46,063 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:46,069 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=48, resume processing ppid=47 2024-12-04T01:16:46,069 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=48, ppid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 293 msec 2024-12-04T01:16:46,079 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-04T01:16:46,086 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:46,086 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:16:46,088 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 333 msec 2024-12-04T01:16:46,390 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-04T01:16:46,390 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:46,391 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:46,394 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:46,397 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=49, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:46,398 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-04T01:16:46,401 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/2/peer-state 2024-12-04T01:16:46,415 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2/peer-state 2024-12-04T01:16:46,415 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-04T01:16:46,415 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-04T01:16:46,416 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=50, ppid=49, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:46,510 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-04T01:16:46,570 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:46,571 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=50 2024-12-04T01:16:46,572 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=REMOVE_PEER 2024-12-04T01:16:46,572 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 2: 0 2024-12-04T01:16:46,572 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSource(657): peerId=2, Closing source 2 because: Replication stream was removed by a user 2024-12-04T01:16:46,573 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] regionserver.ReplicationSource(508): peerId=2, Interrupted while sleeping between retries 2024-12-04T01:16:46,573 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] zookeeper.ZKUtil(165): connection to cluster: 2-0x1019f330cd3002e, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:46,574 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2 {}] zookeeper.ZKWatcher(734): connection to cluster: 2-0x1019f330cd3002e, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:46,683 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 2-0x1019f330cd3002e, quorum=127.0.0.1:53444, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:46,683 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7e7a4ce1 to 127.0.0.1:53444 2024-12-04T01:16:46,683 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:46,684 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(430): Done with the queue 2 2024-12-04T01:16:46,693 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/2/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:46,707 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/2/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:46,707 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/2 2024-12-04T01:16:46,707 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/2 2024-12-04T01:16:46,707 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-04T01:16:46,707 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=50 2024-12-04T01:16:46,708 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=50 2024-12-04T01:16:46,710 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:46,714 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=50, resume processing ppid=49 2024-12-04T01:16:46,714 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=50, ppid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 295 msec 2024-12-04T01:16:46,719 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-04T01:16:46,725 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-04T01:16:46,725 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 2 2024-12-04T01:16:46,727 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 331 msec 2024-12-04T01:16:47,029 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-04T01:16:47,030 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 2 completed 2024-12-04T01:16:47,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:47,031 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:47,032 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=51, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:47,033 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-04T01:16:47,033 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:47,034 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=51, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,036 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=51, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:16:47,036 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:47,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-04T01:16:47,142 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:47,143 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:47,146 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=52, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:47,148 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-04T01:16:47,149 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:47,151 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=52, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,152 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=52, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=8 msec 2024-12-04T01:16:47,152 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:47,260 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-04T01:16:47,261 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:47,277 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=221 (was 223), OpenFileDescriptor=444 (was 450), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=241 (was 236) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=9434 (was 9464) 2024-12-04T01:16:47,284 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=241, ProcessCount=11, AvailableMemoryMB=9433 2024-12-04T01:16:47,286 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=whatever,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:47,287 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=53, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:47,288 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-04T01:16:47,288 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:291) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.lang.ClassNotFoundException: whatever at jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641) ~[?:?] at jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188) ~[?:?] at java.lang.ClassLoader.loadClass(ClassLoader.java:525) ~[?:?] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:288) ~[classes/:?] ... 12 more 2024-12-04T01:16:47,290 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=53, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:291) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.lang.ClassNotFoundException: whatever at jdk.internal.loader.BuiltinClassLoader.loadClass(BuiltinClassLoader.java:641) ~[?:?] at jdk.internal.loader.ClassLoaders$AppClassLoader.loadClass(ClassLoaders.java:188) ~[?:?] at java.lang.ClassLoader.loadClass(ClassLoader.java:525) ~[?:?] at java.lang.Class.forName0(Native Method) ~[?:?] at java.lang.Class.forName(Class.java:375) ~[?:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:288) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,292 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=53, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=4 msec 2024-12-04T01:16:47,292 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. 2024-12-04T01:16:47,399 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-04T01:16:47,399 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 2024-12-04T01:16:47,404 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:47,405 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=54, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:47,406 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-04T01:16:47,407 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:47,408 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=54, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,410 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=54, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:16:47,410 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:47,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-04T01:16:47,510 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:47,510 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:47,512 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=55, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:47,513 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-04T01:16:47,513 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:47,515 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=55, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,516 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=55, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-04T01:16:47,516 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:47,619 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-04T01:16:47,620 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:47,631 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=221 (was 221), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=241 (was 241), ProcessCount=11 (was 11), AvailableMemoryMB=9433 (was 9433) 2024-12-04T01:16:47,638 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=241, ProcessCount=11, AvailableMemoryMB=9433 2024-12-04T01:16:47,639 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=whatever,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:47,640 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=56, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:47,641 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-04T01:16:47,641 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.io.IOException: Cluster key passed whatever is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-12-04T01:16:47,642 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=56, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.io.IOException: Cluster key passed whatever is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,643 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=56, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=4 msec 2024-12-04T01:16:47,643 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. 2024-12-04T01:16:47,749 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-04T01:16:47,750 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Invalid cluster key: whatever 2024-12-04T01:16:47,751 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:47,752 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=57, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:47,753 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-04T01:16:47,753 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:47,755 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=57, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,756 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=57, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:16:47,756 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:47,860 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-04T01:16:47,861 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:47,863 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:47,865 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=58, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:47,867 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-04T01:16:47,867 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:47,870 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=58, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:47,872 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=58, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=7 msec 2024-12-04T01:16:47,872 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:47,969 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-04T01:16:47,970 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:47,987 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=221 (was 221), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=241 (was 241), ProcessCount=11 (was 11), AvailableMemoryMB=9440 (was 9433) - AvailableMemoryMB LEAK? - 2024-12-04T01:16:47,995 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=241, ProcessCount=11, AvailableMemoryMB=9440 2024-12-04T01:16:47,996 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:47,997 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=59, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:47,998 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-04T01:16:48,013 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:48,014 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:48,057 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:48,058 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3002f connected 2024-12-04T01:16:48,109 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-04T01:16:48,166 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3002f, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:48,192 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=60, ppid=59, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:48,319 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-04T01:16:48,344 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:48,345 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=60 2024-12-04T01:16:48,346 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:16:48,368 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=60}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:48,378 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:48,420 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=60 2024-12-04T01:16:48,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=60 2024-12-04T01:16:48,422 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:48,426 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=60, resume processing ppid=59 2024-12-04T01:16:48,426 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:48,426 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=60, ppid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 230 msec 2024-12-04T01:16:48,428 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 430 msec 2024-12-04T01:16:48,447 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x58932784 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@35ad3d4d 2024-12-04T01:16:48,457 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:48,458 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:48,458 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4d015b18, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:48,459 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:48,470 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:48,470 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:48,470 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30031 connected 2024-12-04T01:16:48,629 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-04T01:16:48,630 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:48,631 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:48,632 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=61, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:48,633 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-04T01:16:48,650 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:48,650 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:48,661 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:48,661 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30032 connected 2024-12-04T01:16:48,740 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-04T01:16:48,770 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30032, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:48,784 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=62, ppid=61, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:48,938 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:48,940 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=62 2024-12-04T01:16:48,940 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:48,944 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:48,944 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:48,945 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:48,945 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30031, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:48,946 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30031, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:48,949 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-04T01:16:49,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30031, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:49,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x58932784 to 127.0.0.1:53444 2024-12-04T01:16:49,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:49,082 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:49,082 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:49,083 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=62 2024-12-04T01:16:49,083 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=62 2024-12-04T01:16:49,086 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:49,088 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=62, resume processing ppid=61 2024-12-04T01:16:49,088 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:49,088 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=62, ppid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 302 msec 2024-12-04T01:16:49,090 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 457 msec 2024-12-04T01:16:49,109 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0a3ae5fa to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6ac55995 2024-12-04T01:16:49,120 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:49,120 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:49,120 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@c48c3c2, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:49,121 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:49,164 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:49,165 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:49,165 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30034 connected 2024-12-04T01:16:49,260 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-04T01:16:49,261 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:49,262 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:49,265 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-04T01:16:49,268 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=63, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:49,269 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-04T01:16:49,285 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:49,286 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:49,299 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:49,299 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30035 connected 2024-12-04T01:16:49,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-04T01:16:49,407 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30035, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:49,417 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=64, ppid=63, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:49,571 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:49,571 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=64 2024-12-04T01:16:49,571 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:49,573 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:49,573 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:49,573 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:49,573 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30034, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:49,573 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30034, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:49,589 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-04T01:16:49,682 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30034, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:49,682 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0a3ae5fa to 127.0.0.1:53444 2024-12-04T01:16:49,682 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:49,698 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:49,698 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:49,698 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=64 2024-12-04T01:16:49,699 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=64 2024-12-04T01:16:49,701 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:49,703 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=64, resume processing ppid=63 2024-12-04T01:16:49,703 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-04T01:16:49,703 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=64, ppid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-12-04T01:16:49,704 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 438 msec 2024-12-04T01:16:49,721 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5f70d767 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@8b1d966 2024-12-04T01:16:49,732 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:49,733 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:49,733 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@330f2f9e, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:49,734 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:49,744 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:49,745 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:49,745 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30037 connected 2024-12-04T01:16:49,900 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-04T01:16:49,901 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:49,902 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:49,904 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:49,907 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-04T01:16:49,910 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=65, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:49,911 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-04T01:16:49,922 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:49,923 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:49,932 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:49,932 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30038 connected 2024-12-04T01:16:50,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-04T01:16:50,041 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30038, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:50,054 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=66, ppid=65, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:50,206 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:50,207 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=66 2024-12-04T01:16:50,207 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:50,209 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:50,209 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:50,209 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:50,209 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30037, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:50,209 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30037, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:50,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-04T01:16:50,320 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30037, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:50,320 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5f70d767 to 127.0.0.1:53444 2024-12-04T01:16:50,320 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:50,335 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:50,335 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:50,336 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=66 2024-12-04T01:16:50,336 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=66 2024-12-04T01:16:50,338 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:50,340 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=66, resume processing ppid=65 2024-12-04T01:16:50,340 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-04T01:16:50,340 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=66, ppid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-12-04T01:16:50,342 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 433 msec 2024-12-04T01:16:50,363 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1bb03c24 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@58a2d984 2024-12-04T01:16:50,374 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:50,375 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:50,375 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@13e0449b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:50,376 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:50,386 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:50,387 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:50,387 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3003a connected 2024-12-04T01:16:50,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-04T01:16:50,540 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:50,541 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:50,543 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:50,546 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=67, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:50,547 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-04T01:16:50,550 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:50,561 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:50,561 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:50,561 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:50,562 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=68, ppid=67, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:50,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-04T01:16:50,714 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:50,715 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=68 2024-12-04T01:16:50,715 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:16:50,715 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:16:50,715 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:16:50,716 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:50,716 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3003a, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:50,716 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3003a, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:50,824 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3003a, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:50,824 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1bb03c24 to 127.0.0.1:53444 2024-12-04T01:16:50,824 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:50,825 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:16:50,832 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:50,840 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:50,840 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:50,840 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:50,841 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:50,841 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=68 2024-12-04T01:16:50,841 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=68 2024-12-04T01:16:50,843 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:50,845 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=68, resume processing ppid=67 2024-12-04T01:16:50,845 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=68, ppid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-12-04T01:16:50,857 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:50,857 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:16:50,859 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 315 msec 2024-12-04T01:16:50,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-04T01:16:50,870 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:50,870 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:50,871 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=69, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:50,872 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-04T01:16:50,872 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:50,874 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=69, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:50,875 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=69, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:16:50,875 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:50,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-04T01:16:50,982 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:50,983 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:50,986 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=70, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:50,988 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-04T01:16:50,988 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:50,990 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=70, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:50,991 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=70, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=7 msec 2024-12-04T01:16:50,991 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:51,100 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-04T01:16:51,102 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:51,123 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=220 (was 221), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=230 (was 241), ProcessCount=11 (was 11), AvailableMemoryMB=9422 (was 9440) 2024-12-04T01:16:51,132 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=230, ProcessCount=11, AvailableMemoryMB=9422 2024-12-04T01:16:51,133 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:51,135 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=71, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:51,136 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-04T01:16:51,150 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:51,150 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:51,199 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:51,200 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3003b connected 2024-12-04T01:16:51,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-04T01:16:51,307 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3003b, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:51,329 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=72, ppid=71, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:51,449 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-04T01:16:51,482 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:51,483 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=72 2024-12-04T01:16:51,484 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:16:51,505 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=72}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:51,516 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:51,539 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:16:51,565 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=72 2024-12-04T01:16:51,566 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=72 2024-12-04T01:16:51,568 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:51,570 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=72, resume processing ppid=71 2024-12-04T01:16:51,570 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:51,570 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=72, ppid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 239 msec 2024-12-04T01:16:51,571 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 437 msec 2024-12-04T01:16:51,589 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x0b04d94a to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@85c6fb 2024-12-04T01:16:51,599 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:51,600 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:51,600 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@53aaeaad, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:51,601 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:51,611 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:51,612 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:51,612 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3003d connected 2024-12-04T01:16:51,759 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-04T01:16:51,759 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:51,760 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:51,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=73, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:51,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-04T01:16:51,777 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:51,778 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:51,786 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:51,787 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3003e connected 2024-12-04T01:16:51,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-04T01:16:51,895 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3003e, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:51,909 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=74, ppid=73, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:52,063 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:52,065 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=74 2024-12-04T01:16:52,065 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:52,068 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:52,068 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:52,068 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:52,069 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3003d, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:52,069 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3003d, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:52,080 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-04T01:16:52,178 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3003d, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:52,178 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x0b04d94a to 127.0.0.1:53444 2024-12-04T01:16:52,179 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:52,192 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:52,192 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:52,192 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=74 2024-12-04T01:16:52,193 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=74 2024-12-04T01:16:52,195 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:52,196 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=74, resume processing ppid=73 2024-12-04T01:16:52,196 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:16:52,196 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=74, ppid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-04T01:16:52,198 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 436 msec 2024-12-04T01:16:52,217 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x27066395 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@38585956 2024-12-04T01:16:52,228 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:52,229 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:52,229 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@235dfb26, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:52,230 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:52,240 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:52,240 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:52,241 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30040 connected 2024-12-04T01:16:52,389 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-04T01:16:52,390 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:52,391 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:52,393 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-04T01:16:52,395 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=75, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:52,396 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-04T01:16:52,418 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:52,419 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:52,428 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:52,428 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30041 connected 2024-12-04T01:16:52,499 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-04T01:16:52,536 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30041, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:52,549 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=76, ppid=75, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:52,701 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:52,702 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=76 2024-12-04T01:16:52,702 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:52,704 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:52,704 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:52,704 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:52,704 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30040, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:52,705 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30040, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:52,709 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-04T01:16:52,816 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30040, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:52,816 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x27066395 to 127.0.0.1:53444 2024-12-04T01:16:52,816 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:52,836 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:52,836 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:52,837 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=76 2024-12-04T01:16:52,837 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=76 2024-12-04T01:16:52,839 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:52,840 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=76, resume processing ppid=75 2024-12-04T01:16:52,841 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-04T01:16:52,841 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=76, ppid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-04T01:16:52,842 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 448 msec 2024-12-04T01:16:52,862 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3ac8ecff to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3960a1be 2024-12-04T01:16:52,874 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:52,874 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:52,875 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6280bad4, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:52,876 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:52,886 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:52,887 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:52,887 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30043 connected 2024-12-04T01:16:53,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-04T01:16:53,021 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:53,022 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:53,024 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:53,027 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-04T01:16:53,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=77, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:53,031 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-04T01:16:53,047 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:53,047 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:53,076 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:53,076 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30044 connected 2024-12-04T01:16:53,142 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-04T01:16:53,199 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30044, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:53,209 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=78, ppid=77, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:53,350 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-04T01:16:53,362 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:53,362 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=78 2024-12-04T01:16:53,363 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:53,364 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:53,364 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:53,364 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:53,364 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30043, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:53,365 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30043, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:53,474 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30043, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:53,474 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3ac8ecff to 127.0.0.1:53444 2024-12-04T01:16:53,475 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:53,492 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:53,492 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:53,492 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=78 2024-12-04T01:16:53,493 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=78 2024-12-04T01:16:53,494 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:53,496 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=78, resume processing ppid=77 2024-12-04T01:16:53,496 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-04T01:16:53,496 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=78, ppid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-04T01:16:53,497 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 469 msec 2024-12-04T01:16:53,517 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6271ca1e to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4a2a6910 2024-12-04T01:16:53,528 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:53,529 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:53,529 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@47c582e9, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:53,530 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:53,541 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:53,541 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:53,541 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30046 connected 2024-12-04T01:16:53,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-04T01:16:53,661 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:53,662 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:53,666 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:53,669 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-04T01:16:53,670 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=79, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:53,671 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-04T01:16:53,690 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:53,691 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:53,699 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:53,699 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30047 connected 2024-12-04T01:16:53,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-04T01:16:53,807 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30047, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:53,821 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=80, ppid=79, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:53,973 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:53,974 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=80 2024-12-04T01:16:53,975 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:53,978 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:53,978 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:53,978 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:53,979 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30046, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:53,979 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30046, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:53,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-04T01:16:54,091 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30046, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:54,091 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6271ca1e to 127.0.0.1:53444 2024-12-04T01:16:54,091 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:54,108 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:54,108 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:54,108 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=80 2024-12-04T01:16:54,109 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=80 2024-12-04T01:16:54,110 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:54,112 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=80, resume processing ppid=79 2024-12-04T01:16:54,112 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=80, ppid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-04T01:16:54,112 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-04T01:16:54,114 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 443 msec 2024-12-04T01:16:54,132 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x15687f26 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6bfc116e 2024-12-04T01:16:54,141 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:54,141 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:54,141 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7b7a5c70, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:54,142 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:54,153 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:54,153 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:54,153 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30049 connected 2024-12-04T01:16:54,300 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-04T01:16:54,300 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:54,301 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:54,302 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:54,303 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-04T01:16:54,304 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=81, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:54,305 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-04T01:16:54,324 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:54,325 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:54,332 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:54,332 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3004a connected 2024-12-04T01:16:54,410 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-04T01:16:54,441 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3004a, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:54,455 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=82, ppid=81, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:54,610 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:54,611 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=82 2024-12-04T01:16:54,611 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:54,615 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:54,615 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:54,616 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:54,616 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30049, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:54,617 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30049, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:54,619 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-04T01:16:54,728 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30049, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:54,728 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x15687f26 to 127.0.0.1:53444 2024-12-04T01:16:54,728 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:54,745 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:54,745 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:54,745 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=82 2024-12-04T01:16:54,746 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=82 2024-12-04T01:16:54,747 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:54,749 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=82, resume processing ppid=81 2024-12-04T01:16:54,749 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-04T01:16:54,749 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=82, ppid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 292 msec 2024-12-04T01:16:54,751 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 446 msec 2024-12-04T01:16:54,770 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6ab29148 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2cbcd790 2024-12-04T01:16:54,783 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:54,783 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:54,783 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6604f5ee, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:54,784 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:54,794 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:54,795 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:54,795 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3004c connected 2024-12-04T01:16:54,930 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-04T01:16:54,930 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:54,931 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:54,933 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:54,935 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-04T01:16:54,937 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=83, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:54,939 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-04T01:16:54,955 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:54,955 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:54,965 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:54,966 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3004d connected 2024-12-04T01:16:55,049 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-04T01:16:55,074 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3004d, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:55,083 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=84, ppid=83, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:55,235 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:55,236 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=84 2024-12-04T01:16:55,236 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:55,238 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:55,238 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:55,238 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:55,238 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3004c, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:55,238 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3004c, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:55,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-04T01:16:55,349 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3004c, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:55,349 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6ab29148 to 127.0.0.1:53444 2024-12-04T01:16:55,350 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:55,370 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:55,370 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:55,371 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=84 2024-12-04T01:16:55,371 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=84 2024-12-04T01:16:55,373 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:55,375 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=84, resume processing ppid=83 2024-12-04T01:16:55,375 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-04T01:16:55,375 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=84, ppid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-04T01:16:55,377 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 440 msec 2024-12-04T01:16:55,401 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7a55765e to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2a9e9dcc 2024-12-04T01:16:55,416 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:55,417 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:55,417 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@632d15fd, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:55,418 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:55,428 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:55,428 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:55,428 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3004f connected 2024-12-04T01:16:55,570 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-04T01:16:55,571 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:55,572 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:55,574 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-04T01:16:55,577 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=85, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:55,578 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-04T01:16:55,595 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:55,595 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:55,607 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:55,607 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30050 connected 2024-12-04T01:16:55,689 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-04T01:16:55,716 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30050, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:55,730 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=86, ppid=85, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:55,885 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:55,886 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=86 2024-12-04T01:16:55,886 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:55,887 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=86 2024-12-04T01:16:55,887 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=86 2024-12-04T01:16:55,889 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:55,891 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=86, resume processing ppid=85 2024-12-04T01:16:55,891 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-04T01:16:55,891 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=86, ppid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 159 msec 2024-12-04T01:16:55,893 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 316 msec 2024-12-04T01:16:55,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-04T01:16:55,900 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:55,900 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:55,901 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:55,902 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-04T01:16:55,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=87, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:55,904 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-04T01:16:55,917 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:55,918 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:55,932 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:55,933 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30051 connected 2024-12-04T01:16:56,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-04T01:16:56,041 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30051, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:56,054 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=88, ppid=87, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:56,206 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:56,207 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=88 2024-12-04T01:16:56,207 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:56,208 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:56,208 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:56,209 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:56,209 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3004f, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:56,209 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3004f, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:56,219 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-04T01:16:56,320 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3004f, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:56,320 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7a55765e to 127.0.0.1:53444 2024-12-04T01:16:56,320 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:56,333 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:56,333 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:56,333 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=88 2024-12-04T01:16:56,334 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=88 2024-12-04T01:16:56,336 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:56,337 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=88, resume processing ppid=87 2024-12-04T01:16:56,338 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-04T01:16:56,338 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=88, ppid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-04T01:16:56,339 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 436 msec 2024-12-04T01:16:56,361 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x725025f7 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4c1ea36e 2024-12-04T01:16:56,374 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:56,375 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:56,375 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@727ad788, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:56,376 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:56,386 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:56,387 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:56,387 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30053 connected 2024-12-04T01:16:56,530 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-04T01:16:56,530 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:56,531 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:56,532 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-04T01:16:56,533 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=89, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:16:56,534 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-04T01:16:56,554 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:56,554 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:56,649 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-04T01:16:56,721 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:56,722 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30054 connected 2024-12-04T01:16:56,859 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-04T01:16:56,944 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30054, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:56,984 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=90, ppid=89, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:57,038 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. 2024-12-04T01:16:57,136 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:57,137 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=90 2024-12-04T01:16:57,137 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:16:57,138 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:57,138 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:57,138 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:57,139 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30053, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:57,139 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30053, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:57,169 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-04T01:16:57,253 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30053, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:57,253 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x725025f7 to 127.0.0.1:53444 2024-12-04T01:16:57,253 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:57,274 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:57,274 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:57,274 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=90 2024-12-04T01:16:57,275 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=90 2024-12-04T01:16:57,277 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:57,283 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=90, resume processing ppid=89 2024-12-04T01:16:57,283 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-04T01:16:57,283 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=90, ppid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 294 msec 2024-12-04T01:16:57,286 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 751 msec 2024-12-04T01:16:57,307 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4df9bfab to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4542cd1d 2024-12-04T01:16:57,316 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:57,317 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:57,317 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@79c67695, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:57,318 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:57,328 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:57,328 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:57,329 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30056 connected 2024-12-04T01:16:57,679 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-04T01:16:57,679 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:16:57,680 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:16:57,680 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:57,681 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=91, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:57,682 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-04T01:16:57,684 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:57,704 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:57,705 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:57,705 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:57,706 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=92, ppid=91, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:57,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-04T01:16:57,858 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:57,859 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=92 2024-12-04T01:16:57,859 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:16:57,859 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:16:57,859 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:16:57,859 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:57,859 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30056, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:57,860 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30056, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:57,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30056, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:57,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4df9bfab to 127.0.0.1:53444 2024-12-04T01:16:57,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:57,974 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:16:57,986 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:57,994 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:16:57,995 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:57,995 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:16:57,995 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:57,995 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=92 2024-12-04T01:16:57,996 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=92 2024-12-04T01:16:57,997 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:58,000 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-04T01:16:58,001 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=92, resume processing ppid=91 2024-12-04T01:16:58,001 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=92, ppid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 292 msec 2024-12-04T01:16:58,012 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:16:58,012 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:16:58,013 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 332 msec 2024-12-04T01:16:58,309 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-04T01:16:58,310 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:58,310 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:58,311 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=93, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:58,312 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-04T01:16:58,312 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:58,314 ERROR [PEWorker-3 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=93, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:58,315 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=93, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:16:58,315 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:58,419 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-04T01:16:58,420 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:16:58,421 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:16:58,421 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=94, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:58,422 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-04T01:16:58,422 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:16:58,423 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=94, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:16:58,424 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=94, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-04T01:16:58,424 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:16:58,529 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-04T01:16:58,530 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:16:58,545 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=221 (was 220) - Thread LEAK? -, OpenFileDescriptor=446 (was 444) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=211 (was 230), ProcessCount=11 (was 11), AvailableMemoryMB=10396 (was 9422) - AvailableMemoryMB LEAK? - 2024-12-04T01:16:58,552 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=211, ProcessCount=11, AvailableMemoryMB=10396 2024-12-04T01:16:58,553 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:16:58,554 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=95, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:16:58,555 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-04T01:16:58,570 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:58,571 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:58,586 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:58,587 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30057 connected 2024-12-04T01:16:58,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-04T01:16:58,731 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30057, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:58,758 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=96, ppid=95, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:58,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-04T01:16:58,909 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:58,910 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=96 2024-12-04T01:16:58,910 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:16:58,924 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=96}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:16:58,936 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:59,015 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=96 2024-12-04T01:16:59,016 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=96 2024-12-04T01:16:59,018 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:59,019 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=96, resume processing ppid=95 2024-12-04T01:16:59,019 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:16:59,019 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=96, ppid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 260 msec 2024-12-04T01:16:59,020 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 466 msec 2024-12-04T01:16:59,050 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x08c28a13 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7036994b 2024-12-04T01:16:59,058 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:59,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:59,058 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@72982460, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:59,059 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:59,069 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:59,070 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:59,070 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30059 connected 2024-12-04T01:16:59,179 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-04T01:16:59,179 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:59,180 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:59,182 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3938): Client=jenkins//172.17.0.2 disable replication peer, id=1 2024-12-04T01:16:59,185 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=97, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure 2024-12-04T01:16:59,186 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-04T01:16:59,196 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=98, ppid=97, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:59,289 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-04T01:16:59,348 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:59,349 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=98 2024-12-04T01:16:59,349 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=DISABLE_PEER 2024-12-04T01:16:59,349 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:16:59,350 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:16:59,350 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:59,350 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30059, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:59,350 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30059, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:59,482 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30059, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:16:59,483 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x08c28a13 to 127.0.0.1:53444 2024-12-04T01:16:59,483 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:16:59,499 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-04T01:16:59,500 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:16:59,500 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:16:59,501 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=98 2024-12-04T01:16:59,501 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=98 2024-12-04T01:16:59,503 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for DISABLE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:16:59,504 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=98, resume processing ppid=97 2024-12-04T01:16:59,504 INFO [PEWorker-5 {}] replication.DisablePeerProcedure(67): Successfully disabled peer 1 2024-12-04T01:16:59,504 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=98, ppid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 308 msec 2024-12-04T01:16:59,506 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure in 321 msec 2024-12-04T01:16:59,528 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6944f76f to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@352efb02 2024-12-04T01:16:59,545 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:16:59,545 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:16:59,546 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@26bb78ac, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:16:59,546 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:16:59,592 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:16:59,592 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:16:59,592 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3005b connected 2024-12-04T01:16:59,810 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-04T01:16:59,810 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: DISABLE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:16:59,810 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:16:59,811 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:16:59,812 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=99, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:16:59,812 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-04T01:16:59,814 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:59,828 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:16:59,828 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:59,828 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:16:59,829 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=100, ppid=99, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:16:59,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-04T01:16:59,980 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:16:59,981 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=100 2024-12-04T01:16:59,981 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:16:59,981 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:16:59,981 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:16:59,982 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:16:59,982 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3005b, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:16:59,982 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3005b, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:00,090 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3005b, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:00,091 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6944f76f to 127.0.0.1:53444 2024-12-04T01:17:00,091 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:00,091 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:17:00,107 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:00,115 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:00,115 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:00,115 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:00,116 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:00,116 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=100 2024-12-04T01:17:00,116 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=100 2024-12-04T01:17:00,118 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:00,120 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=100, resume processing ppid=99 2024-12-04T01:17:00,120 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=100, ppid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-04T01:17:00,129 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-04T01:17:00,135 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:00,136 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:17:00,137 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 325 msec 2024-12-04T01:17:00,440 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-04T01:17:00,440 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:00,441 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:00,442 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=101, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:00,443 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-04T01:17:00,443 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:00,445 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=101, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:00,446 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=101, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:17:00,446 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:17:00,549 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-04T01:17:00,551 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:17:00,552 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:00,553 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=102, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:00,554 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-04T01:17:00,555 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:00,557 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:00,559 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=102, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-04T01:17:00,559 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:17:00,659 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-04T01:17:00,660 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:00,677 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=202 (was 211), ProcessCount=11 (was 11), AvailableMemoryMB=10220 (was 10396) 2024-12-04T01:17:00,685 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=202, ProcessCount=11, AvailableMemoryMB=10219 2024-12-04T01:17:00,685 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=dummy_peer 2024-12-04T01:17:00,686 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=103, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:00,687 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-04T01:17:00,687 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:00,688 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:00,689 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=103, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-04T01:17:00,689 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:17:00,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-04T01:17:00,789 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: dummy_peer failed with dummy_peer 2024-12-04T01:17:00,790 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:00,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=104, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:00,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-04T01:17:00,791 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:00,792 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:00,793 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=104, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-04T01:17:00,793 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:17:00,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-04T01:17:00,900 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:17:00,900 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:00,901 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=105, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:00,902 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-04T01:17:00,902 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:00,903 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=105, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:00,903 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=105, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-04T01:17:00,903 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-04T01:17:01,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-04T01:17:01,010 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:01,019 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=202 (was 202), ProcessCount=11 (was 11), AvailableMemoryMB=10201 (was 10219) 2024-12-04T01:17:01,026 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=202, ProcessCount=11, AvailableMemoryMB=10200 2024-12-04T01:17:01,027 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:01,028 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=106, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:17:01,029 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-04T01:17:01,041 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:01,041 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:01,057 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:01,058 ERROR [PEWorker-5-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f21cc8d4e18@4c61058e rejected from java.util.concurrent.ThreadPoolExecutor@9639266[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$AbortPolicy.rejectedExecution(ThreadPoolExecutor.java:2065) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.reject(ThreadPoolExecutor.java:833) ~[?:?] at java.util.concurrent.ThreadPoolExecutor.execute(ThreadPoolExecutor.java:1365) ~[?:?] at java.util.concurrent.Executors$DelegatedExecutorService.execute(Executors.java:721) ~[?:?] at org.apache.hadoop.hbase.zookeeper.ZKWatcher.process(ZKWatcher.java:613) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.PendingWatcher.process(PendingWatcher.java:38) ~[hbase-zookeeper-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.zookeeper.ClientCnxn$EventThread.processEvent(ClientCnxn.java:579) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-12-04T01:17:01,139 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-04T01:17:01,165 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:01,187 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=107, ppid=106, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:01,339 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:01,340 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=107 2024-12-04T01:17:01,340 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:17:01,349 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-04T01:17:01,355 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=107}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:01,366 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:01,466 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=107 2024-12-04T01:17:01,467 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=107 2024-12-04T01:17:01,470 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:01,472 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=107, resume processing ppid=106 2024-12-04T01:17:01,472 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:17:01,473 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=107, ppid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 283 msec 2024-12-04T01:17:01,474 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 446 msec 2024-12-04T01:17:01,501 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x344514c0 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4cba2c52 2024-12-04T01:17:01,512 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:01,512 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:01,512 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2d8b859d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:01,514 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:01,524 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:01,524 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:01,525 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3005e connected 2024-12-04T01:17:01,659 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-04T01:17:01,660 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:01,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-04T01:17:01,661 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:01,662 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=108, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:01,663 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-04T01:17:01,664 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:01,674 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:01,674 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:01,674 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:01,675 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=109, ppid=108, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:01,769 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-04T01:17:01,827 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:01,827 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=109 2024-12-04T01:17:01,828 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:17:01,828 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:17:01,828 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:17:01,828 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:01,828 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3005e, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:01,829 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3005e, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:01,941 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3005e, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:01,941 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x344514c0 to 127.0.0.1:53444 2024-12-04T01:17:01,941 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:01,942 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:17:01,979 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-04T01:17:02,000 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:02,011 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:02,011 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:02,011 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:02,012 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:02,012 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=109 2024-12-04T01:17:02,012 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=109 2024-12-04T01:17:02,014 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:02,015 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=109, resume processing ppid=108 2024-12-04T01:17:02,015 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=109, ppid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 339 msec 2024-12-04T01:17:02,024 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:02,024 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:17:02,025 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 363 msec 2024-12-04T01:17:02,289 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-04T01:17:02,290 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:02,291 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:02,293 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=110, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:02,295 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-04T01:17:02,295 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:02,297 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:02,299 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=7 msec 2024-12-04T01:17:02,299 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. 2024-12-04T01:17:02,400 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-04T01:17:02,402 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:17:02,403 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:02,405 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=111, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:02,407 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-04T01:17:02,407 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:02,408 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=111, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:02,410 INFO [PEWorker-4 {}] 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=6 msec 2024-12-04T01:17:02,410 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. 2024-12-04T01:17:02,508 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-04T01:17:02,509 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:02,523 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=223 (was 221) - Thread LEAK? -, OpenFileDescriptor=448 (was 446) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=202 (was 202), ProcessCount=11 (was 11), AvailableMemoryMB=10140 (was 10200) 2024-12-04T01:17:02,533 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=202, ProcessCount=11, AvailableMemoryMB=10140 2024-12-04T01:17:02,542 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:02,542 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] 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] 2024-12-04T01:17:02,542 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] ipc.CallRunner(138): callId: 350 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:52622 deadline: 1733275082541, exception=java.io.IOException: Replication peer modification disabled 2024-12-04T01:17:02,564 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 1, maxAttempts = 2, timeout = 120000 ms, time elapsed = 23 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.instantiateException(RemoteWithExtrasException.java:110) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.unwrapRemoteException(RemoteWithExtrasException.java:100) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionUtils.translateException(ConnectionUtils.java:245) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncRpcRetryingCaller.onError(AsyncRpcRetryingCaller.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncMasterRequestRpcRetryingCaller.lambda$doCall$4(AsyncMasterRequestRpcRetryingCaller.java:76) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.util.FutureUtils.lambda$addListener$0(FutureUtils.java:71) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:841) ~[?:?] at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:510) ~[?:?] at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2162) ~[?:?] at org.apache.hadoop.hbase.client.RawAsyncHBaseAdmin$1.run(RawAsyncHBaseAdmin.java:431) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:56) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:47) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:397) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.access$100(AbstractRpcClient.java:94) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:430) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.callComplete(Call.java:116) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.setException(Call.java:131) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcConnection.readResponse(RpcConnection.java:457) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.readResponse(NettyRpcDuplexHandler.java:125) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.channelRead(NettyRpcDuplexHandler.java:140) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:289) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1357) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:868) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[hbase-shaded-netty-4.1.9.jar:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-04T01:17:02,669 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:02,669 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] 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] 2024-12-04T01:17:02,669 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] ipc.CallRunner(138): callId: 351 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:52622 deadline: 1733275082669, exception=java.io.IOException: Replication peer modification disabled 2024-12-04T01:17:02,670 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 2, maxAttempts = 2, timeout = 120000 ms, time elapsed = 129 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method) ~[?:?] at jdk.internal.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:77) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.instantiateException(RemoteWithExtrasException.java:110) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RemoteWithExtrasException.unwrapRemoteException(RemoteWithExtrasException.java:100) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionUtils.translateException(ConnectionUtils.java:245) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncRpcRetryingCaller.onError(AsyncRpcRetryingCaller.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.AsyncMasterRequestRpcRetryingCaller.lambda$doCall$4(AsyncMasterRequestRpcRetryingCaller.java:76) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.util.FutureUtils.lambda$addListener$0(FutureUtils.java:71) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:863) ~[?:?] at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:841) ~[?:?] at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:510) ~[?:?] at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:2162) ~[?:?] at org.apache.hadoop.hbase.client.RawAsyncHBaseAdmin$1.run(RawAsyncHBaseAdmin.java:431) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:56) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hbase.thirdparty.com.google.protobuf.RpcUtil$1.run(RpcUtil.java:47) ~[hbase-shaded-protobuf-4.1.9.jar:4.1.9] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:397) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient.access$100(AbstractRpcClient.java:94) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:430) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.AbstractRpcClient$3.run(AbstractRpcClient.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.callComplete(Call.java:116) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.Call.setException(Call.java:131) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcConnection.readResponse(RpcConnection.java:457) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.readResponse(NettyRpcDuplexHandler.java:125) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.NettyRpcDuplexHandler.channelRead(NettyRpcDuplexHandler.java:140) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.fireChannelRead(ByteToMessageDecoder.java:346) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.codec.ByteToMessageDecoder.channelRead(ByteToMessageDecoder.java:318) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:444) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.handler.timeout.IdleStateHandler.channelRead(IdleStateHandler.java:289) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:442) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:412) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1357) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:440) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:420) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:868) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:166) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:788) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:724) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:650) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:562) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) ~[hbase-shaded-netty-4.1.9.jar:?] at org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) ~[hbase-shaded-netty-4.1.9.jar:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.hadoop.hbase.ipc.RemoteWithExtrasException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-04T01:17:02,671 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Failed after attempts=2, exceptions: 2024-12-04T01:17:02.565Z, 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) 2024-12-04T01:17:02.671Z, 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) 2024-12-04T01:17:02,673 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:02,674 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=112, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:02,674 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-04T01:17:02,675 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:02,675 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=112, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:02,677 INFO [PEWorker-5 {}] 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 2024-12-04T01:17:02,677 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. 2024-12-04T01:17:02,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-04T01:17:02,780 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:17:02,780 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:02,781 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=113, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:02,782 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-04T01:17:02,782 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:02,784 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:02,785 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=4 msec 2024-12-04T01:17:02,786 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. 2024-12-04T01:17:02,889 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-04T01:17:02,890 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:02,907 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=223 (was 223), OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=202 (was 202), ProcessCount=11 (was 11), AvailableMemoryMB=10142 (was 10140) - AvailableMemoryMB LEAK? - 2024-12-04T01:17:02,917 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=202, ProcessCount=11, AvailableMemoryMB=10142 2024-12-04T01:17:02,918 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:02,918 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=114, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:17:02,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-04T01:17:02,935 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:02,935 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:02,974 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:02,974 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3005f connected 2024-12-04T01:17:03,029 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-04T01:17:03,082 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3005f, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:03,099 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=115, ppid=114, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:03,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-04T01:17:03,251 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:03,251 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=115 2024-12-04T01:17:03,252 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:17:03,265 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=115}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:03,280 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:03,324 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=115 2024-12-04T01:17:03,324 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=115 2024-12-04T01:17:03,326 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:03,327 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=115, resume processing ppid=114 2024-12-04T01:17:03,327 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=115, ppid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 227 msec 2024-12-04T01:17:03,327 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:17:03,329 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 410 msec 2024-12-04T01:17:03,350 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4e602c53 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@72d46c19 2024-12-04T01:17:03,362 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:03,363 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:03,363 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1f41313, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:03,364 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:03,374 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:03,374 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:03,374 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30061 connected 2024-12-04T01:17:03,487 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:17:03,549 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-04T01:17:03,549 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:03,550 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:03,551 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:03,552 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=116, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:03,553 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-04T01:17:03,555 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:03,565 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:03,565 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:03,565 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:03,566 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=117, ppid=116, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:03,659 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-04T01:17:03,717 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:03,718 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=117 2024-12-04T01:17:03,718 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:17:03,718 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:17:03,718 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:17:03,718 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:03,718 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30061, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:03,718 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30061, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:03,828 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30061, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:03,828 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4e602c53 to 127.0.0.1:53444 2024-12-04T01:17:03,828 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:03,828 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:17:03,837 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:03,844 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:03,845 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:03,845 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:03,845 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:03,845 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=117 2024-12-04T01:17:03,845 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=117 2024-12-04T01:17:03,847 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:03,848 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=117, resume processing ppid=116 2024-12-04T01:17:03,848 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=117, ppid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-12-04T01:17:03,857 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:03,857 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:17:03,859 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 306 msec 2024-12-04T01:17:03,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-04T01:17:03,870 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:03,870 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:03,871 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=118, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:03,871 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-04T01:17:03,871 WARN [PEWorker-5 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:03,872 ERROR [PEWorker-5 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=118, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:03,873 INFO [PEWorker-5 {}] 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=3 msec 2024-12-04T01:17:03,873 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. 2024-12-04T01:17:03,979 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-04T01:17:03,980 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:03,997 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=223 (was 223), OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=202 (was 202), ProcessCount=11 (was 11), AvailableMemoryMB=10078 (was 10142) 2024-12-04T01:17:04,005 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=202, ProcessCount=11, AvailableMemoryMB=10078 2024-12-04T01:17:04,006 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:04,007 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=119, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:17:04,007 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-04T01:17:04,019 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:04,020 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:04,028 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:04,028 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30062 connected 2024-12-04T01:17:04,109 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-04T01:17:04,136 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30062, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:04,158 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=120, ppid=119, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:04,309 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:04,311 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=120 2024-12-04T01:17:04,311 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:17:04,319 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-04T01:17:04,335 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=120}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:04,346 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:04,405 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=120 2024-12-04T01:17:04,406 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=120 2024-12-04T01:17:04,409 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:04,413 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=120, resume processing ppid=119 2024-12-04T01:17:04,413 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=120, ppid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 251 msec 2024-12-04T01:17:04,413 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:17:04,415 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 407 msec 2024-12-04T01:17:04,436 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x72fe0868 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2528d172 2024-12-04T01:17:04,453 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:04,454 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:04,454 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4440904d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:04,455 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:04,465 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:04,466 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30064 connected 2024-12-04T01:17:04,466 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:04,629 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-04T01:17:04,630 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:04,630 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:04,631 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-04T01:17:04,633 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=121, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:04,634 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-04T01:17:04,650 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:04,650 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:04,657 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:04,657 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30065 connected 2024-12-04T01:17:04,739 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-04T01:17:04,765 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30065, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:04,779 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=122, ppid=121, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:04,931 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:04,932 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=122 2024-12-04T01:17:04,932 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:04,933 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=122 2024-12-04T01:17:04,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=122 2024-12-04T01:17:04,935 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:04,936 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-04T01:17:04,936 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=122, resume processing ppid=121 2024-12-04T01:17:04,937 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=122, ppid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 156 msec 2024-12-04T01:17:04,938 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 306 msec 2024-12-04T01:17:04,949 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-04T01:17:04,949 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:04,950 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:04,950 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:04,952 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=123, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:04,952 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-04T01:17:04,954 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:04,965 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:04,965 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:04,965 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:04,966 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=124, ppid=123, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:05,059 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-04T01:17:05,118 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:05,119 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=124 2024-12-04T01:17:05,119 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:17:05,119 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:17:05,119 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:17:05,119 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:05,119 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30064, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:05,119 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30064, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:05,232 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30064, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:05,232 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x72fe0868 to 127.0.0.1:53444 2024-12-04T01:17:05,232 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:05,232 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:17:05,240 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:05,248 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:05,248 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:05,249 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:05,249 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:05,249 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=124 2024-12-04T01:17:05,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=124 2024-12-04T01:17:05,252 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:05,254 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=124, resume processing ppid=123 2024-12-04T01:17:05,254 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=124, ppid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-04T01:17:05,266 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:05,266 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:17:05,267 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 315 msec 2024-12-04T01:17:05,269 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-04T01:17:05,269 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:05,269 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:05,270 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=125, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:05,270 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-04T01:17:05,270 WARN [PEWorker-1 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:05,271 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) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:05,272 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=2 msec 2024-12-04T01:17:05,272 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. 2024-12-04T01:17:05,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-04T01:17:05,380 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-04T01:17:05,380 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:05,381 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=126, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:05,381 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-04T01:17:05,382 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:05,383 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=126, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:05,384 INFO [PEWorker-4 {}] 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 2024-12-04T01:17:05,384 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. 2024-12-04T01:17:05,489 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-04T01:17:05,490 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:05,498 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223 (was 223), OpenFileDescriptor=448 (was 448), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=194 (was 202), ProcessCount=11 (was 11), AvailableMemoryMB=9991 (was 10078) 2024-12-04T01:17:05,507 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=223, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=194, ProcessCount=11, AvailableMemoryMB=9990 2024-12-04T01:17:05,508 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:05,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=127, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:17:05,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-04T01:17:05,529 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=128, ppid=127, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:05,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-04T01:17:05,654 DEBUG [BootstrapNodeManager {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-04T01:17:05,656 INFO [RS-EventLoopGroup-1-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:46854, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-04T01:17:05,681 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:05,682 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=128 2024-12-04T01:17:05,682 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:17:05,709 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:05,749 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=128 2024-12-04T01:17:05,750 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(587): peerId=1, queueId=1 (queues=1) is replicating from cluster=eebc8d6e-7cd5-45b7-ba9a-bccacb7458ca to cluster=eebc8d6e-7cd5-45b7-ba9a-bccacb7458ca 2024-12-04T01:17:05,750 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=128 2024-12-04T01:17:05,753 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(343): peerId=1, starting shipping worker for walGroupId=93574c9bec15%2C41969%2C1733274988845 2024-12-04T01:17:05,754 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:05,757 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=128, resume processing ppid=127 2024-12-04T01:17:05,758 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 2024-12-04T01:17:05,758 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=128, ppid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 225 msec 2024-12-04T01:17:05,759 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSourceWALReader(112): peerClusterZnode=1, ReplicationSourceWALReaderThread : 1 inited, replicationBatchSizeCapacity=67108864, replicationBatchCountCapacity=25000, replicationBatchQueueCapacity=1 2024-12-04T01:17:05,759 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 250 msec 2024-12-04T01:17:05,760 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.shipper93574c9bec15%2C41969%2C1733274988845,1 {}] regionserver.ReplicationSourceShipper(98): Running ReplicationSourceShipper Thread for wal group: 93574c9bec15%2C41969%2C1733274988845 2024-12-04T01:17:05,760 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.wal-reader.93574c9bec15%2C41969%2C1733274988845,1 {}] regionserver.WALEntryStream(260): Creating new reader hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.1733274991949, startPosition=0, beingWritten=true 2024-12-04T01:17:05,808 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.wal-reader.93574c9bec15%2C41969%2C1733274988845,1 {}] regionserver.ReplicationSourceWALReader(181): Read 0 WAL entries eligible for replication 2024-12-04T01:17:05,808 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.wal-reader.93574c9bec15%2C41969%2C1733274988845,1 {}] regionserver.WALEntryStream(223): Reset reader hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.1733274991949 to pos 589, reset compression=false 2024-12-04T01:17:05,808 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.shipper93574c9bec15%2C41969%2C1733274988845,1 {}] regionserver.ReplicationSourceShipper(110): Shipper from source 1 got entry batch from reader: WALEntryBatch [walEntries=[], lastWalPath=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/WALs/93574c9bec15,41969,1733274988845/93574c9bec15%2C41969%2C1733274988845.1733274991949, lastWalPosition=589, nbRowKeys=0, nbHFiles=0, heapSize=0, lastSeqIds={}, endOfFile=false,usedBufferSize=0] 2024-12-04T01:17:05,829 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-04T01:17:05,829 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:05,830 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:05,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=129, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:17:05,831 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-04T01:17:05,831 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: java.io.IOException: Cluster key passed is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] ... 13 more 2024-12-04T01:17:05,832 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=129, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: ; org.apache.hadoop.hbase.master.replication.AddPeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:395) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more Caused by: java.io.IOException: Cluster key passed is invalid, the format should be:hbase.zookeeper.quorum:hbase.zookeeper.property.clientPort:zookeeper.znode.parent at org.apache.hadoop.hbase.zookeeper.ZKConfig.transformClusterKey(ZKConfig.java:228) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ZKConfig.validateClusterKey(ZKConfig.java:178) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkClusterKey(ReplicationPeerManager.java:393) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerConfig(ReplicationPeerManager.java:298) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:119) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:05,833 INFO [PEWorker-4 {}] 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=2 msec 2024-12-04T01:17:05,833 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. 2024-12-04T01:17:05,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-04T01:17:05,941 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 2 failed with Invalid cluster key: 2024-12-04T01:17:05,942 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:05,943 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=130, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:05,945 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:05,948 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:05,957 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:05,957 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:05,957 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:05,958 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=131, ppid=130, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:06,050 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:06,110 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:06,110 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=131 2024-12-04T01:17:06,110 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:17:06,111 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:17:06,111 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:17:06,260 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:06,569 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:07,079 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:07,111 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.shipper93574c9bec15%2C41969%2C1733274988845,1 {}] 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/:?] 2024-12-04T01:17:07,111 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.wal-reader.93574c9bec15%2C41969%2C1733274988845,1 {}] util.Threads(127): sleep interrupted java.lang.InterruptedException: sleep interrupted at java.lang.Thread.sleep(Native Method) ~[?:?] at org.apache.hadoop.hbase.util.Threads.sleep(Threads.java:125) ~[hbase-common-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.sleep(ReplicationSourceWALReader.java:131) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSourceWALReader.run(ReplicationSourceWALReader.java:166) ~[classes/:?] 2024-12-04T01:17:08,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:08,111 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(711): peerId=1, ReplicationSourceWorker RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1.replicationSource.shipper93574c9bec15%2C41969%2C1733274988845,1 terminated 2024-12-04T01:17:08,111 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:17:08,113 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:08,123 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:08,123 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:08,123 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:08,124 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:08,124 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=131 2024-12-04T01:17:08,124 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=131 2024-12-04T01:17:08,126 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:08,128 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=131, resume processing ppid=130 2024-12-04T01:17:08,128 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=131, ppid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 2.1680 sec 2024-12-04T01:17:08,141 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:08,142 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:17:08,144 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 2.2000 sec 2024-12-04T01:17:09,331 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:17:10,099 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-04T01:17:10,100 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:10,100 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-04T01:17:10,102 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=132, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:10,102 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-04T01:17:10,103 WARN [PEWorker-4 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 2, mark the procedure as failure and give up org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] 2024-12-04T01:17:10,104 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=132, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-04T01:17:10,105 INFO [PEWorker-4 {}] 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 2024-12-04T01:17:10,106 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. 2024-12-04T01:17:10,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-04T01:17:10,210 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-04T01:17:10,230 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=221 (was 223), OpenFileDescriptor=451 (was 448) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=194 (was 194), ProcessCount=11 (was 11), AvailableMemoryMB=9939 (was 9990) 2024-12-04T01:17:10,238 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[1] Thread=221, OpenFileDescriptor=451, MaxFileDescriptor=1048576, SystemLoadAverage=194, ProcessCount=11, AvailableMemoryMB=9938 2024-12-04T01:17:10,240 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-04T01:17:10,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=133, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-04T01:17:10,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-04T01:17:10,263 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:10,264 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:10,278 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:10,278 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30066 connected 2024-12-04T01:17:10,349 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-04T01:17:10,386 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30066, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:10,412 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=134, ppid=133, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:10,559 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-04T01:17:10,564 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:10,564 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=134 2024-12-04T01:17:10,564 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-04T01:17:10,585 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=134}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:10,602 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:10,645 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=134 2024-12-04T01:17:10,646 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=134 2024-12-04T01:17:10,648 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:10,650 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=134, resume processing ppid=133 2024-12-04T01:17:10,650 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-04T01:17:10,650 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=134, ppid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 236 msec 2024-12-04T01:17:10,652 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 410 msec 2024-12-04T01:17:10,675 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1275a888 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@11db5633 2024-12-04T01:17:10,699 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:10,699 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:10,699 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@7195eec3, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:10,700 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:10,711 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:10,712 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:10,712 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30068 connected 2024-12-04T01:17:10,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-04T01:17:10,870 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:10,871 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:17:10,872 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=135, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:10,872 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-04T01:17:10,889 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:10,889 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:10,915 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:10,915 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30069 connected 2024-12-04T01:17:10,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-04T01:17:11,028 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30069, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:11,041 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=136, ppid=135, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:11,190 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-04T01:17:11,193 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:11,194 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=136 2024-12-04T01:17:11,194 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:11,196 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:17:11,196 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:17:11,196 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:11,196 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30068, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:11,197 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30068, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:11,307 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30068, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:11,307 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1275a888 to 127.0.0.1:53444 2024-12-04T01:17:11,307 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:11,326 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:11,326 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:17:11,326 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=136 2024-12-04T01:17:11,327 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=136 2024-12-04T01:17:11,328 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:11,330 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=136, resume processing ppid=135 2024-12-04T01:17:11,330 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:17:11,330 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=136, ppid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 287 msec 2024-12-04T01:17:11,331 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 459 msec 2024-12-04T01:17:11,354 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x66fe97b4 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@d9d9033 2024-12-04T01:17:11,366 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:11,366 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:11,366 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@705ca070, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:11,367 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:11,378 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:11,378 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:11,378 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3006b connected 2024-12-04T01:17:11,499 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-04T01:17:11,500 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:11,500 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:11,502 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:11,503 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:11,504 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-04T01:17:11,506 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=137, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:11,507 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-04T01:17:11,527 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:11,528 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:11,536 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:11,537 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3006c connected 2024-12-04T01:17:11,610 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-04T01:17:11,645 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3006c, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:11,659 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=138, ppid=137, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:11,813 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:11,814 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=138 2024-12-04T01:17:11,814 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:11,818 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:17:11,818 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:17:11,819 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:11,819 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3006b, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:11,819 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3006b, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:11,819 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-04T01:17:11,928 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3006b, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:11,928 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x66fe97b4 to 127.0.0.1:53444 2024-12-04T01:17:11,928 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:11,946 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:11,947 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:17:11,947 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=138 2024-12-04T01:17:11,947 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=138 2024-12-04T01:17:11,949 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:11,950 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=138, resume processing ppid=137 2024-12-04T01:17:11,950 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-04T01:17:11,950 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=138, ppid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-04T01:17:11,951 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 446 msec 2024-12-04T01:17:11,974 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x66280734 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@9100193 2024-12-04T01:17:11,982 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:11,982 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:11,982 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@660953e9, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:11,983 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:11,990 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:11,990 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:11,990 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3006e connected 2024-12-04T01:17:12,129 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-04T01:17:12,130 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:12,131 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,132 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,134 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,135 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,137 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-04T01:17:12,138 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=139, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:12,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-04T01:17:12,157 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:12,158 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:12,173 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:12,174 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3006f connected 2024-12-04T01:17:12,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-04T01:17:12,282 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd3006f, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:12,290 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=140, ppid=139, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:12,442 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:12,443 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=140 2024-12-04T01:17:12,444 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:12,447 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:17:12,447 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:17:12,448 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:12,448 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3006e, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:12,448 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3006e, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:12,459 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-04T01:17:12,557 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3006e, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:12,557 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x66280734 to 127.0.0.1:53444 2024-12-04T01:17:12,557 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:12,577 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:12,577 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:17:12,578 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=140 2024-12-04T01:17:12,578 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=140 2024-12-04T01:17:12,579 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:12,580 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=140, resume processing ppid=139 2024-12-04T01:17:12,580 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-04T01:17:12,580 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=140, ppid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-04T01:17:12,581 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 443 msec 2024-12-04T01:17:12,624 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6bc67c34 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3ff6c7e3 2024-12-04T01:17:12,632 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:12,633 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:12,633 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@196ed1fd, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:12,634 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:12,646 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:12,646 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:12,646 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30071 connected 2024-12-04T01:17:12,769 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-04T01:17:12,770 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:12,771 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,773 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,775 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:12,777 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:17:12,778 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=141, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:12,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-04T01:17:12,797 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:12,797 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:12,806 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:12,807 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30072 connected 2024-12-04T01:17:12,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-04T01:17:12,915 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30072, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:12,924 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=142, ppid=141, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:13,076 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:13,077 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=142 2024-12-04T01:17:13,077 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:13,079 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:17:13,079 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:17:13,079 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:13,080 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30071, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:13,080 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30071, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:13,099 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-04T01:17:13,190 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30071, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:13,191 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6bc67c34 to 127.0.0.1:53444 2024-12-04T01:17:13,191 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:13,210 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:13,210 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:17:13,210 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=142 2024-12-04T01:17:13,211 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=142 2024-12-04T01:17:13,212 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:13,213 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=142, resume processing ppid=141 2024-12-04T01:17:13,213 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:17:13,213 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=142, ppid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-12-04T01:17:13,214 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 436 msec 2024-12-04T01:17:13,239 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5ffa8332 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@e7c9d61 2024-12-04T01:17:13,249 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:13,249 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:13,249 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@39c4c5ae, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:13,250 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:13,256 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:13,257 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:13,257 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30074 connected 2024-12-04T01:17:13,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-04T01:17:13,410 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:13,410 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:13,411 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:13,411 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-04T01:17:13,412 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=143, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:13,413 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-04T01:17:13,429 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:13,429 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:13,440 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:13,440 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30075 connected 2024-12-04T01:17:13,519 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-04T01:17:13,548 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30075, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:13,562 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=144, ppid=143, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:13,714 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:13,714 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=144 2024-12-04T01:17:13,714 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:13,716 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:17:13,716 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:17:13,716 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:13,716 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30074, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:13,717 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30074, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:13,729 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-04T01:17:13,832 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30074, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:13,832 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5ffa8332 to 127.0.0.1:53444 2024-12-04T01:17:13,833 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:13,849 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:13,850 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:17:13,850 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=144 2024-12-04T01:17:13,850 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=144 2024-12-04T01:17:13,852 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:13,853 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=144, resume processing ppid=143 2024-12-04T01:17:13,853 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-04T01:17:13,853 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=144, ppid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-04T01:17:13,854 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 442 msec 2024-12-04T01:17:13,872 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3507185b to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6cbba8d2 2024-12-04T01:17:13,882 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:13,882 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:13,882 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@362928b6, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:13,883 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:13,890 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:13,890 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:13,890 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd30077 connected 2024-12-04T01:17:14,039 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-04T01:17:14,039 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:14,040 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:14,040 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:17:14,041 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=145, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-04T01:17:14,041 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-04T01:17:14,053 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-04T01:17:14,053 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:14,073 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id0x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:14,074 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30078 connected 2024-12-04T01:17:14,149 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-04T01:17:14,182 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@317ed821check-peer-cluster-id-0x1019f330cd30078, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:14,190 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=146, ppid=145, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:14,341 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:14,341 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=146 2024-12-04T01:17:14,342 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-04T01:17:14,343 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-04T01:17:14,343 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {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 2024-12-04T01:17:14,343 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:14,343 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd30077, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:14,343 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd30077, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:14,359 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-04T01:17:14,453 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd30077, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:14,453 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3507185b to 127.0.0.1:53444 2024-12-04T01:17:14,453 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:14,465 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-04T01:17:14,466 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-04T01:17:14,466 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=146 2024-12-04T01:17:14,466 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=146 2024-12-04T01:17:14,468 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:14,469 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=146, resume processing ppid=145 2024-12-04T01:17:14,469 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:53444:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-04T01:17:14,469 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=146, ppid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 278 msec 2024-12-04T01:17:14,470 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 429 msec 2024-12-04T01:17:14,498 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x34c3d118 to 127.0.0.1:53444 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4714f05 2024-12-04T01:17:14,507 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at java.util.concurrent.CompletableFuture.reportGet(CompletableFuture.java:396) ~[?:?] at java.util.concurrent.CompletableFuture.get(CompletableFuture.java:2073) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.retrieveClusterId(ConnectionImplementation.java:700) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionImplementation.(ConnectionImplementation.java:358) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at jdk.internal.reflect.GeneratedConstructorAccessor40.newInstance(Unknown Source) ~[?:?] at jdk.internal.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45) ~[?:?] at java.lang.reflect.Constructor.newInstanceWithCaller(Constructor.java:499) ~[?:?] at java.lang.reflect.Constructor.newInstance(Constructor.java:480) ~[?:?] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$0(ConnectionFactory.java:425) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at java.security.AccessController.doPrivileged(AccessController.java:712) ~[?:?] at javax.security.auth.Subject.doAs(Subject.java:439) ~[?:?] at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1953) ~[hadoop-common-3.4.1.jar:?] at org.apache.hadoop.hbase.security.User$SecureHadoopUser.runAs(User.java:328) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.lambda$createConnection$2(ConnectionFactory.java:424) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:400) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:362) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.client.ConnectionFactory.createConnection(ConnectionFactory.java:156) ~[hbase-client-2.7.0-SNAPSHOT.jar:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.createConnection(HBaseInterClusterReplicationEndpoint.java:139) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.HBaseInterClusterReplicationEndpoint.init(HBaseInterClusterReplicationEndpoint.java:170) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initAndStartReplicationEndpoint(ReplicationSource.java:320) ~[classes/:?] at org.apache.hadoop.hbase.replication.regionserver.ReplicationSource.initialize(ReplicationSource.java:539) ~[classes/:?] at java.lang.Thread.run(Thread.java:840) ~[?:?] Caused by: org.apache.zookeeper.KeeperException$NoNodeException: KeeperErrorCode = NoNode for /hbase-test1/hbaseid at org.apache.zookeeper.KeeperException.create(KeeperException.java:118) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.zookeeper.KeeperException.create(KeeperException.java:54) ~[zookeeper-3.8.4.jar:3.8.4] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient$ZKTask$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-04T01:17:14,507 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-04T01:17:14,508 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1991b345, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-04T01:17:14,508 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:53444 2024-12-04T01:17:14,520 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-04T01:17:14,520 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-04T01:17:14,520 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019f330cd3007a connected 2024-12-04T01:17:14,669 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-04T01:17:14,670 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-04T01:17:14,670 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-04T01:17:14,671 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:14,671 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-04T01:17:14,671 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=147, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:14,671 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] procedure2.ProcedureExecutor(1098): Stored pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:14,673 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:14,673 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-04T01:17:14,674 DEBUG [PEWorker-3 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=147 2024-12-04T01:17:14,674 DEBUG [PEWorker-3 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-04T01:17:14,674 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:14,681 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-04T01:17:14,682 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:14,682 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:43769-0x1019f330cd30000, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-04T01:17:14,683 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=149, ppid=147, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-04T01:17:14,746 INFO [master/93574c9bec15:0.Chore.1 {}] migrate.RollingUpgradeChore(116): There is no table to migrate StoreFileTracker! 2024-12-04T01:17:14,746 INFO [master/93574c9bec15:0.Chore.1 {}] migrate.RollingUpgradeChore(85): All Rolling-Upgrade tasks are complete, shutdown RollingUpgradeChore! 2024-12-04T01:17:14,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:14,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-04T01:17:14,835 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 93574c9bec15,41969,1733274988845 2024-12-04T01:17:14,835 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=149 2024-12-04T01:17:14,835 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-04T01:17:14,836 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-04T01:17:14,836 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-04T01:17:14,836 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-04T01:17:14,836 WARN [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019f330cd3007a, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:14,836 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019f330cd3007a, quorum=127.0.0.1:53444, 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) ~[?:?] 2024-12-04T01:17:14,945 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019f330cd3007a, quorum=127.0.0.1:53444, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-04T01:17:14,945 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x34c3d118 to 127.0.0.1:53444 2024-12-04T01:17:14,945 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-04T01:17:14,945 INFO [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-04T01:17:14,953 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ZKUtil(111): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:14,961 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1/93574c9bec15%2C41969%2C1733274988845.1733274991949 2024-12-04T01:17:14,961 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:14,961 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:41969-0x1019f330cd30001, quorum=127.0.0.1:53444, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/93574c9bec15,41969,1733274988845/1 2024-12-04T01:17:14,962 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:14,962 DEBUG [RS_REFRESH_PEER-regionserver/93574c9bec15:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=149 2024-12-04T01:17:14,962 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.HMaster(4106): Remote procedure done, pid=149 2024-12-04T01:17:14,963 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 93574c9bec15,41969,1733274988845 suceeded 2024-12-04T01:17:14,964 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=149, resume processing ppid=147 2024-12-04T01:17:14,965 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=149, ppid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 280 msec 2024-12-04T01:17:14,974 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-04T01:17:14,974 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-04T01:17:14,975 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 303 msec 2024-12-04T01:17:14,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:14,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-04T01:17:14,989 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-04T01:17:15,299 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:15,809 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:16,818 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:18,829 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:20,463 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:17:22,849 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:27,038 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. 2024-12-04T01:17:32,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:34,579 DEBUG [master/93574c9bec15:0.Chore.1 {}] balancer.RegionLocationFinder(172): Locality for region be568d21e6f4779021608a7d7c9d641c changed from -1.0 to 0.0, refreshing cache 2024-12-04T01:17:42,930 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:53,039 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:17:57,038 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. 2024-12-04T01:18:03,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:18:23,190 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:18:27,039 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. 2024-12-04T01:18:43,329 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:18:57,039 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. 2024-12-04T01:19:03,338 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:19:23,399 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:19:27,039 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. 2024-12-04T01:19:43,419 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:19:57,039 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. 2024-12-04T01:20:03,559 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:20:23,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:20:27,040 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. 2024-12-04T01:20:43,699 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:20:57,040 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. 2024-12-04T01:21:03,710 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:21:23,799 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:21:27,040 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. 2024-12-04T01:21:28,863 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 2024-12-04T01:21:28,967 DEBUG [master/93574c9bec15:0: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% 2024-12-04T01:21:28,967 DEBUG [master/93574c9bec15:0: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 2024-12-04T01:21:31,833 INFO [93574c9bec15:41969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-04T01:21:33,279 DEBUG [hconnection-0x71b91111-shared-pool-4 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:21:33,283 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:42022, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:21:33,295 DEBUG [master/93574c9bec15:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-04T01:21:34,762 DEBUG [master/93574c9bec15:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-04T01:21:34,762 DEBUG [master/93574c9bec15:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-04T01:21:34,822 INFO [regionserver/93574c9bec15:0.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 7006 ms 2024-12-04T01:21:34,822 INFO [regionserver/93574c9bec15:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c. because be568d21e6f4779021608a7d7c9d641c/info has an old edit so flush to free WALs after random delay 144398 ms 2024-12-04T01:21:38,597 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:21:41,828 DEBUG [MemStoreFlusher.0 {}] regionserver.FlushAllLargeStoresPolicy(69): Since none of the CFs were above the size, flushing all. 2024-12-04T01:21:41,828 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 1588230740 3/3 column families, dataSize=1.23 KB heapSize=2.87 KB 2024-12-04T01:21:41,893 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/.tmp/info/4f7462534ace4383b318c337cc222871 is 143, key is hbase:namespace,,1733274993276.be568d21e6f4779021608a7d7c9d641c./info:regioninfo/1733274994556/Put/seqid=0 2024-12-04T01:21:41,902 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741837_1013 (size=6595) 2024-12-04T01:21:42,304 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1.14 KB at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/.tmp/info/4f7462534ace4383b318c337cc222871 2024-12-04T01:21:42,383 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/.tmp/table/4fea7695f12e4b348df427e7e5d67cd8 is 51, key is hbase:namespace/table:state/1733274994568/Put/seqid=0 2024-12-04T01:21:42,391 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741838_1014 (size=5242) 2024-12-04T01:21:42,793 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=94 B at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/.tmp/table/4fea7695f12e4b348df427e7e5d67cd8 2024-12-04T01:21:42,808 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/.tmp/info/4f7462534ace4383b318c337cc222871 as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/info/4f7462534ace4383b318c337cc222871 2024-12-04T01:21:42,817 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/info/4f7462534ace4383b318c337cc222871, entries=10, sequenceid=9, filesize=6.4 K 2024-12-04T01:21:42,820 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/.tmp/table/4fea7695f12e4b348df427e7e5d67cd8 as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/table/4fea7695f12e4b348df427e7e5d67cd8 2024-12-04T01:21:42,827 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/meta/1588230740/table/4fea7695f12e4b348df427e7e5d67cd8, entries=2, sequenceid=9, filesize=5.1 K 2024-12-04T01:21:42,828 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 1000ms, sequenceid=9, compaction requested=false 2024-12-04T01:21:42,829 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 1588230740: 2024-12-04T01:21:43,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:21:48,087 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:21:57,040 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. 2024-12-04T01:22:03,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:22:24,179 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:22:27,041 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. 2024-12-04T01:22:33,087 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:22:44,199 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:22:57,041 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. 2024-12-04T01:23:04,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:23:18,088 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:23:24,429 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:23:27,041 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. 2024-12-04T01:23:44,589 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:23:57,041 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. 2024-12-04T01:23:59,220 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing be568d21e6f4779021608a7d7c9d641c 1/1 column families, dataSize=78 B heapSize=488 B 2024-12-04T01:23:59,245 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c/.tmp/info/11618c4b0a2f4e67bef0ba662322d180 is 45, key is default/info:d/1733274994630/Put/seqid=0 2024-12-04T01:23:59,249 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741839_1015 (size=5037) 2024-12-04T01:23:59,652 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=78 B at sequenceid=6 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c/.tmp/info/11618c4b0a2f4e67bef0ba662322d180 2024-12-04T01:23:59,669 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c/.tmp/info/11618c4b0a2f4e67bef0ba662322d180 as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c/info/11618c4b0a2f4e67bef0ba662322d180 2024-12-04T01:23:59,681 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/data/hbase/namespace/be568d21e6f4779021608a7d7c9d641c/info/11618c4b0a2f4e67bef0ba662322d180, entries=2, sequenceid=6, filesize=4.9 K 2024-12-04T01:23:59,682 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~78 B/78, heapSize ~472 B/472, currentSize=0 B/0 for be568d21e6f4779021608a7d7c9d641c in 462ms, sequenceid=6, compaction requested=false 2024-12-04T01:23:59,682 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for be568d21e6f4779021608a7d7c9d641c: 2024-12-04T01:24:03,089 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:24:04,533 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:24:04,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:24:24,830 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:24:27,042 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. 2024-12-04T01:24:45,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:24:48,089 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:24:49,534 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:24:57,042 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. 2024-12-04T01:25:05,070 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:25:25,099 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:25:27,042 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. 2024-12-04T01:25:33,090 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:25:34,534 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:25:45,280 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:25:57,042 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. 2024-12-04T01:26:05,320 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:26:18,090 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:26:19,535 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:26:25,479 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:26:27,043 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. 2024-12-04T01:26:28,862 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 2024-12-04T01:26:28,966 DEBUG [master/93574c9bec15:0: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% 2024-12-04T01:26:28,967 DEBUG [master/93574c9bec15:0: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 2024-12-04T01:26:31,833 INFO [93574c9bec15:41969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-04T01:26:33,404 DEBUG [hconnection-0x71b91111-shared-pool-6 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:26:33,406 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:43218, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:26:33,425 DEBUG [master/93574c9bec15:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-04T01:26:33,426 DEBUG [master/93574c9bec15:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-04T01:26:34,756 DEBUG [master/93574c9bec15:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-04T01:26:34,756 DEBUG [master/93574c9bec15:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-04T01:26:38,604 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:26:45,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:26:57,043 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. 2024-12-04T01:27:03,091 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:27:04,535 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:27:05,729 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:27:25,800 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:27:27,043 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. 2024-12-04T01:27:45,898 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:27:48,091 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:27:49,535 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:27:57,044 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. 2024-12-04T01:28:06,069 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:28:26,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:28:27,044 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. 2024-12-04T01:28:32,262 INFO [regionserver/93574c9bec15:0.Chore.1 {}] hbase.ScheduledChore(145): Chore: MemstoreFlusherChore missed its start time 2024-12-04T01:28:32,263 INFO [JvmPauseMonitor {}] util.JvmPauseMonitor$Monitor(172): Detected pause in JVM or host machine (eg GC): pause of approximately 4218ms No GCs detected 2024-12-04T01:28:32,267 INFO [regionserver/93574c9bec15:0.Chore.1 {}] hbase.ScheduledChore(145): Chore: CompactionChecker missed its start time 2024-12-04T01:28:33,091 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:28:34,535 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:28:35,996 INFO [regionserver/93574c9bec15:0.Chore.3 {}] hbase.ScheduledChore(145): Chore: CompactionChecker missed its start time 2024-12-04T01:28:35,996 INFO [regionserver/93574c9bec15:0.Chore.2 {}] hbase.ScheduledChore(145): Chore: MemstoreFlusherChore missed its start time 2024-12-04T01:28:46,279 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:28:57,044 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. 2024-12-04T01:29:06,399 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:29:18,092 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:29:19,536 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:29:26,560 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:29:27,045 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. 2024-12-04T01:29:46,759 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:29:57,045 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. 2024-12-04T01:30:03,092 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:30:04,536 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:30:06,939 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:30:27,029 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:30:27,046 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. 2024-12-04T01:30:47,109 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:30:48,093 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:30:49,537 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:30:57,046 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. 2024-12-04T01:31:07,249 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:31:27,047 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. 2024-12-04T01:31:27,320 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:31:28,863 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 2024-12-04T01:31:28,966 DEBUG [master/93574c9bec15:0: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% 2024-12-04T01:31:28,967 DEBUG [master/93574c9bec15:0: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 2024-12-04T01:31:31,131 DEBUG [master:store-WAL-Roller {}] wal.AbstractWALRoller(200): WAL AsyncFSWAL 93574c9bec15%2C43769%2C1733274988003:(num 1733274991041) roll period 900000 ms elapsed 2024-12-04T01:31:31,150 DEBUG [master:store-WAL-Roller {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003/93574c9bec15%2C43769%2C1733274988003.1733275891131, exclude list is [], retry=0 2024-12-04T01:31:31,154 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[127.0.0.1:41679,DS-6f395c98-e2e9-4ed4-958d-1a21efae397b,DISK] 2024-12-04T01:31:31,157 INFO [master:store-WAL-Roller {}] wal.AbstractFSWAL(837): Rolled WAL /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003/93574c9bec15%2C43769%2C1733274988003.1733274991041 with entries=1164, filesize=507.03 KB; new WAL /user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003/93574c9bec15%2C43769%2C1733274988003.1733275891131 2024-12-04T01:31:31,157 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:42895:42895)] 2024-12-04T01:31:31,157 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(751): hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/WALs/93574c9bec15,43769,1733274988003/93574c9bec15%2C43769%2C1733274988003.1733274991041 is not closed yet, will try archiving it next time 2024-12-04T01:31:31,160 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741830_1006 (size=519209) 2024-12-04T01:31:31,272 INFO [master:store-Flusher {}] regionserver.HRegion(2837): Flushing 1595e783b53d99cd5eef43b6debb2682 4/4 column families, dataSize=432.38 KB heapSize=534.71 KB 2024-12-04T01:31:31,286 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/4b27f4a686014d34ab751685b3ff9e6b is 82, key is hbase:meta,,1/info:regioninfo/1733274993127/Put/seqid=0 2024-12-04T01:31:31,291 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741841_1017 (size=5672) 2024-12-04T01:31:31,693 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=504 B at sequenceid=1167 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/4b27f4a686014d34ab751685b3ff9e6b 2024-12-04T01:31:31,727 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/5596105c559a412ca743104d30cbcf0a is 293, key is \x00\x00\x00\x00\x00\x00\x00\x94/proc:d/1733275034671/Put/seqid=0 2024-12-04T01:31:31,731 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741842_1018 (size=11283) 2024-12-04T01:31:31,833 INFO [93574c9bec15:41969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-04T01:31:32,134 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=430.82 KB at sequenceid=1167 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/5596105c559a412ca743104d30cbcf0a 2024-12-04T01:31:32,147 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for 5596105c559a412ca743104d30cbcf0a 2024-12-04T01:31:32,161 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/93ee22445c22428192875f4e5d3366b4 is 69, key is 93574c9bec15,41969,1733274988845/rs:state/1733274991721/Put/seqid=0 2024-12-04T01:31:32,165 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741843_1019 (size=5156) 2024-12-04T01:31:32,567 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=65 B at sequenceid=1167 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/93ee22445c22428192875f4e5d3366b4 2024-12-04T01:31:32,595 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/bbbdbeb50d804b48b0c2c6b902bb2790 is 68, key is replication_peer_modification_on/state:d/1733275030213/Put/seqid=0 2024-12-04T01:31:32,598 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:41679 is added to blk_1073741844_1020 (size=5154) 2024-12-04T01:31:33,001 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1 KB at sequenceid=1167 (bloomFilter=true), to=hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/bbbdbeb50d804b48b0c2c6b902bb2790 2024-12-04T01:31:33,014 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/4b27f4a686014d34ab751685b3ff9e6b as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/4b27f4a686014d34ab751685b3ff9e6b 2024-12-04T01:31:33,020 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/4b27f4a686014d34ab751685b3ff9e6b, entries=8, sequenceid=1167, filesize=5.5 K 2024-12-04T01:31:33,021 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/5596105c559a412ca743104d30cbcf0a as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/5596105c559a412ca743104d30cbcf0a 2024-12-04T01:31:33,027 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for 5596105c559a412ca743104d30cbcf0a 2024-12-04T01:31:33,027 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/5596105c559a412ca743104d30cbcf0a, entries=149, sequenceid=1167, filesize=11.0 K 2024-12-04T01:31:33,028 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/93ee22445c22428192875f4e5d3366b4 as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/93ee22445c22428192875f4e5d3366b4 2024-12-04T01:31:33,035 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/93ee22445c22428192875f4e5d3366b4, entries=1, sequenceid=1167, filesize=5.0 K 2024-12-04T01:31:33,036 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/bbbdbeb50d804b48b0c2c6b902bb2790 as hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/bbbdbeb50d804b48b0c2c6b902bb2790 2024-12-04T01:31:33,043 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/bbbdbeb50d804b48b0c2c6b902bb2790, entries=1, sequenceid=1167, filesize=5.0 K 2024-12-04T01:31:33,044 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 1772ms, sequenceid=1167, compaction requested=false 2024-12-04T01:31:33,044 DEBUG [master:store-Flusher {}] regionserver.HRegion(2538): Flush status journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-04T01:31:33,093 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:31:34,537 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:31:38,101 DEBUG [hconnection-0x71b91111-shared-pool-8 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:31:38,102 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:37310, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:31:38,104 DEBUG [master/93574c9bec15:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-04T01:31:38,104 DEBUG [master/93574c9bec15:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-04T01:31:38,107 DEBUG [master/93574c9bec15:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-04T01:31:38,605 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:31:47,419 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:31:57,047 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. 2024-12-04T01:32:07,560 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:32:18,094 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:32:19,538 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:32:27,047 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. 2024-12-04T01:32:27,639 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:32:47,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:32:57,048 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. 2024-12-04T01:33:03,094 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:33:04,538 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:33:07,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:33:27,048 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. 2024-12-04T01:33:27,990 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:33:48,095 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:33:48,139 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:33:49,539 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:33:57,049 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. 2024-12-04T01:34:08,279 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:34:27,049 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. 2024-12-04T01:34:28,309 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:34:33,095 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:34:34,539 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:34:48,399 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:34:57,049 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. 2024-12-04T01:35:08,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:35:18,096 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:35:19,540 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:35:27,050 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. 2024-12-04T01:35:28,599 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:35:48,639 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:35:57,050 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. 2024-12-04T01:36:03,096 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:36:04,540 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:36:08,809 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:36:27,051 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. 2024-12-04T01:36:28,863 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 2024-12-04T01:36:28,966 DEBUG [master/93574c9bec15:0: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% 2024-12-04T01:36:28,967 DEBUG [master/93574c9bec15:0: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 2024-12-04T01:36:28,979 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:36:31,833 INFO [93574c9bec15:41969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-04T01:36:34,752 DEBUG [master/93574c9bec15:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-04T01:36:34,752 DEBUG [master/93574c9bec15:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-04T01:36:34,755 DEBUG [master/93574c9bec15:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-04T01:36:34,762 DEBUG [hconnection-0x71b91111-shared-pool-10 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:36:34,763 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:41828, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:36:34,768 DEBUG [master/93574c9bec15:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-04T01:36:38,606 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:36:48,097 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:36:48,990 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:36:49,541 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:36:57,051 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. 2024-12-04T01:37:09,159 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:37:27,052 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. 2024-12-04T01:37:29,189 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:37:33,098 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:37:34,541 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:37:49,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:37:57,052 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. 2024-12-04T01:38:09,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:38:18,098 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:38:19,542 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:38:27,052 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. 2024-12-04T01:38:29,459 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:38:49,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:38:57,053 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. 2024-12-04T01:39:03,099 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:39:04,542 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:39:09,719 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:39:27,053 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. 2024-12-04T01:39:29,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:39:48,099 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:39:49,543 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:39:49,930 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:39:57,054 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. 2024-12-04T01:40:09,979 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:40:27,054 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. 2024-12-04T01:40:30,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:40:33,100 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:40:34,543 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:40:50,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:40:57,055 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. 2024-12-04T01:41:10,219 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:41:18,100 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:41:19,544 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:41:27,055 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. 2024-12-04T01:41:28,863 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 2024-12-04T01:41:28,966 DEBUG [master/93574c9bec15:0: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% 2024-12-04T01:41:28,967 DEBUG [master/93574c9bec15:0: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 2024-12-04T01:41:30,249 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:41:31,833 INFO [93574c9bec15:41969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-04T01:41:33,265 DEBUG [master/93574c9bec15:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-04T01:41:33,265 DEBUG [master/93574c9bec15:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-04T01:41:33,266 DEBUG [hconnection-0x71b91111-shared-pool-12 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-04T01:41:33,267 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:41760, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-04T01:41:33,273 DEBUG [master/93574c9bec15:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-04T01:41:38,607 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-04T01:41:50,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-04T01:41:57,055 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. 2024-12-04T01:42:03,101 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-04T01:42:04,544 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region be568d21e6f4779021608a7d7c9d641c, had cached 0 bytes from a total of 5037 2024-12-04T01:42:10,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 ====> TEST TIMED OUT. PRINTING THREAD DUMP. <==== Timestamp: 2024-12-04 01:42:23,749 "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) "BootstrapNodeManager" daemon prio=5 tid=257 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Signal Dispatcher" daemon prio=9 tid=4 runnable java.lang.Thread.State: RUNNABLE "qtp1312628392-40" 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$257/0x00007f21cc423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "OldWALsCleaner-0" daemon prio=5 tid=259 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$599/0x00007f21cca78ba0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "DataXceiver for client DFSClient_NONMAPREDUCE_1067618141_22 at /127.0.0.1:49790 [Receiving block BP-304627035-172.17.0.2-1733274984478:blk_1073741840_1016]" daemon prio=5 tid=893 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) "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) "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) "IPC Server listener on 0" daemon prio=5 tid=54 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener.run(Server.java:1559) "Async-Client-Retry-Timer-pool-0" daemon prio=5 tid=319 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=43769" 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) "qtp764466342-88-acceptor-0@73194d7e-ServerConnector@2117487{HTTP/1.1, (http/1.1)}{localhost:40595}" 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) "RS:0;93574c9bec15:41969" 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) "AsyncFSWAL-0-hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49-prefix:93574c9bec15,41969,1733274988845.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) "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) "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) "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) "qtp1312628392-37" 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$257/0x00007f21cc423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/93574c9bec15:0.Chore.2" daemon prio=5 tid=867 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$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1177) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Finalizer" daemon prio=8 tid=3 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:176) at java.base@17.0.11/java.lang.ref.Finalizer$FinalizerThread.run(Finalizer.java:172) "IPC Server idle connection scanner for port 36667" 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) "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) "RS-EventLoopGroup-1-2" daemon prio=10 tid=258 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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 3 on default port 44411" daemon prio=5 tid=107 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Handler.run(Server.java:3165) "regionserver/93574c9bec15:0.leaseChecker" daemon prio=5 tid=274 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.regionserver.LeaseManager.run(LeaseManager.java:82) "master:store-Flusher" daemon prio=5 tid=240 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$481/0x00007f21cc9be2f8.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=41969" 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) "Timer for 'HBase' metrics system" daemon prio=5 tid=1015 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-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) "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) "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) "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) "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) "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) "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) "qtp1312628392-39" 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$257/0x00007f21cc423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "93574c9bec15:43769" 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$1.run(AssignmentManager.java:2332) "RS_COMPACTED_FILES_DISCHARGER-regionserver/93574c9bec15:0-0" daemon prio=5 tid=757 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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) "RS:0;93574c9bec15:41969-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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "JvmPauseMonitor" daemon prio=5 tid=271 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:148) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:53444)" 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$SendThread.run(ClientCnxn.java:1289) "Session-HouseKeeper-67bf5572-1" prio=5 tid=45 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.namenode.LeaseManager$Monitor@6132670e" 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$Monitor.run(LeaseManager.java:537) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-41-acceptor-0@2c832907-ServerConnector@1f7e2804{HTTP/1.1, (http/1.1)}{localhost:33597}" daemon prio=3 tid=41 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at app//org.eclipse.jetty.server.ServerConnector.accept(ServerConnector.java:388) at app//org.eclipse.jetty.server.AbstractConnector$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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "zk-event-processor-pool-0" daemon prio=5 tid=405 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "CacheReplicationMonitor(742816305)" 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$ConditionObject.await(AbstractQueuedSynchronizer.java:1759) at app//org.apache.hadoop.hdfs.server.blockmanagement.CacheReplicationMonitor.run(CacheReplicationMonitor.java:186) "process reaper" daemon prio=10 tid=1009 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.SynchronousQueue$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "SnapshotHandlerChoreCleaner" daemon prio=5 tid=253 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Notification Thread" daemon prio=9 tid=13 runnable java.lang.Thread.State: RUNNABLE "PEWorker-5" daemon prio=5 tid=249 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$WorkerThread.run(ProcedureExecutor.java:2128) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=41969" daemon prio=5 tid=204 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "93574c9bec15:41969Replication Statistics #0" daemon prio=5 tid=279 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:53444)" daemon prio=5 tid=403 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/dfs/data/data1/current/BP-304627035-172.17.0.2-1733274984478" daemon prio=5 tid=124 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "org.apache.hadoop.hdfs.server.datanode.DataXceiverServer@6a67db2f" daemon prio=5 tid=85 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.Net.accept(Native Method) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.implAccept(ServerSocketChannelImpl.java:425) at java.base@17.0.11/sun.nio.ch.ServerSocketChannelImpl.accept(ServerSocketChannelImpl.java:391) at java.base@17.0.11/sun.nio.ch.ServerSocketAdaptor.accept(ServerSocketAdaptor.java:126) at app//org.apache.hadoop.hdfs.net.TcpPeerServer.accept(TcpPeerServer.java:85) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiverServer.run(DataXceiverServer.java:242) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test.named-queue-events-pool-0" daemon prio=5 tid=152 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//com.lmax.disruptor.BlockingWaitStrategy.waitFor(BlockingWaitStrategy.java:47) at app//com.lmax.disruptor.ProcessingSequenceBarrier.waitFor(ProcessingSequenceBarrier.java:56) at app//com.lmax.disruptor.BatchEventProcessor.processEvents(BatchEventProcessor.java:159) at app//com.lmax.disruptor.BatchEventProcessor.run(BatchEventProcessor.java:125) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=41969" daemon prio=5 tid=202 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "ProcessThread(sid:0 cport:53444):" daemon prio=5 tid=143 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.PrepRequestProcessor.run(PrepRequestProcessor.java:142) "org.apache.hadoop.hdfs.server.blockmanagement.PendingReconstructionBlocks$PendingReconstructionMonitor@5ec1d4f9" 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$PendingReconstructionMonitor.run(PendingReconstructionBlocks.java:267) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-0" daemon prio=5 tid=317 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1170) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=41969" 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) "master/93574c9bec15:0:becomeActiveMaster-MemStoreChunkPool Statistics" daemon prio=5 tid=211 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "AsyncFSWAL-0-hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49/MasterData-prefix:93574c9bec15,43769,1733274988003" daemon prio=5 tid=237 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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 handler 1 on default port 44411" 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) "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) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=43769" 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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RequestThrottler" daemon prio=5 tid=144 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.server.RequestThrottler.run(RequestThrottler.java:147) "DatanodeAdminMonitor-0" daemon prio=5 tid=62 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "LruBlockCacheStatsExecutor" daemon prio=5 tid=189 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-38" daemon prio=5 tid=38 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.eclipse.jetty.io.ManagedSelector.nioSelect(ManagedSelector.java:183) at app//org.eclipse.jetty.io.ManagedSelector.select(ManagedSelector.java:190) at app//org.eclipse.jetty.io.ManagedSelector$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$257/0x00007f21cc423440.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) "Time-limited test-SendThread(127.0.0.1:53444)" 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) "master/93574c9bec15:0:becomeActiveMaster-HFileCleaner.large.0-1733274991708" daemon prio=5 tid=266 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at app//org.apache.hadoop.hbase.util.StealJobQueue.take(StealJobQueue.java:101) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner.consumerLoop(HFileCleaner.java:285) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner$1.run(HFileCleaner.java:254) "IPC Server 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) "java.util.concurrent.ThreadPoolExecutor$Worker@618d4c9c[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) "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) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeResourceMonitor@6b49abe4" 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) "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) "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) "DataXceiver for client DFSClient_NONMAPREDUCE_715328100_22 at /127.0.0.1:49248 [Receiving block BP-304627035-172.17.0.2-1733274984478: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) "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) "master/93574c9bec15:0:becomeActiveMaster-HFileCleaner.small.0-1733274991709" daemon prio=5 tid=267 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) "regionserver/93574c9bec15:0.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) "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) "IPC Server handler 1 on default port 36667" 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) "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.replication.FPBQ.Fifo.handler=2,queue=0,port=43769" 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) "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) "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) "HBase-Metrics2-1" daemon prio=5 tid=153 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-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) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$LazyPersistFileScrubber@262e079b" daemon prio=5 tid=74 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.namenode.FSNamesystem$LazyPersistFileScrubber.run(FSNamesystem.java:4689) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=43769" 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) "IPC Server handler 3 on default port 36667" 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) "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) "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) "regionserver/93574c9bec15:0.Chore.1" daemon prio=5 tid=273 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:1177) 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-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) "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) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/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) "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) "IPC Server handler 2 on default port 36667" 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) "qtp1312628392-42" 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) "DataXceiver for client DFSClient_NONMAPREDUCE_715328100_22 at /127.0.0.1:49238 [Receiving block BP-304627035-172.17.0.2-1733274984478: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) "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) "IPC Server idle connection scanner for port 44411" 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) "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.replication.FPBQ.Fifo.handler=1,queue=0,port=43769" 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) "AsyncFSWAL-0-hdfs://localhost:36667/user/jenkins/test-data/9c22928e-333a-243a-4a93-cb42bb014b49-prefix:93574c9bec15,41969,1733274988845" 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) "Session-HouseKeeper-10572911-1" 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) "org.apache.hadoop.hdfs.PeerCache@1fae211a" 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) "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) "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) "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) "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) "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) "IPC Parameter Sending Thread for localhost/127.0.0.1:36667" 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) "BP-304627035-172.17.0.2-1733274984478 heartbeating to localhost/127.0.0.1:36667" 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) "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) "qtp764466342-89" 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) "org.apache.hadoop.hdfs.server.namenode.FSNamesystem$NameNodeEditLogRoller@7a30b880" 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.priority.RWQ.Fifo.read.handler=1,queue=1,port=41969" 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) "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) "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) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=41969" 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) "IPC Client (1688336191) connection to localhost/127.0.0.1:36667 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) "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) "regionserver/93574c9bec15:0.Chore.3" daemon prio=5 tid=868 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_OPEN_META-regionserver/93574c9bec15:0-0" 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) "RS_OPEN_PRIORITY_REGION-regionserver/93574c9bec15:0-0" 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) "IPC Server handler 0 on default port 36667" 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) "qtp764466342-90" 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) "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) "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) "regionserver/93574c9bec15:0.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) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=41969" 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) "IPC Server handler 4 on default port 44411" 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) "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) "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) "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) "master/93574c9bec15:0: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) "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) "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) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/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) "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) "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-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) "PacketResponder: BP-304627035-172.17.0.2-1733274984478: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) "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) "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) "RS_REFRESH_PEER-regionserver/93574c9bec15:0-0" 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) "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) "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) "ReadOnlyZKClient-127.0.0.1:53444@0x53d9c032" 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$760/0x00007f21ccb4ad80.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Socket Reader #1 for port 0" daemon prio=5 tid=95 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener$Reader.doRunLoop(Server.java:1497) at app//org.apache.hadoop.ipc.Server$Listener$Reader.run(Server.java:1476) "PEWorker-1" daemon prio=5 tid=245 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$WorkerThread.run(ProcedureExecutor.java:2128) "PacketResponder: BP-304627035-172.17.0.2-1733274984478:blk_1073741832_1008, type=LAST_IN_PIPELINE" daemon prio=5 tid=282 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@43516cc3" 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$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1312628392-43" daemon prio=5 tid=43 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "IPC Server handler 4 on default port 36667" 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) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=43769" 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.util.JvmPauseMonitor$Monitor@7eb48b85" daemon prio=5 tid=34 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 2 on default port 44411" 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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=43769" daemon prio=5 tid=182 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=43769" daemon prio=5 tid=173 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "org.apache.hadoop.fs.FileSystem$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$StatisticsDataReferenceCleaner.run(FileSystem.java:4171) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "snapshot-hfile-cleaner-cache-refresher" daemon prio=5 tid=265 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/67e6b85d-744f-21fa-784a-4314a237cc48/cluster_2d5ed32e-3254-093a-fed2-50edae6350cf/dfs/data/data2/current/BP-304627035-172.17.0.2-1733274984478" daemon prio=5 tid=123 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor@b364b1a" daemon prio=5 tid=49 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.server.blockmanagement.HeartbeatManager$Monitor.run(HeartbeatManager.java:563) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "master/93574c9bec15:0.Chore.1" daemon prio=5 tid=261 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) "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) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=41969" 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) "LeaseRenewer:jenkins.hfs.0@localhost:36667" 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$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Common-Cleaner" daemon prio=8 tid=12 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.ref.ReferenceQueue.remove(ReferenceQueue.java:155) at java.base@17.0.11/jdk.internal.ref.CleanerImpl.run(CleanerImpl.java:140) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) at java.base@17.0.11/jdk.internal.misc.InnocuousThread.run(InnocuousThread.java:162) "NIOWorkerThread-5" daemon prio=5 tid=161 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=41969" 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) "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$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.DelayQueue.poll(DelayQueue.java:279) at app//org.apache.hadoop.hbase.procedure2.util.DelayedUtil.takeWithoutInterrupt(DelayedUtil.java:81) at app//org.apache.hadoop.hbase.procedure2.TimeoutExecutorThread.run(TimeoutExecutorThread.java:56) "MobFileCache #0" daemon prio=5 tid=191 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "M:0;93574c9bec15:43769" 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) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=41969" 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) "qtp764466342-87" 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$257/0x00007f21cc423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-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) "qtp1312628392-44" 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) "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) "LeaseRenewer:jenkins@localhost:36667" 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) "NIOServerCxnFactory.AcceptThread:localhost/127.0.0.1:53444" 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) "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-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) "RpcClient-timer-pool-0" daemon prio=5 tid=241 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.waitForNextTick(HashedWheelTimer.java:598) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$Worker.run(HashedWheelTimer.java:494) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-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) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=43769" 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) "IPC Server Responder" daemon prio=5 tid=97 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.ipc.Server$Responder.doRunLoop(Server.java:1733) at app//org.apache.hadoop.ipc.Server$Responder.run(Server.java:1716) "ReadOnlyZKClient-127.0.0.1:53444@0x502fe4e9" 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$760/0x00007f21ccb4ad80.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PacketResponder: BP-304627035-172.17.0.2-1733274984478:blk_1073741840_1016, type=LAST_IN_PIPELINE" daemon prio=5 tid=894 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.lang.Object.wait(Object.java:338) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.waitForAckHead(BlockReceiver.java:1367) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver$PacketResponder.run(BlockReceiver.java:1439) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=43769" daemon prio=5 tid=175 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "IPC Server handler 0 on default port 44411" daemon prio=5 tid=104 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Handler.run(Server.java:3165) "RedundancyMonitor" daemon prio=5 tid=47 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at java.base@17.0.11/java.lang.Thread.sleep(Thread.java:344) at java.base@17.0.11/java.util.concurrent.TimeUnit.sleep(TimeUnit.java:446) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$RedundancyMonitor.run(BlockManager.java:5352) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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)