2024-12-03 07:13:58,603 main DEBUG Apache Log4j Core 2.17.2 initializing configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-12-03 07:13:58,617 main DEBUG Took 0.011900 seconds to load 1 plugins from package org.apache.hadoop.hbase.logging 2024-12-03 07:13:58,617 main DEBUG PluginManager 'Core' found 129 plugins 2024-12-03 07:13:58,617 main DEBUG PluginManager 'Level' found 0 plugins 2024-12-03 07:13:58,619 main DEBUG PluginManager 'Lookup' found 16 plugins 2024-12-03 07:13:58,620 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,633 main DEBUG PluginManager 'TypeConverter' found 26 plugins 2024-12-03 07:13:58,644 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.util.MBeans", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,647 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,647 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.logging.TestJul2Slf4j", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,648 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,648 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.zookeeper", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,649 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,650 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSinkAdapter", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,651 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,651 main DEBUG LoggerConfig$Builder(additivity="null", level="ERROR", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsSystemImpl", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,652 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,653 main DEBUG LoggerConfig$Builder(additivity="false", level="WARN", levelAndRefs="null", name="org.apache.directory", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,653 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,654 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.ipc.FailedServers", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,654 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,655 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop.metrics2.impl.MetricsConfig", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,655 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,656 main DEBUG LoggerConfig$Builder(additivity="null", level="INFO", levelAndRefs="null", name="org.apache.hadoop.hbase.ScheduledChore", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,656 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,657 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase.regionserver.RSRpcServices", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,657 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,657 main DEBUG LoggerConfig$Builder(additivity="null", level="WARN", levelAndRefs="null", name="org.apache.hadoop", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,658 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,658 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hadoop.hbase", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,659 main DEBUG Building Plugin[name=logger, class=org.apache.logging.log4j.core.config.LoggerConfig]. 2024-12-03 07:13:58,659 main DEBUG LoggerConfig$Builder(additivity="null", level="DEBUG", levelAndRefs="null", name="org.apache.hbase.thirdparty.io.netty.channel", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,660 main DEBUG Building Plugin[name=root, class=org.apache.logging.log4j.core.config.LoggerConfig$RootLogger]. 2024-12-03 07:13:58,662 main DEBUG LoggerConfig$RootLogger$Builder(additivity="null", level="null", levelAndRefs="INFO,Console", includeLocation="null", ={}, ={}, Configuration(PropertiesConfig), Filter=null) 2024-12-03 07:13:58,663 main DEBUG Building Plugin[name=loggers, class=org.apache.logging.log4j.core.config.LoggersPlugin]. 2024-12-03 07:13:58,665 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}) 2024-12-03 07:13:58,666 main DEBUG Building Plugin[name=layout, class=org.apache.logging.log4j.core.layout.PatternLayout]. 2024-12-03 07:13:58,668 main DEBUG PatternLayout$Builder(pattern="%d{ISO8601} %-5p [%t%notEmpty{ %X}] %C{2}(%L): %m%n", PatternSelector=null, Configuration(PropertiesConfig), Replace=null, charset="null", alwaysWriteExceptions="null", disableAnsi="null", noConsoleNoAnsi="null", header="null", footer="null") 2024-12-03 07:13:58,668 main DEBUG PluginManager 'Converter' found 47 plugins 2024-12-03 07:13:58,679 main DEBUG Building Plugin[name=appender, class=org.apache.hadoop.hbase.logging.HBaseTestAppender]. 2024-12-03 07:13:58,682 main DEBUG HBaseTestAppender$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, ={}) 2024-12-03 07:13:58,684 main DEBUG Starting HBaseTestOutputStreamManager SYSTEM_ERR 2024-12-03 07:13:58,684 main DEBUG Building Plugin[name=appenders, class=org.apache.logging.log4j.core.config.AppendersPlugin]. 2024-12-03 07:13:58,685 main DEBUG createAppenders(={Console}) 2024-12-03 07:13:58,686 main DEBUG Configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f initialized 2024-12-03 07:13:58,686 main DEBUG Starting configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f 2024-12-03 07:13:58,686 main DEBUG Started configuration org.apache.logging.log4j.core.config.properties.PropertiesConfiguration@302c971f OK. 2024-12-03 07:13:58,687 main DEBUG Shutting down OutputStreamManager SYSTEM_OUT.false.false-1 2024-12-03 07:13:58,687 main DEBUG OutputStream closed 2024-12-03 07:13:58,688 main DEBUG Shut down OutputStreamManager SYSTEM_OUT.false.false-1, all resources released: true 2024-12-03 07:13:58,688 main DEBUG Appender DefaultConsole-1 stopped with status true 2024-12-03 07:13:58,688 main DEBUG Stopped org.apache.logging.log4j.core.config.DefaultConfiguration@505fc5a4 OK 2024-12-03 07:13:58,769 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6 2024-12-03 07:13:58,771 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=StatusLogger 2024-12-03 07:13:58,772 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=ContextSelector 2024-12-03 07:13:58,774 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name= 2024-12-03 07:13:58,774 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.directory 2024-12-03 07:13:58,775 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSinkAdapter 2024-12-03 07:13:58,775 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.zookeeper 2024-12-03 07:13:58,776 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.logging.TestJul2Slf4j 2024-12-03 07:13:58,776 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsSystemImpl 2024-12-03 07:13:58,776 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.util.MBeans 2024-12-03 07:13:58,777 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase 2024-12-03 07:13:58,777 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop 2024-12-03 07:13:58,778 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ipc.FailedServers 2024-12-03 07:13:58,778 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.regionserver.RSRpcServices 2024-12-03 07:13:58,778 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.metrics2.impl.MetricsConfig 2024-12-03 07:13:58,779 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hbase.thirdparty.io.netty.channel 2024-12-03 07:13:58,779 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Loggers,name=org.apache.hadoop.hbase.ScheduledChore 2024-12-03 07:13:58,780 main DEBUG Registering MBean org.apache.logging.log4j2:type=1dbd16a6,component=Appenders,name=Console 2024-12-03 07:13:58,781 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-03 07:13:58,782 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 2024-12-03 07:13:58,782 main DEBUG Shutdown hook enabled. Registering a new one. 2024-12-03 07:13:58,783 main DEBUG LoggerContext[name=1dbd16a6, org.apache.logging.log4j.core.LoggerContext@39de3d36] started OK. 2024-12-03T07:13:59,003 DEBUG [main {}] hbase.HBaseTestingUtility(348): Setting hbase.rootdir to /home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690 2024-12-03 07:13:59,006 main DEBUG AsyncLogger.ThreadNameStrategy=UNCACHED (user specified null, default is UNCACHED) 2024-12-03 07:13:59,006 main DEBUG org.apache.logging.log4j.core.util.SystemClock supports precise timestamps. 2024-12-03T07:13:59,028 INFO [main {}] hbase.HBaseClassTestRule(94): Test class org.apache.hadoop.hbase.client.TestAsyncReplicationAdminApi timeout: 26 mins 2024-12-03T07:13:59,044 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} 2024-12-03T07:13:59,047 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/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be, deleteOnExit=true 2024-12-03T07:13:59,047 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1140): STARTING DFS 2024-12-03T07:13:59,048 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/bac87dcc-072f-16ff-6ef9-e99e34745690/test.cache.data in system properties and HBase conf 2024-12-03T07:13:59,048 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/bac87dcc-072f-16ff-6ef9-e99e34745690/hadoop.tmp.dir in system properties and HBase conf 2024-12-03T07:13:59,049 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/bac87dcc-072f-16ff-6ef9-e99e34745690/hadoop.log.dir in system properties and HBase conf 2024-12-03T07:13:59,049 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/bac87dcc-072f-16ff-6ef9-e99e34745690/mapreduce.cluster.local.dir in system properties and HBase conf 2024-12-03T07:13:59,049 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/bac87dcc-072f-16ff-6ef9-e99e34745690/mapreduce.cluster.temp.dir in system properties and HBase conf 2024-12-03T07:13:59,050 INFO [Time-limited test {}] hbase.HBaseTestingUtility(811): read short circuit is OFF 2024-12-03T07:13:59,131 WARN [Time-limited test {}] util.NativeCodeLoader(60): Unable to load native-hadoop library for your platform... using builtin-java classes where applicable 2024-12-03T07:13:59,214 DEBUG [Time-limited test {}] fs.HFileSystem(310): The file system is not a DistributedFileSystem. Skipping on block location reordering 2024-12-03T07:13:59,217 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.node-labels.fs-store.root-dir in system properties and HBase conf 2024-12-03T07:13:59,217 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.node-attribute.fs-store.root-dir in system properties and HBase conf 2024-12-03T07:13:59,218 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.nodemanager.log-dirs in system properties and HBase conf 2024-12-03T07:13:59,218 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-03T07:13:59,219 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.timeline-service.entity-group-fs-store.active-dir in system properties and HBase conf 2024-12-03T07:13:59,219 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.timeline-service.entity-group-fs-store.done-dir in system properties and HBase conf 2024-12-03T07:13:59,220 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/bac87dcc-072f-16ff-6ef9-e99e34745690/yarn.nodemanager.remote-app-log-dir in system properties and HBase conf 2024-12-03T07:13:59,220 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/bac87dcc-072f-16ff-6ef9-e99e34745690/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-03T07:13:59,220 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/bac87dcc-072f-16ff-6ef9-e99e34745690/dfs.datanode.shared.file.descriptor.paths in system properties and HBase conf 2024-12-03T07:13:59,221 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/bac87dcc-072f-16ff-6ef9-e99e34745690/nfs.dump.dir in system properties and HBase conf 2024-12-03T07:13:59,221 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/bac87dcc-072f-16ff-6ef9-e99e34745690/java.io.tmpdir in system properties and HBase conf 2024-12-03T07:13:59,221 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/bac87dcc-072f-16ff-6ef9-e99e34745690/dfs.journalnode.edits.dir in system properties and HBase conf 2024-12-03T07:13:59,222 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/bac87dcc-072f-16ff-6ef9-e99e34745690/dfs.provided.aliasmap.inmemory.leveldb.dir in system properties and HBase conf 2024-12-03T07:13:59,222 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/bac87dcc-072f-16ff-6ef9-e99e34745690/fs.s3a.committer.staging.tmp.path in system properties and HBase conf 2024-12-03T07:14:00,152 WARN [Time-limited test {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-namenode.properties,hadoop-metrics2.properties 2024-12-03T07:14:00,219 INFO [Time-limited test {}] log.Log(170): Logging initialized @2252ms to org.eclipse.jetty.util.log.Slf4jLog 2024-12-03T07:14:00,285 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 2024-12-03T07:14:00,339 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 2024-12-03T07:14:00,356 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-03T07:14:00,356 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-03T07:14:00,357 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 600000ms 2024-12-03T07:14:00,369 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 2024-12-03T07:14:00,372 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/bac87dcc-072f-16ff-6ef9-e99e34745690/hadoop.log.dir/,AVAILABLE} 2024-12-03T07:14:00,372 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} 2024-12-03T07:14:00,532 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/bac87dcc-072f-16ff-6ef9-e99e34745690/java.io.tmpdir/jetty-localhost-34019-hadoop-hdfs-3_4_1-tests_jar-_-any-526449124309096038/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} 2024-12-03T07:14:00,541 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@1f7e2804{HTTP/1.1, (http/1.1)}{localhost:34019} 2024-12-03T07:14:00,541 INFO [Time-limited test {}] server.Server(415): Started @2575ms 2024-12-03T07:14:01,029 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 2024-12-03T07:14:01,035 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 2024-12-03T07:14:01,036 INFO [Time-limited test {}] session.DefaultSessionIdManager(334): DefaultSessionIdManager workerName=node0 2024-12-03T07:14:01,036 INFO [Time-limited test {}] session.DefaultSessionIdManager(339): No SessionScavenger set, using defaults 2024-12-03T07:14:01,036 INFO [Time-limited test {}] session.HouseKeeper(132): node0 Scavenging every 660000ms 2024-12-03T07:14:01,037 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@5854846b{logs,/logs,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/hadoop.log.dir/,AVAILABLE} 2024-12-03T07:14:01,038 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.s.ServletContextHandler@1a2745b0{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} 2024-12-03T07:14:01,132 INFO [Time-limited test {}] handler.ContextHandler(921): Started o.e.j.w.WebAppContext@7d75efc4{datanode,/,file:///home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/java.io.tmpdir/jetty-localhost-39893-hadoop-hdfs-3_4_1-tests_jar-_-any-17690743788888216524/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} 2024-12-03T07:14:01,132 INFO [Time-limited test {}] server.AbstractConnector(333): Started ServerConnector@723ec49{HTTP/1.1, (http/1.1)}{localhost:39893} 2024-12-03T07:14:01,133 INFO [Time-limited test {}] server.Server(415): Started @3167ms 2024-12-03T07:14:01,177 WARN [Time-limited test {}] web.RestCsrfPreventionFilterHandler(75): Got null for restCsrfPreventionFilter - will not do any filtering. 2024-12-03T07:14:01,915 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/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/dfs/data/data1/current/BP-838497965-172.17.0.2-1733210039745/current, will proceed with Du for space computation calculation, 2024-12-03T07:14:01,915 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/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/dfs/data/data2/current/BP-838497965-172.17.0.2-1733210039745/current, will proceed with Du for space computation calculation, 2024-12-03T07:14:01,941 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 2024-12-03T07:14:01,980 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x54d36e28947f4540 with lease ID 0x464fd097fd2887dd: Processing first storage report for DS-4254b93d-839f-4f3c-87c5-b90d28d39653 from datanode DatanodeRegistration(127.0.0.1:38883, datanodeUuid=3ff89783-7d52-424a-af20-ffe50aa4cc47, infoPort=37873, infoSecurePort=0, ipcPort=32817, storageInfo=lv=-57;cid=testClusterID;nsid=1893677559;c=1733210039745) 2024-12-03T07:14:01,982 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x54d36e28947f4540 with lease ID 0x464fd097fd2887dd: from storage DS-4254b93d-839f-4f3c-87c5-b90d28d39653 node DatanodeRegistration(127.0.0.1:38883, datanodeUuid=3ff89783-7d52-424a-af20-ffe50aa4cc47, infoPort=37873, infoSecurePort=0, ipcPort=32817, storageInfo=lv=-57;cid=testClusterID;nsid=1893677559;c=1733210039745), blocks: 0, hasStaleStorage: true, processing time: 1 msecs, invalidatedBlocks: 0 2024-12-03T07:14:01,982 INFO [Block report processor {}] blockmanagement.BlockManager(2940): BLOCK* processReport 0x54d36e28947f4540 with lease ID 0x464fd097fd2887dd: Processing first storage report for DS-bca64946-31da-490c-8f67-708f5b75c2f1 from datanode DatanodeRegistration(127.0.0.1:38883, datanodeUuid=3ff89783-7d52-424a-af20-ffe50aa4cc47, infoPort=37873, infoSecurePort=0, ipcPort=32817, storageInfo=lv=-57;cid=testClusterID;nsid=1893677559;c=1733210039745) 2024-12-03T07:14:01,982 INFO [Block report processor {}] blockmanagement.BlockManager(2972): BLOCK* processReport 0x54d36e28947f4540 with lease ID 0x464fd097fd2887dd: from storage DS-bca64946-31da-490c-8f67-708f5b75c2f1 node DatanodeRegistration(127.0.0.1:38883, datanodeUuid=3ff89783-7d52-424a-af20-ffe50aa4cc47, infoPort=37873, infoSecurePort=0, ipcPort=32817, storageInfo=lv=-57;cid=testClusterID;nsid=1893677559;c=1733210039745), blocks: 0, hasStaleStorage: false, processing time: 0 msecs, invalidatedBlocks: 0 2024-12-03T07:14:02,032 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/bac87dcc-072f-16ff-6ef9-e99e34745690 2024-12-03T07:14:02,093 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/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/zookeeper_0, clientPort=55234, secureClientPort=-1, dataDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/zookeeper_0/version-2, dataDirSize=457 dataLogDir=/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/zookeeper_0/version-2, dataLogSize=457 tickTime=2000, maxClientCnxns=300, minSessionTimeout=4000, maxSessionTimeout=40000, clientPortListenBacklog=-1, serverId=0 2024-12-03T07:14:02,102 INFO [Time-limited test {}] zookeeper.MiniZooKeeperCluster(284): Started MiniZooKeeperCluster and ran 'stat' on client port=55234 2024-12-03T07:14:02,112 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$ReorderWALBlocks 2024-12-03T07:14:02,115 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-03T07:14:02,310 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741825_1001 (size=7) 2024-12-03T07:14:02,723 INFO [Time-limited test {}] util.FSUtils(490): Created version file at hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a with version=8 2024-12-03T07:14:02,723 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1460): Setting hbase.fs.tmp.dir to hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/hbase-staging 2024-12-03T07:14:02,821 DEBUG [Time-limited test {}] channel.MultithreadEventLoopGroup(44): -Dio.netty.eventLoopThreads: 16 2024-12-03T07:14:03,049 INFO [Time-limited test {}] client.ConnectionUtils(129): master/8046980647f4:0 server-side Connection retries=6 2024-12-03T07:14:03,063 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-03T07:14:03,063 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-03T07:14:03,064 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-03T07:14:03,064 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-03T07:14:03,064 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-03T07:14:03,170 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 2024-12-03T07:14:03,218 INFO [Time-limited test {}] metrics.MetricRegistriesLoader(60): Loaded MetricRegistries class org.apache.hadoop.hbase.metrics.impl.MetricRegistriesImpl 2024-12-03T07:14:03,227 DEBUG [Time-limited test {}] util.ClassSize(228): Using Unsafe to estimate memory layout 2024-12-03T07:14:03,230 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-03T07:14:03,252 DEBUG [Time-limited test {}] channel.DefaultChannelId(84): -Dio.netty.processId: 28791 (auto-detected) 2024-12-03T07:14:03,253 DEBUG [Time-limited test {}] channel.DefaultChannelId(106): -Dio.netty.machineId: 02:42:ac:ff:fe:11:00:02 (auto-detected) 2024-12-03T07:14:03,271 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:33011 2024-12-03T07:14:03,279 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$ReorderWALBlocks 2024-12-03T07:14:03,281 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-03T07:14:03,293 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=master:33011 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:03,397 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:330110x0, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:03,401 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): master:33011-0x1019b5411520000 connected 2024-12-03T07:14:03,476 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-03T07:14:03,483 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-03T07:14:03,488 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-03T07:14:03,492 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=33011 2024-12-03T07:14:03,492 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=33011 2024-12-03T07:14:03,492 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=33011 2024-12-03T07:14:03,493 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=33011 2024-12-03T07:14:03,493 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=33011 2024-12-03T07:14:03,499 INFO [Time-limited test {}] master.HMaster(488): hbase.rootdir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a, hbase.cluster.distributed=false 2024-12-03T07:14:03,548 INFO [Time-limited test {}] client.ConnectionUtils(129): regionserver/8046980647f4:0 server-side Connection retries=6 2024-12-03T07:14:03,549 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated default.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-03T07:14:03,549 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated priority.RWQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=2, maxQueueLength=30, handlerCount=3 2024-12-03T07:14:03,549 INFO [Time-limited test {}] ipc.RWQueueRpcExecutor(113): priority.RWQ.Fifo writeQueues=1 writeHandlers=1 readQueues=1 readHandlers=2 scanQueues=0 scanHandlers=0 2024-12-03T07:14:03,549 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated replication.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=3 2024-12-03T07:14:03,549 INFO [Time-limited test {}] ipc.RpcExecutor(188): Instantiated metaPriority.FPBQ.Fifo with queueClass=class java.util.concurrent.LinkedBlockingQueue; numCallQueues=1, maxQueueLength=30, handlerCount=1 2024-12-03T07:14:03,551 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 2024-12-03T07:14:03,552 INFO [Time-limited test {}] ipc.NettyRpcServer(315): Using org.apache.hbase.thirdparty.io.netty.buffer.PooledByteBufAllocator for buffer allocation 2024-12-03T07:14:03,553 INFO [Time-limited test {}] ipc.NettyRpcServer(197): Bind to /172.17.0.2:39969 2024-12-03T07:14:03,555 INFO [Time-limited test {}] hfile.BlockCacheFactory(123): Allocating BlockCache size=880 MB, blockSize=64 KB 2024-12-03T07:14:03,559 DEBUG [Time-limited test {}] mob.MobFileCache(124): MobFileCache enabled with cacheSize=1000, evictPeriods=3600sec, evictRemainRatio=0.5 2024-12-03T07:14:03,560 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$ReorderWALBlocks 2024-12-03T07:14:03,562 INFO [Time-limited test {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-03T07:14:03,565 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=regionserver:39969 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:03,572 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:399690x0, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:03,572 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/master 2024-12-03T07:14:03,572 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): regionserver:39969-0x1019b5411520001 connected 2024-12-03T07:14:03,574 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/running 2024-12-03T07:14:03,575 DEBUG [Time-limited test {}] zookeeper.ZKUtil(113): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/acl 2024-12-03T07:14:03,577 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=default.FPBQ.Fifo, numCallQueues=1, port=39969 2024-12-03T07:14:03,577 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=priority.RWQ.Fifo.write, numCallQueues=1, port=39969 2024-12-03T07:14:03,577 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=priority.RWQ.Fifo.read, numCallQueues=1, port=39969 2024-12-03T07:14:03,578 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=3 with threadPrefix=replication.FPBQ.Fifo, numCallQueues=1, port=39969 2024-12-03T07:14:03,578 DEBUG [Time-limited test {}] ipc.RpcExecutor(290): Started handlerCount=1 with threadPrefix=metaPriority.FPBQ.Fifo, numCallQueues=1, port=39969 2024-12-03T07:14:03,580 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.HMaster(2445): Adding backup master ZNode /hbase/backup-masters/8046980647f4,33011,1733210042815 2024-12-03T07:14:03,593 DEBUG [M:0;8046980647f4:33011 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:M:0;8046980647f4:33011 2024-12-03T07:14:03,595 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-03T07:14:03,595 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-03T07:14:03,597 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/backup-masters/8046980647f4,33011,1733210042815 2024-12-03T07:14:03,621 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-03T07:14:03,621 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/master 2024-12-03T07:14:03,622 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:03,622 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:03,622 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-03T07:14:03,623 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/master 2024-12-03T07:14:03,623 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.ActiveMasterManager(245): Deleting ZNode for /hbase/backup-masters/8046980647f4,33011,1733210042815 from backup master directory 2024-12-03T07:14:03,629 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-03T07:14:03,629 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/backup-masters/8046980647f4,33011,1733210042815 2024-12-03T07:14:03,630 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/backup-masters 2024-12-03T07:14:03,630 WARN [master/8046980647f4:0:becomeActiveMaster {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-03T07:14:03,630 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.ActiveMasterManager(255): Registered as active master=8046980647f4,33011,1733210042815 2024-12-03T07:14:03,632 INFO [master/8046980647f4:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating data MemStoreChunkPool with chunk size 2 MB, max count 396, initial count 0 2024-12-03T07:14:03,633 INFO [master/8046980647f4:0:becomeActiveMaster {}] regionserver.ChunkCreator(488): Allocating index MemStoreChunkPool with chunk size 204.80 KB, max count 440, initial count 0 2024-12-03T07:14:03,691 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741826_1002 (size=42) 2024-12-03T07:14:04,095 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] util.FSUtils(639): Created cluster ID file at hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/hbase.id with ID: 2f367829-c73d-418d-bffa-92c17acb01a4 2024-12-03T07:14:04,137 INFO [master/8046980647f4:0:becomeActiveMaster {}] fs.HFileSystem(339): Added intercepting call to namenode#getBlockLocations so can do block reordering using class org.apache.hadoop.hbase.fs.HFileSystem$ReorderWALBlocks 2024-12-03T07:14:04,197 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:04,197 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:04,215 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741827_1003 (size=196) 2024-12-03T07:14:04,632 INFO [master/8046980647f4:0: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)'} 2024-12-03T07:14:04,636 INFO [master/8046980647f4:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(132): Injected flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000 2024-12-03T07:14:04,650 DEBUG [master/8046980647f4:0: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) ~[?:?] 2024-12-03T07:14:04,654 INFO [master/8046980647f4:0:becomeActiveMaster {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-03T07:14:04,682 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741828_1004 (size=1189) 2024-12-03T07:14:04,706 INFO [master/8046980647f4:0: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:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store 2024-12-03T07:14:04,722 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741829_1005 (size=34) 2024-12-03T07:14:05,133 INFO [master/8046980647f4:0: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. 2024-12-03T07:14:05,134 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-03T07:14:05,135 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1681): Closing 1595e783b53d99cd5eef43b6debb2682, disabling compactions & flushes 2024-12-03T07:14:05,135 INFO [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1703): Closing region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-03T07:14:05,136 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1724): Waiting without time limit for close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-03T07:14:05,136 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1791): Acquired close lock on master:store,,1.1595e783b53d99cd5eef43b6debb2682. after waiting 0 ms 2024-12-03T07:14:05,136 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1801): Updates disabled for region master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-03T07:14:05,136 INFO [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1922): Closed master:store,,1.1595e783b53d99cd5eef43b6debb2682. 2024-12-03T07:14:05,137 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1635): Region close journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-03T07:14:05,139 WARN [master/8046980647f4:0:becomeActiveMaster {}] region.MasterRegion(249): failed to clean up initializing flag: hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/.initializing 2024-12-03T07:14:05,140 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] region.MasterRegion(219): WALDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815 2024-12-03T07:14:05,146 INFO [master/8046980647f4:0:becomeActiveMaster {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-03T07:14:05,156 INFO [master/8046980647f4:0:becomeActiveMaster {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=8046980647f4%2C33011%2C1733210042815, suffix=, logDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815, archiveDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/oldWALs, maxLogs=10 2024-12-03T07:14:05,175 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815/8046980647f4%2C33011%2C1733210042815.1733210045161, exclude list is [], retry=0 2024-12-03T07:14:05,189 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[127.0.0.1:38883,DS-4254b93d-839f-4f3c-87c5-b90d28d39653,DISK] 2024-12-03T07:14:05,191 DEBUG [RS-EventLoopGroup-3-2 {}] asyncfs.ProtobufDecoder(117): Hadoop 3.3 and above shades protobuf. 2024-12-03T07:14:05,220 INFO [master/8046980647f4:0:becomeActiveMaster {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815/8046980647f4%2C33011%2C1733210042815.1733210045161 2024-12-03T07:14:05,221 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37873:37873)] 2024-12-03T07:14:05,222 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(7285): Opening region: {ENCODED => 1595e783b53d99cd5eef43b6debb2682, NAME => 'master:store,,1.1595e783b53d99cd5eef43b6debb2682.', STARTKEY => '', ENDKEY => ''} 2024-12-03T07:14:05,222 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(894): Instantiated master:store,,1.1595e783b53d99cd5eef43b6debb2682.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-03T07:14:05,225 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(7327): checking encryption for 1595e783b53d99cd5eef43b6debb2682 2024-12-03T07:14:05,226 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(7330): checking classloading for 1595e783b53d99cd5eef43b6debb2682 2024-12-03T07:14:05,259 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 2024-12-03T07:14:05,279 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 2024-12-03T07:14:05,282 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:05,284 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 2024-12-03T07:14:05,284 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 2024-12-03T07:14:05,288 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 2024-12-03T07:14:05,288 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:05,289 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/proc, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-03T07:14:05,289 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 2024-12-03T07:14:05,292 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 2024-12-03T07:14:05,292 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:05,293 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/rs, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-03T07:14:05,293 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 2024-12-03T07:14:05,296 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 2024-12-03T07:14:05,296 DEBUG [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:05,297 INFO [StoreOpener-1595e783b53d99cd5eef43b6debb2682-1 {}] regionserver.HStore(327): Store=1595e783b53d99cd5eef43b6debb2682/state, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-03T07:14:05,300 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-03T07:14:05,302 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682 2024-12-03T07:14:05,311 DEBUG [master/8046980647f4:0: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. 2024-12-03T07:14:05,315 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1085): writing seq id for 1595e783b53d99cd5eef43b6debb2682 2024-12-03T07:14:05,319 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-03T07:14:05,320 INFO [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1102): Opened 1595e783b53d99cd5eef43b6debb2682; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=72642422, jitterRate=0.08245643973350525}}}, FlushLargeStoresPolicy{flushSizeLowerBound=33554432} 2024-12-03T07:14:05,324 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] regionserver.HRegion(1001): Region open journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-03T07:14:05,325 INFO [master/8046980647f4:0:becomeActiveMaster {}] region.MasterRegionFlusherAndCompactor(122): Constructor flushSize=134217728, flushPerChanges=1000000, flushIntervalMs=900000, compactMin=4 2024-12-03T07:14:05,350 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@48364df1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:05,376 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.HMaster(882): No meta location available on zookeeper, skip migrating... 2024-12-03T07:14:05,387 INFO [master/8046980647f4:0:becomeActiveMaster {}] region.RegionProcedureStore(104): Starting the Region Procedure Store, number threads=5 2024-12-03T07:14:05,387 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(633): Starting 5 core workers (bigger of cpus/4 or 16) with max (burst) worker count=50 2024-12-03T07:14:05,389 INFO [master/8046980647f4:0:becomeActiveMaster {}] region.RegionProcedureStore(255): Starting Region Procedure Store lease recovery... 2024-12-03T07:14:05,391 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(653): Recovered RegionProcedureStore lease in 1 msec 2024-12-03T07:14:05,396 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(667): Loaded RegionProcedureStore in 4 msec 2024-12-03T07:14:05,396 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.RemoteProcedureDispatcher(96): Instantiated, coreThreads=3 (allowCoreThreadTimeOut=true), queueMaxSize=32, operationDelay=150 2024-12-03T07:14:05,418 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.RegionServerTracker(127): Upgrading RegionServerTracker to active master mode; 0 have existingServerCrashProcedures, 0 possibly 'live' servers, and 0 'splitting'. 2024-12-03T07:14:05,429 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Unable to get data of znode /hbase/balancer because node does not exist (not necessarily an error) 2024-12-03T07:14:05,463 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/balancer already deleted, retry=false 2024-12-03T07:14:05,466 INFO [master/8046980647f4:0:becomeActiveMaster {}] normalizer.SimpleRegionNormalizer(163): Updated configuration for key 'hbase.normalizer.merge.min_region_size.mb' from 0 to 1 2024-12-03T07:14:05,467 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Unable to get data of znode /hbase/normalizer because node does not exist (not necessarily an error) 2024-12-03T07:14:05,478 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/normalizer already deleted, retry=false 2024-12-03T07:14:05,480 INFO [master/8046980647f4:0:becomeActiveMaster {}] normalizer.RegionNormalizerWorker(137): Normalizer rate limit set to unlimited 2024-12-03T07:14:05,484 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Unable to get data of znode /hbase/switch/split because node does not exist (not necessarily an error) 2024-12-03T07:14:05,495 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/split already deleted, retry=false 2024-12-03T07:14:05,496 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Unable to get data of znode /hbase/switch/merge because node does not exist (not necessarily an error) 2024-12-03T07:14:05,505 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/switch/merge already deleted, retry=false 2024-12-03T07:14:05,518 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(444): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Unable to get data of znode /hbase/snapshot-cleanup because node does not exist (not necessarily an error) 2024-12-03T07:14:05,528 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.RecoverableZooKeeper(215): Node /hbase/snapshot-cleanup already deleted, retry=false 2024-12-03T07:14:05,538 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-03T07:14:05,538 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/running 2024-12-03T07:14:05,538 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:05,538 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:05,538 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.HMaster(826): Active/primary master=8046980647f4,33011,1733210042815, sessionid=0x1019b5411520000, setting cluster-up flag (Was=false) 2024-12-03T07:14:05,563 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:05,563 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:05,588 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/flush-table-proc/acquired, /hbase/flush-table-proc/reached, /hbase/flush-table-proc/abort 2024-12-03T07:14:05,591 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=8046980647f4,33011,1733210042815 2024-12-03T07:14:05,613 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:05,613 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:05,638 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure.ZKProcedureUtil(251): Clearing all znodes /hbase/online-snapshot/acquired, /hbase/online-snapshot/reached, /hbase/online-snapshot/abort 2024-12-03T07:14:05,640 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure.ZKProcedureCoordinator(245): Starting controller for procedure member=8046980647f4,33011,1733210042815 2024-12-03T07:14:05,693 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.ShutdownHook(81): Installed shutdown hook thread: Shutdownhook:RS:0;8046980647f4:39969 2024-12-03T07:14:05,694 INFO [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(1008): ClusterId : 2f367829-c73d-418d-bffa-92c17acb01a4 2024-12-03T07:14:05,697 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(43): Procedure flush-table-proc initializing 2024-12-03T07:14:05,706 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(45): Procedure flush-table-proc initialized 2024-12-03T07:14:05,706 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(43): Procedure online-snapshot initializing 2024-12-03T07:14:05,712 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT; InitMetaProcedure table=hbase:meta 2024-12-03T07:14:05,714 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(45): Procedure online-snapshot initialized 2024-12-03T07:14:05,715 DEBUG [RS:0;8046980647f4:39969 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@3626e3ba, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:05,716 DEBUG [RS:0;8046980647f4:39969 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@5b7b237a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=8046980647f4/172.17.0.2:0 2024-12-03T07:14:05,717 INFO [master/8046980647f4:0:becomeActiveMaster {}] balancer.BaseLoadBalancer(575): slop=0.2 2024-12-03T07:14:05,719 INFO [RS:0;8046980647f4:39969 {}] regionserver.RegionServerCoprocessorHost(67): System coprocessor loading is enabled 2024-12-03T07:14:05,719 INFO [RS:0;8046980647f4:39969 {}] regionserver.RegionServerCoprocessorHost(68): Table coprocessor loading is enabled 2024-12-03T07:14:05,719 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(1090): About to register with Master. 2024-12-03T07:14:05,719 INFO [master/8046980647f4:0: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. 2024-12-03T07:14:05,721 INFO [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(3073): reportForDuty to master=8046980647f4,33011,1733210042815 with isa=8046980647f4/172.17.0.2:39969, startcode=1733210043547 2024-12-03T07:14:05,725 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] balancer.RegionLocationFinder(146): Skipping locality-based refresh due to oldStatus=null, newStatus=Master: 8046980647f4,33011,1733210042815 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 2024-12-03T07:14:05,728 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_OPEN_REGION-master/8046980647f4:0, corePoolSize=5, maxPoolSize=5 2024-12-03T07:14:05,728 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_CLOSE_REGION-master/8046980647f4:0, corePoolSize=5, maxPoolSize=5 2024-12-03T07:14:05,728 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SERVER_OPERATIONS-master/8046980647f4:0, corePoolSize=5, maxPoolSize=5 2024-12-03T07:14:05,729 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_META_SERVER_OPERATIONS-master/8046980647f4:0, corePoolSize=5, maxPoolSize=5 2024-12-03T07:14:05,729 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=M_LOG_REPLAY_OPS-master/8046980647f4:0, corePoolSize=10, maxPoolSize=10 2024-12-03T07:14:05,729 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_SNAPSHOT_OPERATIONS-master/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,729 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_MERGE_OPERATIONS-master/8046980647f4:0, corePoolSize=2, maxPoolSize=2 2024-12-03T07:14:05,729 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] executor.ExecutorService(95): Starting executor service name=MASTER_TABLE_OPERATIONS-master/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,731 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.procedure2.CompletedProcedureCleaner; timeout=30000, timestamp=1733210075731 2024-12-03T07:14:05,732 DEBUG [RS:0;8046980647f4:39969 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-03T07:14:05,732 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.DirScanPool(74): log_cleaner Cleaner pool size is 1 2024-12-03T07:14:05,733 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveLogCleaner 2024-12-03T07:14:05,735 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_WRITE_FS_LAYOUT, locked=true; InitMetaProcedure table=hbase:meta 2024-12-03T07:14:05,735 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(75): BOOTSTRAP: creating hbase:meta region 2024-12-03T07:14:05,736 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.replication.master.ReplicationLogCleaner 2024-12-03T07:14:05,736 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreWALCleaner 2024-12-03T07:14:05,737 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveProcedureWALCleaner 2024-12-03T07:14:05,737 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.LogCleaner(148): Creating 1 old WALs cleaner threads 2024-12-03T07:14:05,737 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=LogsCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,739 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.DirScanPool(74): hfile_cleaner Cleaner pool size is 2 2024-12-03T07:14:05,739 DEBUG [PEWorker-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:05,739 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)'} 2024-12-03T07:14:05,740 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveMasterLocalStoreHFileCleaner 2024-12-03T07:14:05,740 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.HFileLinkCleaner 2024-12-03T07:14:05,742 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.snapshot.SnapshotHFileCleaner 2024-12-03T07:14:05,742 INFO [master/8046980647f4:0:becomeActiveMaster {}] cleaner.CleanerChore(192): Initialize cleaner=org.apache.hadoop.hbase.master.cleaner.TimeToLiveHFileCleaner 2024-12-03T07:14:05,743 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] cleaner.HFileCleaner(260): Starting for large file=Thread[master/8046980647f4:0:becomeActiveMaster-HFileCleaner.large.0-1733210045743,5,FailOnTimeoutGroup] 2024-12-03T07:14:05,744 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] cleaner.HFileCleaner(275): Starting for small files=Thread[master/8046980647f4:0:becomeActiveMaster-HFileCleaner.small.0-1733210045744,5,FailOnTimeoutGroup] 2024-12-03T07:14:05,744 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HFileCleaner, period=600000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,744 INFO [master/8046980647f4:0: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. 2024-12-03T07:14:05,746 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=ReplicationBarrierCleaner, period=43200000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,746 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=SnapshotCleaner, period=1800000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,748 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741831_1007 (size=1039) 2024-12-03T07:14:05,762 INFO [RS-EventLoopGroup-1-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:45209, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-03T07:14:05,767 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=33011 {}] master.ServerManager(332): Checking decommissioned status of RegionServer 8046980647f4,39969,1733210043547 2024-12-03T07:14:05,768 INFO [RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=33011 {}] master.ServerManager(486): Registering regionserver=8046980647f4,39969,1733210043547 2024-12-03T07:14:05,781 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(1725): Config from master: hbase.rootdir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a 2024-12-03T07:14:05,781 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(1725): Config from master: fs.defaultFS=hdfs://localhost:42129 2024-12-03T07:14:05,781 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(1725): Config from master: hbase.master.info.port=-1 2024-12-03T07:14:05,788 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/rs 2024-12-03T07:14:05,788 DEBUG [RS:0;8046980647f4:39969 {}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/rs/8046980647f4,39969,1733210043547 2024-12-03T07:14:05,789 WARN [RS:0;8046980647f4:39969 {}] hbase.ZNodeClearer(69): Environment variable HBASE_ZNODE_FILE not set; znodes will not be cleared on crash by start scripts (Longer MTTR!) 2024-12-03T07:14:05,789 INFO [RS:0;8046980647f4:39969 {}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-03T07:14:05,789 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(2100): logDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547 2024-12-03T07:14:05,791 INFO [RegionServerTracker-0 {}] master.RegionServerTracker(179): RegionServer ephemeral node created, adding [8046980647f4,39969,1733210043547] 2024-12-03T07:14:05,804 DEBUG [RS:0;8046980647f4:39969 {}] regionserver.Replication(140): Replication stats-in-log period=300 seconds 2024-12-03T07:14:05,816 INFO [RS:0;8046980647f4:39969 {}] regionserver.MetricsRegionServerWrapperImpl(120): Computing regionserver metrics every 5000 milliseconds 2024-12-03T07:14:05,828 INFO [RS:0;8046980647f4:39969 {}] regionserver.MemStoreFlusher(130): globalMemStoreLimit=880 M, globalMemStoreLimitLowMark=836 M, Offheap=false 2024-12-03T07:14:05,830 INFO [RS:0;8046980647f4:39969 {}] 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 2024-12-03T07:14:05,831 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionThroughputTuner, period=60000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,831 INFO [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer$CompactionChecker(1988): CompactionChecker runs every PT1S 2024-12-03T07:14:05,837 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactedHFilesCleaner, period=120000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_REGION-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_META-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_REGION-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_CLOSE_META-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_LOG_REPLAY_OPS-regionserver/8046980647f4:0, corePoolSize=2, maxPoolSize=2 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_COMPACTED_FILES_DISCHARGER-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,838 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_REGION_REPLICA_FLUSH_OPS-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,839 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_REFRESH_PEER-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,839 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_SWITCH_RPC_THROTTLE-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,839 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_CLAIM_REPLICATION_QUEUE-regionserver/8046980647f4:0, corePoolSize=1, maxPoolSize=1 2024-12-03T07:14:05,839 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_SNAPSHOT_OPERATIONS-regionserver/8046980647f4:0, corePoolSize=3, maxPoolSize=3 2024-12-03T07:14:05,839 DEBUG [RS:0;8046980647f4:39969 {}] executor.ExecutorService(95): Starting executor service name=RS_FLUSH_OPERATIONS-regionserver/8046980647f4:0, corePoolSize=3, maxPoolSize=3 2024-12-03T07:14:05,840 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=CompactionChecker, period=1000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,840 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=MemstoreFlusherChore, period=1000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,840 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=nonceCleaner, period=360000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,841 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=BrokenStoreFileCleaner, period=21600000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,841 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,39969,1733210043547-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-03T07:14:05,858 INFO [RS:0;8046980647f4:39969 {}] regionserver.HeapMemoryManager(209): Starting, tuneOn=false 2024-12-03T07:14:05,860 INFO [RS:0;8046980647f4:39969 {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,39969,1733210043547-HeapMemoryTunerChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:05,878 INFO [RS:0;8046980647f4:39969 {}] regionserver.Replication(204): 8046980647f4,39969,1733210043547 started 2024-12-03T07:14:05,878 INFO [RS:0;8046980647f4:39969 {}] regionserver.HRegionServer(1767): Serving as 8046980647f4,39969,1733210043547, RpcServer on 8046980647f4/172.17.0.2:39969, sessionid=0x1019b5411520001 2024-12-03T07:14:05,879 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(51): Procedure flush-table-proc starting 2024-12-03T07:14:05,879 DEBUG [RS:0;8046980647f4:39969 {}] flush.RegionServerFlushTableProcedureManager(108): Start region server flush procedure manager 8046980647f4,39969,1733210043547 2024-12-03T07:14:05,879 DEBUG [RS:0;8046980647f4:39969 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '8046980647f4,39969,1733210043547' 2024-12-03T07:14:05,879 DEBUG [RS:0;8046980647f4:39969 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/flush-table-proc/abort' 2024-12-03T07:14:05,880 DEBUG [RS:0;8046980647f4:39969 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/flush-table-proc/acquired' 2024-12-03T07:14:05,881 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(53): Procedure flush-table-proc started 2024-12-03T07:14:05,881 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(51): Procedure online-snapshot starting 2024-12-03T07:14:05,881 DEBUG [RS:0;8046980647f4:39969 {}] snapshot.RegionServerSnapshotManager(126): Start Snapshot Manager 8046980647f4,39969,1733210043547 2024-12-03T07:14:05,881 DEBUG [RS:0;8046980647f4:39969 {}] procedure.ZKProcedureMemberRpcs(357): Starting procedure member '8046980647f4,39969,1733210043547' 2024-12-03T07:14:05,881 DEBUG [RS:0;8046980647f4:39969 {}] procedure.ZKProcedureMemberRpcs(134): Checking for aborted procedures on node: '/hbase/online-snapshot/abort' 2024-12-03T07:14:05,882 DEBUG [RS:0;8046980647f4:39969 {}] procedure.ZKProcedureMemberRpcs(154): Looking for new procedures under znode:'/hbase/online-snapshot/acquired' 2024-12-03T07:14:05,883 DEBUG [RS:0;8046980647f4:39969 {}] procedure.RegionServerProcedureManagerHost(53): Procedure online-snapshot started 2024-12-03T07:14:05,883 INFO [RS:0;8046980647f4:39969 {}] quotas.RegionServerRpcQuotaManager(64): Quota support disabled 2024-12-03T07:14:05,883 INFO [RS:0;8046980647f4:39969 {}] quotas.RegionServerSpaceQuotaManager(80): Quota support disabled, not starting space quota manager. 2024-12-03T07:14:05,987 INFO [RS:0;8046980647f4:39969 {}] monitor.StreamSlowMonitor(122): New stream slow monitor defaultMonitorName 2024-12-03T07:14:05,990 INFO [RS:0;8046980647f4:39969 {}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=8046980647f4%2C39969%2C1733210043547, suffix=, logDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547, archiveDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/oldWALs, maxLogs=32 2024-12-03T07:14:06,005 DEBUG [RS:0;8046980647f4:39969 {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.1733210045992, exclude list is [], retry=0 2024-12-03T07:14:06,010 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[127.0.0.1:38883,DS-4254b93d-839f-4f3c-87c5-b90d28d39653,DISK] 2024-12-03T07:14:06,013 INFO [RS:0;8046980647f4:39969 {}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:06,013 DEBUG [RS:0;8046980647f4:39969 {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37873:37873)] 2024-12-03T07:14:06,154 INFO [PEWorker-1 {}] util.FSTableDescriptors(140): Updated hbase:meta table descriptor to hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/.tabledesc/.tableinfo.0000000001.1039 2024-12-03T07:14:06,154 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:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a 2024-12-03T07:14:06,166 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741833_1009 (size=32) 2024-12-03T07:14:06,570 DEBUG [PEWorker-1 {}] regionserver.HRegion(894): Instantiated hbase:meta,,1.1588230740; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-03T07:14:06,575 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 2024-12-03T07:14:06,580 INFO [StoreOpener-1588230740-1 {}] compactions.CompactionConfiguration(181): size [minCompactSize:128 MB, maxCompactSize:8.00 EB, offPeakMaxCompactSize:8.00 EB); files [minFilesToCompact:3, maxFilesToCompact:10); ratio 1.200000; off-peak ratio 5.000000; throttle point 2684354560; major period 604800000, major jitter 0.500000, min locality to compact 0.000000; tiered compaction: max_age 9223372036854775807, incoming window min 6, compaction policy for tiered window org.apache.hadoop.hbase.regionserver.compactions.ExploringCompactionPolicy, single output for minor true, compaction window factory org.apache.hadoop.hbase.regionserver.compactions.ExponentialCompactionWindowFactory, region 1588230740 columnFamilyName info 2024-12-03T07:14:06,581 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:06,582 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 2024-12-03T07:14:06,582 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 2024-12-03T07:14:06,586 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 2024-12-03T07:14:06,586 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:06,588 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 2024-12-03T07:14:06,588 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 2024-12-03T07:14:06,591 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 2024-12-03T07:14:06,591 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:06,592 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 2024-12-03T07:14:06,593 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740 2024-12-03T07:14:06,594 DEBUG [PEWorker-1 {}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740 2024-12-03T07:14:06,597 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. 2024-12-03T07:14:06,599 DEBUG [PEWorker-1 {}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-03T07:14:06,602 DEBUG [PEWorker-1 {}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-03T07:14:06,603 INFO [PEWorker-1 {}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=69002365, jitterRate=0.02821536362171173}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-03T07:14:06,605 DEBUG [PEWorker-1 {}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-03T07:14:06,605 DEBUG [PEWorker-1 {}] regionserver.HRegion(1681): Closing 1588230740, disabling compactions & flushes 2024-12-03T07:14:06,605 INFO [PEWorker-1 {}] regionserver.HRegion(1703): Closing region hbase:meta,,1.1588230740 2024-12-03T07:14:06,605 DEBUG [PEWorker-1 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:meta,,1.1588230740 2024-12-03T07:14:06,606 DEBUG [PEWorker-1 {}] regionserver.HRegion(1791): Acquired close lock on hbase:meta,,1.1588230740 after waiting 0 ms 2024-12-03T07:14:06,606 DEBUG [PEWorker-1 {}] regionserver.HRegion(1801): Updates disabled for region hbase:meta,,1.1588230740 2024-12-03T07:14:06,607 INFO [PEWorker-1 {}] regionserver.HRegion(1922): Closed hbase:meta,,1.1588230740 2024-12-03T07:14:06,607 DEBUG [PEWorker-1 {}] regionserver.HRegion(1635): Region close journal for 1588230740: 2024-12-03T07:14:06,609 DEBUG [PEWorker-1 {}] procedure.InitMetaProcedure(96): Execute pid=1, state=RUNNABLE:INIT_META_ASSIGN_META, locked=true; InitMetaProcedure table=hbase:meta 2024-12-03T07:14:06,609 INFO [PEWorker-1 {}] procedure.InitMetaProcedure(107): Going to assign meta 2024-12-03T07:14:06,614 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}] 2024-12-03T07:14:06,621 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 2024-12-03T07:14:06,623 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 2024-12-03T07:14:06,775 DEBUG [8046980647f4:33011 {}] assignment.AssignmentManager(2444): Processing assignQueue; systemServersCount=1, allServersCount=1 2024-12-03T07:14:06,781 INFO [PEWorker-3 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPENING, regionLocation=8046980647f4,39969,1733210043547 2024-12-03T07:14:06,787 INFO [PEWorker-3 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 8046980647f4,39969,1733210043547, state=OPENING 2024-12-03T07:14:06,804 DEBUG [PEWorker-3 {}] zookeeper.MetaTableLocator(183): hbase:meta region location doesn't exist, create it 2024-12-03T07:14:06,813 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:06,813 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:06,814 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-03T07:14:06,814 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-03T07:14:06,817 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=3, ppid=2, state=RUNNABLE; OpenRegionProcedure 1588230740, server=8046980647f4,39969,1733210043547}] 2024-12-03T07:14:06,999 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:07,000 DEBUG [RSProcedureDispatcher-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=AdminService, sasl=false 2024-12-03T07:14:07,003 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:47248, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=AdminService 2024-12-03T07:14:07,014 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(135): Open hbase:meta,,1.1588230740 2024-12-03T07:14:07,014 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.WALFactory(183): Instantiating WALProvider of type class org.apache.hadoop.hbase.wal.AsyncFSWALProvider 2024-12-03T07:14:07,015 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] monitor.StreamSlowMonitor(122): New stream slow monitor .meta 2024-12-03T07:14:07,018 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(500): WAL configuration: blocksize=256 MB, rollsize=128 MB, prefix=8046980647f4%2C39969%2C1733210043547.meta, suffix=.meta, logDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547, archiveDir=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/oldWALs, maxLogs=32 2024-12-03T07:14:07,032 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.meta.1733210047019.meta, exclude list is [], retry=0 2024-12-03T07:14:07,035 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[127.0.0.1:38883,DS-4254b93d-839f-4f3c-87c5-b90d28d39653,DISK] 2024-12-03T07:14:07,038 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(841): New WAL /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.meta.1733210047019.meta 2024-12-03T07:14:07,038 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37873:37873)] 2024-12-03T07:14:07,039 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7285): Opening region: {ENCODED => 1588230740, NAME => 'hbase:meta,,1', STARTKEY => '', ENDKEY => ''} 2024-12-03T07:14:07,040 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:07,083 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7999): Registered coprocessor service: region=hbase:meta,,1 service=MultiRowMutationService 2024-12-03T07:14:07,087 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {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. 2024-12-03T07:14:07,090 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table meta 1588230740 2024-12-03T07:14:07,090 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:07,090 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7327): checking encryption for 1588230740 2024-12-03T07:14:07,090 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(7330): checking classloading for 1588230740 2024-12-03T07:14:07,093 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 info of region 1588230740 2024-12-03T07:14:07,094 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 info 2024-12-03T07:14:07,094 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:07,095 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 2024-12-03T07:14:07,095 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 2024-12-03T07:14:07,097 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 rep_barrier 2024-12-03T07:14:07,097 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:07,097 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 2024-12-03T07:14:07,098 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 2024-12-03T07:14:07,099 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 2024-12-03T07:14:07,099 DEBUG [StoreOpener-1588230740-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:07,100 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 2024-12-03T07:14:07,101 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740 2024-12-03T07:14:07,104 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740 2024-12-03T07:14:07,106 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {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. 2024-12-03T07:14:07,109 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1085): writing seq id for 1588230740 2024-12-03T07:14:07,110 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1102): Opened 1588230740; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=58844902, jitterRate=-0.12314262986183167}}}, FlushLargeStoresPolicy{flushSizeLowerBound=44739242} 2024-12-03T07:14:07,111 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegion(1001): Region open journal for 1588230740: 2024-12-03T07:14:07,118 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:meta,,1.1588230740, pid=3, masterSystemTime=1733210046993 2024-12-03T07:14:07,128 DEBUG [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:meta,,1.1588230740 2024-12-03T07:14:07,129 INFO [RS_OPEN_META-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_META, pid=3}] handler.AssignRegionHandler(164): Opened hbase:meta,,1.1588230740 2024-12-03T07:14:07,129 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=2 updating hbase:meta row=1588230740, regionState=OPEN, openSeqNum=2, regionLocation=8046980647f4,39969,1733210043547 2024-12-03T07:14:07,131 INFO [PEWorker-5 {}] zookeeper.MetaTableLocator(171): Setting hbase:meta replicaId=0 location in ZooKeeper as 8046980647f4,39969,1733210043547, state=OPEN 2024-12-03T07:14:07,229 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-03T07:14:07,229 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/meta-region-server 2024-12-03T07:14:07,229 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-03T07:14:07,229 DEBUG [zk-event-processor-pool-0 {}] hbase.MetaRegionLocationCache(167): Updating meta znode for path /hbase/meta-region-server: CHANGED 2024-12-03T07:14:07,237 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=3, resume processing ppid=2 2024-12-03T07:14:07,238 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=3, ppid=2, state=SUCCESS; OpenRegionProcedure 1588230740, server=8046980647f4,39969,1733210043547 in 412 msec 2024-12-03T07:14:07,246 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=2, resume processing ppid=1 2024-12-03T07:14:07,246 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=2, ppid=1, state=SUCCESS; TransitRegionStateProcedure table=hbase:meta, region=1588230740, ASSIGN in 625 msec 2024-12-03T07:14:07,251 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=1, state=SUCCESS; InitMetaProcedure table=hbase:meta in 1.5760 sec 2024-12-03T07:14:07,251 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.HMaster(1088): Wait for region servers to report in: status=status unset, state=RUNNING, startTime=1733210047251, completionTime=-1 2024-12-03T07:14:07,252 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.ServerManager(907): Finished waiting on RegionServer count=1; waited=0ms, expected min=1 server(s), max=1 server(s), master is running 2024-12-03T07:14:07,252 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] assignment.AssignmentManager(1747): Joining cluster... 2024-12-03T07:14:07,282 DEBUG [hconnection-0x311e3d67-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:14:07,284 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:47254, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:14:07,296 INFO [master/8046980647f4:0:becomeActiveMaster {}] assignment.AssignmentManager(1759): Number of RegionServers=1 2024-12-03T07:14:07,297 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$RegionInTransitionChore; timeout=60000, timestamp=1733210107297 2024-12-03T07:14:07,297 INFO [master/8046980647f4:0:becomeActiveMaster {}] procedure2.TimeoutExecutorThread(81): ADDED pid=-1, state=WAITING_TIMEOUT; org.apache.hadoop.hbase.master.assignment.AssignmentManager$DeadServerMetricRegionChore; timeout=120000, timestamp=1733210167297 2024-12-03T07:14:07,297 INFO [master/8046980647f4:0:becomeActiveMaster {}] assignment.AssignmentManager(1766): Joined the cluster in 45 msec 2024-12-03T07:14:07,331 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,33011,1733210042815-ClusterStatusChore, period=60000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:07,331 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,33011,1733210042815-BalancerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:07,331 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,33011,1733210042815-RegionNormalizerChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:07,332 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=CatalogJanitor-8046980647f4:33011, period=300000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:07,333 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=HbckChore-, period=3600000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:07,337 DEBUG [master/8046980647f4:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-03T07:14:07,339 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.TableNamespaceManager(92): Namespace table not found. Creating... 2024-12-03T07:14:07,340 INFO [master/8046980647f4:0: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)'} 2024-12-03T07:14:07,345 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=4, state=RUNNABLE:CREATE_TABLE_PRE_OPERATION; CreateTableProcedure table=hbase:namespace 2024-12-03T07:14:07,348 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 2024-12-03T07:14:07,349 DEBUG [PEWorker-3 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:07,350 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 2024-12-03T07:14:07,360 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741835_1011 (size=358) 2024-12-03T07:14:07,768 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(7106): creating {ENCODED => ef235488523e821f809aed54184195da, NAME => 'hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da.', 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:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a 2024-12-03T07:14:07,779 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741836_1012 (size=42) 2024-12-03T07:14:08,182 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(894): Instantiated hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-03T07:14:08,182 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1681): Closing ef235488523e821f809aed54184195da, disabling compactions & flushes 2024-12-03T07:14:08,183 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1703): Closing region hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,183 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1724): Waiting without time limit for close lock on hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,183 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1791): Acquired close lock on hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. after waiting 0 ms 2024-12-03T07:14:08,183 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1801): Updates disabled for region hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,183 INFO [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1922): Closed hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,183 DEBUG [RegionOpenAndInit-hbase:namespace-pool-0 {}] regionserver.HRegion(1635): Region close journal for ef235488523e821f809aed54184195da: 2024-12-03T07:14:08,188 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 2024-12-03T07:14:08,196 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":2,"row":"hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da.","families":{"info":[{"qualifier":"regioninfo","vlen":41,"tag":[],"timestamp":"1733210048190"},{"qualifier":"state","vlen":6,"tag":[],"timestamp":"1733210048190"}]},"ts":"1733210048190"} 2024-12-03T07:14:08,216 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1516): Added 1 regions to meta. 2024-12-03T07:14:08,219 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 2024-12-03T07:14:08,222 DEBUG [PEWorker-3 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1733210048219"}]},"ts":"1733210048219"} 2024-12-03T07:14:08,226 INFO [PEWorker-3 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLING in hbase:meta 2024-12-03T07:14:08,273 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=ef235488523e821f809aed54184195da, ASSIGN}] 2024-12-03T07:14:08,277 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=ef235488523e821f809aed54184195da, ASSIGN 2024-12-03T07:14:08,280 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=ef235488523e821f809aed54184195da, ASSIGN; state=OFFLINE, location=8046980647f4,39969,1733210043547; forceNewPlan=false, retain=false 2024-12-03T07:14:08,430 INFO [PEWorker-5 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=ef235488523e821f809aed54184195da, regionState=OPENING, regionLocation=8046980647f4,39969,1733210043547 2024-12-03T07:14:08,434 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=6, ppid=5, state=RUNNABLE; OpenRegionProcedure ef235488523e821f809aed54184195da, server=8046980647f4,39969,1733210043547}] 2024-12-03T07:14:08,589 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:08,599 INFO [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(135): Open hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,600 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7285): Opening region: {ENCODED => ef235488523e821f809aed54184195da, NAME => 'hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da.', STARTKEY => '', ENDKEY => ''} 2024-12-03T07:14:08,600 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.MetricsRegionSourceImpl(79): Creating new MetricsRegionSourceImpl for table namespace ef235488523e821f809aed54184195da 2024-12-03T07:14:08,600 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(894): Instantiated hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da.; StoreHotnessProtector, parallelPutToStoreThreadLimit=0 ; minColumnNum=100 ; preparePutThreadLimit=0 ; hotProtect now disable 2024-12-03T07:14:08,601 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7327): checking encryption for ef235488523e821f809aed54184195da 2024-12-03T07:14:08,601 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(7330): checking classloading for ef235488523e821f809aed54184195da 2024-12-03T07:14:08,603 INFO [StoreOpener-ef235488523e821f809aed54184195da-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 ef235488523e821f809aed54184195da 2024-12-03T07:14:08,606 INFO [StoreOpener-ef235488523e821f809aed54184195da-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 ef235488523e821f809aed54184195da columnFamilyName info 2024-12-03T07:14:08,606 DEBUG [StoreOpener-ef235488523e821f809aed54184195da-1 {}] storefiletracker.StoreFileTrackerFactory(122): instantiating StoreFileTracker impl org.apache.hadoop.hbase.regionserver.storefiletracker.DefaultStoreFileTracker 2024-12-03T07:14:08,607 INFO [StoreOpener-ef235488523e821f809aed54184195da-1 {}] regionserver.HStore(327): Store=ef235488523e821f809aed54184195da/info, memstore type=DefaultMemStore, storagePolicy=NONE, verifyBulkLoads=false, parallelPutCountPrintThreshold=50, encoding=NONE, compression=NONE 2024-12-03T07:14:08,608 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da 2024-12-03T07:14:08,609 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(5301): Found 0 recovered edits file(s) under hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da 2024-12-03T07:14:08,613 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1085): writing seq id for ef235488523e821f809aed54184195da 2024-12-03T07:14:08,617 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] wal.WALSplitUtil(409): Wrote file=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da/recovered.edits/1.seqid, newMaxSeqId=1, maxSeqId=-1 2024-12-03T07:14:08,618 INFO [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1102): Opened ef235488523e821f809aed54184195da; next sequenceid=2; SteppingSplitPolicysuper{IncreasingToUpperBoundRegionSplitPolicy{initialSize=268435456, ConstantSizeRegionSplitPolicy{desiredMaxFileSize=65659461, jitterRate=-0.021597787737846375}}}, FlushLargeStoresPolicy{flushSizeLowerBound=-1} 2024-12-03T07:14:08,620 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegion(1001): Region open journal for ef235488523e821f809aed54184195da: 2024-12-03T07:14:08,622 INFO [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2601): Post open deploy tasks for hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da., pid=6, masterSystemTime=1733210048589 2024-12-03T07:14:08,626 DEBUG [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] regionserver.HRegionServer(2628): Finished post open deploy task for hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,626 INFO [RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0 {event_type=M_RS_OPEN_PRIORITY_REGION, pid=6}] handler.AssignRegionHandler(164): Opened hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. 2024-12-03T07:14:08,627 INFO [PEWorker-2 {}] assignment.RegionStateStore(202): pid=5 updating hbase:meta row=ef235488523e821f809aed54184195da, regionState=OPEN, openSeqNum=2, regionLocation=8046980647f4,39969,1733210043547 2024-12-03T07:14:08,633 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=6, resume processing ppid=5 2024-12-03T07:14:08,634 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=6, ppid=5, state=SUCCESS; OpenRegionProcedure ef235488523e821f809aed54184195da, server=8046980647f4,39969,1733210043547 in 196 msec 2024-12-03T07:14:08,637 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=5, resume processing ppid=4 2024-12-03T07:14:08,637 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=5, ppid=4, state=SUCCESS; TransitRegionStateProcedure table=hbase:namespace, region=ef235488523e821f809aed54184195da, ASSIGN in 361 msec 2024-12-03T07:14:08,639 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 2024-12-03T07:14:08,639 DEBUG [PEWorker-4 {}] hbase.MetaTableAccessor(2113): Put {"totalColumns":1,"row":"hbase:namespace","families":{"table":[{"qualifier":"state","vlen":2,"tag":[],"timestamp":"1733210048639"}]},"ts":"1733210048639"} 2024-12-03T07:14:08,643 INFO [PEWorker-4 {}] hbase.MetaTableAccessor(1655): Updated tableName=hbase:namespace, state=ENABLED in hbase:meta 2024-12-03T07:14:08,682 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKUtil(113): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on znode that does not yet exist, /hbase/namespace 2024-12-03T07:14:08,682 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 2024-12-03T07:14:08,687 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=4, state=SUCCESS; CreateTableProcedure table=hbase:namespace in 1.3410 sec 2024-12-03T07:14:08,688 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeCreated, state=SyncConnected, path=/hbase/namespace 2024-12-03T07:14:08,688 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:08,688 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:08,712 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=7, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=default 2024-12-03T07:14:08,729 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-03T07:14:08,743 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=7, state=SUCCESS; CreateNamespaceProcedure, namespace=default in 31 msec 2024-12-03T07:14:08,748 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] procedure2.ProcedureExecutor(1098): Stored pid=8, state=RUNNABLE:CREATE_NAMESPACE_PREPARE; CreateNamespaceProcedure, namespace=hbase 2024-12-03T07:14:08,762 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/namespace 2024-12-03T07:14:08,774 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=8, state=SUCCESS; CreateNamespaceProcedure, namespace=hbase in 26 msec 2024-12-03T07:14:08,796 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/default 2024-12-03T07:14:08,813 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDataChanged, state=SyncConnected, path=/hbase/namespace/hbase 2024-12-03T07:14:08,813 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.HMaster(1218): Master has completed initialization 5.182sec 2024-12-03T07:14:08,816 INFO [master/8046980647f4:0:becomeActiveMaster {}] quotas.MasterQuotaManager(97): Quota support disabled 2024-12-03T07:14:08,819 INFO [master/8046980647f4:0:becomeActiveMaster {}] slowlog.SlowLogMasterService(57): Slow/Large requests logging to system table hbase:slowlog is disabled. Quitting. 2024-12-03T07:14:08,821 INFO [master/8046980647f4:0:becomeActiveMaster {}] waleventtracker.WALEventTrackerTableCreator(75): wal event tracker requests logging to table REPLICATION.WALEVENTTRACKER is disabled. Quitting. 2024-12-03T07:14:08,822 INFO [master/8046980647f4:0:becomeActiveMaster {}] master.ReplicationSinkTrackerTableCreator(90): replication sink tracker requests logging to table REPLICATION.SINK_TRACKER is disabled. Quitting. 2024-12-03T07:14:08,822 INFO [master/8046980647f4:0:becomeActiveMaster {}] zookeeper.ZKWatcher(271): not a secure deployment, proceeding 2024-12-03T07:14:08,825 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,33011,1733210042815-MobFileCleanerChore, period=86400, unit=SECONDS is enabled. 2024-12-03T07:14:08,826 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,33011,1733210042815-MobFileCompactionChore, period=604800, unit=SECONDS is enabled. 2024-12-03T07:14:08,831 DEBUG [master/8046980647f4:0:becomeActiveMaster {}] master.HMaster(1321): Balancer post startup initialization complete, took 0 seconds 2024-12-03T07:14:08,832 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=RollingUpgradeChore, period=10, unit=SECONDS is enabled. 2024-12-03T07:14:08,832 INFO [master/8046980647f4:0:becomeActiveMaster {}] hbase.ChoreService(168): Chore ScheduledChore name=8046980647f4,33011,1733210042815-OldWALsDirSizeChore, period=300000, unit=MILLISECONDS is enabled. 2024-12-03T07:14:08,905 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7502c059 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6ea82e8f 2024-12-03T07:14:08,905 WARN [Time-limited test {}] client.ZKConnectionRegistry(90): ZKConnectionRegistry is deprecated. See https://hbase.apache.org/book.html#client.rpcconnectionregistry 2024-12-03T07:14:08,915 DEBUG [Time-limited test {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@707adb81, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:08,918 DEBUG [Time-limited test {}] nio.NioEventLoop(110): -Dio.netty.noKeySetOptimization: false 2024-12-03T07:14:08,918 DEBUG [Time-limited test {}] nio.NioEventLoop(111): -Dio.netty.selectorAutoRebuildThreshold: 512 2024-12-03T07:14:08,927 DEBUG [hconnection-0x3e1871-shared-pool-0 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:14:08,934 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:60768, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:14:08,941 INFO [Time-limited test {}] hbase.HBaseTestingUtility(1199): Minicluster is up; activeMaster=8046980647f4,33011,1733210042815 2024-12-03T07:14:08,943 DEBUG [Time-limited test {}] zookeeper.ReadOnlyZKClient(149): Connect 0x57d89e0d to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7d7b22aa 2024-12-03T07:14:08,956 DEBUG [ReadOnlyZKClient-127.0.0.1:55234@0x57d89e0d {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodec@7640f337, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:08,971 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=222, OpenFileDescriptor=448, MaxFileDescriptor=1048576, SystemLoadAverage=168, ProcessCount=11, AvailableMemoryMB=2581 2024-12-03T07:14:09,017 DEBUG [Time-limited test {}] client.ConnectionUtils(573): Start fetching master stub from registry 2024-12-03T07:14:09,018 DEBUG [ReadOnlyZKClient-127.0.0.1:55234@0x57d89e0d {}] client.AsyncConnectionImpl(310): The fetched master address is 8046980647f4,33011,1733210042815 2024-12-03T07:14:09,023 DEBUG [ReadOnlyZKClient-127.0.0.1:55234@0x57d89e0d {}] client.ConnectionUtils(581): The fetched master stub is org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$Stub@7177257b 2024-12-03T07:14:09,025 DEBUG [ReadOnlyZKClient-127.0.0.1:55234@0x57d89e0d {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=MasterService, sasl=false 2024-12-03T07:14:09,027 INFO [RS-EventLoopGroup-1-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:54796, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=MasterService 2024-12-03T07:14:09,028 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:09,034 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=9, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:09,039 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-03T07:14:09,052 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:09,053 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:09,063 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:09,063 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520004 connected 2024-12-03T07:14:09,150 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-03T07:14:09,172 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520004, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:09,196 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:09,196 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase 2024-12-03T07:14:09,217 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=10, ppid=9, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:09,360 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-03T07:14:09,389 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:09,390 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=10 2024-12-03T07:14:09,391 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:09,409 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=10}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:09,425 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:09,484 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=10}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=10 2024-12-03T07:14:09,487 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=10 2024-12-03T07:14:09,491 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:09,495 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=10, resume processing ppid=9 2024-12-03T07:14:09,495 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:09,495 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=10, ppid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 274 msec 2024-12-03T07:14:09,497 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=9, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 465 msec 2024-12-03T07:14:09,517 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1e3bf0d5 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@14db1236 2024-12-03T07:14:09,529 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:09,529 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:09,530 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3f7f686c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:09,532 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:09,538 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:09,538 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:09,538 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520006 connected 2024-12-03T07:14:09,671 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=9 2024-12-03T07:14:09,673 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:09,678 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:09,683 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=11, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:09,685 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-03T07:14:09,702 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:09,703 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:09,713 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:09,713 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520007 connected 2024-12-03T07:14:09,791 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-03T07:14:09,821 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520007, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:09,839 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=12, ppid=11, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:09,993 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:09,995 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=12 2024-12-03T07:14:09,995 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:09,997 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:09,997 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:09,997 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:09,998 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520006, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:09,998 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520006, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:10,000 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-03T07:14:10,105 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520006, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:10,107 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1e3bf0d5 to 127.0.0.1:55234 2024-12-03T07:14:10,107 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:10,129 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:10,130 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:10,130 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=12}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=12 2024-12-03T07:14:10,131 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=12 2024-12-03T07:14:10,134 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:10,137 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=12, resume processing ppid=11 2024-12-03T07:14:10,137 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:10,137 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=12, ppid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 296 msec 2024-12-03T07:14:10,139 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=11, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 458 msec 2024-12-03T07:14:10,157 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x44a233be to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@d248249 2024-12-03T07:14:10,163 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:10,164 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:10,164 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6037c2b2, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:10,165 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:10,171 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:10,172 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:10,172 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520009 connected 2024-12-03T07:14:10,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=11 2024-12-03T07:14:10,311 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:10,317 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,319 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,320 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,323 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-03T07:14:10,325 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=13, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:10,326 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-03T07:14:10,341 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:10,342 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:10,353 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:10,353 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152000a connected 2024-12-03T07:14:10,431 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-03T07:14:10,463 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152000a, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:10,491 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=14, ppid=13, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:10,640 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-03T07:14:10,648 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:10,649 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=14 2024-12-03T07:14:10,650 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:10,654 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:10,654 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:10,654 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:10,655 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520009, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:10,656 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520009, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:10,771 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520009, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:10,772 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x44a233be to 127.0.0.1:55234 2024-12-03T07:14:10,772 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:10,792 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:10,792 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:10,793 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=14}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=14 2024-12-03T07:14:10,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=14 2024-12-03T07:14:10,796 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:10,800 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=14, resume processing ppid=13 2024-12-03T07:14:10,800 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-03T07:14:10,800 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=14, ppid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 305 msec 2024-12-03T07:14:10,802 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=13, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 477 msec 2024-12-03T07:14:10,818 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7f77a91a to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1c19e73e 2024-12-03T07:14:10,830 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:10,830 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:10,831 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4c51a00b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:10,832 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:10,838 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:10,838 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:10,838 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152000c connected 2024-12-03T07:14:10,950 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=13 2024-12-03T07:14:10,951 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:10,952 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,955 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,956 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,958 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:10,960 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-03T07:14:10,961 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=15, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:10,962 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-03T07:14:10,975 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:10,976 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:10,988 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:10,988 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152000d connected 2024-12-03T07:14:11,070 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-03T07:14:11,096 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152000d, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:11,115 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=16, ppid=15, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:11,270 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:11,272 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=16 2024-12-03T07:14:11,273 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:11,277 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:11,278 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:11,278 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:11,279 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152000c, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:11,279 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152000c, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:11,280 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-03T07:14:11,388 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152000c, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:11,388 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7f77a91a to 127.0.0.1:55234 2024-12-03T07:14:11,389 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:11,408 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:11,409 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:11,409 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=16}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=16 2024-12-03T07:14:11,410 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=16 2024-12-03T07:14:11,413 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:11,416 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=16, resume processing ppid=15 2024-12-03T07:14:11,416 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-03T07:14:11,416 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=16, ppid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 299 msec 2024-12-03T07:14:11,418 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=15, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 456 msec 2024-12-03T07:14:11,436 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x77096b03 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@70657a7a 2024-12-03T07:14:11,447 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:11,447 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:11,447 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4af1ea67, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:11,449 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:11,454 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:11,455 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152000f connected 2024-12-03T07:14:11,455 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:11,591 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=15 2024-12-03T07:14:11,592 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:11,593 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:11,595 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:11,596 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:11,598 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:11,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=17, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:11,602 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-03T07:14:11,616 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:11,616 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:11,621 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:11,621 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520010 connected 2024-12-03T07:14:11,711 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-03T07:14:11,730 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520010, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:11,809 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:meta' 2024-12-03T07:14:11,812 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsTableSourceImpl(133): Creating new MetricsTableSourceImpl for table 'hbase:namespace' 2024-12-03T07:14:11,814 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=18, ppid=17, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:11,920 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-03T07:14:11,969 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:11,970 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=18 2024-12-03T07:14:11,971 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:11,975 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:11,975 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:11,975 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:11,976 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152000f, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:11,976 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152000f, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:12,088 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152000f, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:12,088 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x77096b03 to 127.0.0.1:55234 2024-12-03T07:14:12,089 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:12,106 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:12,106 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:12,106 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=18}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=18 2024-12-03T07:14:12,107 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=18 2024-12-03T07:14:12,110 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:12,113 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=18, resume processing ppid=17 2024-12-03T07:14:12,113 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=18, ppid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 296 msec 2024-12-03T07:14:12,113 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:12,115 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=17, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 515 msec 2024-12-03T07:14:12,131 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x64897f8a to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2a4c6aca 2024-12-03T07:14:12,138 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:12,138 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:12,139 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1380e2d0, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:12,140 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:12,146 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:12,146 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:12,146 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520012 connected 2024-12-03T07:14:12,230 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=17 2024-12-03T07:14:12,232 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:12,233 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:12,236 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:12,238 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-03T07:14:12,240 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=19, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:12,241 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-03T07:14:12,258 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:12,259 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:12,270 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:12,270 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520013 connected 2024-12-03T07:14:12,350 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-03T07:14:12,379 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520013, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:12,390 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=20, ppid=19, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:12,545 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:12,546 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=20 2024-12-03T07:14:12,547 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:12,550 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:12,550 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:12,551 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:12,551 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520012, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:12,552 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520012, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:12,559 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-03T07:14:12,604 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:14:12,663 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520012, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:12,663 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x64897f8a to 127.0.0.1:55234 2024-12-03T07:14:12,663 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:12,681 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:12,681 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:12,681 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=20}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=20 2024-12-03T07:14:12,682 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=20 2024-12-03T07:14:12,684 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:12,687 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=20, resume processing ppid=19 2024-12-03T07:14:12,687 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-03T07:14:12,687 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=20, ppid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 294 msec 2024-12-03T07:14:12,689 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=19, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 449 msec 2024-12-03T07:14:12,708 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x76fbf94c to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@470a561b 2024-12-03T07:14:12,720 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:12,721 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:12,721 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4febe3df, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:12,722 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:12,729 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:12,730 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:12,730 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520015 connected 2024-12-03T07:14:12,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=19 2024-12-03T07:14:12,870 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:12,870 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:12,871 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:12,872 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=21, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:12,873 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-03T07:14:12,889 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:12,889 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:12,896 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:12,896 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520016 connected 2024-12-03T07:14:12,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-03T07:14:13,005 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520016, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:13,021 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=22, ppid=21, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:13,174 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:13,175 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=22 2024-12-03T07:14:13,176 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:13,179 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:13,180 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:13,180 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:13,180 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520015, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:13,181 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520015, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:13,191 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-03T07:14:13,216 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_meta 2024-12-03T07:14:13,216 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_meta Metrics about Tables on a single HBase RegionServer 2024-12-03T07:14:13,221 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_hbase_table_namespace 2024-12-03T07:14:13,221 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_hbase_table_namespace Metrics about Tables on a single HBase RegionServer 2024-12-03T07:14:13,223 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint 2024-12-03T07:14:13,223 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=Coprocessor.Region.CP_org.apache.hadoop.hbase.coprocessor.MultiRowMutationEndpoint Metrics about HBase RegionObservers 2024-12-03T07:14:13,224 DEBUG [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(131): Registering adapter for the MetricRegistry: RegionServer,sub=TableRequests_Namespace_master_table_store 2024-12-03T07:14:13,224 INFO [HBase-Metrics2-1 {}] impl.GlobalMetricRegistriesAdapter(135): Registering RegionServer,sub=TableRequests_Namespace_master_table_store Metrics about Tables on a single HBase RegionServer 2024-12-03T07:14:13,288 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520015, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:13,288 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x76fbf94c to 127.0.0.1:55234 2024-12-03T07:14:13,288 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:13,309 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:13,309 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:13,309 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=22}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=22 2024-12-03T07:14:13,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=22 2024-12-03T07:14:13,312 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:13,314 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=22, resume processing ppid=21 2024-12-03T07:14:13,315 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:13,315 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=22, ppid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 291 msec 2024-12-03T07:14:13,316 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=21, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 444 msec 2024-12-03T07:14:13,339 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6378a4d4 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@41cb8fbf 2024-12-03T07:14:13,346 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:13,347 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:13,347 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@a6fd97a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:13,349 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:13,354 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:13,354 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:13,355 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520018 connected 2024-12-03T07:14:13,499 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=21 2024-12-03T07:14:13,500 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:13,500 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:13,503 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:13,504 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:13,507 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=24, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:13,507 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:13,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-03T07:14:13,509 DEBUG [PEWorker-1 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=24 2024-12-03T07:14:13,509 DEBUG [PEWorker-1 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=23, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:13,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:13,511 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:13,521 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:13,521 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:13,521 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:13,523 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=25, ppid=24, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:13,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-03T07:14:13,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:13,676 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:13,677 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=25 2024-12-03T07:14:13,677 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:13,677 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:13,678 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:13,678 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:13,678 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520018, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:13,679 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520018, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:13,788 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520018, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:13,788 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6378a4d4 to 127.0.0.1:55234 2024-12-03T07:14:13,789 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:13,790 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:13,798 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:13,804 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:13,804 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:13,805 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:13,806 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:13,807 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=25}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=25 2024-12-03T07:14:13,808 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=25 2024-12-03T07:14:13,812 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:13,814 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=25, resume processing ppid=24 2024-12-03T07:14:13,815 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=25, ppid=24, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-03T07:14:13,821 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:13,822 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:13,824 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=24, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 318 msec 2024-12-03T07:14:13,829 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=24 2024-12-03T07:14:13,829 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:13,830 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:13,830 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:13,832 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=26, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:13,833 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-03T07:14:13,833 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] 2024-12-03T07:14:13,841 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:13,842 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=26, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=11 msec 2024-12-03T07:14:13,842 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:13,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=26 2024-12-03T07:14:13,944 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:13,946 INFO [Time-limited test {}] zookeeper.RecoverableZooKeeper(138): Process identifier=testing utility connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:13,954 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): testing utility0x0, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:13,955 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): testing utility-0x1019b5411520019 connected 2024-12-03T07:14:13,990 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[0] Thread=223 (was 222) Potentially hanging thread: RS_REFRESH_PEER-regionserver/8046980647f4:0-0 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$Worker.run(ThreadPoolExecutor.java:635) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: RSProcedureDispatcher-pool-2 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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: 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: ForkJoinPool.commonPool-worker-1 java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkUntil(LockSupport.java:410) java.base@17.0.11/java.util.concurrent.ForkJoinPool.awaitWork(ForkJoinPool.java:1726) java.base@17.0.11/java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1623) java.base@17.0.11/java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:165) Potentially hanging thread: RS-EventLoopGroup-1-3 app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) java.base@17.0.11/java.lang.Thread.run(Thread.java:840) Potentially hanging thread: 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) - Thread LEAK? -, OpenFileDescriptor=452 (was 448) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=154 (was 168), ProcessCount=11 (was 11), AvailableMemoryMB=2535 (was 2581) 2024-12-03T07:14:14,000 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testNamespacesAndTableCfsConfigConflict[0] Thread=223, OpenFileDescriptor=452, MaxFileDescriptor=1048576, SystemLoadAverage=154, ProcessCount=11, AvailableMemoryMB=2533 2024-12-03T07:14:14,001 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:14,003 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=27, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:14,004 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-03T07:14:14,020 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:14,021 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:14,029 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:14,030 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152001a connected 2024-12-03T07:14:14,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-03T07:14:14,138 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152001a, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:14,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:14,164 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=28, ppid=27, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:14,317 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:14,319 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=28 2024-12-03T07:14:14,319 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:14,320 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-03T07:14:14,338 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=28}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:14,349 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:14,438 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=28}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=28 2024-12-03T07:14:14,439 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=28 2024-12-03T07:14:14,441 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:14,444 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=28, resume processing ppid=27 2024-12-03T07:14:14,444 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:14,444 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=28, ppid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-03T07:14:14,446 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=27, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 443 msec 2024-12-03T07:14:14,464 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1695ae4d to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@dc22f54 2024-12-03T07:14:14,471 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:14,472 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:14,472 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@531d6935, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:14,473 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:14,479 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:14,480 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:14,480 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152001c connected 2024-12-03T07:14:14,630 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=27 2024-12-03T07:14:14,631 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:14,633 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:14,636 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=29, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:14,638 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-03T07:14:14,650 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:14,652 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:14,652 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:14,662 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:14,663 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152001d connected 2024-12-03T07:14:14,750 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-03T07:14:14,771 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152001d, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:14,780 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=30, ppid=29, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:14,933 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:14,935 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=30 2024-12-03T07:14:14,935 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:14,940 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:14,940 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:14,940 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:14,941 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152001c, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:14,941 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152001c, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:14,960 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-03T07:14:15,046 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152001c, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:15,047 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1695ae4d to 127.0.0.1:55234 2024-12-03T07:14:15,047 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:15,067 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:15,067 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:15,067 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=30}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=30 2024-12-03T07:14:15,068 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=30 2024-12-03T07:14:15,071 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:15,074 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=30, resume processing ppid=29 2024-12-03T07:14:15,074 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:15,074 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=30, ppid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 291 msec 2024-12-03T07:14:15,076 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=29, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 441 msec 2024-12-03T07:14:15,092 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x781859ef to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3fb3587d 2024-12-03T07:14:15,105 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:15,105 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:15,105 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@246cdb91, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:15,107 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:15,112 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:15,113 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152001f connected 2024-12-03T07:14:15,113 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:15,270 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=29 2024-12-03T07:14:15,270 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:15,271 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:15,273 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-03T07:14:15,274 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=31, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:15,276 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-03T07:14:15,295 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:15,296 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:15,304 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:15,304 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520020 connected 2024-12-03T07:14:15,380 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-03T07:14:15,413 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520020, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:15,424 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=32, ppid=31, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:15,578 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:15,580 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=32 2024-12-03T07:14:15,581 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:15,584 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:15,584 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:15,585 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:15,585 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152001f, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:15,585 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152001f, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:15,589 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-03T07:14:15,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:15,696 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152001f, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:15,696 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x781859ef to 127.0.0.1:55234 2024-12-03T07:14:15,696 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:15,715 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:15,715 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:15,716 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=32}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=32 2024-12-03T07:14:15,717 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=32 2024-12-03T07:14:15,720 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:15,723 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=32, resume processing ppid=31 2024-12-03T07:14:15,723 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-03T07:14:15,723 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=32, ppid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 296 msec 2024-12-03T07:14:15,726 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=31, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 450 msec 2024-12-03T07:14:15,758 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1897a5e9 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@71ccc3f6 2024-12-03T07:14:15,771 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:15,772 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:15,772 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5aee8c3d, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:15,773 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:15,779 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:15,780 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:15,781 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520022 connected 2024-12-03T07:14:15,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=31 2024-12-03T07:14:15,900 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:15,900 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:15,902 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns1:testNamespacesAndTableCfsConfigConflict1=null},bandwidth=0,serial=false 2024-12-03T07:14:15,903 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=33, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:15,904 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-03T07:14:15,920 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:15,921 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:15,931 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:15,932 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520023 connected 2024-12-03T07:14:16,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-03T07:14:16,038 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520023, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:16,038 WARN [PEWorker-5 {}] 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] 2024-12-03T07:14:16,040 ERROR [PEWorker-5 {}] 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 2024-12-03T07:14:16,042 INFO [PEWorker-5 {}] 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=138 msec 2024-12-03T07:14:16,042 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. 2024-12-03T07:14:16,220 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=33 2024-12-03T07:14:16,221 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 2024-12-03T07:14:16,222 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:16,223 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-03T07:14:16,225 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=34, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:16,226 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-03T07:14:16,247 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:16,248 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:16,254 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:16,255 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520024 connected 2024-12-03T07:14:16,330 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-03T07:14:16,363 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520024, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:16,373 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=35, ppid=34, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:16,526 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:16,527 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=35 2024-12-03T07:14:16,527 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:16,529 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:16,529 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:16,529 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:16,529 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520022, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:16,529 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520022, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:16,540 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-03T07:14:16,638 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520022, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:16,638 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1897a5e9 to 127.0.0.1:55234 2024-12-03T07:14:16,638 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:16,658 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:16,658 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:16,658 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=35}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=35 2024-12-03T07:14:16,659 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=35 2024-12-03T07:14:16,662 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:16,666 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=35, resume processing ppid=34 2024-12-03T07:14:16,666 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-03T07:14:16,666 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=35, ppid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-03T07:14:16,669 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=34, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 443 msec 2024-12-03T07:14:16,692 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x139a3c3f to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7e728a43 2024-12-03T07:14:16,705 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:16,705 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:16,705 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3552c530, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:16,706 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:16,712 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:16,713 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:16,713 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520026 connected 2024-12-03T07:14:16,850 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=34 2024-12-03T07:14:16,850 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:16,851 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:16,852 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2],tableCFs={ns2:testNamespacesAndTableCfsConfigConflict2=null},bandwidth=0,serial=false 2024-12-03T07:14:16,853 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=36, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:16,854 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-03T07:14:16,869 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:16,870 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:16,886 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:16,887 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520027 connected 2024-12-03T07:14:16,960 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-03T07:14:16,996 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520027, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:16,996 WARN [PEWorker-5 {}] 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] 2024-12-03T07:14:16,997 ERROR [PEWorker-5 {}] 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 2024-12-03T07:14:16,999 INFO [PEWorker-5 {}] 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=146 msec 2024-12-03T07:14:16,999 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. 2024-12-03T07:14:17,170 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=36 2024-12-03T07:14:17,170 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 2024-12-03T07:14:17,171 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:17,172 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=37, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:17,173 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-03T07:14:17,176 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:17,187 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:17,188 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:17,188 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:17,189 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=38, ppid=37, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:17,280 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-03T07:14:17,341 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:17,342 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=38 2024-12-03T07:14:17,342 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:17,343 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:17,343 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:17,343 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:17,343 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520026, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:17,343 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520026, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:17,454 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520026, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:17,454 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x139a3c3f to 127.0.0.1:55234 2024-12-03T07:14:17,454 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:17,455 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:17,489 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-03T07:14:17,489 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:17,513 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:17,513 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:17,513 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:17,514 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:17,514 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=38}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=38 2024-12-03T07:14:17,516 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=38 2024-12-03T07:14:17,518 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:17,522 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=38, resume processing ppid=37 2024-12-03T07:14:17,522 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=38, ppid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 329 msec 2024-12-03T07:14:17,539 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:17,539 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:17,542 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=37, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 368 msec 2024-12-03T07:14:17,669 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:17,800 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=37 2024-12-03T07:14:17,801 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:17,802 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:17,805 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=39, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:17,807 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-03T07:14:17,807 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] 2024-12-03T07:14:17,810 ERROR [PEWorker-5 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:17,813 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=39, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=9 msec 2024-12-03T07:14:17,813 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:17,910 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=39 2024-12-03T07:14:17,911 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:17,911 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:17,913 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=40, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:17,914 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-03T07:14:17,914 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] 2024-12-03T07:14:17,916 ERROR [PEWorker-3 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:17,918 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=40, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-03T07:14:17,918 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:18,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=40 2024-12-03T07:14:18,021 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:18,033 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=154 (was 154), ProcessCount=11 (was 11), AvailableMemoryMB=2480 (was 2533) 2024-12-03T07:14:18,041 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAddRemovePeer[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=154, ProcessCount=11, AvailableMemoryMB=2480 2024-12-03T07:14:18,042 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:18,044 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=41, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:18,044 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-03T07:14:18,057 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:18,057 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:18,071 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:18,071 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520028 connected 2024-12-03T07:14:18,150 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-03T07:14:18,179 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520028, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:18,230 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=42, ppid=41, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:18,359 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-03T07:14:18,383 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:18,383 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=42 2024-12-03T07:14:18,383 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:18,396 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=42}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:18,406 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:18,596 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=42}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=42 2024-12-03T07:14:18,597 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=42 2024-12-03T07:14:18,599 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:18,603 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=42, resume processing ppid=41 2024-12-03T07:14:18,603 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:18,603 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=42, ppid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 371 msec 2024-12-03T07:14:18,605 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=41, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 561 msec 2024-12-03T07:14:18,630 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x26394294 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@105334cb 2024-12-03T07:14:18,670 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=41 2024-12-03T07:14:18,670 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:18,671 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:18,672 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=43, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:18,673 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-03T07:14:18,682 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$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 2024-12-03T07:14:18,683 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:18,683 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@67b8b47f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:18,684 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:18,686 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:18,687 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:18,720 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:18,720 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152002a connected 2024-12-03T07:14:18,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-03T07:14:18,826 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:18,826 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:18,827 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152002b connected 2024-12-03T07:14:18,984 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152002b, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:18,984 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: 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] 2024-12-03T07:14:18,987 ERROR [PEWorker-3 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preAddPeer(ReplicationPeerManager.java:121) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.AddPeerProcedure.prePeerModification(AddPeerProcedure.java:90) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:18,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-03T07:14:18,989 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=43, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Replication peer 1 already exists; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=316 msec 2024-12-03T07:14:18,989 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:19,291 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:14:19,299 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=43 2024-12-03T07:14:19,300 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Replication peer 1 already exists 2024-12-03T07:14:19,305 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:19,308 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:19,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=44, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:19,311 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-03T07:14:19,311 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] 2024-12-03T07:14:19,313 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:19,314 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=44, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-03T07:14:19,314 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:19,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=44 2024-12-03T07:14:19,422 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:19,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:19,424 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=2, config=clusterKey=127.0.0.1:55234:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:19,426 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=45, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:19,428 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-03T07:14:19,442 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:19,442 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:19,481 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:19,482 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152002c connected 2024-12-03T07:14:19,540 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-03T07:14:19,613 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152002c, quorum=127.0.0.1:55234, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:19,666 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=46, ppid=45, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:19,750 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-03T07:14:19,818 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:19,819 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=46 2024-12-03T07:14:19,819 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=ADD_PEER 2024-12-03T07:14:19,827 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 2000 millis 2024-12-03T07:14:19,834 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=46}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:19,846 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.ReplicationSource(229): queueId=2, ReplicationSource: 2, currentBandwidth=0 2024-12-03T07:14:19,882 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=46}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=46 2024-12-03T07:14:19,882 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=46 2024-12-03T07:14:19,885 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:19,888 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=46, resume processing ppid=45 2024-12-03T07:14:19,888 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 2, config clusterKey=127.0.0.1:55234:/hbase-test2,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:19,888 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=46, ppid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 219 msec 2024-12-03T07:14:19,890 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=45, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 464 msec 2024-12-03T07:14:19,907 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x14a1c7e7 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3fc08f4b 2024-12-03T07:14:19,913 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:19,913 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:19,913 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1a667b5b, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:19,914 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 2 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:19,921 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 20x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:19,921 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] regionserver.ReplicationSource(569): peerId=2, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:19,921 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 2-0x1019b541152002e connected 2024-12-03T07:14:20,059 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=45 2024-12-03T07:14:20,060 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 2 completed 2024-12-03T07:14:20,060 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:20,062 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:20,064 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=47, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:20,065 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-03T07:14:20,068 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:20,079 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:20,079 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:20,079 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:20,080 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=48, ppid=47, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:20,169 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-03T07:14:20,232 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:20,233 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=48 2024-12-03T07:14:20,233 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:20,233 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:20,233 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:20,233 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:20,233 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152002a, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:20,234 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152002a, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:20,337 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152002a, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:20,337 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x26394294 to 127.0.0.1:55234 2024-12-03T07:14:20,338 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:20,338 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:20,346 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:20,354 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:20,354 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:20,354 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:20,354 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:20,355 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=48}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=48 2024-12-03T07:14:20,355 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=48 2024-12-03T07:14:20,358 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:20,360 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=48, resume processing ppid=47 2024-12-03T07:14:20,360 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=48, ppid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 278 msec 2024-12-03T07:14:20,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-03T07:14:20,379 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:20,379 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:20,382 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=47, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 317 msec 2024-12-03T07:14:20,690 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=47 2024-12-03T07:14:20,690 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:20,690 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:20,691 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:20,692 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=49, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:20,693 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-03T07:14:20,695 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/2/peer-state 2024-12-03T07:14:20,704 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2/peer-state 2024-12-03T07:14:20,704 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-03T07:14:20,704 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/2 2024-12-03T07:14:20,705 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=50, ppid=49, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:20,800 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-03T07:14:20,858 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:20,859 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=50 2024-12-03T07:14:20,859 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=2, type=REMOVE_PEER 2024-12-03T07:14:20,860 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 2: 0 2024-12-03T07:14:20,860 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSource(657): peerId=2, Closing source 2 because: Replication stream was removed by a user 2024-12-03T07:14:20,860 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] regionserver.ReplicationSource(508): peerId=2, Interrupted while sleeping between retries 2024-12-03T07:14:20,860 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] zookeeper.ZKUtil(165): connection to cluster: 2-0x1019b541152002e, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:20,861 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2 {}] zookeeper.ZKWatcher(734): connection to cluster: 2-0x1019b541152002e, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:20,971 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,2-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 2-0x1019b541152002e, quorum=127.0.0.1:55234, baseZNode=/hbase-test2 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:20,971 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x14a1c7e7 to 127.0.0.1:55234 2024-12-03T07:14:20,971 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:20,971 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.ReplicationSourceManager(430): Done with the queue 2 2024-12-03T07:14:20,979 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/2/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:20,987 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/2/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:20,987 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/2 2024-12-03T07:14:20,987 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/2 2024-12-03T07:14:20,988 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-03T07:14:20,988 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=50}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=50 2024-12-03T07:14:20,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=50 2024-12-03T07:14:20,991 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 2 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:20,993 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=50, resume processing ppid=49 2024-12-03T07:14:20,993 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=50, ppid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-03T07:14:21,005 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/2 not found in hfile reference queue. 2024-12-03T07:14:21,005 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 2 2024-12-03T07:14:21,007 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=49, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 314 msec 2024-12-03T07:14:21,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=49 2024-12-03T07:14:21,009 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 2 completed 2024-12-03T07:14:21,010 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:21,010 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:21,012 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=51, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:21,012 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-03T07:14:21,013 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] 2024-12-03T07:14:21,014 ERROR [PEWorker-5 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:21,016 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=51, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-03T07:14:21,016 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:21,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=51 2024-12-03T07:14:21,120 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:21,120 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:21,121 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=52, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:21,122 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-03T07:14:21,123 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] 2024-12-03T07:14:21,124 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=52, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:21,125 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=52, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-03T07:14:21,125 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:21,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=52 2024-12-03T07:14:21,231 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:21,249 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=174 (was 154) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=2401 (was 2480) 2024-12-03T07:14:21,261 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidReplicationEndpoint[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=174, ProcessCount=11, AvailableMemoryMB=2400 2024-12-03T07:14:21,263 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] 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 2024-12-03T07:14:21,264 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=53, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:21,265 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-03T07:14:21,266 WARN [PEWorker-3 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.AddPeerProcedure failed to call pre CP hook or the pre check is failed for peer 1, mark the procedure as failure and give up org.apache.hadoop.hbase.DoNotRetryIOException: 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 2024-12-03T07:14:21,267 ERROR [PEWorker-3 {}] 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 2024-12-03T07:14:21,269 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=53, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Can not instantiate configured replication endpoint class=whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=5 msec 2024-12-03T07:14:21,269 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. 2024-12-03T07:14:21,370 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=53 2024-12-03T07:14:21,371 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 2024-12-03T07:14:21,376 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:21,378 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=54, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:21,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-03T07:14:21,379 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] 2024-12-03T07:14:21,381 ERROR [PEWorker-4 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:21,382 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=54, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-03T07:14:21,382 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:21,490 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=54 2024-12-03T07:14:21,491 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:21,493 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:21,496 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=55, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:21,497 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-03T07:14:21,497 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] 2024-12-03T07:14:21,499 ERROR [PEWorker-2 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=55, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:21,500 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=55, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-03T07:14:21,500 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:21,599 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=55 2024-12-03T07:14:21,600 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:21,614 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=174 (was 174), ProcessCount=11 (was 11), AvailableMemoryMB=2398 (was 2400) 2024-12-03T07:14:21,621 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testInvalidClusterKey[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=174, ProcessCount=11, AvailableMemoryMB=2398 2024-12-03T07:14:21,622 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] 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 2024-12-03T07:14:21,623 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=56, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:21,624 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-03T07:14:21,625 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: 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 2024-12-03T07:14:21,627 ERROR [PEWorker-5 {}] 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 2024-12-03T07:14:21,628 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=56, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.DoNotRetryIOException via master-add-peer:org.apache.hadoop.hbase.DoNotRetryIOException: Invalid cluster key: whatever; org.apache.hadoop.hbase.master.replication.AddPeerProcedure exec-time=5 msec 2024-12-03T07:14:21,628 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. 2024-12-03T07:14:21,689 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:21,730 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=56 2024-12-03T07:14:21,731 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Invalid cluster key: whatever 2024-12-03T07:14:21,732 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:21,735 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=57, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:21,737 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-03T07:14:21,737 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] 2024-12-03T07:14:21,739 ERROR [PEWorker-1 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=57, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:21,742 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=57, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=8 msec 2024-12-03T07:14:21,742 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:21,840 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=57 2024-12-03T07:14:21,841 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:21,842 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:21,844 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=58, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:21,845 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-03T07:14:21,846 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] 2024-12-03T07:14:21,847 ERROR [PEWorker-3 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:21,849 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=58, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=6 msec 2024-12-03T07:14:21,849 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:21,949 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=58 2024-12-03T07:14:21,950 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:21,964 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=174 (was 174), ProcessCount=11 (was 11), AvailableMemoryMB=2397 (was 2398) 2024-12-03T07:14:21,974 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetPeerNamespaces[0] Thread=221, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=174, ProcessCount=11, AvailableMemoryMB=2397 2024-12-03T07:14:21,975 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:21,976 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=59, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:21,977 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-03T07:14:21,996 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:21,996 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:22,004 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:22,004 ERROR [PEWorker-4-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f0c208d4e18@40caa18f rejected from java.util.concurrent.ThreadPoolExecutor@5c827f2[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] 2024-12-03T07:14:22,080 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-03T07:14:22,113 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:22,132 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=60, ppid=59, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:22,286 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:22,287 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=60 2024-12-03T07:14:22,287 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:22,290 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-03T07:14:22,301 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=60}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:22,312 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:22,354 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=60}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=60 2024-12-03T07:14:22,356 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=60 2024-12-03T07:14:22,359 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:22,364 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=60, resume processing ppid=59 2024-12-03T07:14:22,364 INFO [PEWorker-1 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:22,364 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=60, ppid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 228 msec 2024-12-03T07:14:22,367 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=59, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 390 msec 2024-12-03T07:14:22,389 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4b13155c to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1d9cb14c 2024-12-03T07:14:22,396 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:22,397 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:22,397 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3d37de91, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:22,398 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:22,404 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:22,404 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:22,404 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520031 connected 2024-12-03T07:14:22,599 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=59 2024-12-03T07:14:22,599 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:22,600 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:22,601 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=61, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:22,602 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-03T07:14:22,619 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:22,620 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:22,629 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:22,629 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520032 connected 2024-12-03T07:14:22,709 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-03T07:14:22,737 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520032, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:22,747 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=62, ppid=61, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:22,901 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:22,902 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=62 2024-12-03T07:14:22,902 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:22,903 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:22,903 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:22,903 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:22,903 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520031, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:22,903 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520031, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:22,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-03T07:14:23,012 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520031, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:23,013 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4b13155c to 127.0.0.1:55234 2024-12-03T07:14:23,013 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:23,031 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:23,031 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:23,032 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=62}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=62 2024-12-03T07:14:23,032 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=62 2024-12-03T07:14:23,034 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:23,037 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=62, resume processing ppid=61 2024-12-03T07:14:23,037 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:23,037 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=62, ppid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 288 msec 2024-12-03T07:14:23,039 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=61, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 437 msec 2024-12-03T07:14:23,056 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2359be58 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2f376a8 2024-12-03T07:14:23,063 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:23,063 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:23,063 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@510e0933, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:23,064 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:23,093 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:23,093 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:23,093 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520034 connected 2024-12-03T07:14:23,230 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=61 2024-12-03T07:14:23,231 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:23,231 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:23,233 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-03T07:14:23,234 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=63, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:23,235 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-03T07:14:23,248 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:23,248 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:23,254 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:23,254 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520035 connected 2024-12-03T07:14:23,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-03T07:14:23,362 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520035, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:23,372 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=64, ppid=63, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:23,525 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:23,526 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=64 2024-12-03T07:14:23,527 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:23,530 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:23,531 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:23,531 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:23,531 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520034, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:23,532 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520034, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:23,550 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-03T07:14:23,638 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520034, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:23,638 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2359be58 to 127.0.0.1:55234 2024-12-03T07:14:23,638 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:23,651 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:23,651 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:23,651 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=64}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=64 2024-12-03T07:14:23,652 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=64 2024-12-03T07:14:23,654 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:23,657 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=64, resume processing ppid=63 2024-12-03T07:14:23,657 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns2, ns1],bandwidth=0,serial=false 2024-12-03T07:14:23,657 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=64, ppid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-03T07:14:23,658 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=63, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 424 msec 2024-12-03T07:14:23,678 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x44332ae1 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4552fd24 2024-12-03T07:14:23,688 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:23,688 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:23,688 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@65cd433e, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:23,689 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:23,695 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:23,696 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:23,696 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520037 connected 2024-12-03T07:14:23,860 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=63 2024-12-03T07:14:23,861 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:23,861 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:23,862 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:23,864 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-03T07:14:23,866 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=65, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:23,867 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-03T07:14:23,882 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:23,882 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:23,895 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:23,896 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520038 connected 2024-12-03T07:14:23,969 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-03T07:14:24,004 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520038, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:24,013 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=66, ppid=65, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:24,165 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:24,166 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=66 2024-12-03T07:14:24,166 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:24,168 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:24,168 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:24,169 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:24,169 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520037, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:24,169 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520037, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:24,180 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-03T07:14:24,279 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520037, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:24,279 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x44332ae1 to 127.0.0.1:55234 2024-12-03T07:14:24,279 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:24,300 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:24,301 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:24,301 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=66}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=66 2024-12-03T07:14:24,302 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=66 2024-12-03T07:14:24,307 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:24,312 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=66, resume processing ppid=65 2024-12-03T07:14:24,312 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,namespaces=[ns1],bandwidth=0,serial=false 2024-12-03T07:14:24,312 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=66, ppid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 294 msec 2024-12-03T07:14:24,315 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=65, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 448 msec 2024-12-03T07:14:24,331 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4ff6b342 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5d82bc16 2024-12-03T07:14:24,338 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:24,338 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:24,338 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@3fed6823, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:24,339 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:24,346 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:24,346 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:24,346 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152003a connected 2024-12-03T07:14:24,490 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=65 2024-12-03T07:14:24,490 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:24,491 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:24,491 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:24,493 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=67, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:24,494 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-03T07:14:24,498 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:24,512 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:24,512 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:24,512 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:24,514 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=68, ppid=67, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:24,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-03T07:14:24,667 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:24,667 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=68 2024-12-03T07:14:24,668 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:24,668 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:24,668 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:24,668 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:24,668 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152003a, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:24,668 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152003a, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:24,779 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152003a, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:24,779 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4ff6b342 to 127.0.0.1:55234 2024-12-03T07:14:24,779 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:24,780 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:24,787 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:24,795 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:24,796 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:24,796 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:24,796 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:24,796 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=68}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=68 2024-12-03T07:14:24,797 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=68 2024-12-03T07:14:24,799 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:24,802 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=68, resume processing ppid=67 2024-12-03T07:14:24,802 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=68, ppid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-03T07:14:24,810 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-03T07:14:24,813 DEBUG [PEWorker-1 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:24,813 INFO [PEWorker-1 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:24,815 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=67, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 322 msec 2024-12-03T07:14:25,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=67 2024-12-03T07:14:25,121 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:25,122 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:25,124 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=69, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:25,125 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-03T07:14:25,125 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] 2024-12-03T07:14:25,127 ERROR [PEWorker-3 {}] 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 2024-12-03T07:14:25,129 INFO [PEWorker-3 {}] 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=6 msec 2024-12-03T07:14:25,129 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. 2024-12-03T07:14:25,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=69 2024-12-03T07:14:25,230 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:25,231 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:25,232 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=70, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:25,232 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-03T07:14:25,233 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] 2024-12-03T07:14:25,234 ERROR [PEWorker-4 {}] 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 2024-12-03T07:14:25,235 INFO [PEWorker-4 {}] 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=3 msec 2024-12-03T07:14:25,235 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. 2024-12-03T07:14:25,339 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=70 2024-12-03T07:14:25,340 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:25,350 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=160 (was 174), ProcessCount=11 (was 11), AvailableMemoryMB=2335 (was 2397) 2024-12-03T07:14:25,357 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=220, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=160, ProcessCount=11, AvailableMemoryMB=2334 2024-12-03T07:14:25,358 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:25,359 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=71, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:25,360 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-03T07:14:25,374 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:25,375 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:25,379 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:25,379 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152003b connected 2024-12-03T07:14:25,470 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-03T07:14:25,487 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152003b, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:25,505 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=72, ppid=71, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:25,657 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:25,657 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=72 2024-12-03T07:14:25,658 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:25,675 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=72}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:25,680 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-03T07:14:25,686 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:25,729 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=72}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=72 2024-12-03T07:14:25,730 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=72 2024-12-03T07:14:25,732 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:25,734 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=72, resume processing ppid=71 2024-12-03T07:14:25,734 INFO [PEWorker-3 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:25,734 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=72, ppid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 227 msec 2024-12-03T07:14:25,736 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=71, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 376 msec 2024-12-03T07:14:25,755 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x421553d4 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2cb9b13a 2024-12-03T07:14:25,762 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:25,763 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:25,763 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@2e5a73c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:25,764 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:25,770 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:25,771 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:25,771 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152003d connected 2024-12-03T07:14:25,839 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:14:25,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=71 2024-12-03T07:14:25,990 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:25,990 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:25,992 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=73, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:25,992 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-03T07:14:26,007 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:26,007 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:26,012 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:26,013 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152003e connected 2024-12-03T07:14:26,099 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-03T07:14:26,121 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152003e, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:26,130 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=74, ppid=73, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:26,283 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:26,284 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=74 2024-12-03T07:14:26,284 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:26,285 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:26,286 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:26,286 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:26,286 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152003d, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:26,286 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152003d, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:26,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-03T07:14:26,395 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152003d, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:26,396 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x421553d4 to 127.0.0.1:55234 2024-12-03T07:14:26,396 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:26,408 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:26,409 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:26,409 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=74}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=74 2024-12-03T07:14:26,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=74 2024-12-03T07:14:26,411 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:26,414 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=74, resume processing ppid=73 2024-12-03T07:14:26,414 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:26,414 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=74, ppid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-12-03T07:14:26,416 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=73, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 424 msec 2024-12-03T07:14:26,439 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6271ca1e to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@4a2a6910 2024-12-03T07:14:26,446 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:26,447 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:26,447 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:26,448 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:26,454 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:26,454 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:26,454 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520040 connected 2024-12-03T07:14:26,620 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=73 2024-12-03T07:14:26,621 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:26,621 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:26,623 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-03T07:14:26,625 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=75, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:26,626 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-03T07:14:26,644 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:26,644 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:26,654 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:26,654 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520041 connected 2024-12-03T07:14:26,730 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-03T07:14:26,762 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520041, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:26,773 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=76, ppid=75, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:26,927 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:26,927 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=76 2024-12-03T07:14:26,927 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:26,929 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:26,929 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:26,929 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:26,929 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520040, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:26,929 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520040, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:26,940 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-03T07:14:27,037 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520040, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:27,037 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6271ca1e to 127.0.0.1:55234 2024-12-03T07:14:27,037 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:27,054 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:27,055 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:27,055 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=76}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=76 2024-12-03T07:14:27,056 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=76 2024-12-03T07:14:27,058 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:27,061 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=76, resume processing ppid=75 2024-12-03T07:14:27,061 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null},bandwidth=0,serial=false 2024-12-03T07:14:27,061 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=76, ppid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-03T07:14:27,062 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=75, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 438 msec 2024-12-03T07:14:27,081 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x15687f26 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6bfc116e 2024-12-03T07:14:27,096 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:27,097 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:27,097 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:27,098 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:27,104 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:27,104 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:27,104 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520043 connected 2024-12-03T07:14:27,251 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=75 2024-12-03T07:14:27,252 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:27,253 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:27,254 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:27,255 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-03T07:14:27,257 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=77, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:27,257 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-03T07:14:27,273 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:27,274 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:27,332 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:27,333 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520044 connected 2024-12-03T07:14:27,371 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-03T07:14:27,466 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520044, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:27,479 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=78, ppid=77, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:27,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-03T07:14:27,631 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:27,632 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=78 2024-12-03T07:14:27,632 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:27,633 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:27,633 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:27,633 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:27,634 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520043, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:27,634 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520043, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:27,745 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520043, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:27,746 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x15687f26 to 127.0.0.1:55234 2024-12-03T07:14:27,746 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:27,760 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:27,761 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:27,761 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=78}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=78 2024-12-03T07:14:27,761 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=78 2024-12-03T07:14:27,763 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:27,764 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=78, resume processing ppid=77 2024-12-03T07:14:27,764 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-03T07:14:27,765 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=78, ppid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-12-03T07:14:27,766 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=77, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 510 msec 2024-12-03T07:14:27,790 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6ab29148 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2cbcd790 2024-12-03T07:14:27,838 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:27,838 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:27,839 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:27,840 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:27,879 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:27,879 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:27,879 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520046 connected 2024-12-03T07:14:27,889 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=77 2024-12-03T07:14:27,890 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:27,890 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:27,891 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:27,892 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-03T07:14:27,893 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=79, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:27,894 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-03T07:14:27,908 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:27,908 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:27,957 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:27,958 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520047 connected 2024-12-03T07:14:27,999 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-03T07:14:28,087 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520047, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:28,137 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=80, ppid=79, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:28,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-03T07:14:28,289 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:28,290 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=80 2024-12-03T07:14:28,290 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:28,293 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:28,293 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:28,293 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:28,293 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520046, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:28,294 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520046, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:28,431 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520046, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:28,431 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6ab29148 to 127.0.0.1:55234 2024-12-03T07:14:28,431 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:28,452 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:28,452 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:28,453 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=80}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=80 2024-12-03T07:14:28,453 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=80 2024-12-03T07:14:28,455 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:28,457 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=80, resume processing ppid=79 2024-12-03T07:14:28,457 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null},bandwidth=0,serial=false 2024-12-03T07:14:28,457 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=80, ppid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 318 msec 2024-12-03T07:14:28,458 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=79, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 565 msec 2024-12-03T07:14:28,478 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7a55765e to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2a9e9dcc 2024-12-03T07:14:28,519 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=79 2024-12-03T07:14:28,520 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:28,520 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:28,522 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:28,523 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-03T07:14:28,525 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=81, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:28,526 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-03T07:14:28,541 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:28,541 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:28,541 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:28,542 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:28,549 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:28,549 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:28,595 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:28,595 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520049 connected 2024-12-03T07:14:28,629 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-03T07:14:28,646 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:28,646 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:28,646 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152004a connected 2024-12-03T07:14:28,799 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152004a, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:28,831 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=82, ppid=81, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:28,840 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-03T07:14:28,985 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:28,986 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=82 2024-12-03T07:14:28,986 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:28,987 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:28,987 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:28,988 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:28,988 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520049, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:28,988 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520049, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:29,121 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520049, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:29,121 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7a55765e to 127.0.0.1:55234 2024-12-03T07:14:29,121 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:29,134 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:29,134 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:29,134 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=82}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=82 2024-12-03T07:14:29,135 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=82 2024-12-03T07:14:29,137 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:29,139 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=82, resume processing ppid=81 2024-12-03T07:14:29,139 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-03T07:14:29,139 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=82, ppid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 306 msec 2024-12-03T07:14:29,141 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=81, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 616 msec 2024-12-03T07:14:29,149 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=81 2024-12-03T07:14:29,149 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:29,150 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:29,151 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:29,151 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-03T07:14:29,153 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=83, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:29,153 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-03T07:14:29,163 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7ac73cdf to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7fc810dc 2024-12-03T07:14:29,166 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:29,167 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:29,179 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:29,179 ERROR [PEWorker-5-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f0c208d4e18@7dcfe486 rejected from java.util.concurrent.ThreadPoolExecutor@79f06fe7[Terminated, pool size = 0, active threads = 0, queued tasks = 0, completed tasks = 0] at java.util.concurrent.ThreadPoolExecutor$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$EventThread.run(ClientCnxn.java:554) ~[zookeeper-3.8.4.jar:3.8.4] 2024-12-03T07:14:29,179 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$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 2024-12-03T07:14:29,180 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:29,180 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@35d95b60, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:29,181 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:29,245 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:29,246 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:29,246 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152004d connected 2024-12-03T07:14:29,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-03T07:14:29,303 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:29,314 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=84, ppid=83, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:29,466 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:29,467 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=84 2024-12-03T07:14:29,467 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:29,468 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:29,468 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:29,468 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:29,469 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152004d, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:29,469 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152004d, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:29,470 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-03T07:14:29,579 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152004d, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:29,579 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7ac73cdf to 127.0.0.1:55234 2024-12-03T07:14:29,579 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:29,592 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:29,592 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:29,592 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=84}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=84 2024-12-03T07:14:29,593 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=84 2024-12-03T07:14:29,595 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:29,597 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=84, resume processing ppid=83 2024-12-03T07:14:29,597 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-03T07:14:29,597 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=84, ppid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-03T07:14:29,599 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=83, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 445 msec 2024-12-03T07:14:29,620 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x7c3cd9ae to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1985a464 2024-12-03T07:14:29,629 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:29,629 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:29,630 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1ec105e5, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:29,630 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:29,637 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:29,637 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:29,638 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152004f connected 2024-12-03T07:14:29,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=83 2024-12-03T07:14:29,780 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:29,780 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:29,781 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-03T07:14:29,782 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=85, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:29,783 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-03T07:14:29,798 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:29,799 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:29,804 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:29,804 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520050 connected 2024-12-03T07:14:29,890 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-03T07:14:29,912 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520050, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:29,921 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=86, ppid=85, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:30,073 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:30,074 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=86 2024-12-03T07:14:30,074 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:30,076 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=86}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=86 2024-12-03T07:14:30,077 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=86 2024-12-03T07:14:30,080 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:30,083 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=86, resume processing ppid=85 2024-12-03T07:14:30,083 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2]},bandwidth=0,serial=false 2024-12-03T07:14:30,083 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=86, ppid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 159 msec 2024-12-03T07:14:30,086 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=85, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 302 msec 2024-12-03T07:14:30,099 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=85 2024-12-03T07:14:30,100 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:30,100 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:30,100 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:30,101 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-03T07:14:30,102 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=87, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:30,103 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-03T07:14:30,115 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:30,115 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:30,120 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:30,121 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520051 connected 2024-12-03T07:14:30,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-03T07:14:30,229 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520051, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:30,238 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=88, ppid=87, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:30,390 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:30,390 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=88 2024-12-03T07:14:30,390 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:30,392 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:30,392 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:30,392 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:30,392 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152004f, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:30,392 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152004f, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:30,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-03T07:14:30,501 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152004f, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:30,501 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x7c3cd9ae to 127.0.0.1:55234 2024-12-03T07:14:30,501 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:30,521 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:30,521 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:30,521 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=88}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=88 2024-12-03T07:14:30,522 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=88 2024-12-03T07:14:30,524 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:30,525 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=88, resume processing ppid=87 2024-12-03T07:14:30,525 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=88, ppid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 286 msec 2024-12-03T07:14:30,525 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=[f1]},bandwidth=0,serial=false 2024-12-03T07:14:30,527 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=87, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 424 msec 2024-12-03T07:14:30,547 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5e816d0f to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@7acc7221 2024-12-03T07:14:30,554 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:30,554 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:30,554 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@73dbf4a5, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:30,555 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:30,562 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:30,562 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:30,562 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520053 connected 2024-12-03T07:14:30,730 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=87 2024-12-03T07:14:30,730 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:30,730 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:30,731 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-03T07:14:30,732 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=89, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:30,733 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-03T07:14:30,748 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:30,749 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:30,754 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:30,754 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520054 connected 2024-12-03T07:14:30,839 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-03T07:14:30,862 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520054, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:30,902 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=90, ppid=89, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:31,049 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-03T07:14:31,054 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:31,054 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=90 2024-12-03T07:14:31,055 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:31,056 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:31,056 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:31,056 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:31,056 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520053, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:31,057 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520053, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:31,162 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520053, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:31,162 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5e816d0f to 127.0.0.1:55234 2024-12-03T07:14:31,162 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:31,181 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:31,181 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:31,182 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=90}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=90 2024-12-03T07:14:31,182 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=90 2024-12-03T07:14:31,184 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:31,187 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=90, resume processing ppid=89 2024-12-03T07:14:31,187 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testAppendPeerTableCFst1=null, testAppendPeerTableCFst3=[f1], testAppendPeerTableCFst2=null, testAppendPeerTableCFst5=null, testAppendPeerTableCFst4=[f1, f2], testAppendPeerTableCFst6=null},bandwidth=0,serial=false 2024-12-03T07:14:31,187 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=90, ppid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-03T07:14:31,189 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=89, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 456 msec 2024-12-03T07:14:31,212 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x3ab61c8a to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@3d72652d 2024-12-03T07:14:31,221 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:31,222 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:31,222 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4bbc5b8c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:31,223 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:31,229 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:31,229 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:31,229 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520056 connected 2024-12-03T07:14:31,359 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=89 2024-12-03T07:14:31,360 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:31,360 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:31,361 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:31,362 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=91, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:31,362 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-03T07:14:31,364 DEBUG [PEWorker-5 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:31,370 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:31,370 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:31,370 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:31,371 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=92, ppid=91, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:31,469 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-03T07:14:31,523 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:31,524 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=92 2024-12-03T07:14:31,524 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:31,524 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:31,524 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:31,524 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:31,524 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520056, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:31,524 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520056, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:31,629 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520056, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:31,629 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x3ab61c8a to 127.0.0.1:55234 2024-12-03T07:14:31,629 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:31,629 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:31,637 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:31,645 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:31,645 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:31,645 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:31,645 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:31,646 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=92}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=92 2024-12-03T07:14:31,646 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=92 2024-12-03T07:14:31,648 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:31,650 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=92, resume processing ppid=91 2024-12-03T07:14:31,650 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=92, ppid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-03T07:14:31,654 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:31,654 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:31,656 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=91, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 293 msec 2024-12-03T07:14:31,679 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=91 2024-12-03T07:14:31,679 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:31,680 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:31,680 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=93, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:31,681 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-03T07:14:31,681 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] 2024-12-03T07:14:31,682 ERROR [PEWorker-4 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:31,683 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=93, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-03T07:14:31,683 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:31,709 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:31,789 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=93 2024-12-03T07:14:31,790 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:31,791 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:31,792 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=94, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:31,793 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-03T07:14:31,793 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] 2024-12-03T07:14:31,795 ERROR [PEWorker-5 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:31,797 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=94, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-03T07:14:31,797 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:31,900 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=94 2024-12-03T07:14:31,901 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:31,914 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testAppendPeerTableCFs[0] Thread=219 (was 220), OpenFileDescriptor=444 (was 444), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=187 (was 160) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=2177 (was 2334) 2024-12-03T07:14:31,921 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=219, OpenFileDescriptor=444, MaxFileDescriptor=1048576, SystemLoadAverage=187, ProcessCount=11, AvailableMemoryMB=2176 2024-12-03T07:14:31,922 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:31,923 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=95, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:31,924 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-03T07:14:31,939 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:31,939 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:31,945 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:31,946 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520057 connected 2024-12-03T07:14:32,028 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. 2024-12-03T07:14:32,029 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-03T07:14:32,054 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520057, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:32,071 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=96, ppid=95, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:32,223 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:32,224 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=96 2024-12-03T07:14:32,224 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:32,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-03T07:14:32,243 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=96}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:32,260 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:32,304 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=96}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=96 2024-12-03T07:14:32,304 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=96 2024-12-03T07:14:32,306 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:32,308 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=96, resume processing ppid=95 2024-12-03T07:14:32,308 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:32,308 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=96, ppid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 235 msec 2024-12-03T07:14:32,309 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=95, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 386 msec 2024-12-03T07:14:32,338 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x5eeb9654 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@57a92366 2024-12-03T07:14:32,346 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:32,346 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:32,346 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@13efe077, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:32,347 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:32,354 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:32,354 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:32,354 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520059 connected 2024-12-03T07:14:32,550 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=95 2024-12-03T07:14:32,550 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:32,551 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:32,555 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3938): Client=jenkins//172.17.0.2 disable replication peer, id=1 2024-12-03T07:14:32,558 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=97, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure 2024-12-03T07:14:32,559 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-03T07:14:32,571 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=98, ppid=97, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:32,670 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-03T07:14:32,723 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:32,724 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=98 2024-12-03T07:14:32,724 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=DISABLE_PEER 2024-12-03T07:14:32,724 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:32,724 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:32,725 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:32,725 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520059, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:32,725 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520059, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:32,829 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520059, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:32,829 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x5eeb9654 to 127.0.0.1:55234 2024-12-03T07:14:32,829 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:32,845 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:32,846 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:32,846 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=98}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=98 2024-12-03T07:14:32,847 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=98 2024-12-03T07:14:32,849 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for DISABLE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:32,851 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=98, resume processing ppid=97 2024-12-03T07:14:32,851 INFO [PEWorker-3 {}] replication.DisablePeerProcedure(67): Successfully disabled peer 1 2024-12-03T07:14:32,851 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=98, ppid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 278 msec 2024-12-03T07:14:32,852 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=97, state=SUCCESS; org.apache.hadoop.hbase.master.replication.DisablePeerProcedure in 296 msec 2024-12-03T07:14:32,879 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=97 2024-12-03T07:14:32,880 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: DISABLE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:32,880 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:32,882 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:32,882 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x18afbd98 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2d8aa74d 2024-12-03T07:14:32,883 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=99, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:32,884 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-03T07:14:32,887 DEBUG [PEWorker-4 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:32,887 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(702): Retrieve cluster id failed java.util.concurrent.ExecutionException: org.apache.zookeeper.KeeperException$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 2024-12-03T07:14:32,888 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:32,888 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5f8ff8c, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:32,889 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:32,895 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:32,895 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:32,895 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:32,896 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=100, ppid=99, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:32,904 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:32,904 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152005b connected 2024-12-03T07:14:32,904 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:32,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-03T07:14:33,048 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:33,049 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=100 2024-12-03T07:14:33,049 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:33,049 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:33,049 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:33,049 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:33,049 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152005b, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:33,049 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152005b, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:33,154 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152005b, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:33,154 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x18afbd98 to 127.0.0.1:55234 2024-12-03T07:14:33,154 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:33,154 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:33,162 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:33,171 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:33,171 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=100}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=100 2024-12-03T07:14:33,172 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=100 2024-12-03T07:14:33,174 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:33,175 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:33,175 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:33,175 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:33,177 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=100, resume processing ppid=99 2024-12-03T07:14:33,178 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=100, ppid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 278 msec 2024-12-03T07:14:33,187 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:33,187 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:33,191 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=99, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 305 msec 2024-12-03T07:14:33,200 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=99 2024-12-03T07:14:33,200 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:33,200 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:33,201 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=101, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:33,202 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-03T07:14:33,202 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] 2024-12-03T07:14:33,203 ERROR [PEWorker-3 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:33,205 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=101, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-03T07:14:33,205 WARN [PEWorker-3 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:33,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=101 2024-12-03T07:14:33,311 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:33,312 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:33,313 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=102, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:33,314 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-03T07:14:33,315 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] 2024-12-03T07:14:33,316 ERROR [PEWorker-4 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:33,318 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=102, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-03T07:14:33,318 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:33,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=102 2024-12-03T07:14:33,421 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:33,435 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testEnableDisablePeer[0] Thread=221 (was 219) - Thread LEAK? -, OpenFileDescriptor=446 (was 444) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=187 (was 187), ProcessCount=11 (was 11), AvailableMemoryMB=2115 (was 2176) 2024-12-03T07:14:33,444 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerNotFoundException[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=228, ProcessCount=11, AvailableMemoryMB=2114 2024-12-03T07:14:33,445 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=dummy_peer 2024-12-03T07:14:33,446 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=103, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:33,447 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-03T07:14:33,447 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 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] 2024-12-03T07:14:33,448 ERROR [PEWorker-5 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:33,450 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=103, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: dummy_peer; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-03T07:14:33,450 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:33,550 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=103 2024-12-03T07:14:33,551 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: dummy_peer failed with dummy_peer 2024-12-03T07:14:33,551 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:33,552 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=104, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:33,553 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-03T07:14:33,553 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] 2024-12-03T07:14:33,554 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:33,556 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=104, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=4 msec 2024-12-03T07:14:33,556 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:33,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=104 2024-12-03T07:14:33,660 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:33,661 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:33,662 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=105, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:33,663 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-03T07:14:33,663 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] 2024-12-03T07:14:33,664 ERROR [PEWorker-2 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:33,664 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=105, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-03T07:14:33,665 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:33,769 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=105 2024-12-03T07:14:33,770 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:33,782 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=228 (was 228), ProcessCount=11 (was 11), AvailableMemoryMB=2112 (was 2114) 2024-12-03T07:14:33,793 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=228, ProcessCount=11, AvailableMemoryMB=2112 2024-12-03T07:14:33,795 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:33,796 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=106, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:33,797 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-03T07:14:33,813 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:33,814 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:33,854 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:33,854 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152005c connected 2024-12-03T07:14:33,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-03T07:14:33,962 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152005c, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:33,980 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=107, ppid=106, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:34,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-03T07:14:34,133 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:34,133 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=107 2024-12-03T07:14:34,133 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:34,148 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=107}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:34,163 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:34,237 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=107}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=107 2024-12-03T07:14:34,238 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=107 2024-12-03T07:14:34,240 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:34,244 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=107, resume processing ppid=106 2024-12-03T07:14:34,244 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=107, ppid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 260 msec 2024-12-03T07:14:34,244 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:34,246 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=106, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 449 msec 2024-12-03T07:14:34,281 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x2e016fb8 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@5fb2939a 2024-12-03T07:14:34,288 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:34,288 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:34,289 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@4acdb8c1, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:34,291 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:34,295 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:34,296 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:34,298 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152005e connected 2024-12-03T07:14:34,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=106 2024-12-03T07:14:34,420 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:34,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3971): Client=jenkins//172.17.0.2 list replication peers, regex=null 2024-12-03T07:14:34,421 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:34,422 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=108, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:34,423 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-03T07:14:34,424 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:34,428 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:34,429 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:34,429 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:34,430 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=109, ppid=108, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:34,530 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-03T07:14:34,581 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:34,582 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=109 2024-12-03T07:14:34,582 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:34,582 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:34,582 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:34,583 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:34,583 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152005e, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:34,583 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152005e, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:34,687 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152005e, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:34,687 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x2e016fb8 to 127.0.0.1:55234 2024-12-03T07:14:34,687 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:34,687 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:34,695 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:34,703 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:34,703 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:34,703 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:34,704 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:34,704 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=109}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=109 2024-12-03T07:14:34,704 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=109 2024-12-03T07:14:34,706 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:34,708 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=109, resume processing ppid=108 2024-12-03T07:14:34,708 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=109, ppid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-03T07:14:34,712 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:34,712 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:34,714 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=108, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 291 msec 2024-12-03T07:14:34,739 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=108 2024-12-03T07:14:34,740 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:34,740 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:34,741 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=110, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:34,742 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-03T07:14:34,742 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] 2024-12-03T07:14:34,743 ERROR [PEWorker-5 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:34,744 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=110, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-03T07:14:34,744 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:34,849 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=110 2024-12-03T07:14:34,850 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:34,851 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:34,852 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=111, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:34,852 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-03T07:14:34,852 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] 2024-12-03T07:14:34,853 ERROR [PEWorker-2 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:34,854 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=111, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-03T07:14:34,854 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:34,960 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=111 2024-12-03T07:14:34,961 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:34,974 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerConfig[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=228 (was 228), ProcessCount=11 (was 11), AvailableMemoryMB=2092 (was 2112) 2024-12-03T07:14:34,982 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=228, ProcessCount=11, AvailableMemoryMB=2091 2024-12-03T07:14:34,988 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:34,988 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] 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$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-12-03T07:14:34,988 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] ipc.CallRunner(138): callId: 351 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:54796 deadline: 1733210134988, exception=java.io.IOException: Replication peer modification disabled 2024-12-03T07:14:35,008 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 1, maxAttempts = 2, timeout = 120000 ms, time elapsed = 21 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$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$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-03T07:14:35,120 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:35,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] ipc.MetricsHBaseServer(152): Unknown exception type java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) ~[classes/:?] at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) ~[classes/:?] at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) ~[classes/:?] at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$MasterService$2.callBlockingMethod(MasterProtos.java) ~[hbase-protocol-shaded-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) ~[classes/:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) ~[classes/:2.7.0-SNAPSHOT] 2024-12-03T07:14:35,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] ipc.CallRunner(138): callId: 352 service: MasterService methodName: AddReplicationPeer size: 80 connection: 172.17.0.2:54796 deadline: 1733210135119, exception=java.io.IOException: Replication peer modification disabled 2024-12-03T07:14:35,122 WARN [RPCClient-NioEventLoopGroup-4-2 {}] client.AsyncRpcRetryingCaller(168): Call to master failed, tries = 2, maxAttempts = 2, timeout = 120000 ms, time elapsed = 134 ms java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$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$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) at org.apache.hadoop.hbase.ipc.AbstractRpcClient.onCallFinished(AbstractRpcClient.java:392) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 33 more 2024-12-03T07:14:35,124 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 1 failed with Failed after attempts=2, exceptions: 2024-12-03T07:14:35.009Z, 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$2.callBlockingMethod(MasterProtos.java) at org.apache.hadoop.hbase.ipc.RpcServer.call(RpcServer.java:443) at org.apache.hadoop.hbase.ipc.CallRunner.run(CallRunner.java:124) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:105) at org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) 2024-12-03T07:14:35.123Z, java.io.IOException: java.io.IOException: Replication peer modification disabled at org.apache.hadoop.hbase.master.HMaster.executePeerProcedure(HMaster.java:3909) at org.apache.hadoop.hbase.master.HMaster.addReplicationPeer(HMaster.java:3921) at org.apache.hadoop.hbase.master.MasterRpcServices.addReplicationPeer(MasterRpcServices.java:2115) at org.apache.hadoop.hbase.shaded.protobuf.generated.MasterProtos$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) 2024-12-03T07:14:35,130 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:35,131 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=112, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:35,132 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-03T07:14:35,132 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] 2024-12-03T07:14:35,133 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=112, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:35,134 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=112, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=2 msec 2024-12-03T07:14:35,134 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:35,239 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=112 2024-12-03T07:14:35,240 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:35,240 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:35,242 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=113, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:35,243 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-03T07:14:35,244 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] 2024-12-03T07:14:35,248 ERROR [PEWorker-1 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:35,250 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=113, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=9 msec 2024-12-03T07:14:35,250 WARN [PEWorker-1 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:35,349 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=113 2024-12-03T07:14:35,350 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:35,365 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testReplicationPeerModificationSwitch[0] Thread=221 (was 221), OpenFileDescriptor=446 (was 446), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=228 (was 228), ProcessCount=11 (was 11), AvailableMemoryMB=2085 (was 2091) 2024-12-03T07:14:35,374 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=221, OpenFileDescriptor=446, MaxFileDescriptor=1048576, SystemLoadAverage=228, ProcessCount=11, AvailableMemoryMB=2085 2024-12-03T07:14:35,375 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:35,376 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=114, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:35,377 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-03T07:14:35,395 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:35,396 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:35,437 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:35,438 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152005f connected 2024-12-03T07:14:35,479 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-03T07:14:35,545 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152005f, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:35,563 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=115, ppid=114, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:35,689 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-03T07:14:35,714 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:35,715 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=115 2024-12-03T07:14:35,715 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:35,718 DEBUG [BootstrapNodeManager {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=RegionServerStatusService, sasl=false 2024-12-03T07:14:35,720 INFO [RS-EventLoopGroup-1-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:52726, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins.hfs.0 (auth:SIMPLE), service=RegionServerStatusService 2024-12-03T07:14:35,731 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=115}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:35,747 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:35,787 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=115}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=115 2024-12-03T07:14:35,788 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=115 2024-12-03T07:14:35,790 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:35,792 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=115, resume processing ppid=114 2024-12-03T07:14:35,792 INFO [PEWorker-4 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:35,792 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=115, ppid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 227 msec 2024-12-03T07:14:35,793 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=114, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 417 msec 2024-12-03T07:14:35,828 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x56f14796 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@6853724c 2024-12-03T07:14:35,837 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:35,838 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:35,838 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@1df85973, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:35,840 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:35,845 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:35,846 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520061 connected 2024-12-03T07:14:35,846 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:35,999 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=114 2024-12-03T07:14:35,999 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:36,000 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:36,000 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:36,001 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=116, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:36,002 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-03T07:14:36,004 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:36,012 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:36,012 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:36,012 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:36,013 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=117, ppid=116, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:36,110 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-03T07:14:36,165 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:36,166 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=117 2024-12-03T07:14:36,166 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:36,166 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:36,166 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:36,166 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:36,167 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520061, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:36,167 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520061, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:36,270 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520061, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:36,271 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x56f14796 to 127.0.0.1:55234 2024-12-03T07:14:36,271 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:36,273 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:36,279 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:36,287 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:36,287 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:36,287 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:36,288 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:36,288 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=117}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=117 2024-12-03T07:14:36,289 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=117 2024-12-03T07:14:36,296 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:36,301 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=117, resume processing ppid=116 2024-12-03T07:14:36,301 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=117, ppid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 283 msec 2024-12-03T07:14:36,312 DEBUG [PEWorker-2 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:36,313 INFO [PEWorker-2 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:36,315 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=116, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 313 msec 2024-12-03T07:14:36,320 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=116 2024-12-03T07:14:36,321 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:36,322 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:36,324 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=118, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:36,325 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-03T07:14:36,326 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] 2024-12-03T07:14:36,327 ERROR [PEWorker-4 {}] procedure2.ProcedureExecutor(1656): Root Procedure pid=118, state=FAILED, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure does not support rollback but the execution failed and try to rollback, code bug? org.apache.hadoop.hbase.procedure2.RemoteProcedureException: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.procedure2.Procedure.setFailure(Procedure.java:768) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:284) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:54) ~[classes/:?] at org.apache.hadoop.hbase.procedure2.StateMachineProcedure.execute(StateMachineProcedure.java:188) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.Procedure.doExecute(Procedure.java:944) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.execProcedure(ProcedureExecutor.java:1784) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.executeProcedure(ProcedureExecutor.java:1462) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor.access$1000(ProcedureExecutor.java:77) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.runProcedure(ProcedureExecutor.java:2106) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.trace.TraceUtil.trace(TraceUtil.java:216) ~[hbase-common-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.procedure2.ProcedureExecutor$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:36,328 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=118, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-03T07:14:36,329 WARN [PEWorker-4 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:36,429 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=118 2024-12-03T07:14:36,430 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:36,448 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testClusterKeyWithTrailingSpace[0] Thread=223 (was 221) - Thread LEAK? -, OpenFileDescriptor=450 (was 446) - OpenFileDescriptor LEAK? -, MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=228 (was 228), ProcessCount=11 (was 11), AvailableMemoryMB=2053 (was 2085) 2024-12-03T07:14:36,458 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=228, ProcessCount=11, AvailableMemoryMB=2053 2024-12-03T07:14:36,459 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:36,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=119, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:36,461 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-03T07:14:36,481 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:36,482 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:36,495 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:36,496 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520062 connected 2024-12-03T07:14:36,569 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-03T07:14:36,604 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520062, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:36,621 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=120, ppid=119, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:36,773 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:36,774 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=120 2024-12-03T07:14:36,774 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:36,783 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-03T07:14:36,801 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=120}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:36,824 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:36,879 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=120}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=120 2024-12-03T07:14:36,880 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=120 2024-12-03T07:14:36,882 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:36,887 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=120, resume processing ppid=119 2024-12-03T07:14:36,887 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=120, ppid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 261 msec 2024-12-03T07:14:36,887 INFO [PEWorker-2 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:36,889 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=119, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 428 msec 2024-12-03T07:14:36,918 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1abf3764 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@67504355 2024-12-03T07:14:36,934 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:36,935 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:36,935 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@699787f4, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:36,937 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:36,945 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:36,946 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:36,946 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520064 connected 2024-12-03T07:14:37,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=119 2024-12-03T07:14:37,090 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:37,091 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:37,092 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-03T07:14:37,093 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=121, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:37,094 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-03T07:14:37,110 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:37,111 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:37,120 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:37,121 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520065 connected 2024-12-03T07:14:37,151 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:14:37,199 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-03T07:14:37,228 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520065, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:37,316 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=122, ppid=121, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:37,410 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-03T07:14:37,468 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:37,469 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=122 2024-12-03T07:14:37,469 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:37,470 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=122}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=122 2024-12-03T07:14:37,475 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=122 2024-12-03T07:14:37,477 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:37,480 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=122, resume processing ppid=121 2024-12-03T07:14:37,480 INFO [PEWorker-5 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=2097152,serial=false 2024-12-03T07:14:37,480 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=122, ppid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 161 msec 2024-12-03T07:14:37,481 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=121, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 388 msec 2024-12-03T07:14:37,720 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=121 2024-12-03T07:14:37,720 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:37,721 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:37,721 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:37,723 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=123, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:37,725 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-03T07:14:37,727 DEBUG [PEWorker-2 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:37,762 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:37,762 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:37,762 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:37,763 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=124, ppid=123, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:37,829 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-03T07:14:37,916 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:37,916 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=124 2024-12-03T07:14:37,916 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:37,917 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:37,917 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:37,917 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:37,917 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520064, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:37,917 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520064, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:38,020 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520064, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:38,020 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1abf3764 to 127.0.0.1:55234 2024-12-03T07:14:38,020 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:38,021 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:38,029 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:38,039 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-03T07:14:38,045 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:38,045 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:38,045 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:38,046 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:38,046 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=124}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=124 2024-12-03T07:14:38,046 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=124 2024-12-03T07:14:38,048 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:38,049 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=124, resume processing ppid=123 2024-12-03T07:14:38,049 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=124, ppid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 285 msec 2024-12-03T07:14:38,053 DEBUG [PEWorker-3 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:38,054 INFO [PEWorker-3 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:38,055 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=123, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 333 msec 2024-12-03T07:14:38,350 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=123 2024-12-03T07:14:38,350 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:38,351 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:38,352 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=125, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:38,353 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-03T07:14:38,353 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] 2024-12-03T07:14:38,354 ERROR [PEWorker-5 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:38,355 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=125, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 1; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-03T07:14:38,355 WARN [PEWorker-5 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:38,460 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=125 2024-12-03T07:14:38,461 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 1 failed with 1 2024-12-03T07:14:38,461 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:38,462 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=126, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:38,463 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-03T07:14:38,463 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] 2024-12-03T07:14:38,464 ERROR [PEWorker-2 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:38,465 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=126, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=3 msec 2024-12-03T07:14:38,465 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:38,570 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=126 2024-12-03T07:14:38,571 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:38,581 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testPeerBandwidth[0] Thread=223 (was 223), OpenFileDescriptor=450 (was 450), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=258 (was 228) - SystemLoadAverage LEAK? -, ProcessCount=11 (was 11), AvailableMemoryMB=2017 (was 2053) 2024-12-03T07:14:38,591 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=223, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=258, ProcessCount=11, AvailableMemoryMB=2017 2024-12-03T07:14:38,592 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] 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 2024-12-03T07:14:38,593 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=127, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:38,594 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-03T07:14:38,646 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=128, ppid=127, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:38,699 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-03T07:14:38,797 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:38,798 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=128 2024-12-03T07:14:38,798 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:38,838 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:38,879 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=128}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=128 2024-12-03T07:14:38,879 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(587): peerId=1, queueId=1 (queues=1) is replicating from cluster=2f367829-c73d-418d-bffa-92c17acb01a4 to cluster=2f367829-c73d-418d-bffa-92c17acb01a4 2024-12-03T07:14:38,879 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=128 2024-12-03T07:14:38,880 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(343): peerId=1, starting shipping worker for walGroupId=8046980647f4%2C39969%2C1733210043547 2024-12-03T07:14:38,881 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:38,883 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=128, resume processing ppid=127 2024-12-03T07:14:38,883 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=,replicationEndpointImpl=org.apache.hadoop.hbase.replication.VerifyWALEntriesReplicationEndpoint,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:38,883 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=128, ppid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 235 msec 2024-12-03T07:14:38,884 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSourceWALReader(112): peerClusterZnode=1, ReplicationSourceWALReaderThread : 1 inited, replicationBatchSizeCapacity=67108864, replicationBatchCountCapacity=25000, replicationBatchQueueCapacity=1 2024-12-03T07:14:38,885 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=127, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 291 msec 2024-12-03T07:14:38,886 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.shipper8046980647f4%2C39969%2C1733210043547,1 {}] regionserver.ReplicationSourceShipper(98): Running ReplicationSourceShipper Thread for wal group: 8046980647f4%2C39969%2C1733210043547 2024-12-03T07:14:38,887 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.wal-reader.8046980647f4%2C39969%2C1733210043547,1 {}] regionserver.WALEntryStream(260): Creating new reader hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.1733210045992, startPosition=0, beingWritten=true 2024-12-03T07:14:38,910 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=127 2024-12-03T07:14:38,910 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:38,911 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] 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 2024-12-03T07:14:38,912 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=129, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:38,913 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-03T07:14:38,913 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 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 2024-12-03T07:14:38,914 ERROR [PEWorker-2 {}] 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 2024-12-03T07:14:38,916 INFO [PEWorker-2 {}] 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=4 msec 2024-12-03T07:14:38,916 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. 2024-12-03T07:14:38,977 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.wal-reader.8046980647f4%2C39969%2C1733210043547,1 {}] regionserver.ReplicationSourceWALReader(181): Read 0 WAL entries eligible for replication 2024-12-03T07:14:38,977 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.wal-reader.8046980647f4%2C39969%2C1733210043547,1 {}] regionserver.WALEntryStream(223): Reset reader hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.1733210045992 to pos 589, reset compression=false 2024-12-03T07:14:38,977 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.shipper8046980647f4%2C39969%2C1733210043547,1 {}] regionserver.ReplicationSourceShipper(110): Shipper from source 1 got entry batch from reader: WALEntryBatch [walEntries=[], lastWalPath=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/WALs/8046980647f4,39969,1733210043547/8046980647f4%2C39969%2C1733210043547.1733210045992, lastWalPosition=589, nbRowKeys=0, nbHFiles=0, heapSize=0, lastSeqIds={}, endOfFile=false,usedBufferSize=0] 2024-12-03T07:14:39,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=129 2024-12-03T07:14:39,020 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: ADD_REPLICATION_PEER, peerId: 2 failed with Invalid cluster key: 2024-12-03T07:14:39,021 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:39,022 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=130, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:39,023 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:39,024 DEBUG [PEWorker-1 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:39,028 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:39,028 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:39,029 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:39,029 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=131, ppid=130, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:39,130 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:39,181 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:39,182 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=131 2024-12-03T07:14:39,182 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:39,182 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:39,182 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:39,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:39,649 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:40,160 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:40,183 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.wal-reader.8046980647f4%2C39969%2C1733210043547,1 {}] 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/:?] 2024-12-03T07:14:40,183 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.shipper8046980647f4%2C39969%2C1733210043547,1 {}] 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/:?] 2024-12-03T07:14:41,180 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:41,183 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSource(711): peerId=1, ReplicationSourceWorker RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1.replicationSource.shipper8046980647f4%2C39969%2C1733210043547,1 terminated 2024-12-03T07:14:41,183 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:41,184 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:41,228 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:41,228 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:41,228 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:41,229 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:41,229 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=131}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=131 2024-12-03T07:14:41,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=131 2024-12-03T07:14:41,230 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:41,231 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=131, resume processing ppid=130 2024-12-03T07:14:41,232 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=131, ppid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 2.2010 sec 2024-12-03T07:14:41,256 DEBUG [PEWorker-5 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:41,256 INFO [PEWorker-5 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:41,257 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=130, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 2.2350 sec 2024-12-03T07:14:41,779 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:43,200 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=130 2024-12-03T07:14:43,201 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:43,202 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=2 2024-12-03T07:14:43,204 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=132, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:43,206 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-03T07:14:43,206 WARN [PEWorker-2 {}] replication.ModifyPeerProcedure(282): org.apache.hadoop.hbase.master.replication.RemovePeerProcedure failed to call pre CP hook or the pre check is failed for peer 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] 2024-12-03T07:14:43,207 ERROR [PEWorker-2 {}] 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$WorkerThread.run(ProcedureExecutor.java:2133) ~[hbase-procedure-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] Caused by: org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2 at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.checkPeerExists(ReplicationPeerManager.java:133) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ReplicationPeerManager.preRemovePeer(ReplicationPeerManager.java:139) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.RemovePeerProcedure.prePeerModification(RemovePeerProcedure.java:61) ~[classes/:?] at org.apache.hadoop.hbase.master.replication.ModifyPeerProcedure.executeFromState(ModifyPeerProcedure.java:280) ~[classes/:?] ... 9 more 2024-12-03T07:14:43,208 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1666): Rolled back pid=132, state=ROLLEDBACK, locked=true, exception=org.apache.hadoop.hbase.ReplicationPeerNotFoundException via master-remove-peer:org.apache.hadoop.hbase.ReplicationPeerNotFoundException: 2; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure exec-time=5 msec 2024-12-03T07:14:43,208 WARN [PEWorker-2 {}] procedure2.ProcedureExecutor(2020): Usually this should not happen, we will release the lock before if the procedure is finished, even if the holdLock is true, arrive here means we have some holes where we do not release the lock. And the releaseLock below may fail since the procedure may have already been deleted from the procedure store. 2024-12-03T07:14:43,310 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=132 2024-12-03T07:14:43,311 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2976): Operation: REMOVE_REPLICATION_PEER, peerId: 2 failed with 2 2024-12-03T07:14:43,330 INFO [Time-limited test {}] hbase.ResourceChecker(175): after: client.TestAsyncReplicationAdminApi#testSetReplicationEndpoint[0] Thread=220 (was 223), OpenFileDescriptor=450 (was 450), MaxFileDescriptor=1048576 (was 1048576), SystemLoadAverage=258 (was 258), ProcessCount=11 (was 11), AvailableMemoryMB=2001 (was 2017) 2024-12-03T07:14:43,338 INFO [Time-limited test {}] hbase.ResourceChecker(147): before: client.TestAsyncReplicationAdminApi#testRemovePeerTableCFs[1] Thread=220, OpenFileDescriptor=450, MaxFileDescriptor=1048576, SystemLoadAverage=258, ProcessCount=11, AvailableMemoryMB=2000 2024-12-03T07:14:43,340 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3919): Client=jenkins//172.17.0.2 creating replication peer, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false, state=ENABLED 2024-12-03T07:14:43,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=133, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.AddPeerProcedure 2024-12-03T07:14:43,341 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-03T07:14:43,357 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:43,358 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:43,361 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:43,362 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520066 connected 2024-12-03T07:14:43,450 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-03T07:14:43,470 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520066, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:43,488 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=134, ppid=133, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:43,524 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:14:43,639 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:43,640 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=134 2024-12-03T07:14:43,640 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=ADD_PEER 2024-12-03T07:14:43,655 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=134}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:43,660 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-03T07:14:43,666 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:43,703 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=134}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=134 2024-12-03T07:14:43,704 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=134 2024-12-03T07:14:43,705 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for ADD on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:43,707 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=134, resume processing ppid=133 2024-12-03T07:14:43,707 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=134, ppid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 217 msec 2024-12-03T07:14:43,707 INFO [PEWorker-5 {}] replication.AddPeerProcedure(102): Successfully added ENABLED peer 1, config clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=true,bandwidth=0,serial=false 2024-12-03T07:14:43,708 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=133, state=SUCCESS; org.apache.hadoop.hbase.master.replication.AddPeerProcedure in 367 msec 2024-12-03T07:14:43,732 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1e58bff1 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@1e535f60 2024-12-03T07:14:43,737 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:43,737 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:43,737 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@f0cb890, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:43,738 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:43,745 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:43,745 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:43,745 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520068 connected 2024-12-03T07:14:43,969 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=133 2024-12-03T07:14:43,970 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: ADD_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:43,970 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:43,971 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=135, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:43,972 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-03T07:14:43,995 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:43,996 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:44,047 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:44,047 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520069 connected 2024-12-03T07:14:44,080 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-03T07:14:44,162 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520069, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:44,171 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=136, ppid=135, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:44,289 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-03T07:14:44,322 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:44,323 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=136 2024-12-03T07:14:44,323 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:44,324 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:44,324 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:44,324 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:44,324 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520068, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:44,325 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520068, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:44,428 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520068, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:44,428 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1e58bff1 to 127.0.0.1:55234 2024-12-03T07:14:44,429 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:44,442 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:44,442 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:44,442 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=136}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=136 2024-12-03T07:14:44,443 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=136 2024-12-03T07:14:44,444 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:44,446 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=136, resume processing ppid=135 2024-12-03T07:14:44,446 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:44,446 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=136, ppid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 274 msec 2024-12-03T07:14:44,447 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=135, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 476 msec 2024-12-03T07:14:44,468 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x4245f275 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@f6a020e 2024-12-03T07:14:44,479 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:44,479 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:44,479 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@6ee93c14, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:44,480 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:44,486 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:44,487 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:44,487 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152006b connected 2024-12-03T07:14:44,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=135 2024-12-03T07:14:44,601 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:44,601 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:44,603 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:44,603 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:44,604 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-03T07:14:44,605 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=137, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:44,605 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-03T07:14:44,618 INFO [PEWorker-5 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:44,619 INFO [PEWorker-5 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:44,639 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:44,639 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152006c connected 2024-12-03T07:14:44,709 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-03T07:14:44,753 DEBUG [PEWorker-5-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b541152006c, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:44,762 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=138, ppid=137, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:44,914 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:44,914 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=138 2024-12-03T07:14:44,914 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:44,915 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:44,915 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:44,916 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:44,916 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152006b, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:44,916 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152006b, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:44,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-03T07:14:45,020 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152006b, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:45,021 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x4245f275 to 127.0.0.1:55234 2024-12-03T07:14:45,021 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:45,041 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:45,041 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:45,041 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=138}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=138 2024-12-03T07:14:45,042 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=138 2024-12-03T07:14:45,044 INFO [PEWorker-2 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:45,046 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=138, resume processing ppid=137 2024-12-03T07:14:45,047 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1], testRemovePeerTableCFst1=null},bandwidth=0,serial=false 2024-12-03T07:14:45,047 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=138, ppid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 282 msec 2024-12-03T07:14:45,049 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=137, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 443 msec 2024-12-03T07:14:45,083 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x6c39b862 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@13d01d26 2024-12-03T07:14:45,096 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:45,096 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:45,097 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@77dfbee3, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:45,099 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:45,112 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:45,126 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:45,131 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152006e connected 2024-12-03T07:14:45,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=137 2024-12-03T07:14:45,230 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:45,230 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,232 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,233 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,234 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,235 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-03T07:14:45,237 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=139, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:45,243 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-03T07:14:45,263 INFO [PEWorker-3 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:45,263 INFO [PEWorker-3 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:45,278 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:45,349 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-03T07:14:45,387 DEBUG [PEWorker-3-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:45,404 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=140, ppid=139, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:45,557 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:45,558 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=140 2024-12-03T07:14:45,558 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:45,559 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-03T07:14:45,559 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:45,559 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:45,559 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:45,559 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152006e, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:45,559 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152006e, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:45,670 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152006e, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:45,670 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x6c39b862 to 127.0.0.1:55234 2024-12-03T07:14:45,670 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:45,691 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:45,691 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:45,691 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=140}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=140 2024-12-03T07:14:45,692 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=140 2024-12-03T07:14:45,694 INFO [PEWorker-1 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:45,695 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=140, resume processing ppid=139 2024-12-03T07:14:45,695 INFO [PEWorker-2 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst2=[cf1]},bandwidth=0,serial=false 2024-12-03T07:14:45,695 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=140, ppid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 290 msec 2024-12-03T07:14:45,697 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1480): Finished pid=139, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 459 msec 2024-12-03T07:14:45,719 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x42f35406 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@fa452df 2024-12-03T07:14:45,745 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:45,746 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:45,746 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@25079bb8, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:45,747 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:45,753 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:45,754 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:45,754 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520071 connected 2024-12-03T07:14:45,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=139 2024-12-03T07:14:45,871 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:45,872 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,874 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,875 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:45,876 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:45,877 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=141, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:45,878 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-03T07:14:45,893 INFO [PEWorker-4 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:45,893 INFO [PEWorker-4 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:45,903 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:45,903 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520072 connected 2024-12-03T07:14:45,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-03T07:14:46,012 DEBUG [PEWorker-4-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520072, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:46,021 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=142, ppid=141, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:46,173 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:46,173 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=142 2024-12-03T07:14:46,173 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:46,174 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:46,175 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:46,175 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:46,175 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520071, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:46,175 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520071, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:46,199 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-03T07:14:46,287 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520071, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:46,287 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x42f35406 to 127.0.0.1:55234 2024-12-03T07:14:46,287 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:46,302 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:46,303 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:46,303 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=142}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=142 2024-12-03T07:14:46,303 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=142 2024-12-03T07:14:46,305 INFO [PEWorker-3 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:46,306 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=142, resume processing ppid=141 2024-12-03T07:14:46,306 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=142, ppid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 284 msec 2024-12-03T07:14:46,306 INFO [PEWorker-1 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:46,308 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1480): Finished pid=141, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 431 msec 2024-12-03T07:14:46,344 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1961afe5 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@178fed72 2024-12-03T07:14:46,355 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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$1.exec(ReadOnlyZKClient.java:185) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] at org.apache.hadoop.hbase.zookeeper.ReadOnlyZKClient.run(ReadOnlyZKClient.java:386) ~[hbase-client-2.7.0-SNAPSHOT.jar:2.7.0-SNAPSHOT] ... 1 more 2024-12-03T07:14:46,355 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:46,355 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@d78177a, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:46,356 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:46,362 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:46,362 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:46,363 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520074 connected 2024-12-03T07:14:46,509 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=141 2024-12-03T07:14:46,509 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:46,510 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:46,510 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:46,511 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-03T07:14:46,512 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=143, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:46,513 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-03T07:14:46,527 INFO [PEWorker-2 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:46,527 INFO [PEWorker-2 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:46,536 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:46,537 ERROR [PEWorker-2-EventThread {}] zookeeper.ClientCnxn$EventThread(581): Error while calling watcher. java.util.concurrent.RejectedExecutionException: Task org.apache.hadoop.hbase.trace.TraceUtil$$Lambda$361/0x00007f0c208d4e18@42c0d140 rejected from java.util.concurrent.ThreadPoolExecutor@46ff5dc0[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] 2024-12-03T07:14:46,619 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-03T07:14:46,645 DEBUG [PEWorker-2-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:46,654 INFO [PEWorker-2 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=144, ppid=143, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:46,806 DEBUG [RSProcedureDispatcher-pool-1 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:46,806 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=144 2024-12-03T07:14:46,806 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:46,807 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:46,807 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:46,807 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:46,808 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520074, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:46,808 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520074, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:46,829 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-03T07:14:46,912 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520074, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:46,912 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1961afe5 to 127.0.0.1:55234 2024-12-03T07:14:46,912 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:46,932 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:46,932 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:46,933 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=144}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=144 2024-12-03T07:14:46,933 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=144 2024-12-03T07:14:46,935 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:46,937 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=144, resume processing ppid=143 2024-12-03T07:14:46,937 INFO [PEWorker-3 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,tableCFs={testRemovePeerTableCFst4=null},bandwidth=0,serial=false 2024-12-03T07:14:46,937 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=144, ppid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 281 msec 2024-12-03T07:14:46,939 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1480): Finished pid=143, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 426 msec 2024-12-03T07:14:46,975 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x1385c436 to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@55d091ba 2024-12-03T07:14:46,987 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:46,987 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:46,987 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@5476af66, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:46,988 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:46,995 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:46,995 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:46,995 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b5411520077 connected 2024-12-03T07:14:47,139 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=143 2024-12-03T07:14:47,139 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:47,140 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:47,143 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3960): Client=jenkins//172.17.0.2 update replication peer config, id=1, config=clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:47,144 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=145, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure 2024-12-03T07:14:47,145 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-03T07:14:47,161 INFO [PEWorker-1 {}] hbase.HBaseConfiguration(308): Overriding client registry implementation to org.apache.hadoop.hbase.client.ZKConnectionRegistry 2024-12-03T07:14:47,162 INFO [PEWorker-1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:47,170 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id0x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:47,170 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520078 connected 2024-12-03T07:14:47,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-03T07:14:47,283 DEBUG [PEWorker-1-EventThread {}] zookeeper.ZKWatcher(609): org.apache.hadoop.hbase.master.replication.ReplicationPeerManager@251372a6check-peer-cluster-id-0x1019b5411520078, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:47,287 INFO [PEWorker-1 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=146, ppid=145, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:47,440 DEBUG [RSProcedureDispatcher-pool-2 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:47,440 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=146 2024-12-03T07:14:47,440 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=UPDATE_PEER_CONFIG 2024-12-03T07:14:47,442 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(373): Terminate replication source for 1 2024-12-03T07:14:47,442 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {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 2024-12-03T07:14:47,442 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:47,442 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b5411520077, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:47,442 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b5411520077, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:47,459 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-03T07:14:47,553 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b5411520077, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:47,553 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x1385c436 to 127.0.0.1:55234 2024-12-03T07:14:47,553 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:47,573 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSource(229): queueId=1, ReplicationSource: 1, currentBandwidth=0 2024-12-03T07:14:47,573 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.ReplicationSourceManager(383): Startup replication source for 1 2024-12-03T07:14:47,573 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=146}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=146 2024-12-03T07:14:47,574 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=146 2024-12-03T07:14:47,576 INFO [PEWorker-4 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for UPDATE_CONFIG on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:47,578 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=146, resume processing ppid=145 2024-12-03T07:14:47,578 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=146, ppid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 289 msec 2024-12-03T07:14:47,578 INFO [PEWorker-4 {}] replication.UpdatePeerConfigProcedure(197): Successfully updated peer config of 1 to clusterKey=127.0.0.1:55234:/hbase-test1,replicationEndpointImpl=null,replicateAllUserTables=false,bandwidth=0,serial=false 2024-12-03T07:14:47,580 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=145, state=SUCCESS; org.apache.hadoop.hbase.master.replication.UpdatePeerConfigProcedure in 435 msec 2024-12-03T07:14:47,601 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ReadOnlyZKClient(149): Connect 0x691a098e to 127.0.0.1:55234 with session timeout=90000ms, retries=30, retry interval=1000ms, keepAlive=60000ms, zk client config=org.apache.zookeeper.client.ZKClientConfig@2a003854 2024-12-03T07:14:47,733 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.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 2024-12-03T07:14:47,734 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] client.ConnectionImplementation(706): clusterid came back null, using default default-cluster 2024-12-03T07:14:47,734 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] ipc.AbstractRpcClient(198): Codec=org.apache.hadoop.hbase.codec.KeyValueCodecWithTags@bbb977f, compressor=null, tcpKeepAlive=true, tcpNoDelay=true, connectTO=10000, readTO=20000, writeTO=60000, minIdleTimeBeforeClose=120000, maxRetries=0, fallbackAllowed=true, bind address=null 2024-12-03T07:14:47,735 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.RecoverableZooKeeper(138): Process identifier=connection to cluster: 1 connecting to ZooKeeper ensemble=127.0.0.1:55234 2024-12-03T07:14:47,770 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=145 2024-12-03T07:14:47,770 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: UPDATE_REPLICATION_PEER_CONFIG, peerId: 1 completed 2024-12-03T07:14:47,771 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3948): Client=jenkins//172.17.0.2 get replication peer config, id=1 2024-12-03T07:14:47,771 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 10x0, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=SyncConnected, path=null 2024-12-03T07:14:47,772 INFO [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:47,772 INFO [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.HMaster(3926): Client=jenkins//172.17.0.2 removing replication peer, id=1 2024-12-03T07:14:47,772 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(569): peerId=1, Could not connect to Peer ZK. Sleeping for 1000 millis 2024-12-03T07:14:47,772 DEBUG [zk-event-processor-pool-0 {}] zookeeper.ZKWatcher(635): connection to cluster: 1-0x1019b541152007a connected 2024-12-03T07:14:47,773 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=147, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:47,773 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] procedure2.ProcedureExecutor(1098): Stored pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:47,773 DEBUG [PEWorker-1 {}] procedure.MasterProcedureScheduler(583): PEER '1', shared lock count=0, exclusively locked by procId=147 2024-12-03T07:14:47,773 DEBUG [PEWorker-1 {}] procedure2.ProcedureExecutor(1470): LOCK_EVENT_WAIT pid=148, state=RUNNABLE:PRE_PEER_MODIFICATION; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure 2024-12-03T07:14:47,774 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-03T07:14:47,774 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:47,775 DEBUG [PEWorker-3 {}] zookeeper.ZKUtil(111): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:47,786 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1/peer-state 2024-12-03T07:14:47,786 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:47,786 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): master:33011-0x1019b5411520000, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/peers/1 2024-12-03T07:14:47,788 INFO [PEWorker-3 {}] procedure2.ProcedureExecutor(1819): Initialized subprocedures=[{pid=149, ppid=147, state=RUNNABLE; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure}] 2024-12-03T07:14:47,880 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-03T07:14:47,880 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:47,939 DEBUG [RSProcedureDispatcher-pool-0 {}] master.ServerManager(801): New admin connection to 8046980647f4,39969,1733210043547 2024-12-03T07:14:47,940 DEBUG [RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=39969 {}] regionserver.RSRpcServices(3992): Executing remote procedure class org.apache.hadoop.hbase.replication.regionserver.RefreshPeerCallable, pid=149 2024-12-03T07:14:47,940 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RefreshPeerCallable(45): Received a peer change event, peerId=1, type=REMOVE_PEER 2024-12-03T07:14:47,940 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(287): Number of deleted recovered sources for 1: 0 2024-12-03T07:14:47,940 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSource(657): peerId=1, Closing source 1 because: Replication stream was removed by a user 2024-12-03T07:14:47,940 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] regionserver.ReplicationSource(508): peerId=1, Interrupted while sleeping between retries 2024-12-03T07:14:47,940 WARN [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKUtil(165): connection to cluster: 1-0x1019b541152007a, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:47,941 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1 {}] zookeeper.ZKWatcher(734): connection to cluster: 1-0x1019b541152007a, quorum=127.0.0.1:55234, 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) ~[?:?] 2024-12-03T07:14:48,045 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0.replicationSource,1-EventThread {}] zookeeper.ZKWatcher(609): connection to cluster: 1-0x1019b541152007a, quorum=127.0.0.1:55234, baseZNode=/hbase-test1 Received ZooKeeper Event, type=None, state=Closed, path=null 2024-12-03T07:14:48,045 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ReadOnlyZKClient(407): Close zookeeper connection 0x691a098e to 127.0.0.1:55234 2024-12-03T07:14:48,045 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] ipc.AbstractRpcClient(514): Stopping rpc client 2024-12-03T07:14:48,045 INFO [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.ReplicationSourceManager(430): Done with the queue 1 2024-12-03T07:14:48,054 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] zookeeper.ZKUtil(111): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Set watcher on existing znode=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:48,062 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1/8046980647f4%2C39969%2C1733210043547.1733210045992 2024-12-03T07:14:48,062 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeChildrenChanged, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:48,062 DEBUG [Time-limited test-EventThread {}] zookeeper.ZKWatcher(609): regionserver:39969-0x1019b5411520001, quorum=127.0.0.1:55234, baseZNode=/hbase Received ZooKeeper Event, type=NodeDeleted, state=SyncConnected, path=/hbase/replication/rs/8046980647f4,39969,1733210043547/1 2024-12-03T07:14:48,062 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:48,062 DEBUG [RS_REFRESH_PEER-regionserver/8046980647f4:0-0 {event_type=RS_REFRESH_PEER, pid=149}] regionserver.RemoteProcedureResultReporter(62): Successfully complete execution of pid=149 2024-12-03T07:14:48,063 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.HMaster(4106): Remote procedure done, pid=149 2024-12-03T07:14:48,064 INFO [PEWorker-5 {}] replication.RefreshPeerProcedure(119): Refresh peer 1 for REMOVE on 8046980647f4,39969,1733210043547 suceeded 2024-12-03T07:14:48,065 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1976): Finished subprocedure pid=149, resume processing ppid=147 2024-12-03T07:14:48,065 INFO [PEWorker-5 {}] procedure2.ProcedureExecutor(1480): Finished pid=149, ppid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RefreshPeerProcedure in 277 msec 2024-12-03T07:14:48,070 DEBUG [PEWorker-4 {}] replication.ZKReplicationQueueStorage(578): Peer /hbase/replication/hfile-refs/1 not found in hfile reference queue. 2024-12-03T07:14:48,070 INFO [PEWorker-4 {}] replication.RemovePeerProcedure(76): Successfully removed peer 1 2024-12-03T07:14:48,072 INFO [PEWorker-4 {}] procedure2.ProcedureExecutor(1480): Finished pid=147, state=SUCCESS; org.apache.hadoop.hbase.master.replication.RemovePeerProcedure in 298 msec 2024-12-03T07:14:48,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:48,090 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=147 2024-12-03T07:14:48,090 INFO [RPCClient-NioEventLoopGroup-4-2 {}] client.RawAsyncHBaseAdmin$ReplicationProcedureBiConsumer(2971): Operation: REMOVE_REPLICATION_PEER, peerId: 1 completed 2024-12-03T07:14:48,399 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:48,909 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:49,409 INFO [master/8046980647f4:0.Chore.1 {}] migrate.RollingUpgradeChore(116): There is no table to migrate StoreFileTracker! 2024-12-03T07:14:49,409 INFO [master/8046980647f4:0.Chore.1 {}] migrate.RollingUpgradeChore(85): All Rolling-Upgrade tasks are complete, shutdown RollingUpgradeChore! 2024-12-03T07:14:49,919 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:51,800 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:14:51,929 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:14:53,548 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:14:55,939 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:15:01,819 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:15:02,028 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. 2024-12-03T07:15:05,969 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:15:07,360 DEBUG [master/8046980647f4:0.Chore.1 {}] balancer.RegionLocationFinder(172): Locality for region ef235488523e821f809aed54184195da changed from -1.0 to 0.0, refreshing cache 2024-12-03T07:15:15,989 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:15:21,869 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:15:26,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:15:32,029 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. 2024-12-03T07:15:36,100 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:15:42,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:15:56,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:16:02,029 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. 2024-12-03T07:16:02,079 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:16:16,420 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:16:22,099 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:16:32,030 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. 2024-12-03T07:16:36,440 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:16:42,149 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:16:56,579 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:17:02,030 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. 2024-12-03T07:17:02,349 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:17:16,710 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:17:22,499 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:17:32,030 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. 2024-12-03T07:17:36,830 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:17:42,669 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:17:56,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:18:02,031 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. 2024-12-03T07:18:02,769 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:18:17,000 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:18:22,820 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:18:32,031 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. 2024-12-03T07:18:37,159 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:18:42,859 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:18:57,179 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:19:02,031 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. 2024-12-03T07:19:03,040 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:19:03,558 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 2024-12-03T07:19:03,634 DEBUG [master/8046980647f4:0: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% 2024-12-03T07:19:03,634 DEBUG [master/8046980647f4:0: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 2024-12-03T07:19:05,877 INFO [8046980647f4:39969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-03T07:19:08,910 INFO [regionserver/8046980647f4:0.Chore.1 {}] regionserver.HRegionServer$PeriodicMemStoreFlusher(2070): MemstoreFlusherChore requesting flush of hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da. because ef235488523e821f809aed54184195da/info has an old edit so flush to free WALs after random delay 294774 ms 2024-12-03T07:19:08,910 INFO [regionserver/8046980647f4:0.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 291599 ms 2024-12-03T07:19:09,460 DEBUG [hconnection-0x311e3d67-shared-pool-4 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:19:09,464 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:45860, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:19:09,473 DEBUG [master/8046980647f4:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-03T07:19:09,476 DEBUG [master/8046980647f4:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-03T07:19:09,476 DEBUG [master/8046980647f4:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-03T07:19:12,610 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:19:17,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:19:23,050 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:19:32,031 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. 2024-12-03T07:19:37,330 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:19:43,249 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:19:57,439 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:20:02,032 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. 2024-12-03T07:20:03,269 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:20:17,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:20:23,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:20:32,032 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. 2024-12-03T07:20:37,610 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:20:43,490 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:20:57,769 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:21:02,032 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. 2024-12-03T07:21:03,599 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:21:17,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:21:23,649 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:21:32,032 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. 2024-12-03T07:21:38,130 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:21:43,849 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:21:58,160 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:22:02,033 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. 2024-12-03T07:22:03,939 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:22:18,220 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:22:24,119 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:22:32,033 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. 2024-12-03T07:22:38,340 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:22:44,190 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:22:58,529 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:23:02,033 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. 2024-12-03T07:23:04,399 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:23:18,550 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:23:24,549 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:23:32,034 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. 2024-12-03T07:23:38,599 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:23:44,719 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:23:58,709 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:24:00,510 DEBUG [MemStoreFlusher.0 {}] regionserver.FlushAllLargeStoresPolicy(69): Since none of the CFs were above the size, flushing all. 2024-12-03T07:24:00,510 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing 1588230740 3/3 column families, dataSize=1.23 KB heapSize=2.87 KB 2024-12-03T07:24:00,576 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/.tmp/info/5b4df0d4fa6c4cf8aa520103d37ccaf2 is 143, key is hbase:namespace,,1733210047339.ef235488523e821f809aed54184195da./info:regioninfo/1733210048627/Put/seqid=0 2024-12-03T07:24:00,585 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741837_1013 (size=6595) 2024-12-03T07:24:00,986 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1.14 KB at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/.tmp/info/5b4df0d4fa6c4cf8aa520103d37ccaf2 2024-12-03T07:24:01,041 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/.tmp/table/be45dd2286954966b5b0f8f7272cf10b is 51, key is hbase:namespace/table:state/1733210048639/Put/seqid=0 2024-12-03T07:24:01,047 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741838_1014 (size=5242) 2024-12-03T07:24:01,448 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=94 B at sequenceid=9 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/.tmp/table/be45dd2286954966b5b0f8f7272cf10b 2024-12-03T07:24:01,464 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/.tmp/info/5b4df0d4fa6c4cf8aa520103d37ccaf2 as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/info/5b4df0d4fa6c4cf8aa520103d37ccaf2 2024-12-03T07:24:01,472 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/info/5b4df0d4fa6c4cf8aa520103d37ccaf2, entries=10, sequenceid=9, filesize=6.4 K 2024-12-03T07:24:01,474 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/.tmp/table/be45dd2286954966b5b0f8f7272cf10b as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/table/be45dd2286954966b5b0f8f7272cf10b 2024-12-03T07:24:01,483 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/meta/1588230740/table/be45dd2286954966b5b0f8f7272cf10b, entries=2, sequenceid=9, filesize=5.1 K 2024-12-03T07:24:01,484 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 974ms, sequenceid=9, compaction requested=false 2024-12-03T07:24:01,485 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for 1588230740: 2024-12-03T07:24:02,034 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. 2024-12-03T07:24:03,557 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 2024-12-03T07:24:03,633 DEBUG [master/8046980647f4:0:becomeActiveMaster-MemStoreChunkPool Statistics {}] regionserver.ChunkCreator$MemStoreChunkPool$StatisticsThread(417): data stats (chunk size=2097152): current pool size=2, created chunk count=7, reused chunk count=0, reuseRatio=0.00% 2024-12-03T07:24:03,634 DEBUG [master/8046980647f4:0: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 2024-12-03T07:24:03,683 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(2837): Flushing ef235488523e821f809aed54184195da 1/1 column families, dataSize=78 B heapSize=488 B 2024-12-03T07:24:03,707 DEBUG [MemStoreFlusher.0 {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da/.tmp/info/cb26a956e61645099f3fe845431521de is 45, key is default/info:d/1733210048721/Put/seqid=0 2024-12-03T07:24:03,711 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741839_1015 (size=5037) 2024-12-03T07:24:04,114 INFO [MemStoreFlusher.0 {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=78 B at sequenceid=6 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da/.tmp/info/cb26a956e61645099f3fe845431521de 2024-12-03T07:24:04,130 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da/.tmp/info/cb26a956e61645099f3fe845431521de as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da/info/cb26a956e61645099f3fe845431521de 2024-12-03T07:24:04,142 INFO [MemStoreFlusher.0 {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/data/hbase/namespace/ef235488523e821f809aed54184195da/info/cb26a956e61645099f3fe845431521de, entries=2, sequenceid=6, filesize=4.9 K 2024-12-03T07:24:04,142 INFO [MemStoreFlusher.0 {}] regionserver.HRegion(3040): Finished flush of dataSize ~78 B/78, heapSize ~472 B/472, currentSize=0 B/0 for ef235488523e821f809aed54184195da in 459ms, sequenceid=6, compaction requested=false 2024-12-03T07:24:04,142 DEBUG [MemStoreFlusher.0 {}] regionserver.HRegion(2538): Flush status journal for ef235488523e821f809aed54184195da: 2024-12-03T07:24:04,760 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:24:05,877 INFO [8046980647f4:39969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-03T07:24:10,903 DEBUG [master/8046980647f4:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-03T07:24:10,913 DEBUG [master/8046980647f4:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-03T07:24:10,913 DEBUG [master/8046980647f4:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-03T07:24:10,915 DEBUG [hconnection-0x311e3d67-shared-pool-6 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:24:10,917 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:56856, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:24:10,935 DEBUG [master/8046980647f4:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-03T07:24:12,616 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:24:18,780 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:24:24,809 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:24:32,035 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. 2024-12-03T07:24:37,092 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:24:38,603 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:24:38,979 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:24:44,859 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:24:59,079 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:25:02,035 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. 2024-12-03T07:25:04,879 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:25:19,209 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:25:22,093 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:25:23,604 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:25:25,079 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:25:32,035 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. 2024-12-03T07:25:39,379 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:25:45,170 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:25:59,480 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:26:02,035 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. 2024-12-03T07:26:05,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:26:07,093 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:26:08,604 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:26:19,639 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:26:25,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:26:32,036 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. 2024-12-03T07:26:39,680 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:26:45,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:26:52,094 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:26:53,604 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:26:59,729 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:27:02,036 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. 2024-12-03T07:27:05,729 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:27:19,889 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:27:25,769 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:27:32,036 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. 2024-12-03T07:27:37,095 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:27:38,605 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:27:40,019 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:27:45,899 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:28:00,079 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:28:02,037 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. 2024-12-03T07:28:06,089 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:28:20,129 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:28:22,095 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:28:23,605 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:28:26,129 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:28:32,037 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. 2024-12-03T07:28:40,179 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:28:46,320 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:29:00,259 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:29:02,038 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. 2024-12-03T07:29:03,558 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 2024-12-03T07:29:03,634 DEBUG [master/8046980647f4:0: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% 2024-12-03T07:29:03,634 DEBUG [master/8046980647f4:0: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 2024-12-03T07:29:05,237 DEBUG [master:store-WAL-Roller {}] wal.AbstractWALRoller(200): WAL AsyncFSWAL 8046980647f4%2C33011%2C1733210042815:(num 1733210045161) roll period 900000 ms elapsed 2024-12-03T07:29:05,255 DEBUG [master:store-WAL-Roller {}] asyncfs.FanOutOneBlockAsyncDFSOutputHelper(617): When create output stream for /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815/8046980647f4%2C33011%2C1733210042815.1733210945237, exclude list is [], retry=0 2024-12-03T07:29:05,275 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[127.0.0.1:38883,DS-4254b93d-839f-4f3c-87c5-b90d28d39653,DISK] 2024-12-03T07:29:05,281 INFO [master:store-WAL-Roller {}] wal.AbstractFSWAL(837): Rolled WAL /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815/8046980647f4%2C33011%2C1733210042815.1733210045161 with entries=1161, filesize=503.14 KB; new WAL /user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815/8046980647f4%2C33011%2C1733210042815.1733210945237 2024-12-03T07:29:05,282 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(925): Create new AsyncFSWAL writer with pipeline: [(127.0.0.1/127.0.0.1:37873:37873)] 2024-12-03T07:29:05,282 DEBUG [master:store-WAL-Roller {}] wal.AbstractFSWAL(751): hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/WALs/8046980647f4,33011,1733210042815/8046980647f4%2C33011%2C1733210042815.1733210045161 is not closed yet, will try archiving it next time 2024-12-03T07:29:05,285 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741830_1006 (size=515222) 2024-12-03T07:29:05,325 INFO [master:store-Flusher {}] regionserver.HRegion(2837): Flushing 1595e783b53d99cd5eef43b6debb2682 4/4 column families, dataSize=428.68 KB heapSize=530.64 KB 2024-12-03T07:29:05,348 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/fdb0e1cc5e854607aeac8ca4293d1b7d is 82, key is hbase:meta,,1/info:regioninfo/1733210047129/Put/seqid=0 2024-12-03T07:29:05,352 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741841_1017 (size=5672) 2024-12-03T07:29:05,754 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=504 B at sequenceid=1164 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/fdb0e1cc5e854607aeac8ca4293d1b7d 2024-12-03T07:29:05,788 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/ce72f10e478546f88416eb4ac2363fb2 is 293, key is \x00\x00\x00\x00\x00\x00\x00\x94/proc:d/1733210087772/Put/seqid=0 2024-12-03T07:29:05,792 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741842_1018 (size=11538) 2024-12-03T07:29:05,877 INFO [8046980647f4:39969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-03T07:29:06,194 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=427.13 KB at sequenceid=1164 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/ce72f10e478546f88416eb4ac2363fb2 2024-12-03T07:29:06,208 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for ce72f10e478546f88416eb4ac2363fb2 2024-12-03T07:29:06,222 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/95509d157b6248c2ab58a2f7f24bcccb is 69, key is 8046980647f4,39969,1733210043547/rs:state/1733210045770/Put/seqid=0 2024-12-03T07:29:06,226 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741843_1019 (size=5156) 2024-12-03T07:29:06,329 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:29:06,629 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=65 B at sequenceid=1164 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/95509d157b6248c2ab58a2f7f24bcccb 2024-12-03T07:29:06,656 DEBUG [master:store-Flusher {}] hfile.HFileWriterImpl(814): Len of the biggest cell in hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/998d7261c54f45c8867baed3ced3658c is 68, key is replication_peer_modification_on/state:d/1733210083313/Put/seqid=0 2024-12-03T07:29:06,660 INFO [Block report processor {}] blockmanagement.BlockManager(3777): BLOCK* addStoredBlock: 127.0.0.1:38883 is added to blk_1073741844_1020 (size=5154) 2024-12-03T07:29:07,063 INFO [master:store-Flusher {}] regionserver.DefaultStoreFlusher(81): Flushed memstore data size=1 KB at sequenceid=1164 (bloomFilter=true), to=hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/998d7261c54f45c8867baed3ced3658c 2024-12-03T07:29:07,078 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/info/fdb0e1cc5e854607aeac8ca4293d1b7d as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/fdb0e1cc5e854607aeac8ca4293d1b7d 2024-12-03T07:29:07,087 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/info/fdb0e1cc5e854607aeac8ca4293d1b7d, entries=8, sequenceid=1164, filesize=5.5 K 2024-12-03T07:29:07,088 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/proc/ce72f10e478546f88416eb4ac2363fb2 as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/ce72f10e478546f88416eb4ac2363fb2 2024-12-03T07:29:07,095 INFO [master:store-Flusher {}] regionserver.StoreFileReader(539): Loaded Delete Family Bloom (CompoundBloomFilter) metadata for ce72f10e478546f88416eb4ac2363fb2 2024-12-03T07:29:07,096 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:29:07,096 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/proc/ce72f10e478546f88416eb4ac2363fb2, entries=149, sequenceid=1164, filesize=11.3 K 2024-12-03T07:29:07,097 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/rs/95509d157b6248c2ab58a2f7f24bcccb as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/95509d157b6248c2ab58a2f7f24bcccb 2024-12-03T07:29:07,104 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/rs/95509d157b6248c2ab58a2f7f24bcccb, entries=1, sequenceid=1164, filesize=5.0 K 2024-12-03T07:29:07,105 DEBUG [master:store-Flusher {}] regionserver.HRegionFileSystem(442): Committing hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/.tmp/state/998d7261c54f45c8867baed3ced3658c as hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/998d7261c54f45c8867baed3ced3658c 2024-12-03T07:29:07,113 INFO [master:store-Flusher {}] regionserver.HStore$StoreFlusherImpl(1989): Added hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData/data/master/store/1595e783b53d99cd5eef43b6debb2682/state/998d7261c54f45c8867baed3ced3658c, entries=1, sequenceid=1164, filesize=5.0 K 2024-12-03T07:29:07,114 INFO [master:store-Flusher {}] regionserver.HRegion(3040): Finished flush of dataSize ~428.68 KB/438973, heapSize ~530.58 KB/543312, currentSize=0 B/0 for 1595e783b53d99cd5eef43b6debb2682 in 1789ms, sequenceid=1164, compaction requested=false 2024-12-03T07:29:07,114 DEBUG [master:store-Flusher {}] regionserver.HRegion(2538): Flush status journal for 1595e783b53d99cd5eef43b6debb2682: 2024-12-03T07:29:07,333 DEBUG [hconnection-0x311e3d67-shared-pool-8 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:29:07,336 INFO [RS-EventLoopGroup-3-1 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:43456, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:29:07,340 DEBUG [master/8046980647f4:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-03T07:29:07,341 DEBUG [master/8046980647f4:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-03T07:29:07,344 DEBUG [master/8046980647f4:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-03T07:29:08,606 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:29:12,610 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:29:20,449 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:29:26,430 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:29:32,038 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. 2024-12-03T07:29:40,610 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:29:46,570 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:29:52,096 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:29:53,606 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:30:00,650 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:30:02,038 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. 2024-12-03T07:30:06,679 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:30:20,730 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:30:26,830 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:30:32,039 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. 2024-12-03T07:30:37,097 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:30:38,607 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:30:40,939 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:30:47,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:31:01,009 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:31:02,039 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. 2024-12-03T07:31:07,020 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:31:21,059 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:31:22,097 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:31:23,608 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:31:27,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:31:32,039 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. 2024-12-03T07:31:41,230 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:31:47,409 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:32:01,320 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:32:02,040 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. 2024-12-03T07:32:07,098 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:32:07,479 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:32:08,608 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:32:21,369 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:32:27,549 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:32:32,040 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. 2024-12-03T07:32:41,540 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:32:47,700 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:32:52,098 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:32:53,608 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:33:01,690 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:33:02,040 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. 2024-12-03T07:33:07,889 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:33:21,810 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:33:27,950 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:33:32,041 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. 2024-12-03T07:33:37,099 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:33:38,609 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:33:41,949 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:33:48,030 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:34:02,041 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. 2024-12-03T07:34:02,109 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:34:03,558 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 2024-12-03T07:34:03,634 DEBUG [master/8046980647f4:0: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% 2024-12-03T07:34:03,634 DEBUG [master/8046980647f4:0: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 2024-12-03T07:34:05,877 INFO [8046980647f4:39969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-03T07:34:08,080 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:34:08,853 DEBUG [master/8046980647f4:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-03T07:34:08,853 DEBUG [master/8046980647f4:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-03T07:34:08,858 DEBUG [master/8046980647f4:0.Chore.1 {}] replication.ZKReplicationQueueStorage(530): Didn't find a RegionServer that replicates, won't prevent deletions. 2024-12-03T07:34:08,865 DEBUG [hconnection-0x311e3d67-shared-pool-10 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:34:08,867 INFO [RS-EventLoopGroup-3-2 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:49250, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:34:08,873 DEBUG [master/8046980647f4:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-03T07:34:12,618 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:34:22,100 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:34:22,229 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:34:23,609 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:34:28,120 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:34:32,042 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. 2024-12-03T07:34:42,250 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:34:48,140 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:35:02,042 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. 2024-12-03T07:35:02,369 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:35:07,100 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:35:08,210 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:35:08,610 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:35:22,500 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:35:28,370 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:35:32,042 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. 2024-12-03T07:35:42,700 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:35:48,390 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:35:52,101 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:35:53,611 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:36:02,043 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. 2024-12-03T07:36:02,799 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:36:08,520 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:36:22,980 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:36:28,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:36:32,043 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. 2024-12-03T07:36:37,101 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:36:38,611 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:36:43,019 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:36:48,560 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:37:02,044 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. 2024-12-03T07:37:03,190 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:37:08,739 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:37:22,102 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:37:23,249 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:37:23,612 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:37:28,859 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:37:32,044 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. 2024-12-03T07:37:43,450 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:37:49,060 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:38:02,044 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. 2024-12-03T07:38:03,539 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:38:07,103 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:38:08,612 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:38:09,159 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:38:23,669 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:38:29,360 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:38:32,045 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. 2024-12-03T07:38:43,870 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:38:49,410 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:38:52,103 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:38:53,613 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:39:02,045 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. 2024-12-03T07:39:03,558 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 2024-12-03T07:39:03,633 DEBUG [master/8046980647f4:0: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% 2024-12-03T07:39:03,634 DEBUG [master/8046980647f4:0: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 2024-12-03T07:39:03,969 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:39:05,877 INFO [8046980647f4:39969Replication Statistics #0 {}] regionserver.Replication$ReplicationStatisticsTask(247): Global stats: WAL Edits Buffer Used=0B, Limit=268435456B 2024-12-03T07:39:08,463 DEBUG [master/8046980647f4:0.Chore.1 {}] balancer.BaseLoadBalancer(778): Start Generate Balance plan for cluster. 2024-12-03T07:39:08,463 DEBUG [master/8046980647f4:0.Chore.1 {}] master.HMaster(2144): Balancer is going into sleep until next period in 300000ms 2024-12-03T07:39:08,465 DEBUG [hconnection-0x311e3d67-shared-pool-12 {}] ipc.RpcConnection(159): Using SIMPLE authentication for service=ClientService, sasl=false 2024-12-03T07:39:08,467 INFO [RS-EventLoopGroup-3-3 {}] ipc.ServerRpcConnection(484): Connection from 172.17.0.2:38322, version=2.7.0-SNAPSHOT, sasl=false, ugi=jenkins (auth:SIMPLE), service=ClientService 2024-12-03T07:39:08,475 DEBUG [master/8046980647f4:0.Chore.1 {}] janitor.CatalogJanitor(179): 2024-12-03T07:39:09,480 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:39:12,610 WARN [HBase-Metrics2-1 {}] impl.MetricsConfig(138): Cannot locate configuration: tried hadoop-metrics2-hbase.properties,hadoop-metrics2.properties 2024-12-03T07:39:24,070 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:39:29,490 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 2024-12-03T07:39:32,046 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. 2024-12-03T07:39:37,104 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region 1588230740, had cached 0 bytes from a total of 11837 2024-12-03T07:39:38,613 DEBUG [HBase-Metrics2-1 {}] regionserver.MetricsRegionWrapperImpl$HRegionMetricsWrapperRunnable(324): Region ef235488523e821f809aed54184195da, had cached 0 bytes from a total of 5037 2024-12-03T07:39:44,169 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=148 2024-12-03T07:39:49,600 DEBUG [RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=33011 {}] master.MasterRpcServices(1305): Checking to see if procedure is done pid=23 ====> TEST TIMED OUT. PRINTING THREAD DUMP. <==== Timestamp: 2024-12-03 07:39:59,080 "IPC Server handler 0 on default port 32817" 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) "master/8046980647f4:0.Chore.1" daemon prio=5 tid=259 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS_REFRESH_PEER-regionserver/8046980647f4:0-0" 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) "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) "pool-1-thread-2" daemon prio=5 tid=15 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.poll(EPollPort.java:200) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.run(EPollPort.java:281) at java.base@17.0.11/sun.nio.ch.AsynchronousChannelGroupImpl$1.run(AsynchronousChannelGroupImpl.java:113) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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$257/0x00007f0c20423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-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) "Timer for 'HBase' metrics system" daemon prio=5 tid=1009 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-1-2" daemon prio=10 tid=267 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-2" daemon prio=5 tid=749 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RedundancyMonitor" daemon prio=5 tid=47 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at java.base@17.0.11/java.lang.Thread.sleep(Thread.java:344) at java.base@17.0.11/java.util.concurrent.TimeUnit.sleep(TimeUnit.java:446) at app//org.apache.hadoop.hdfs.server.blockmanagement.BlockManager$RedundancyMonitor.run(BlockManager.java:5352) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "IPC Server handler 3 on default port 42129" 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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "OldWALsCleaner-0" daemon prio=5 tid=258 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$594/0x00007f0c20a60800.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-EventThread" daemon prio=5 tid=193 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.zookeeper.ClientCnxn$EventThread.run(ClientCnxn.java:550) "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) "RS_OPEN_PRIORITY_REGION-regionserver/8046980647f4:0-0" 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) "org.apache.hadoop.hdfs.PeerCache@6d5b9bad" 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) "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) "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$257/0x00007f0c20423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "pool-1-thread-1" daemon prio=5 tid=14 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at java.base@17.0.11/sun.nio.ch.EPollPort$EventHandlerTask.run(EPollPort.java:275) at java.base@17.0.11/sun.nio.ch.AsynchronousChannelGroupImpl$1.run(AsynchronousChannelGroupImpl.java:113) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1136) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcClient-timer-pool-0" daemon prio=5 tid=241 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hbase.thirdparty.io.netty.util.HashedWheelTimer$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) "LeaseRenewer:jenkins.hfs.0@localhost:42129" 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$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "java.util.concurrent.ThreadPoolExecutor$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) "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) "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$FinalizerThread.run(Finalizer.java:172) "process reaper" daemon prio=10 tid=1007 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.SynchronousQueue$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/dfs/data/data2/current/BP-838497965-172.17.0.2-1733210039745" daemon prio=5 tid=124 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.fs.CachingGetSpaceUsed$RefreshThread.run(CachingGetSpaceUsed.java:225) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1965036093-89" daemon prio=5 tid=89 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at app//org.eclipse.jetty.util.BlockingArrayQueue.poll(BlockingArrayQueue.java:382) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.idleJobPoll(QueuedThreadPool.java:974) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1018) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-12" daemon prio=5 tid=168 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "ReadOnlyZKClient-127.0.0.1:55234@0x7502c059" 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$760/0x00007f0c20b4d8e0.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=33011" 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) "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.default.FPBQ.Fifo.handler=1,queue=0,port=33011" 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) "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) "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$257/0x00007f0c20423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "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) "regionserver/8046980647f4:0.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) "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$FlushHandler.run(MemStoreFlusher.java:322) "NIOWorkerThread-4" daemon prio=5 tid=159 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-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) "IPC Server idle connection scanner for port 42129" 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) "qtp1312628392-41-acceptor-0@2c832907-ServerConnector@1f7e2804{HTTP/1.1, (http/1.1)}{localhost:34019}" 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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "regionserver/8046980647f4:0.Chore.1" daemon prio=5 tid=273 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:1182) at java.base@17.0.11/java.util.concurrent.ScheduledThreadPoolExecutor$DelayedWorkQueue.take(ScheduledThreadPoolExecutor.java:899) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "CacheReplicationMonitor(742816305)" daemon prio=5 tid=75 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1759) at app//org.apache.hadoop.hdfs.server.blockmanagement.CacheReplicationMonitor.run(CacheReplicationMonitor.java:186) "PacketResponder: BP-838497965-172.17.0.2-1733210039745:blk_1073741840_1016, type=LAST_IN_PIPELINE" daemon prio=5 tid=890 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) "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) "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) "master/8046980647f4:0: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) "AsyncFSWAL-0-hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a-prefix:8046980647f4,39969,1733210043547" 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) "RS-EventLoopGroup-1-1" daemon prio=10 tid=154 runnable java.lang.Thread.State: RUNNABLE at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native Method) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:220) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.Native.epollWait(Native.java:213) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.epollWaitNoTimerChange(EpollEventLoop.java:308) at app//org.apache.hbase.thirdparty.io.netty.channel.epoll.EpollEventLoop.run(EpollEventLoop.java:365) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.SingleThreadEventExecutor$4.run(SingleThreadEventExecutor.java:997) at app//org.apache.hbase.thirdparty.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/8046980647f4:0:becomeActiveMaster-HFileCleaner.small.0-1733210045744" daemon prio=5 tid=263 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.PriorityBlockingQueue.take(PriorityBlockingQueue.java:535) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner.consumerLoop(HFileCleaner.java:285) at app//org.apache.hadoop.hbase.master.cleaner.HFileCleaner$2.run(HFileCleaner.java:269) "IPC Server handler 1 on default port 32817" daemon prio=5 tid=105 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Handler.run(Server.java:3165) "Time-limited test-EventThread" daemon prio=5 tid=156 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$MonitorRunnable.run(TaskMonitor.java:325) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "qtp1965036093-90" daemon prio=5 tid=90 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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) "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) "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$MarkedDeleteBlockScrubber.run(BlockManager.java:5326) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master/8046980647f4:0:becomeActiveMaster-MemStoreChunkPool Statistics" daemon prio=5 tid=211 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "master:store-WAL-Roller" daemon prio=5 tid=225 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.wal.AbstractWALRoller.run(AbstractWALRoller.java:179) "RS_OPEN_META-regionserver/8046980647f4:0-0" daemon prio=5 tid=294 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "8046980647f4:33011" daemon prio=5 tid=251 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$1.run(AssignmentManager.java:2332) "IPC Client (1877429482) connection to localhost/127.0.0.1:42129 from jenkins" daemon prio=5 tid=109 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.ipc.Client$Connection.waitForWork(Client.java:1042) at app//org.apache.hadoop.ipc.Client$Connection.run(Client.java:1093) "pool-5-thread-1" prio=5 tid=36 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=33011" daemon prio=5 tid=181 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "HBase-Metrics2-1" daemon prio=5 tid=153 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Block report processor" daemon prio=5 tid=51 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$BlockReportProcessingThread.run(BlockManager.java:5614) "zk-event-processor-pool-0" daemon prio=5 tid=194 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$257/0x00007f0c20423440.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) "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) "RpcServer.default.FPBQ.Fifo.handler=1,queue=0,port=39969" 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) "IPC Server handler 2 on default port 42129" 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) "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) "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) "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) "NIOServerCxnFactory.AcceptThread:localhost/127.0.0.1:55234" 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) "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) "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=1,queue=1,port=39969" 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) "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) "PacketResponder: BP-838497965-172.17.0.2-1733210039745: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) "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) "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) "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) "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) "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) "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$481/0x00007f0c209ba518.run(Unknown Source) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-2" daemon prio=5 tid=157 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=33011" 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) "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) "org.apache.hadoop.util.JvmPauseMonitor$Monitor@df7e1a0" daemon prio=5 tid=93 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.util.JvmPauseMonitor$Monitor.run(JvmPauseMonitor.java:189) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ReadOnlyZKClient-127.0.0.1:55234@0x57d89e0d" 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$760/0x00007f0c20b4d8e0.run(Unknown Source) 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 "IPC Server handler 3 on default port 32817" 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) "refreshUsed-/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/dfs/data/data1/current/BP-838497965-172.17.0.2-1733210039745" 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) "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) "regionserver/8046980647f4:0.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) "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) "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) "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) "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) "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) "qtp1312628392-42" 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) "RS:0;8046980647f4:39969-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) "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) "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) "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) "AsyncFSWAL-0-hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a-prefix:8046980647f4,39969,1733210043547.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) "PacketResponder: BP-838497965-172.17.0.2-1733210039745: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) "IPC Server idle connection scanner for port 32817" 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) "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) "Time-limited test-SendThread(127.0.0.1:55234)" 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) "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) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=33011" 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) "RpcServer.priority.RWQ.Fifo.read.handler=1,queue=1,port=33011" 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) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/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) "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) "Notification Thread" daemon prio=9 tid=13 runnable java.lang.Thread.State: RUNNABLE "qtp1965036093-87" 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$257/0x00007f0c20423440.run(Unknown Source) at app//org.eclipse.jetty.util.thread.QueuedThreadPool.runJob(QueuedThreadPool.java:883) at app//org.eclipse.jetty.util.thread.QueuedThreadPool$Runner.run(QueuedThreadPool.java:1034) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "PEWorker-1" daemon prio=5 tid=245 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$WorkerThread.run(ProcedureExecutor.java:2128) "ConnnectionExpirer" daemon prio=5 tid=137 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.zookeeper.server.NIOServerCnxnFactory$ConnectionExpirerThread.run(NIOServerCnxnFactory.java:554) "DataXceiver for client DFSClient_NONMAPREDUCE_-789091245_22 at /127.0.0.1:51648 [Receiving block BP-838497965-172.17.0.2-1733210039745: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) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=39969" 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) "VolumeScannerThread(/home/jenkins/jenkins-home/workspace/HBase-Flaky-Tests_branch-2/hbase-server/target/test-data/bac87dcc-072f-16ff-6ef9-e99e34745690/cluster_18e8fc36-9b74-63bf-9c40-22ccabb189be/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) "Session-HouseKeeper-3685d53b-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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.default.FPBQ.Fifo.handler=2,queue=0,port=39969" daemon prio=5 tid=197 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "RS_COMPACTED_FILES_DISCHARGER-regionserver/8046980647f4:0-0" daemon prio=5 tid=756 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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 4 on default port 42129" 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) "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) "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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "region-location-1" daemon prio=5 tid=318 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "8046980647f4:39969Replication 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) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=39969" 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) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=39969" 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) "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) "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) "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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "ProcExecTimeout" daemon prio=5 tid=243 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "AsyncFSWAL-0-hdfs://localhost:42129/user/jenkins/test-data/5099e2a8-f0d1-cd3b-900d-900136dfc51a/MasterData-prefix:8046980647f4,33011,1733210042815" 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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-5" daemon prio=5 tid=161 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "NIOWorkerThread-6" daemon prio=5 tid=162 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.getTask(ThreadPoolExecutor.java:1062) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1122) at java.base@17.0.11/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.replication.FPBQ.Fifo.handler=0,queue=0,port=39969" daemon prio=5 tid=201 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "Time-limited test" daemon prio=5 tid=22 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.CompletableFuture$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$CallableStatement.call(FailOnTimeout.java:293) at java.base@17.0.11/java.util.concurrent.FutureTask.run(FutureTask.java:264) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "FSEditLogAsync" daemon prio=5 tid=53 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionNode.block(AbstractQueuedSynchronizer.java:506) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.unmanagedBlock(ForkJoinPool.java:3465) at java.base@17.0.11/java.util.concurrent.ForkJoinPool.managedBlock(ForkJoinPool.java:3436) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.ArrayBlockingQueue.take(ArrayBlockingQueue.java:420) at app//org.apache.hadoop.hdfs.server.namenode.FSEditLogAsync.dequeueEdit(FSEditLogAsync.java:241) at app//org.apache.hadoop.hdfs.server.namenode.FSEditLogAsync.run(FSEditLogAsync.java:250) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "IPC Server handler 0 on default port 42129" daemon prio=5 tid=64 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "BP-838497965-172.17.0.2-1733210039745 heartbeating to localhost/127.0.0.1:42129" daemon prio=5 tid=102 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hdfs.server.datanode.IncrementalBlockReportManager.waitTillNextIBR(IncrementalBlockReportManager.java:158) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor.offerService(BPServiceActor.java:771) at app//org.apache.hadoop.hdfs.server.datanode.BPServiceActor.run(BPServiceActor.java:914) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RS-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$2.run(ThreadExecutorMap.java:74) at app//org.apache.hbase.thirdparty.io.netty.util.concurrent.FastThreadLocalRunnable.run(FastThreadLocalRunnable.java:30) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Command processor" daemon prio=5 tid=101 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$CommandProcessingThread.run(BPServiceActor.java:1395) "PEWorker-2" daemon prio=5 tid=246 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$WorkerThread.run(ProcedureExecutor.java:2128) "qtp1312628392-43" daemon prio=5 tid=43 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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) "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) "IPC Parameter Sending Thread for localhost/127.0.0.1:42129" 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$RpcRequestSender.run(Client.java:1121) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-16" daemon prio=5 tid=172 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=33011" daemon prio=5 tid=178 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "FsDatasetAsyncDiskServiceFixer" daemon prio=5 tid=136 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hbase.HBaseTestingUtility$FsDatasetAsyncDiskServiceFixer.run(HBaseTestingUtility.java:599) "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) "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) "RS:0;8046980647f4:39969" 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$MiniHBaseClusterRegionServer.run(MiniHBaseCluster.java:157) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RegionServerTracker-0" daemon prio=5 tid=268 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "regionserver/8046980647f4:0.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) "IPC Server handler 1 on default port 42129" 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) "org.apache.hadoop.hdfs.server.datanode.DataXceiverServer@a467a69" 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) "RpcServer.replication.FPBQ.Fifo.handler=2,queue=0,port=39969" 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) "DataXceiver for client DFSClient_NONMAPREDUCE_-789091245_22 at /127.0.0.1:51658 [Receiving block BP-838497965-172.17.0.2-1733210039745:blk_1073741834_1010]" daemon prio=5 tid=295 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.hadoop.net.SocketIOWithTimeout$SelectorPool.select(SocketIOWithTimeout.java:335) at app//org.apache.hadoop.net.SocketIOWithTimeout.doIO(SocketIOWithTimeout.java:156) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:161) at app//org.apache.hadoop.net.SocketInputStream.read(SocketInputStream.java:131) at java.base@17.0.11/java.io.BufferedInputStream.fill(BufferedInputStream.java:244) at java.base@17.0.11/java.io.BufferedInputStream.read1(BufferedInputStream.java:284) at java.base@17.0.11/java.io.BufferedInputStream.read(BufferedInputStream.java:343) at java.base@17.0.11/java.io.DataInputStream.read(DataInputStream.java:151) at app//org.apache.hadoop.io.IOUtils.readFully(IOUtils.java:214) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doReadFully(PacketReceiver.java:221) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.doRead(PacketReceiver.java:144) at app//org.apache.hadoop.hdfs.protocol.datatransfer.PacketReceiver.receiveNextPacket(PacketReceiver.java:119) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receivePacket(BlockReceiver.java:553) at app//org.apache.hadoop.hdfs.server.datanode.BlockReceiver.receiveBlock(BlockReceiver.java:1011) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.writeBlock(DataXceiver.java:920) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opWriteBlock(Receiver.java:176) at app//org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:110) at app//org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:299) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "surefire-forkedjvm-stream-flusher" daemon prio=5 tid=16 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "NIOWorkerThread-9" daemon prio=5 tid=165 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "master/8046980647f4:0:becomeActiveMaster-HFileCleaner.large.0-1733210045743" daemon prio=5 tid=262 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$1.run(HFileCleaner.java:254) "RpcServer.priority.RWQ.Fifo.write.handler=0,queue=0,port=33011" daemon prio=5 tid=176 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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) "RpcServer.default.FPBQ.Fifo.handler=0,queue=0,port=39969" 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) "M:0;8046980647f4:33011" 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) "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) "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) "LeaseRenewer:jenkins@localhost:42129" daemon prio=5 tid=147 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Thread.sleep(Native Method) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.run(LeaseRenewer.java:441) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer.access$800(LeaseRenewer.java:77) at app//org.apache.hadoop.hdfs.client.impl.LeaseRenewer$1.run(LeaseRenewer.java:336) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "RpcServer.priority.RWQ.Fifo.read.handler=2,queue=1,port=39969" daemon prio=5 tid=200 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:341) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$ConditionObject.await(AbstractQueuedSynchronizer.java:1625) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.take(LinkedBlockingQueue.java:435) at app//org.apache.hadoop.hbase.ipc.RpcHandler.getCallRunner(RpcHandler.java:71) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "RpcServer.metaPriority.FPBQ.Fifo.handler=0,queue=0,port=33011" daemon prio=5 tid=182 in Object.wait() java.lang.Thread.State: WAITING (on object monitor) at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.park(LockSupport.java:211) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquire(AbstractQueuedSynchronizer.java:715) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer.acquireSharedInterruptibly(AbstractQueuedSynchronizer.java:1047) at java.base@17.0.11/java.util.concurrent.Semaphore.acquire(Semaphore.java:318) at app//org.apache.hadoop.hbase.ipc.FastPathRpcHandler.getCallRunner(FastPathRpcHandler.java:55) at app//org.apache.hadoop.hbase.ipc.RpcHandler.run(RpcHandler.java:85) "Time-limited test-SendThread(127.0.0.1:55234)" daemon prio=5 tid=155 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "qtp1965036093-88-acceptor-0@73194d7e-ServerConnector@723ec49{HTTP/1.1, (http/1.1)}{localhost:39893}" 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) "ProcessThread(sid:0 cport:55234):" 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) "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$Worker.run(ThreadPoolExecutor.java:635) at java.base@17.0.11/java.lang.Thread.run(Thread.java:840) "Time-limited test-SendThread(127.0.0.1:55234)" daemon prio=5 tid=192 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:141) at app//org.apache.zookeeper.ClientCnxnSocketNIO.doTransport(ClientCnxnSocketNIO.java:332) at app//org.apache.zookeeper.ClientCnxn$SendThread.run(ClientCnxn.java:1289) "snapshot-hfile-cleaner-cache-refresher" daemon prio=5 tid=260 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at java.base@17.0.11/java.util.TimerThread.mainLoop(Timer.java:563) at java.base@17.0.11/java.util.TimerThread.run(Timer.java:516) "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$ReferenceHandler.run(Reference.java:215) "Time-limited test.LruBlockCache.EvictionThread" daemon prio=5 tid=187 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/java.lang.Object.wait(Native Method) at app//org.apache.hadoop.hbase.io.hfile.LruBlockCache$EvictionThread.run(LruBlockCache.java:957) "IPC Server handler 2 on default port 32817" 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) "DataXceiver for client DFSClient_NONMAPREDUCE_170005640_22 at /127.0.0.1:56176 [Receiving block BP-838497965-172.17.0.2-1733210039745:blk_1073741840_1016]" daemon prio=5 tid=889 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) "RpcServer.replication.FPBQ.Fifo.handler=1,queue=0,port=33011" 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) "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$TimeoutExecutorThread.run(RemoteProcedureDispatcher.java:328) "PEWorker-3" daemon prio=5 tid=247 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$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$WorkerThread.run(ProcedureExecutor.java:2128) "IPC Server handler 4 on default port 32817" daemon prio=5 tid=108 timed_waiting java.lang.Thread.State: TIMED_WAITING at java.base@17.0.11/jdk.internal.misc.Unsafe.park(Native Method) at java.base@17.0.11/java.util.concurrent.locks.LockSupport.parkNanos(LockSupport.java:252) at java.base@17.0.11/java.util.concurrent.locks.AbstractQueuedSynchronizer$ConditionObject.awaitNanos(AbstractQueuedSynchronizer.java:1674) at java.base@17.0.11/java.util.concurrent.LinkedBlockingQueue.poll(LinkedBlockingQueue.java:460) at app//org.apache.hadoop.ipc.CallQueueManager.take(CallQueueManager.java:370) at app//org.apache.hadoop.ipc.Server$Handler.run(Server.java:3165) "IPC Server listener on 0" daemon prio=5 tid=54 runnable java.lang.Thread.State: RUNNABLE at java.base@17.0.11/sun.nio.ch.EPoll.wait(Native Method) at java.base@17.0.11/sun.nio.ch.EPollSelectorImpl.doSelect(EPollSelectorImpl.java:118) at java.base@17.0.11/sun.nio.ch.SelectorImpl.lockAndDoSelect(SelectorImpl.java:129) at java.base@17.0.11/sun.nio.ch.SelectorImpl.select(SelectorImpl.java:146) at app//org.apache.hadoop.ipc.Server$Listener.run(Server.java:1559) "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)