You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@flink.apache.org by "Dawid Wysakowicz (Jira)" <ji...@apache.org> on 2021/03/19 07:53:00 UTC

[jira] [Created] (FLINK-21866) JMXJobManagerMetricTest crashes on azure

Dawid Wysakowicz created FLINK-21866:
----------------------------------------

             Summary: JMXJobManagerMetricTest crashes on azure
                 Key: FLINK-21866
                 URL: https://issues.apache.org/jira/browse/FLINK-21866
             Project: Flink
          Issue Type: Bug
          Components: Runtime / Coordination
    Affects Versions: 1.13.0
            Reporter: Dawid Wysakowicz


https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=14990&view=logs&j=c91190b6-40ae-57b2-5999-31b869b0a7c1&t=43529380-51b4-5e90-5af4-2dccec0ef402&l=14134

{code}
[ERROR] Failed to execute goal org.apache.maven.plugins:maven-surefire-plugin:2.22.1:test (default-test) on project flink-metrics-jmx_2.11: There are test failures.
[ERROR] 
[ERROR] Please refer to /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire-reports for the individual test results.
[ERROR] Please refer to dump files (if any exist) [date].dump, [date]-jvmRun[N].dump and [date].dumpstream.
[ERROR] ExecutionException The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
[ERROR] Command was /bin/sh -c cd /__w/3/s/flink-metrics/flink-metrics-jmx && /usr/lib/jvm/java-8-openjdk-amd64/jre/bin/java -Xms256m -Xmx2048m -Dmvn.forkNumber=2 -XX:+UseG1GC -jar /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire/surefirebooter6251600074636448230.jar /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire 2021-03-18T23-30-30_066-jvmRun2 surefire5926299627725589334tmp surefire_1185286162062283237015tmp
[ERROR] Error occurred in starting fork, check output in log
[ERROR] Process Exit Code: 239
[ERROR] Crashed tests:
[ERROR] org.apache.flink.runtime.jobmanager.JMXJobManagerMetricTest
[ERROR] org.apache.maven.surefire.booter.SurefireBooterForkException: ExecutionException The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
[ERROR] Command was /bin/sh -c cd /__w/3/s/flink-metrics/flink-metrics-jmx && /usr/lib/jvm/java-8-openjdk-amd64/jre/bin/java -Xms256m -Xmx2048m -Dmvn.forkNumber=2 -XX:+UseG1GC -jar /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire/surefirebooter6251600074636448230.jar /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire 2021-03-18T23-30-30_066-jvmRun2 surefire5926299627725589334tmp surefire_1185286162062283237015tmp
[ERROR] Error occurred in starting fork, check output in log
[ERROR] Process Exit Code: 239
[ERROR] Crashed tests:
[ERROR] org.apache.flink.runtime.jobmanager.JMXJobManagerMetricTest
[ERROR] at org.apache.maven.plugin.surefire.booterclient.ForkStarter.awaitResultsDone(ForkStarter.java:510)
[ERROR] at org.apache.maven.plugin.surefire.booterclient.ForkStarter.runSuitesForkOnceMultiple(ForkStarter.java:382)
[ERROR] at org.apache.maven.plugin.surefire.booterclient.ForkStarter.run(ForkStarter.java:297)
[ERROR] at org.apache.maven.plugin.surefire.booterclient.ForkStarter.run(ForkStarter.java:246)
[ERROR] at org.apache.maven.plugin.surefire.AbstractSurefireMojo.executeProvider(AbstractSurefireMojo.java:1183)
[ERROR] at org.apache.maven.plugin.surefire.AbstractSurefireMojo.executeAfterPreconditionsChecked(AbstractSurefireMojo.java:1011)
[ERROR] at org.apache.maven.plugin.surefire.AbstractSurefireMojo.execute(AbstractSurefireMojo.java:857)
[ERROR] at org.apache.maven.plugin.DefaultBuildPluginManager.executeMojo(DefaultBuildPluginManager.java:132)
[ERROR] at org.apache.maven.lifecycle.internal.MojoExecutor.execute(MojoExecutor.java:208)
[ERROR] at org.apache.maven.lifecycle.internal.MojoExecutor.execute(MojoExecutor.java:153)
[ERROR] at org.apache.maven.lifecycle.internal.MojoExecutor.execute(MojoExecutor.java:145)
[ERROR] at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject(LifecycleModuleBuilder.java:116)
[ERROR] at org.apache.maven.lifecycle.internal.LifecycleModuleBuilder.buildProject(LifecycleModuleBuilder.java:80)
[ERROR] at org.apache.maven.lifecycle.internal.builder.singlethreaded.SingleThreadedBuilder.build(SingleThreadedBuilder.java:51)
[ERROR] at org.apache.maven.lifecycle.internal.LifecycleStarter.execute(LifecycleStarter.java:120)
[ERROR] at org.apache.maven.DefaultMaven.doExecute(DefaultMaven.java:355)
[ERROR] at org.apache.maven.DefaultMaven.execute(DefaultMaven.java:155)
[ERROR] at org.apache.maven.cli.MavenCli.execute(MavenCli.java:584)
[ERROR] at org.apache.maven.cli.MavenCli.doMain(MavenCli.java:216)
[ERROR] at org.apache.maven.cli.MavenCli.main(MavenCli.java:160)
[ERROR] at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
[ERROR] at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
[ERROR] at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
[ERROR] at java.lang.reflect.Method.invoke(Method.java:498)
[ERROR] at org.codehaus.plexus.classworlds.launcher.Launcher.launchEnhanced(Launcher.java:289)
[ERROR] at org.codehaus.plexus.classworlds.launcher.Launcher.launch(Launcher.java:229)
[ERROR] at org.codehaus.plexus.classworlds.launcher.Launcher.mainWithExitCode(Launcher.java:415)
[ERROR] at org.codehaus.plexus.classworlds.launcher.Launcher.main(Launcher.java:356)
[ERROR] Caused by: org.apache.maven.surefire.booter.SurefireBooterForkException: The forked VM terminated without properly saying goodbye. VM crash or System.exit called?
[ERROR] Command was /bin/sh -c cd /__w/3/s/flink-metrics/flink-metrics-jmx && /usr/lib/jvm/java-8-openjdk-amd64/jre/bin/java -Xms256m -Xmx2048m -Dmvn.forkNumber=2 -XX:+UseG1GC -jar /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire/surefirebooter6251600074636448230.jar /__w/3/s/flink-metrics/flink-metrics-jmx/target/surefire 2021-03-18T23-30-30_066-jvmRun2 surefire5926299627725589334tmp surefire_1185286162062283237015tmp
[ERROR] Error occurred in starting fork, check output in log
[ERROR] Process Exit Code: 239
[ERROR] Crashed tests:
[ERROR] org.apache.flink.runtime.jobmanager.JMXJobManagerMetricTest
[ERROR] at org.apache.maven.plugin.surefire.booterclient.ForkStarter.fork(ForkStarter.java:669)
[ERROR] at java.util.concurrent.FutureTask.run(FutureTask.java:266)
[ERROR] at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
[ERROR] at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
[ERROR] at java.lang.Thread.run(Thread.java:748)
{code}

Going through the logs I found out logs like the following:

{code}
23:52:01,173 [flink-akka.actor.default-dispatcher-2] ERROR org.apache.flink.runtime.util.FatalExitExceptionHandler      [] - FATAL: Thread 'flink-akka.actor.default-dispatcher-2' produced an uncaught exception. Stopping the process...
java.util.concurrent.CompletionException: org.apache.flink.util.FlinkException: Could not properly shut down the JobManagerRunner
        at java.util.concurrent.CompletableFuture.encodeRelay(CompletableFuture.java:326) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.uniComposeStage(CompletableFuture.java:998) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.thenCompose(CompletableFuture.java:2137) ~[?:1.8.0_282]
        at org.apache.flink.runtime.dispatcher.DispatcherJob.lambda$closeAsync$8(DispatcherJob.java:273) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:836) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.uniHandleStage(CompletableFuture.java:848) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.handle(CompletableFuture.java:2168) ~[?:1.8.0_282]
        at org.apache.flink.runtime.dispatcher.DispatcherJob.closeAsync(DispatcherJob.java:268) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.dispatcher.Dispatcher.removeJob(Dispatcher.java:754) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.dispatcher.Dispatcher.lambda$runJob$4(Dispatcher.java:432) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.postFire(CompletableFuture.java:575) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:814) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture$Completion.run(CompletableFuture.java:456) ~[?:1.8.0_282]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:440) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:208) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) [scala-library-2.11.12.jar:?]
        at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) [scala-library-2.11.12.jar:?]
        at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) [scala-library-2.11.12.jar:?]
        at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) [scala-library-2.11.12.jar:?]
        at akka.actor.Actor$class.aroundReceive(Actor.scala:517) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.actor.ActorCell.invoke(ActorCell.scala:561) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.Mailbox.run(Mailbox.scala:225) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.Mailbox.exec(Mailbox.scala:235) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) [akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) [akka-actor_2.11-2.5.21.jar:2.5.21]
Caused by: org.apache.flink.util.FlinkException: Could not properly shut down the JobManagerRunner
        at org.apache.flink.runtime.jobmaster.JobManagerRunnerImpl.lambda$closeAsync$0(JobManagerRunnerImpl.java:224) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.uniWhenCompleteStage(CompletableFuture.java:792) ~[?:1.8.0_282]
        at java.util.concurrent.CompletableFuture.whenComplete(CompletableFuture.java:2153) ~[?:1.8.0_282]
        at org.apache.flink.runtime.jobmaster.JobManagerRunnerImpl.closeAsync(JobManagerRunnerImpl.java:208) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at java.util.concurrent.CompletableFuture.uniComposeStage(CompletableFuture.java:995) ~[?:1.8.0_282]
        ... 36 more
Caused by: org.apache.flink.runtime.rpc.akka.exceptions.AkkaRpcException: Could not start RpcEndpoint jobmanager_3.
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:610) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:180) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) ~[scala-library-2.11.12.jar:?]
        at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) ~[scala-library-2.11.12.jar:?]
        ... 12 more
Caused by: org.apache.flink.runtime.jobmaster.JobMasterException: Could not start the JobMaster.
        at org.apache.flink.runtime.jobmaster.JobMaster.onStart(JobMaster.java:384) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStart(RpcEndpoint.java:181) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:605) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:180) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) ~[scala-library-2.11.12.jar:?]
        at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) ~[scala-library-2.11.12.jar:?]
        ... 12 more
Caused by: java.lang.IllegalArgumentException
        at org.apache.flink.util.Preconditions.checkArgument(Preconditions.java:122) ~[flink-core-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.util.ResourceCounter.withResource(ResourceCounter.java:244) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.scheduler.adaptive.allocator.SlotSharingSlotAllocator.calculateRequiredSlots(SlotSharingSlotAllocator.java:61) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.scheduler.adaptive.AdaptiveScheduler.calculateDesiredResources(AdaptiveScheduler.java:728) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.scheduler.adaptive.AdaptiveScheduler.goToWaitingForResources(AdaptiveScheduler.java:720) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.scheduler.adaptive.Created.startScheduling(Created.java:72) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.scheduler.adaptive.AdaptiveScheduler.startScheduling(AdaptiveScheduler.java:308) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.jobmaster.JobMaster.startScheduling(JobMaster.java:960) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.jobmaster.JobMaster.startJobExecution(JobMaster.java:873) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.jobmaster.JobMaster.onStart(JobMaster.java:382) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.RpcEndpoint.internalCallOnStart(RpcEndpoint.java:181) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor$StoppedState.start(AkkaRpcActor.java:605) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleControlMessage(AkkaRpcActor.java:180) ~[flink-runtime_2.11-1.13-SNAPSHOT.jar:1.13-SNAPSHOT]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) ~[scala-library-2.11.12.jar:?]
        at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) ~[akka-actor_2.11-2.5.21.jar:2.5.21]
        at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) ~[scala-library-2.11.12.jar:?]
        ... 12 more
{code}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)