You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Chesnay Schepler (JIRA)" <ji...@apache.org> on 2019/05/09 15:33:00 UTC

[jira] [Assigned] (FLINK-12111) TaskManagerProcessFailureBatchRecoveryITCase fails due to removed Slot

     [ https://issues.apache.org/jira/browse/FLINK-12111?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Chesnay Schepler reassigned FLINK-12111:
----------------------------------------

    Assignee: Chesnay Schepler

> TaskManagerProcessFailureBatchRecoveryITCase fails due to removed Slot
> ----------------------------------------------------------------------
>
>                 Key: FLINK-12111
>                 URL: https://issues.apache.org/jira/browse/FLINK-12111
>             Project: Flink
>          Issue Type: Bug
>          Components: Runtime / Coordination
>    Affects Versions: 1.8.1
>            Reporter: Chesnay Schepler
>            Assignee: Chesnay Schepler
>            Priority: Critical
>              Labels: test-stability
>
> https://travis-ci.org/apache/flink/jobs/515636826
> {code}
> org.apache.flink.client.program.ProgramInvocationException: Job failed. (JobID: 4f32093d9c7554c3de832d20f0a06eb5)
> 	at org.apache.flink.client.program.rest.RestClusterClient.submitJob(RestClusterClient.java:268)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:483)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:471)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:446)
> 	at org.apache.flink.client.RemoteExecutor.executePlanWithJars(RemoteExecutor.java:210)
> 	at org.apache.flink.client.RemoteExecutor.executePlan(RemoteExecutor.java:187)
> 	at org.apache.flink.api.java.RemoteEnvironment.execute(RemoteEnvironment.java:173)
> 	at org.apache.flink.api.java.ExecutionEnvironment.execute(ExecutionEnvironment.java:817)
> 	at org.apache.flink.api.java.DataSet.collect(DataSet.java:413)
> 	at org.apache.flink.test.recovery.TaskManagerProcessFailureBatchRecoveryITCase.testTaskManagerFailure(TaskManagerProcessFailureBatchRecoveryITCase.java:115)
> 	at org.apache.flink.test.recovery.AbstractTaskManagerProcessFailureRecoveryTest$1.run(AbstractTaskManagerProcessFailureRecoveryTest.java:143)
> Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
> 	at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:146)
> 	at org.apache.flink.client.program.rest.RestClusterClient.submitJob(RestClusterClient.java:265)
> 	... 10 more
> Caused by: org.apache.flink.util.FlinkException: The assigned slot 786ec47f893240315bb01291aab680ec_1 was removed.
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.removeSlot(SlotManager.java:893)
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.removeSlots(SlotManager.java:863)
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.internalUnregisterTaskManager(SlotManager.java:1058)
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.unregisterTaskManager(SlotManager.java:385)
> 	at org.apache.flink.runtime.resourcemanager.ResourceManager.closeTaskManagerConnection(ResourceManager.java:847)
> 	at org.apache.flink.runtime.resourcemanager.ResourceManager$TaskManagerHeartbeatListener$1.run(ResourceManager.java:1161)
> 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:392)
> 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:185)
> 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
> 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.onReceive(AkkaRpcActor.java:147)
> 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.onReceive(FencedAkkaRpcActor.java:40)
> 	at akka.actor.UntypedActor$$anonfun$receive$1.applyOrElse(UntypedActor.scala:165)
> 	at akka.actor.Actor$class.aroundReceive(Actor.scala:502)
> 	at akka.actor.UntypedActor.aroundReceive(UntypedActor.scala:95)
> 	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:526)
> 	at akka.actor.ActorCell.invoke(ActorCell.scala:495)
> 	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:257)
> 	at akka.dispatch.Mailbox.run(Mailbox.scala:224)
> 	at akka.dispatch.Mailbox.exec(Mailbox.scala:234)
> 	at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> 	at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> 	at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> 	at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> org.apache.flink.client.program.ProgramInvocationException: Job failed. (JobID: 4f32093d9c7554c3de832d20f0a06eb5)
> 	at org.apache.flink.client.program.rest.RestClusterClient.submitJob(RestClusterClient.java:268)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:483)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:471)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:446)
> 	at org.apache.flink.client.RemoteExecutor.executePlanWithJars(RemoteExecutor.java:210)
> 	at org.apache.flink.client.RemoteExecutor.executePlan(RemoteExecutor.java:187)
> 	at org.apache.flink.api.java.RemoteEnvironment.execute(RemoteEnvironment.java:173)
> 	at org.apache.flink.api.java.ExecutionEnvironment.execute(ExecutionEnvironment.java:817)
> 	at org.apache.flink.api.java.DataSet.collect(DataSet.java:413)
> 	at org.apache.flink.test.recovery.TaskManagerProcessFailureBatchRecoveryITCase.testTaskManagerFailure(TaskManagerProcessFailureBatchRecoveryITCase.java:115)
> 	at org.apache.flink.test.recovery.AbstractTaskManagerProcessFailureRecoveryTest$1.run(AbstractTaskManagerProcessFailureRecoveryTest.java:143)
> Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
> 	at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:146)
> 	at org.apache.flink.client.program.rest.RestClusterClient.submitJob(RestClusterClient.java:265)
> 	... 10 more
> Caused by: org.apache.flink.util.FlinkException: The assigned slot 786ec47f893240315bb01291aab680ec_1 was removed.
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.removeSlot(SlotManager.java:893)
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.removeSlots(SlotManager.java:863)
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.internalUnregisterTaskManager(SlotManager.java:1058)
> 	at org.apache.flink.runtime.resourcemanager.slotmanager.SlotManager.unregisterTaskManager(SlotManager.java:385)
> 	at org.apache.flink.runtime.resourcemanager.ResourceManager.closeTaskManagerConnection(ResourceManager.java:847)
> 	at org.apache.flink.runtime.resourcemanager.ResourceManager$TaskManagerHeartbeatListener$1.run(ResourceManager.java:1161)
> 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:392)
> 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:185)
> 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
> 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.onReceive(AkkaRpcActor.java:147)
> 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.onReceive(FencedAkkaRpcActor.java:40)
> 	at akka.actor.UntypedActor$$anonfun$receive$1.applyOrElse(UntypedActor.scala:165)
> 	at akka.actor.Actor$class.aroundReceive(Actor.scala:502)
> 	at akka.actor.UntypedActor.aroundReceive(UntypedActor.scala:95)
> 	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:526)
> 	at akka.actor.ActorCell.invoke(ActorCell.scala:495)
> 	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:257)
> 	at akka.dispatch.Mailbox.run(Mailbox.scala:224)
> 	at akka.dispatch.Mailbox.exec(Mailbox.scala:234)
> 	at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> 	at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
> 	at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> 	at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> java.lang.AssertionError: The program encountered a ProgramInvocationException : Job failed. (JobID: 4f32093d9c7554c3de832d20f0a06eb5)
> 	at org.junit.Assert.fail(Assert.java:88)
> 	at org.apache.flink.test.recovery.AbstractTaskManagerProcessFailureRecoveryTest.testTaskManagerProcessFailure(AbstractTaskManagerProcessFailureRecoveryTest.java:190)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> 	at java.lang.reflect.Method.invoke(Method.java:498)
> 	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
> 	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
> 	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
> 	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
> 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
> 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
> 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
> 	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
> 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
> 	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
> 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
> 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
> 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
> 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
> 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
> 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
> 	at org.junit.runners.Suite.runChild(Suite.java:128)
> 	at org.junit.runners.Suite.runChild(Suite.java:27)
> 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
> 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
> 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
> 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
> 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
> 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
> 	at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:384)
> 	at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:345)
> 	at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:126)
> 	at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:418)
> {code}



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)