Uploaded image for project: 'Flink'
  1. Flink
  2. FLINK-19237

LeaderChangeClusterComponentsTest.testReelectionOfJobMaster failed with "NoResourceAvailableException: Could not allocate the required slot within slot request timeout"

    XMLWordPrintableJSON

    Details

      Description

      https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=6499&view=logs&j=6bfdaf55-0c08-5e3f-a2d2-2a0285fd41cf&t=fd9796c3-9ce8-5619-781c-42f873e126a6

      2020-09-14T21:11:02.8200203Z [ERROR] testReelectionOfJobMaster(org.apache.flink.runtime.leaderelection.LeaderChangeClusterComponentsTest)  Time elapsed: 300.14 s  <<< FAILURE!
      2020-09-14T21:11:02.8201761Z java.lang.AssertionError: Job failed.
      2020-09-14T21:11:02.8202749Z 	at org.apache.flink.runtime.jobmaster.utils.JobResultUtils.throwAssertionErrorOnFailedResult(JobResultUtils.java:54)
      2020-09-14T21:11:02.8203794Z 	at org.apache.flink.runtime.jobmaster.utils.JobResultUtils.assertSuccess(JobResultUtils.java:30)
      2020-09-14T21:11:02.8205177Z 	at org.apache.flink.runtime.leaderelection.LeaderChangeClusterComponentsTest.testReelectionOfJobMaster(LeaderChangeClusterComponentsTest.java:152)
      2020-09-14T21:11:02.8206191Z 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
      2020-09-14T21:11:02.8206985Z 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
      2020-09-14T21:11:02.8207930Z 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
      2020-09-14T21:11:02.8208927Z 	at java.lang.reflect.Method.invoke(Method.java:498)
      2020-09-14T21:11:02.8209753Z 	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
      2020-09-14T21:11:02.8210710Z 	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
      2020-09-14T21:11:02.8211608Z 	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
      2020-09-14T21:11:02.8214473Z 	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
      2020-09-14T21:11:02.8215398Z 	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
      2020-09-14T21:11:02.8216199Z 	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
      2020-09-14T21:11:02.8216947Z 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
      2020-09-14T21:11:02.8217695Z 	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
      2020-09-14T21:11:02.8218635Z 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
      2020-09-14T21:11:02.8219499Z 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
      2020-09-14T21:11:02.8220313Z 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
      2020-09-14T21:11:02.8221060Z 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
      2020-09-14T21:11:02.8222171Z 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
      2020-09-14T21:11:02.8222937Z 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
      2020-09-14T21:11:02.8223688Z 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
      2020-09-14T21:11:02.8225191Z 	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
      2020-09-14T21:11:02.8226086Z 	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27)
      2020-09-14T21:11:02.8226761Z 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
      2020-09-14T21:11:02.8227453Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
      2020-09-14T21:11:02.8228392Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
      2020-09-14T21:11:02.8229256Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
      2020-09-14T21:11:02.8235798Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
      2020-09-14T21:11:02.8237650Z 	at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:384)
      2020-09-14T21:11:02.8239039Z 	at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:345)
      2020-09-14T21:11:02.8239894Z 	at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:126)
      2020-09-14T21:11:02.8240591Z 	at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:418)
      2020-09-14T21:11:02.8241325Z Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by NoRestartBackoffTimeStrategy
      2020-09-14T21:11:02.8242225Z 	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:116)
      2020-09-14T21:11:02.8243358Z 	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:78)
      2020-09-14T21:11:02.8244425Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:215)
      2020-09-14T21:11:02.8245291Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:208)
      2020-09-14T21:11:02.8246150Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:202)
      2020-09-14T21:11:02.8247006Z 	at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:523)
      2020-09-14T21:11:02.8247960Z 	at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyTaskFailure(UpdateSchedulerNgOnInternalFailuresListener.java:49)
      2020-09-14T21:11:02.8249102Z 	at org.apache.flink.runtime.executiongraph.ExecutionGraph.notifySchedulerNgAboutInternalTaskFailure(ExecutionGraph.java:1722)
      2020-09-14T21:11:02.8249971Z 	at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1283)
      2020-09-14T21:11:02.8250675Z 	at org.apache.flink.runtime.executiongraph.Execution.processFail(Execution.java:1251)
      2020-09-14T21:11:02.8251369Z 	at org.apache.flink.runtime.executiongraph.Execution.markFailed(Execution.java:1082)
      2020-09-14T21:11:02.8252104Z 	at org.apache.flink.runtime.executiongraph.ExecutionVertex.markFailed(ExecutionVertex.java:748)
      2020-09-14T21:11:02.8253060Z 	at org.apache.flink.runtime.scheduler.DefaultExecutionVertexOperations.markFailed(DefaultExecutionVertexOperations.java:41)
      2020-09-14T21:11:02.8253956Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskDeploymentFailure(DefaultScheduler.java:458)
      2020-09-14T21:11:02.8254967Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.lambda$assignResourceOrHandleError$6(DefaultScheduler.java:445)
      2020-09-14T21:11:02.8393562Z 	at java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:836)
      2020-09-14T21:11:02.8394920Z 	at java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:811)
      2020-09-14T21:11:02.8396122Z 	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
      2020-09-14T21:11:02.8397194Z 	at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990)
      2020-09-14T21:11:02.8398150Z 	at org.apache.flink.runtime.jobmaster.slotpool.SchedulerImpl.lambda$internalAllocateSlot$0(SchedulerImpl.java:169)
      2020-09-14T21:11:02.8399234Z 	at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
      2020-09-14T21:11:02.8400048Z 	at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
      2020-09-14T21:11:02.8401048Z 	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
      2020-09-14T21:11:02.8402025Z 	at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990)
      2020-09-14T21:11:02.8403171Z 	at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$SingleTaskSlot.release(SlotSharingManager.java:731)
      2020-09-14T21:11:02.8404708Z 	at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.release(SlotSharingManager.java:537)
      2020-09-14T21:11:02.8405751Z 	at org.apache.flink.runtime.jobmaster.slotpool.SlotSharingManager$MultiTaskSlot.lambda$new$0(SlotSharingManager.java:432)
      2020-09-14T21:11:02.8406633Z 	at java.util.concurrent.CompletableFuture.uniHandle(CompletableFuture.java:836)
      2020-09-14T21:11:02.8407378Z 	at java.util.concurrent.CompletableFuture$UniHandle.tryFire(CompletableFuture.java:811)
      2020-09-14T21:11:02.8408120Z 	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
      2020-09-14T21:11:02.8408948Z 	at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990)
      2020-09-14T21:11:02.8409748Z 	at org.apache.flink.runtime.concurrent.FutureUtils.lambda$forwardTo$21(FutureUtils.java:1168)
      2020-09-14T21:11:02.8410511Z 	at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
      2020-09-14T21:11:02.8411543Z 	at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
      2020-09-14T21:11:02.8412553Z 	at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
      2020-09-14T21:11:02.8413340Z 	at java.util.concurrent.CompletableFuture.completeExceptionally(CompletableFuture.java:1990)
      2020-09-14T21:11:02.8414204Z 	at org.apache.flink.runtime.concurrent.FutureUtils$Timeout.run(FutureUtils.java:1072)
      2020-09-14T21:11:02.8415364Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:402)
      2020-09-14T21:11:02.8416128Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:195)
      2020-09-14T21:11:02.8417172Z 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
      2020-09-14T21:11:02.8417995Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
      2020-09-14T21:11:02.8418997Z 	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
      2020-09-14T21:11:02.8419692Z 	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
      2020-09-14T21:11:02.8420336Z 	at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
      2020-09-14T21:11:02.8421055Z 	at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
      2020-09-14T21:11:02.8421655Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
      2020-09-14T21:11:02.8422336Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
      2020-09-14T21:11:02.8423049Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
      2020-09-14T21:11:02.8423681Z 	at akka.actor.Actor$class.aroundReceive(Actor.scala:517)
      2020-09-14T21:11:02.8424505Z 	at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
      2020-09-14T21:11:02.8425209Z 	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
      2020-09-14T21:11:02.8425760Z 	at akka.actor.ActorCell.invoke(ActorCell.scala:561)
      2020-09-14T21:11:02.8426376Z 	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
      2020-09-14T21:11:02.8427252Z 	at akka.dispatch.Mailbox.run(Mailbox.scala:225)
      2020-09-14T21:11:02.8427931Z 	at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
      2020-09-14T21:11:02.8428684Z 	at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
      2020-09-14T21:11:02.8429375Z 	at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
      2020-09-14T21:11:02.8430118Z 	at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
      2020-09-14T21:11:02.8430853Z 	at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
      2020-09-14T21:11:02.8431971Z Caused by: org.apache.flink.runtime.jobmanager.scheduler.NoResourceAvailableException: Could not allocate the required slot within slot request timeout. Please make sure that the cluster has enough resources.
      2020-09-14T21:11:02.8433179Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeWrapWithNoResourceAvailableException(DefaultScheduler.java:464)
      2020-09-14T21:11:02.8434082Z 	... 45 more
      2020-09-14T21:11:02.8434809Z Caused by: java.util.concurrent.CompletionException: java.util.concurrent.TimeoutException
      2020-09-14T21:11:02.8435611Z 	at java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:292)
      2020-09-14T21:11:02.8436379Z 	at java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:308)
      2020-09-14T21:11:02.8437159Z 	at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:607)
      2020-09-14T21:11:02.8437976Z 	at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
      2020-09-14T21:11:02.8438658Z 	... 25 more
      2020-09-14T21:11:02.8439085Z Caused by: java.util.concurrent.TimeoutException
      2020-09-14T21:11:02.8439476Z 	... 23 more
      

        Attachments

          Issue Links

            Activity

              People

              • Assignee:
                rmetzger Robert Metzger
                Reporter:
                dian.fu Dian Fu
              • Votes:
                0 Vote for this issue
                Watchers:
                6 Start watching this issue

                Dates

                • Created:
                  Updated:
                  Resolved: