Dawid Wysakowicz created FLINK-22173: ----------------------------------------
Summary: UnalignedCheckpointRescaleITCase fails on azure Key: FLINK-22173 URL: https://issues.apache.org/jira/browse/FLINK-22173 Project: Flink Issue Type: Bug Components: Runtime / Checkpointing Affects Versions: 1.13.0 Reporter: Dawid Wysakowicz https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=16232&view=logs&j=d8d26c26-7ec2-5ed2-772e-7a1a1eb8317c&t=be5fb08e-1ad7-563c-4f1a-a97ad4ce4865&l=9628 {code} 2021-04-08T23:25:56.3131361Z [ERROR] Tests run: 31, Failures: 0, Errors: 1, Skipped: 0, Time elapsed: 839.623 s <<< FAILURE! - in org.apache.flink.test.checkpointing.UnalignedCheckpointRescaleITCase 2021-04-08T23:25:56.3132784Z [ERROR] shouldRescaleUnalignedCheckpoint[no scale union from 7 to 7](org.apache.flink.test.checkpointing.UnalignedCheckpointRescaleITCase) Time elapsed: 607.467 s <<< ERROR! 2021-04-08T23:25:56.3133586Z org.apache.flink.runtime.client.JobExecutionException: Job execution failed. 2021-04-08T23:25:56.3134070Z at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144) 2021-04-08T23:25:56.3134643Z at org.apache.flink.test.checkpointing.UnalignedCheckpointTestBase.execute(UnalignedCheckpointTestBase.java:168) 2021-04-08T23:25:56.3135577Z at org.apache.flink.test.checkpointing.UnalignedCheckpointRescaleITCase.shouldRescaleUnalignedCheckpoint(UnalignedCheckpointRescaleITCase.java:368) 2021-04-08T23:25:56.3138843Z at sun.reflect.GeneratedMethodAccessor93.invoke(Unknown Source) 2021-04-08T23:25:56.3139402Z at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) 2021-04-08T23:25:56.3139880Z at java.lang.reflect.Method.invoke(Method.java:498) 2021-04-08T23:25:56.3140328Z at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50) 2021-04-08T23:25:56.3140844Z at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12) 2021-04-08T23:25:56.3141768Z at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47) 2021-04-08T23:25:56.3142272Z at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17) 2021-04-08T23:25:56.3142706Z at org.junit.rules.Verifier$1.evaluate(Verifier.java:35) 2021-04-08T23:25:56.3143142Z at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48) 2021-04-08T23:25:56.3143608Z at org.apache.flink.util.TestNameProvider$1.evaluate(TestNameProvider.java:45) 2021-04-08T23:25:56.3144039Z at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55) 2021-04-08T23:25:56.3144434Z at org.junit.rules.RunRules.evaluate(RunRules.java:20) 2021-04-08T23:25:56.3145027Z at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325) 2021-04-08T23:25:56.3145484Z at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78) 2021-04-08T23:25:56.3145981Z at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57) 2021-04-08T23:25:56.3146421Z at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290) 2021-04-08T23:25:56.3146843Z at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71) 2021-04-08T23:25:56.3147274Z at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288) 2021-04-08T23:25:56.3147692Z at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58) 2021-04-08T23:25:56.3148116Z at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268) 2021-04-08T23:25:56.3148543Z at org.junit.runners.ParentRunner.run(ParentRunner.java:363) 2021-04-08T23:25:56.3148930Z at org.junit.runners.Suite.runChild(Suite.java:128) 2021-04-08T23:25:56.3149298Z at org.junit.runners.Suite.runChild(Suite.java:27) 2021-04-08T23:25:56.3149663Z at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290) 2021-04-08T23:25:56.3150075Z at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71) 2021-04-08T23:25:56.3150488Z at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288) 2021-04-08T23:25:56.3151148Z at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58) 2021-04-08T23:25:56.3151691Z at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268) 2021-04-08T23:25:56.3152115Z at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48) 2021-04-08T23:25:56.3152534Z at org.junit.rules.RunRules.evaluate(RunRules.java:20) 2021-04-08T23:25:56.3152919Z at org.junit.runners.ParentRunner.run(ParentRunner.java:363) 2021-04-08T23:25:56.3153349Z at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365) 2021-04-08T23:25:56.3154029Z at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273) 2021-04-08T23:25:56.3154670Z at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238) 2021-04-08T23:25:56.3155183Z at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159) 2021-04-08T23:25:56.3155715Z at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:384) 2021-04-08T23:25:56.3156250Z at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:345) 2021-04-08T23:25:56.3156749Z at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:126) 2021-04-08T23:25:56.3157343Z at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:418) 2021-04-08T23:25:56.3157928Z Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=1, backoffTimeMS=100) 2021-04-08T23:25:56.3158627Z at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138) 2021-04-08T23:25:56.3159356Z at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getGlobalFailureHandlingResult(ExecutionFailureHandler.java:101) 2021-04-08T23:25:56.3160053Z at org.apache.flink.runtime.scheduler.DefaultScheduler.handleGlobalFailure(DefaultScheduler.java:227) 2021-04-08T23:25:56.3160721Z at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyGlobalFailure(UpdateSchedulerNgOnInternalFailuresListener.java:57) 2021-04-08T23:25:56.3161721Z at org.apache.flink.runtime.executiongraph.DefaultExecutionGraph.failGlobal(DefaultExecutionGraph.java:973) 2021-04-08T23:25:56.3162331Z at org.apache.flink.runtime.executiongraph.DefaultExecutionGraph$1.lambda$failJob$0(DefaultExecutionGraph.java:412) 2021-04-08T23:25:56.3162910Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:440) 2021-04-08T23:25:56.3163435Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:208) 2021-04-08T23:25:56.3164057Z at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77) 2021-04-08T23:25:56.3164599Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:158) 2021-04-08T23:25:56.3165052Z at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26) 2021-04-08T23:25:56.3165471Z at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21) 2021-04-08T23:25:56.3165895Z at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123) 2021-04-08T23:25:56.3166322Z at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21) 2021-04-08T23:25:56.3166767Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170) 2021-04-08T23:25:56.3167194Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) 2021-04-08T23:25:56.3167636Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) 2021-04-08T23:25:56.3168056Z at akka.actor.Actor$class.aroundReceive(Actor.scala:517) 2021-04-08T23:25:56.3168447Z at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) 2021-04-08T23:25:56.3168867Z at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592) 2021-04-08T23:25:56.3169254Z at akka.actor.ActorCell.invoke(ActorCell.scala:561) 2021-04-08T23:25:56.3169616Z at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) 2021-04-08T23:25:56.3169991Z at akka.dispatch.Mailbox.run(Mailbox.scala:225) 2021-04-08T23:25:56.3170328Z at akka.dispatch.Mailbox.exec(Mailbox.scala:235) 2021-04-08T23:25:56.3170716Z at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260) 2021-04-08T23:25:56.3171420Z at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339) 2021-04-08T23:25:56.3171886Z at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979) 2021-04-08T23:25:56.3172349Z at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107) 2021-04-08T23:25:56.3172851Z Caused by: org.apache.flink.util.FlinkRuntimeException: Exceeded checkpoint tolerable failure threshold. 2021-04-08T23:25:56.3173453Z at org.apache.flink.runtime.checkpoint.CheckpointFailureManager.handleCheckpointException(CheckpointFailureManager.java:98) 2021-04-08T23:25:56.3174129Z at org.apache.flink.runtime.checkpoint.CheckpointFailureManager.handleJobLevelCheckpointException(CheckpointFailureManager.java:67) 2021-04-08T23:25:56.3174771Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator.abortPendingCheckpoint(CheckpointCoordinator.java:1935) 2021-04-08T23:25:56.3175481Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator.abortPendingCheckpoint(CheckpointCoordinator.java:1907) 2021-04-08T23:25:56.3176078Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator.access$600(CheckpointCoordinator.java:95) 2021-04-08T23:25:56.3176658Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator$CheckpointCanceller.run(CheckpointCoordinator.java:1991) 2021-04-08T23:25:56.3177209Z at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511) 2021-04-08T23:25:56.3177627Z at java.util.concurrent.FutureTask.run(FutureTask.java:266) 2021-04-08T23:25:56.3178141Z at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$201(ScheduledThreadPoolExecutor.java:180) 2021-04-08T23:25:56.3178766Z at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:293) 2021-04-08T23:25:56.3179308Z at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149) 2021-04-08T23:25:56.3179799Z at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624) 2021-04-08T23:25:56.3180204Z at java.lang.Thread.run(Thread.java:748) {code} -- This message was sent by Atlassian Jira (v8.3.4#803005)