Dian Fu created FLINK-20331:
-------------------------------

             Summary: UnalignedCheckpointITCase.execute failed with "Sequence 
number for checkpoint 20 is not known (it was likely been overwritten by a 
newer checkpoint 21)"
                 Key: FLINK-20331
                 URL: https://issues.apache.org/jira/browse/FLINK-20331
             Project: Flink
          Issue Type: Bug
          Components: Runtime / Checkpointing
    Affects Versions: 1.12.0
            Reporter: Dian Fu
             Fix For: 1.12.0


https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=10059&view=logs&j=119bbba7-f5e3-5e08-e72d-09f1529665de&t=7dc1f5a9-54e1-502e-8b02-c7df69073cfc

{code}
2020-11-24T22:42:17.6704402Z [ERROR] execute[parallel pipeline with mixed 
channels, p = 
20](org.apache.flink.test.checkpointing.UnalignedCheckpointITCase)  Time 
elapsed: 7.901 s  <<< ERROR!
2020-11-24T22:42:17.6706095Z 
org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
2020-11-24T22:42:17.6707450Z    at 
org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:147)
2020-11-24T22:42:17.6708569Z    at 
org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$2(MiniClusterJobClient.java:119)
2020-11-24T22:42:17.6709626Z    at 
java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
2020-11-24T22:42:17.6710452Z    at 
java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
2020-11-24T22:42:17.6711271Z    at 
java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
2020-11-24T22:42:17.6713170Z    at 
java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
2020-11-24T22:42:17.6713974Z    at 
org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:229)
2020-11-24T22:42:17.6714517Z    at 
java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
2020-11-24T22:42:17.6715372Z    at 
java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
2020-11-24T22:42:17.6715871Z    at 
java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
2020-11-24T22:42:17.6716514Z    at 
java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
2020-11-24T22:42:17.6718475Z    at 
org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:996)
2020-11-24T22:42:17.6719322Z    at 
akka.dispatch.OnComplete.internal(Future.scala:264)
2020-11-24T22:42:17.6719887Z    at 
akka.dispatch.OnComplete.internal(Future.scala:261)
2020-11-24T22:42:17.6720271Z    at 
akka.dispatch.japi$CallbackBridge.apply(Future.scala:191)
2020-11-24T22:42:17.6720645Z    at 
akka.dispatch.japi$CallbackBridge.apply(Future.scala:188)
2020-11-24T22:42:17.6721114Z    at 
scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
2020-11-24T22:42:17.6721585Z    at 
org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:74)
2020-11-24T22:42:17.6722078Z    at 
scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:44)
2020-11-24T22:42:17.6722738Z    at 
scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:252)
2020-11-24T22:42:17.6723183Z    at 
akka.pattern.PromiseActorRef.$bang(AskSupport.scala:572)
2020-11-24T22:42:17.6723862Z    at 
akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:22)
2020-11-24T22:42:17.6724435Z    at 
akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21)
2020-11-24T22:42:17.6724914Z    at 
scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:436)
2020-11-24T22:42:17.6725323Z    at 
scala.concurrent.Future$$anonfun$andThen$1.apply(Future.scala:435)
2020-11-24T22:42:17.6725866Z    at 
scala.concurrent.impl.CallbackRunnable.run(Promise.scala:36)
2020-11-24T22:42:17.6726313Z    at 
akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55)
2020-11-24T22:42:17.6726829Z    at 
akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply$mcV$sp(BatchingExecutor.scala:91)
2020-11-24T22:42:17.6727376Z    at 
akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
2020-11-24T22:42:17.6727891Z    at 
akka.dispatch.BatchingExecutor$BlockableBatch$$anonfun$run$1.apply(BatchingExecutor.scala:91)
2020-11-24T22:42:17.6728400Z    at 
scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:72)
2020-11-24T22:42:17.6728855Z    at 
akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:90)
2020-11-24T22:42:17.6729390Z    at 
akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
2020-11-24T22:42:17.6729853Z    at 
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
2020-11-24T22:42:17.6730345Z    at 
akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
2020-11-24T22:42:17.6730781Z    at 
akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
2020-11-24T22:42:17.6731212Z    at 
akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
2020-11-24T22:42:17.6731657Z    at 
akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
2020-11-24T22:42:17.6732230Z Caused by: org.apache.flink.runtime.JobException: 
Recovery is suppressed by 
FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=5, 
backoffTimeMS=100)
2020-11-24T22:42:17.6733094Z    at 
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:116)
2020-11-24T22:42:17.6733759Z    at 
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:78)
2020-11-24T22:42:17.6734418Z    at 
org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:224)
2020-11-24T22:42:17.6734964Z    at 
org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:217)
2020-11-24T22:42:17.6735683Z    at 
org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:208)
2020-11-24T22:42:17.6736231Z    at 
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:533)
2020-11-24T22:42:17.6736756Z    at 
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
2020-11-24T22:42:17.6737270Z    at 
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:419)
2020-11-24T22:42:17.6737684Z    at 
sun.reflect.GeneratedMethodAccessor16.invoke(Unknown Source)
2020-11-24T22:42:17.6738114Z    at 
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
2020-11-24T22:42:17.6738542Z    at 
java.lang.reflect.Method.invoke(Method.java:498)
2020-11-24T22:42:17.6738960Z    at 
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:286)
2020-11-24T22:42:17.6739537Z    at 
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:201)
2020-11-24T22:42:17.6740059Z    at 
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
2020-11-24T22:42:17.6740560Z    at 
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:154)
2020-11-24T22:42:17.6741004Z    at 
akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
2020-11-24T22:42:17.6741489Z    at 
akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
2020-11-24T22:42:17.6741882Z    at 
scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
2020-11-24T22:42:17.6742302Z    at 
akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
2020-11-24T22:42:17.6743029Z    at 
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
2020-11-24T22:42:17.6743601Z    at 
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
2020-11-24T22:42:17.6744206Z    at 
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
2020-11-24T22:42:17.6744642Z    at 
akka.actor.Actor$class.aroundReceive(Actor.scala:517)
2020-11-24T22:42:17.6745047Z    at 
akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
2020-11-24T22:42:17.6745450Z    at 
akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
2020-11-24T22:42:17.6745807Z    at 
akka.actor.ActorCell.invoke(ActorCell.scala:561)
2020-11-24T22:42:17.6746184Z    at 
akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
2020-11-24T22:42:17.6746540Z    at akka.dispatch.Mailbox.run(Mailbox.scala:225)
2020-11-24T22:42:17.6746880Z    at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
2020-11-24T22:42:17.6747244Z    ... 4 more
2020-11-24T22:42:17.6747712Z Caused by: java.lang.IllegalStateException: 
Sequence number for checkpoint 20 is not known (it was likely been overwritten 
by a newer checkpoint 21)
2020-11-24T22:42:17.6748244Z    at 
org.apache.flink.util.Preconditions.checkState(Preconditions.java:220)
2020-11-24T22:42:17.6749007Z    at 
org.apache.flink.runtime.io.network.partition.consumer.RemoteInputChannel.getInflightBuffersUnsafe(RemoteInputChannel.java:542)
2020-11-24T22:42:17.6750046Z    at 
org.apache.flink.runtime.io.network.partition.consumer.RemoteInputChannel.checkpointStarted(RemoteInputChannel.java:514)
2020-11-24T22:42:17.6750982Z    at 
org.apache.flink.runtime.io.network.partition.consumer.IndexedInputGate.checkpointStarted(IndexedInputGate.java:35)
2020-11-24T22:42:17.6751825Z    at 
org.apache.flink.streaming.runtime.io.UnalignedController.preProcessFirstBarrier(UnalignedController.java:54)
2020-11-24T22:42:17.6752730Z    at 
org.apache.flink.streaming.runtime.io.AlternatingController.preProcessFirstBarrier(AlternatingController.java:57)
2020-11-24T22:42:17.6753372Z    at 
org.apache.flink.streaming.runtime.io.SingleCheckpointBarrierHandler.processBarrier(SingleCheckpointBarrierHandler.java:121)
2020-11-24T22:42:17.6754237Z    at 
org.apache.flink.streaming.runtime.io.CheckpointedInputGate.handleEvent(CheckpointedInputGate.java:174)
2020-11-24T22:42:17.6754995Z    at 
org.apache.flink.streaming.runtime.io.CheckpointedInputGate.pollNext(CheckpointedInputGate.java:151)
2020-11-24T22:42:17.6755929Z    at 
org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:157)
2020-11-24T22:42:17.6756494Z    at 
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:67)
2020-11-24T22:42:17.6757294Z    at 
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:372)
2020-11-24T22:42:17.6757944Z    at 
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:186)
2020-11-24T22:42:17.6758714Z    at 
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:575)
2020-11-24T22:42:17.6759583Z    at 
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:539)
2020-11-24T22:42:17.6760205Z    at 
org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:722)
2020-11-24T22:42:17.6760774Z    at 
org.apache.flink.runtime.taskmanager.Task.run(Task.java:547)
2020-11-24T22:42:17.6761323Z    at java.lang.Thread.run(Thread.java:748)
{code}



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

Reply via email to