[jira] [Created] (FLINK-21117) KafkaProducerExactlyOnceITCase fails with "Exceeded checkpoint tolerable failure threshold."

[Shang Yuanchun (Jira)]

Dawid Wysakowicz created FLINK-21117:
----------------------------------------

             Summary: KafkaProducerExactlyOnceITCase fails with "Exceeded checkpoint tolerable failure threshold."
                 Key: FLINK-21117
                 URL: https://issues.apache.org/jira/browse/FLINK-21117
             Project: Flink
          Issue Type: Bug
          Components: Connectors / Kafka, Runtime / Checkpointing, Tests
    Affects Versions: 1.12.2
            Reporter: Dawid Wysakowicz


https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=12398&view=logs&j=4be4ed2b-549a-533d-aa33-09e28e360cc8&t=0db94045-2aa0-53fa-f444-0130d6933518

{code}
2021-01-22T23:26:30.2357543Z org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
2021-01-22T23:26:30.2359069Z at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144)
2021-01-22T23:26:30.2360668Z at org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$2(MiniClusterJobClient.java:117)
2021-01-22T23:26:30.2361340Z at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616)
2021-01-22T23:26:30.2361840Z at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591)
2021-01-22T23:26:30.2362915Z at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
2021-01-22T23:26:30.2363367Z at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
2021-01-22T23:26:30.2364353Z at org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$0(AkkaInvocationHandler.java:238)
2021-01-22T23:26:30.2364961Z at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774)
2021-01-22T23:26:30.2365453Z at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750)
2021-01-22T23:26:30.2365945Z at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488)
2021-01-22T23:26:30.2366487Z at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975)
2021-01-22T23:26:30.2367049Z at org.apache.flink.runtime.concurrent.FutureUtils$1.onComplete(FutureUtils.java:1046)
2021-01-22T23:26:30.2367478Z at akka.dispatch.OnComplete.internal(Future.scala:264)
2021-01-22T23:26:30.2367854Z at akka.dispatch.OnComplete.internal(Future.scala:261)
2021-01-22T23:26:30.2368504Z at akka.dispatch.japi$CallbackBridge.apply(Future.scala:191)
2021-01-22T23:26:30.2368897Z at akka.dispatch.japi$CallbackBridge.apply(Future.scala:188)
2021-01-22T23:26:30.2369329Z at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:60)
2021-01-22T23:26:30.2369870Z at org.apache.flink.runtime.concurrent.Executors$DirectExecutionContext.execute(Executors.java:73)
2021-01-22T23:26:30.2370616Z at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:68)
2021-01-22T23:26:30.2371383Z at scala.concurrent.impl.Promise$DefaultPromise.$anonfun$tryComplete$1(Promise.scala:284)
2021-01-22T23:26:30.2372228Z at scala.concurrent.impl.Promise$DefaultPromise.$anonfun$tryComplete$1$adapted(Promise.scala:284)
2021-01-22T23:26:30.2373105Z at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:284)
2021-01-22T23:26:30.2373665Z at akka.pattern.PromiseActorRef.$bang(AskSupport.scala:573)
2021-01-22T23:26:30.2374466Z at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:22)
2021-01-22T23:26:30.2375351Z at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:21)
2021-01-22T23:26:30.2376150Z at scala.concurrent.Future.$anonfun$andThen$1(Future.scala:532)
2021-01-22T23:26:30.2376815Z at scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:29)
2021-01-22T23:26:30.2377509Z at scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:29)
2021-01-22T23:26:30.2378343Z at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:60)
2021-01-22T23:26:30.2386385Z at akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:55)
2021-01-22T23:26:30.2387350Z at akka.dispatch.BatchingExecutor$BlockableBatch.$anonfun$run$1(BatchingExecutor.scala:91)
2021-01-22T23:26:30.2388300Z at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:12)
2021-01-22T23:26:30.2389046Z at scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:81)
2021-01-22T23:26:30.2389951Z at akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:91)
2021-01-22T23:26:30.2390743Z at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:40)
2021-01-22T23:26:30.2391867Z at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:44)
2021-01-22T23:26:30.2392817Z at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
2021-01-22T23:26:30.2393474Z at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
2021-01-22T23:26:30.2394399Z at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
2021-01-22T23:26:30.2395072Z at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
2021-01-22T23:26:30.2395893Z Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=1, backoffTimeMS=0)
2021-01-22T23:26:30.2396782Z at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:118)
2021-01-22T23:26:30.2397456Z at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getGlobalFailureHandlingResult(ExecutionFailureHandler.java:93)
2021-01-22T23:26:30.2398248Z at org.apache.flink.runtime.scheduler.DefaultScheduler.handleGlobalFailure(DefaultScheduler.java:252)
2021-01-22T23:26:30.2398909Z at org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyGlobalFailure(UpdateSchedulerNgOnInternalFailuresListener.java:62)
2021-01-22T23:26:30.2399563Z at org.apache.flink.runtime.executiongraph.ExecutionGraph.failGlobal(ExecutionGraph.java:1116)
2021-01-22T23:26:30.2400478Z at org.apache.flink.runtime.executiongraph.ExecutionGraph$1.lambda$failJob$0(ExecutionGraph.java:492)
2021-01-22T23:26:30.2401281Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRunAsync(AkkaRpcActor.java:442)
2021-01-22T23:26:30.2402081Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:209)
2021-01-22T23:26:30.2402962Z at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:77)
2021-01-22T23:26:30.2403825Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:159)
2021-01-22T23:26:30.2404611Z at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
2021-01-22T23:26:30.2405283Z at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
2021-01-22T23:26:30.2405777Z at scala.PartialFunction.applyOrElse(PartialFunction.scala:123)
2021-01-22T23:26:30.2406165Z at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122)
2021-01-22T23:26:30.2406578Z at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
2021-01-22T23:26:30.2407001Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
2021-01-22T23:26:30.2407403Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
2021-01-22T23:26:30.2407823Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172)
2021-01-22T23:26:30.2408349Z at akka.actor.Actor.aroundReceive(Actor.scala:517)
2021-01-22T23:26:30.2408696Z at akka.actor.Actor.aroundReceive$(Actor.scala:515)
2021-01-22T23:26:30.2409087Z at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
2021-01-22T23:26:30.2409564Z at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
2021-01-22T23:26:30.2409999Z at akka.actor.ActorCell.invoke(ActorCell.scala:561)
2021-01-22T23:26:30.2410365Z at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
2021-01-22T23:26:30.2410727Z at akka.dispatch.Mailbox.run(Mailbox.scala:225)
2021-01-22T23:26:30.2411050Z at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
2021-01-22T23:26:30.2411309Z ... 4 more
2021-01-22T23:26:30.2411661Z Caused by: org.apache.flink.util.FlinkRuntimeException: Exceeded checkpoint tolerable failure threshold.
2021-01-22T23:26:30.2412222Z at org.apache.flink.runtime.checkpoint.CheckpointFailureManager.handleCheckpointException(CheckpointFailureManager.java:96)
2021-01-22T23:26:30.2412860Z at org.apache.flink.runtime.checkpoint.CheckpointFailureManager.handleJobLevelCheckpointException(CheckpointFailureManager.java:65)
2021-01-22T23:26:30.2413617Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator.abortPendingCheckpoint(CheckpointCoordinator.java:1931)
2021-01-22T23:26:30.2414261Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator.abortPendingCheckpoint(CheckpointCoordinator.java:1904)
2021-01-22T23:26:30.2414839Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator.access$600(CheckpointCoordinator.java:93)
2021-01-22T23:26:30.2415494Z at org.apache.flink.runtime.checkpoint.CheckpointCoordinator$CheckpointCanceller.run(CheckpointCoordinator.java:2045)
2021-01-22T23:26:30.2416004Z at java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:511)
2021-01-22T23:26:30.2416422Z at java.util.concurrent.FutureTask.run(FutureTask.java:266)
2021-01-22T23:26:30.2416932Z at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.access$201(ScheduledThreadPoolExecutor.java:180)
2021-01-22T23:26:30.2417516Z at java.util.concurrent.ScheduledThreadPoolExecutor$ScheduledFutureTask.run(ScheduledThreadPoolExecutor.java:293)
2021-01-22T23:26:30.2418143Z at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1149)
2021-01-22T23:26:30.2418664Z at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:624)
2021-01-22T23:26:30.2419036Z at java.lang.Thread.run(Thread.java:748)
{code}



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