Huang Xingbo created FLINK-28440: ------------------------------------ Summary: EventTimeWindowCheckpointingITCase.testSlidingTimeWindow failed with restore Key: FLINK-28440 URL: https://issues.apache.org/jira/browse/FLINK-28440 Project: Flink Issue Type: Bug Components: Runtime / State Backends Affects Versions: 1.16.0 Reporter: Huang Xingbo
{code:java} 2022-07-07T03:27:47.5779102Z org.apache.flink.runtime.client.JobExecutionException: Job execution failed. 2022-07-07T03:27:47.5779722Z at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:144) 2022-07-07T03:27:47.5780444Z at org.apache.flink.runtime.minicluster.MiniClusterJobClient.lambda$getJobExecutionResult$3(MiniClusterJobClient.java:141) 2022-07-07T03:27:47.5781338Z at java.util.concurrent.CompletableFuture.uniApply(CompletableFuture.java:616) 2022-07-07T03:27:47.5781955Z at java.util.concurrent.CompletableFuture$UniApply.tryFire(CompletableFuture.java:591) 2022-07-07T03:27:47.5782587Z at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) 2022-07-07T03:27:47.5783184Z at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) 2022-07-07T03:27:47.5783843Z at org.apache.flink.runtime.rpc.akka.AkkaInvocationHandler.lambda$invokeRpc$1(AkkaInvocationHandler.java:268) 2022-07-07T03:27:47.5784599Z at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) 2022-07-07T03:27:47.5785284Z at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750) 2022-07-07T03:27:47.5785907Z at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) 2022-07-07T03:27:47.5786528Z at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) 2022-07-07T03:27:47.5787121Z at org.apache.flink.util.concurrent.FutureUtils.doForward(FutureUtils.java:1277) 2022-07-07T03:27:47.5787874Z at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.lambda$null$1(ClassLoadingUtils.java:93) 2022-07-07T03:27:47.5788498Z at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:68) 2022-07-07T03:27:47.5789265Z at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.lambda$guardCompletionWithContextClassLoader$2(ClassLoadingUtils.java:92) 2022-07-07T03:27:47.5789968Z at java.util.concurrent.CompletableFuture.uniWhenComplete(CompletableFuture.java:774) 2022-07-07T03:27:47.5790582Z at java.util.concurrent.CompletableFuture$UniWhenComplete.tryFire(CompletableFuture.java:750) 2022-07-07T03:27:47.5791198Z at java.util.concurrent.CompletableFuture.postComplete(CompletableFuture.java:488) 2022-07-07T03:27:47.5791799Z at java.util.concurrent.CompletableFuture.complete(CompletableFuture.java:1975) 2022-07-07T03:27:47.5792351Z at org.apache.flink.runtime.concurrent.akka.AkkaFutureUtils$1.onComplete(AkkaFutureUtils.java:47) 2022-07-07T03:27:47.5793075Z at akka.dispatch.OnComplete.internal(Future.scala:300) 2022-07-07T03:27:47.5793572Z at akka.dispatch.OnComplete.internal(Future.scala:297) 2022-07-07T03:27:47.5794075Z at akka.dispatch.japi$CallbackBridge.apply(Future.scala:224) 2022-07-07T03:27:47.5794586Z at akka.dispatch.japi$CallbackBridge.apply(Future.scala:221) 2022-07-07T03:27:47.5795094Z at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:60) 2022-07-07T03:27:47.5795654Z at org.apache.flink.runtime.concurrent.akka.AkkaFutureUtils$DirectExecutionContext.execute(AkkaFutureUtils.java:65) 2022-07-07T03:27:47.5796307Z at scala.concurrent.impl.CallbackRunnable.executeWithValue(Promise.scala:68) 2022-07-07T03:27:47.5796922Z at scala.concurrent.impl.Promise$DefaultPromise.$anonfun$tryComplete$1(Promise.scala:284) 2022-07-07T03:27:47.5797574Z at scala.concurrent.impl.Promise$DefaultPromise.$anonfun$tryComplete$1$adapted(Promise.scala:284) 2022-07-07T03:27:47.5798196Z at scala.concurrent.impl.Promise$DefaultPromise.tryComplete(Promise.scala:284) 2022-07-07T03:27:47.5798739Z at akka.pattern.PromiseActorRef.$bang(AskSupport.scala:621) 2022-07-07T03:27:47.5799255Z at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:24) 2022-07-07T03:27:47.5799921Z at akka.pattern.PipeToSupport$PipeableFuture$$anonfun$pipeTo$1.applyOrElse(PipeToSupport.scala:23) 2022-07-07T03:27:47.5800515Z at scala.concurrent.Future.$anonfun$andThen$1(Future.scala:532) 2022-07-07T03:27:47.5801036Z at scala.concurrent.impl.Promise.liftedTree1$1(Promise.scala:29) 2022-07-07T03:27:47.5801575Z at scala.concurrent.impl.Promise.$anonfun$transform$1(Promise.scala:29) 2022-07-07T03:27:47.5802124Z at scala.concurrent.impl.CallbackRunnable.run(Promise.scala:60) 2022-07-07T03:27:47.5802696Z at akka.dispatch.BatchingExecutor$AbstractBatch.processBatch(BatchingExecutor.scala:63) 2022-07-07T03:27:47.5803417Z at akka.dispatch.BatchingExecutor$BlockableBatch.$anonfun$run$1(BatchingExecutor.scala:100) 2022-07-07T03:27:47.5804022Z at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:12) 2022-07-07T03:27:47.5804596Z at scala.concurrent.BlockContext$.withBlockContext(BlockContext.scala:81) 2022-07-07T03:27:47.5805174Z at akka.dispatch.BatchingExecutor$BlockableBatch.run(BatchingExecutor.scala:100) 2022-07-07T03:27:47.5805736Z at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:49) 2022-07-07T03:27:47.5806274Z at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(ForkJoinExecutorConfigurator.scala:48) 2022-07-07T03:27:47.5806893Z at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) 2022-07-07T03:27:47.5807470Z at java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056) 2022-07-07T03:27:47.5808029Z at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) 2022-07-07T03:27:47.5808597Z at java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175) 2022-07-07T03:27:47.5809263Z Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=1, backoffTimeMS=0) 2022-07-07T03:27:47.5810116Z at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138) 2022-07-07T03:27:47.5810858Z at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82) 2022-07-07T03:27:47.5811615Z at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:260) 2022-07-07T03:27:47.5812290Z at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:248) 2022-07-07T03:27:47.5813012Z at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:239) 2022-07-07T03:27:47.5813717Z at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:716) 2022-07-07T03:27:47.5814375Z at org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:78) 2022-07-07T03:27:47.5815017Z at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:443) 2022-07-07T03:27:47.5815568Z at sun.reflect.GeneratedMethodAccessor21.invoke(Unknown Source) 2022-07-07T03:27:47.5816050Z at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) 2022-07-07T03:27:47.5816602Z at java.lang.reflect.Method.invoke(Method.java:498) 2022-07-07T03:27:47.5817176Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:309) 2022-07-07T03:27:47.5817893Z at org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83) 2022-07-07T03:27:47.5818571Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:307) 2022-07-07T03:27:47.5819207Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:222) 2022-07-07T03:27:47.5819789Z at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:84) 2022-07-07T03:27:47.5820432Z at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:168) 2022-07-07T03:27:47.5821007Z at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24) 2022-07-07T03:27:47.5821531Z at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20) 2022-07-07T03:27:47.5822051Z at scala.PartialFunction.applyOrElse(PartialFunction.scala:123) 2022-07-07T03:27:47.5822569Z at scala.PartialFunction.applyOrElse$(PartialFunction.scala:122) 2022-07-07T03:27:47.5823367Z at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20) 2022-07-07T03:27:47.5823959Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) 2022-07-07T03:27:47.5824585Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) 2022-07-07T03:27:47.5825125Z at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) 2022-07-07T03:27:47.5825640Z at akka.actor.Actor.aroundReceive(Actor.scala:537) 2022-07-07T03:27:47.5826114Z at akka.actor.Actor.aroundReceive$(Actor.scala:535) 2022-07-07T03:27:47.5826547Z at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220) 2022-07-07T03:27:47.5827069Z at akka.actor.ActorCell.receiveMessage(ActorCell.scala:580) 2022-07-07T03:27:47.5827576Z at akka.actor.ActorCell.invoke(ActorCell.scala:548) 2022-07-07T03:27:47.5828086Z at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270) 2022-07-07T03:27:47.5828567Z at akka.dispatch.Mailbox.run(Mailbox.scala:231) 2022-07-07T03:27:47.5828953Z at akka.dispatch.Mailbox.exec(Mailbox.scala:243) 2022-07-07T03:27:47.5829341Z ... 4 more 2022-07-07T03:27:47.5829756Z Caused by: java.lang.Exception: Exception while creating StreamOperatorStateContext. 2022-07-07T03:27:47.5830424Z at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.streamOperatorStateContext(StreamTaskStateInitializerImpl.java:256) 2022-07-07T03:27:47.5842669Z at org.apache.flink.streaming.api.operators.AbstractStreamOperator.initializeState(AbstractStreamOperator.java:268) 2022-07-07T03:27:47.5843505Z at org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.initializeStateAndOpenOperators(RegularOperatorChain.java:106) 2022-07-07T03:27:47.5844138Z at org.apache.flink.streaming.runtime.tasks.StreamTask.restoreGates(StreamTask.java:722) 2022-07-07T03:27:47.5844815Z at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.call(StreamTaskActionExecutor.java:55) 2022-07-07T03:27:47.5845666Z at org.apache.flink.streaming.runtime.tasks.StreamTask.restoreInternal(StreamTask.java:698) 2022-07-07T03:27:47.5846288Z at org.apache.flink.streaming.runtime.tasks.StreamTask.restore(StreamTask.java:665) 2022-07-07T03:27:47.5846900Z at org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:935) 2022-07-07T03:27:47.5847608Z at org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:904) 2022-07-07T03:27:47.5848166Z at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:728) 2022-07-07T03:27:47.5848620Z at org.apache.flink.runtime.taskmanager.Task.run(Task.java:550) 2022-07-07T03:27:47.5849125Z at java.lang.Thread.run(Thread.java:748) 2022-07-07T03:27:47.5849772Z Caused by: org.apache.flink.util.FlinkException: Could not restore keyed state backend for WindowOperator_0a448493b4782967b150582570326227_(2/4) from any of the 1 provided restore options. 2022-07-07T03:27:47.5850580Z at org.apache.flink.streaming.api.operators.BackendRestorerProcedure.createAndRestore(BackendRestorerProcedure.java:160) 2022-07-07T03:27:47.5851359Z at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.keyedStatedBackend(StreamTaskStateInitializerImpl.java:353) 2022-07-07T03:27:47.5852189Z at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.streamOperatorStateContext(StreamTaskStateInitializerImpl.java:165) 2022-07-07T03:27:47.5852759Z ... 11 more 2022-07-07T03:27:47.5866514Z Caused by: java.lang.RuntimeException: java.io.FileNotFoundException: /tmp/junit1835099326935900400/junit1113650082510421526/52ee65b7-033f-4429-8ddd-adbe85e27ced (No such file or directory) 2022-07-07T03:27:47.5867538Z at org.apache.flink.util.ExceptionUtils.rethrow(ExceptionUtils.java:321) 2022-07-07T03:27:47.5868192Z at org.apache.flink.runtime.state.changelog.StateChangelogHandleStreamHandleReader$1.advance(StateChangelogHandleStreamHandleReader.java:87) 2022-07-07T03:27:47.5869036Z at org.apache.flink.runtime.state.changelog.StateChangelogHandleStreamHandleReader$1.hasNext(StateChangelogHandleStreamHandleReader.java:69) 2022-07-07T03:27:47.5869858Z at org.apache.flink.state.changelog.restore.ChangelogBackendRestoreOperation.readBackendHandle(ChangelogBackendRestoreOperation.java:96) 2022-07-07T03:27:47.5870659Z at org.apache.flink.state.changelog.restore.ChangelogBackendRestoreOperation.restore(ChangelogBackendRestoreOperation.java:75) 2022-07-07T03:27:47.5871640Z at org.apache.flink.state.changelog.ChangelogStateBackend.restore(ChangelogStateBackend.java:92) 2022-07-07T03:27:47.5872398Z at org.apache.flink.state.changelog.AbstractChangelogStateBackend.createKeyedStateBackend(AbstractChangelogStateBackend.java:136) 2022-07-07T03:27:47.5873334Z at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.lambda$keyedStatedBackend$1(StreamTaskStateInitializerImpl.java:336) 2022-07-07T03:27:47.5874139Z at org.apache.flink.streaming.api.operators.BackendRestorerProcedure.attemptCreateAndRestore(BackendRestorerProcedure.java:168) 2022-07-07T03:27:47.5874820Z at org.apache.flink.streaming.api.operators.BackendRestorerProcedure.createAndRestore(BackendRestorerProcedure.java:135) 2022-07-07T03:27:47.5875411Z ... 13 more 2022-07-07T03:27:47.5876295Z Caused by: java.io.FileNotFoundException: /tmp/junit1835099326935900400/junit1113650082510421526/52ee65b7-033f-4429-8ddd-adbe85e27ced (No such file or directory) 2022-07-07T03:27:47.5876909Z at java.io.FileInputStream.open0(Native Method) 2022-07-07T03:27:47.5877488Z at java.io.FileInputStream.open(FileInputStream.java:195) 2022-07-07T03:27:47.5878017Z at java.io.FileInputStream.<init>(FileInputStream.java:138) 2022-07-07T03:27:47.5878507Z at org.apache.flink.core.fs.local.LocalDataInputStream.<init>(LocalDataInputStream.java:50) 2022-07-07T03:27:47.5879128Z at org.apache.flink.core.fs.local.LocalFileSystem.open(LocalFileSystem.java:134) 2022-07-07T03:27:47.5879759Z at org.apache.flink.core.fs.SafetyNetWrapperFileSystem.open(SafetyNetWrapperFileSystem.java:87) 2022-07-07T03:27:47.5880521Z at org.apache.flink.runtime.state.filesystem.FileStateHandle.openInputStream(FileStateHandle.java:72) 2022-07-07T03:27:47.5881167Z at org.apache.flink.changelog.fs.StateChangeFormat.read(StateChangeFormat.java:92) 2022-07-07T03:27:47.5881884Z at org.apache.flink.runtime.state.changelog.StateChangelogHandleStreamHandleReader$1.advance(StateChangelogHandleStreamHandleReader.java:85) 2022-07-07T03:27:47.5882452Z ... 21 more {code} https://dev.azure.com/apache-flink/apache-flink/_build/results?buildId=37772&view=logs&j=4d4a0d10-fca2-5507-8eed-c07f0bdf4887&t=7b25afdf-cc6c-566f-5459-359dc2585798 -- This message was sent by Atlassian Jira (v8.20.10#820010)