You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Robert Metzger (Jira)" <ji...@apache.org> on 2020/04/06 09:30:00 UTC

[jira] [Created] (FLINK-17006) AggregateITCase.testDistinctGroupBy fails with FileNotFoundException (in Rocksdb)

Robert Metzger created FLINK-17006:
--------------------------------------

             Summary: AggregateITCase.testDistinctGroupBy fails with FileNotFoundException (in Rocksdb)
                 Key: FLINK-17006
                 URL: https://issues.apache.org/jira/browse/FLINK-17006
             Project: Flink
          Issue Type: Bug
          Components: Runtime / State Backends, Table SQL / Runtime, Tests
    Affects Versions: 1.11.0
            Reporter: Robert Metzger


CI run: https://dev.azure.com/rmetzger/Flink/_build/results?buildId=7045&view=logs&j=e25d5e7e-2a9c-5589-4940-0b638d75a414&t=294c2388-20e6-57a2-5721-91db544b1e69
Log output:
{code}
2020-04-03T17:17:44.4036304Z [ERROR] Tests run: 234, Failures: 0, Errors: 1, Skipped: 6, Time elapsed: 155.577 s <<< FAILURE! - in org.apache.flink.table.planner.runtime.stream.sql.AggregateITCase
2020-04-03T17:17:44.4038781Z [ERROR] testDistinctGroupBy[LocalGlobal=OFF, MiniBatch=ON, StateBackend=ROCKSDB](org.apache.flink.table.planner.runtime.stream.sql.AggregateITCase)  Time elapsed: 0.456 s  <<< ERROR!
2020-04-03T17:17:44.4040384Z org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
2020-04-03T17:17:44.4041520Z 	at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:147)
2020-04-03T17:17:44.4042712Z 	at org.apache.flink.runtime.minicluster.MiniCluster.executeJobBlocking(MiniCluster.java:659)
2020-04-03T17:17:44.4043972Z 	at org.apache.flink.streaming.util.TestStreamEnvironment.execute(TestStreamEnvironment.java:77)
2020-04-03T17:17:44.4045540Z 	at org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1644)
2020-04-03T17:17:44.4047015Z 	at org.apache.flink.streaming.api.environment.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.java:1626)
2020-04-03T17:17:44.4048576Z 	at org.apache.flink.streaming.api.scala.StreamExecutionEnvironment.execute(StreamExecutionEnvironment.scala:673)
2020-04-03T17:17:44.4050073Z 	at org.apache.flink.table.planner.runtime.stream.sql.AggregateITCase.testDistinctGroupBy(AggregateITCase.scala:172)
2020-04-03T17:17:44.4051200Z 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
2020-04-03T17:17:44.4052171Z 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
2020-04-03T17:17:44.4053308Z 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
2020-04-03T17:17:44.4054322Z 	at java.lang.reflect.Method.invoke(Method.java:498)
2020-04-03T17:17:44.4055410Z 	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
2020-04-03T17:17:44.4056570Z 	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
2020-04-03T17:17:44.4057800Z 	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
2020-04-03T17:17:44.4059019Z 	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
2020-04-03T17:17:44.4060178Z 	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
2020-04-03T17:17:44.4061261Z 	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27)
2020-04-03T17:17:44.4062617Z 	at org.junit.rules.ExpectedException$ExpectedExceptionStatement.evaluate(ExpectedException.java:239)
2020-04-03T17:17:44.4063782Z 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
2020-04-03T17:17:44.4064838Z 	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
2020-04-03T17:17:44.4065742Z 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
2020-04-03T17:17:44.4066636Z 	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
2020-04-03T17:17:44.4067762Z 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
2020-04-03T17:17:44.4068895Z 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
2020-04-03T17:17:44.4069978Z 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
2020-04-03T17:17:44.4070920Z 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
2020-04-03T17:17:44.4071901Z 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
2020-04-03T17:17:44.4072875Z 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
2020-04-03T17:17:44.4073850Z 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
2020-04-03T17:17:44.4074854Z 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
2020-04-03T17:17:44.4075729Z 	at org.junit.runners.Suite.runChild(Suite.java:128)
2020-04-03T17:17:44.4076541Z 	at org.junit.runners.Suite.runChild(Suite.java:27)
2020-04-03T17:17:44.4077479Z 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
2020-04-03T17:17:44.4078422Z 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
2020-04-03T17:17:44.4079501Z 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
2020-04-03T17:17:44.4080503Z 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
2020-04-03T17:17:44.4081483Z 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
2020-04-03T17:17:44.4082477Z 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
2020-04-03T17:17:44.4083522Z 	at org.junit.rules.ExternalResource$1.evaluate(ExternalResource.java:48)
2020-04-03T17:17:44.4084529Z 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
2020-04-03T17:17:44.4085420Z 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
2020-04-03T17:17:44.4086433Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:365)
2020-04-03T17:17:44.4087696Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:273)
2020-04-03T17:17:44.4088900Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:238)
2020-04-03T17:17:44.4090109Z 	at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:159)
2020-04-03T17:17:44.4091331Z 	at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:384)
2020-04-03T17:17:44.4092600Z 	at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:345)
2020-04-03T17:17:44.4093737Z 	at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:126)
2020-04-03T17:17:44.4094894Z 	at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:418)
2020-04-03T17:17:44.4096257Z Caused by: org.apache.flink.runtime.JobException: Recovery is suppressed by FixedDelayRestartBackoffTimeStrategy(maxNumberRestartAttempts=1, backoffTimeMS=0)
2020-04-03T17:17:44.4097915Z 	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:110)
2020-04-03T17:17:44.4099539Z 	at org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:76)
2020-04-03T17:17:44.4101039Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:190)
2020-04-03T17:17:44.4102353Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:184)
2020-04-03T17:17:44.4103808Z 	at org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:178)
2020-04-03T17:17:44.4105242Z 	at org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:505)
2020-04-03T17:17:44.4106478Z 	at org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:384)
2020-04-03T17:17:44.4107561Z 	at sun.reflect.GeneratedMethodAccessor16.invoke(Unknown Source)
2020-04-03T17:17:44.4108552Z 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
2020-04-03T17:17:44.4109560Z 	at java.lang.reflect.Method.invoke(Method.java:498)
2020-04-03T17:17:44.4110604Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:284)
2020-04-03T17:17:44.4111812Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:199)
2020-04-03T17:17:44.4113054Z 	at org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
2020-04-03T17:17:44.4114282Z 	at org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:152)
2020-04-03T17:17:44.4115417Z 	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)
2020-04-03T17:17:44.4116357Z 	at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)
2020-04-03T17:17:44.4117338Z 	at scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)
2020-04-03T17:17:44.4118401Z 	at akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)
2020-04-03T17:17:44.4119414Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)
2020-04-03T17:17:44.4120443Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
2020-04-03T17:17:44.4121538Z 	at scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)
2020-04-03T17:17:44.4122461Z 	at akka.actor.Actor$class.aroundReceive(Actor.scala:517)
2020-04-03T17:17:44.4123383Z 	at akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225)
2020-04-03T17:17:44.4124315Z 	at akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)
2020-04-03T17:17:44.4125257Z 	at akka.actor.ActorCell.invoke(ActorCell.scala:561)
2020-04-03T17:17:44.4126107Z 	at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258)
2020-04-03T17:17:44.4126953Z 	at akka.dispatch.Mailbox.run(Mailbox.scala:225)
2020-04-03T17:17:44.4127798Z 	at akka.dispatch.Mailbox.exec(Mailbox.scala:235)
2020-04-03T17:17:44.4128829Z 	at akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
2020-04-03T17:17:44.4129875Z 	at akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
2020-04-03T17:17:44.4130957Z 	at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
2020-04-03T17:17:44.4132016Z 	at akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
2020-04-03T17:17:44.4133098Z Caused by: java.lang.Exception: Exception while creating StreamOperatorStateContext.
2020-04-03T17:17:44.4134528Z 	at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.streamOperatorStateContext(StreamTaskStateInitializerImpl.java:191)
2020-04-03T17:17:44.4136100Z 	at org.apache.flink.streaming.api.operators.AbstractStreamOperator.initializeState(AbstractStreamOperator.java:246)
2020-04-03T17:17:44.4137580Z 	at org.apache.flink.streaming.runtime.tasks.OperatorChain.initializeStateAndOpenOperators(OperatorChain.java:293)
2020-04-03T17:17:44.4138925Z 	at org.apache.flink.streaming.runtime.tasks.StreamTask.lambda$beforeInvoke$0(StreamTask.java:436)
2020-04-03T17:17:44.4140304Z 	at org.apache.flink.streaming.runtime.tasks.StreamTaskActionExecutor$1.runThrowing(StreamTaskActionExecutor.java:47)
2020-04-03T17:17:44.4141631Z 	at org.apache.flink.streaming.runtime.tasks.StreamTask.beforeInvoke(StreamTask.java:432)
2020-04-03T17:17:44.4142783Z 	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:445)
2020-04-03T17:17:44.4143814Z 	at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:718)
2020-04-03T17:17:44.4144935Z 	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:542)
2020-04-03T17:17:44.4145756Z 	at java.lang.Thread.run(Thread.java:748)
2020-04-03T17:17:44.4147095Z Caused by: org.apache.flink.util.FlinkException: Could not restore keyed state backend for KeyedMapBundleOperator_f6dc7f4d2283f4605b127b9364e21148_(2/4) from any of the 1 provided restore options.
2020-04-03T17:17:44.4148863Z 	at org.apache.flink.streaming.api.operators.BackendRestorerProcedure.createAndRestore(BackendRestorerProcedure.java:135)
2020-04-03T17:17:44.4150449Z 	at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.keyedStatedBackend(StreamTaskStateInitializerImpl.java:304)
2020-04-03T17:17:44.4152096Z 	at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.streamOperatorStateContext(StreamTaskStateInitializerImpl.java:131)
2020-04-03T17:17:44.4153151Z 	... 9 more
2020-04-03T17:17:44.4153946Z Caused by: org.apache.flink.runtime.state.BackendBuildingException: Caught unexpected exception.
2020-04-03T17:17:44.4155379Z 	at org.apache.flink.contrib.streaming.state.RocksDBKeyedStateBackendBuilder.build(RocksDBKeyedStateBackendBuilder.java:336)
2020-04-03T17:17:44.4156850Z 	at org.apache.flink.contrib.streaming.state.RocksDBStateBackend.createKeyedStateBackend(RocksDBStateBackend.java:548)
2020-04-03T17:17:44.4158503Z 	at org.apache.flink.streaming.api.operators.StreamTaskStateInitializerImpl.lambda$keyedStatedBackend$1(StreamTaskStateInitializerImpl.java:288)
2020-04-03T17:17:44.4160158Z 	at org.apache.flink.streaming.api.operators.BackendRestorerProcedure.attemptCreateAndRestore(BackendRestorerProcedure.java:142)
2020-04-03T17:17:44.4161662Z 	at org.apache.flink.streaming.api.operators.BackendRestorerProcedure.createAndRestore(BackendRestorerProcedure.java:121)
2020-04-03T17:17:44.4162706Z 	... 11 more
2020-04-03T17:17:44.4164646Z Caused by: java.io.FileNotFoundException: /tmp/junit1553841028375950249/junit3479071836389613442/babdd750dc1c5b3874a0dd55d14a84f6/shared/2aa67d1b-8841-4755-84c4-b891fc8c3352 (No such file or directory)
2020-04-03T17:17:44.4166003Z 	at java.io.FileInputStream.open0(Native Method)
2020-04-03T17:17:44.4166782Z 	at java.io.FileInputStream.open(FileInputStream.java:195)
2020-04-03T17:17:44.4167752Z 	at java.io.FileInputStream.<init>(FileInputStream.java:138)
2020-04-03T17:17:44.4168802Z 	at org.apache.flink.core.fs.local.LocalDataInputStream.<init>(LocalDataInputStream.java:50)
2020-04-03T17:17:44.4170003Z 	at org.apache.flink.core.fs.local.LocalFileSystem.open(LocalFileSystem.java:142)
2020-04-03T17:17:44.4171168Z 	at org.apache.flink.core.fs.SafetyNetWrapperFileSystem.open(SafetyNetWrapperFileSystem.java:85)
2020-04-03T17:17:44.4172447Z 	at org.apache.flink.runtime.state.filesystem.FileStateHandle.openInputStream(FileStateHandle.java:68)
2020-04-03T17:17:44.4173862Z 	at org.apache.flink.contrib.streaming.state.RocksDBStateDownloader.downloadDataForStateHandle(RocksDBStateDownloader.java:126)
2020-04-03T17:17:44.4175519Z 	at org.apache.flink.contrib.streaming.state.RocksDBStateDownloader.lambda$createDownloadRunnables$0(RocksDBStateDownloader.java:109)
2020-04-03T17:17:44.4176945Z 	at org.apache.flink.util.function.ThrowingRunnable.lambda$unchecked$0(ThrowingRunnable.java:50)
2020-04-03T17:17:44.4178185Z 	at java.util.concurrent.CompletableFuture$AsyncRun.run(CompletableFuture.java:1640)
2020-04-03T17:17:44.4179404Z 	at org.apache.flink.runtime.concurrent.DirectExecutorService.execute(DirectExecutorService.java:211)
2020-04-03T17:17:44.4180647Z 	at java.util.concurrent.CompletableFuture.asyncRunStage(CompletableFuture.java:1654)
2020-04-03T17:17:44.4181769Z 	at java.util.concurrent.CompletableFuture.runAsync(CompletableFuture.java:1871)
2020-04-03T17:17:44.4183098Z 	at org.apache.flink.contrib.streaming.state.RocksDBStateDownloader.downloadDataForAllStateHandles(RocksDBStateDownloader.java:83)
2020-04-03T17:17:44.4184752Z 	at org.apache.flink.contrib.streaming.state.RocksDBStateDownloader.transferAllStateDataToDirectory(RocksDBStateDownloader.java:67)
2020-04-03T17:17:44.4186598Z 	at org.apache.flink.contrib.streaming.state.restore.RocksDBIncrementalRestoreOperation.transferRemoteStateToLocalDirectory(RocksDBIncrementalRestoreOperation.java:229)
2020-04-03T17:17:44.4188548Z 	at org.apache.flink.contrib.streaming.state.restore.RocksDBIncrementalRestoreOperation.restoreFromRemoteState(RocksDBIncrementalRestoreOperation.java:194)
2020-04-03T17:17:44.4190380Z 	at org.apache.flink.contrib.streaming.state.restore.RocksDBIncrementalRestoreOperation.restoreWithoutRescaling(RocksDBIncrementalRestoreOperation.java:168)
2020-04-03T17:17:44.4192129Z 	at org.apache.flink.contrib.streaming.state.restore.RocksDBIncrementalRestoreOperation.restore(RocksDBIncrementalRestoreOperation.java:154)
2020-04-03T17:17:44.4193725Z 	at org.apache.flink.contrib.streaming.state.RocksDBKeyedStateBackendBuilder.build(RocksDBKeyedStateBackendBuilder.java:279)
2020-04-03T17:17:44.4194758Z 	... 15 more
2020-04-03T17:17:44.4195053Z 
{code}

I'm uncertain about the component assignment of this ticket. This error can probably have many causes?



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