You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@flink.apache.org by "Gary Yao (Jira)" <ji...@apache.org> on 2019/11/22 13:46:00 UTC

[jira] [Commented] (FLINK-5125) ContinuousFileProcessingCheckpointITCase is Flaky

    [ https://issues.apache.org/jira/browse/FLINK-5125?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16980156#comment-16980156 ] 

Gary Yao commented on FLINK-5125:
---------------------------------

I observed the following error today

{noformat}

org.apache.flink.client.program.ProgramInvocationException: Job failed (JobID: 6aa3b0495461a1456ef8f0322998501c)
 at org.apache.flink.client.ClientUtils.submitJobAndWaitForResult(ClientUtils.java:144)
 at org.apache.flink.test.checkpointing.StreamFaultToleranceTestBase.runCheckpointedProgram(StreamFaultToleranceTestBase.java:132)
 at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
 at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
 at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
 at java.lang.reflect.Method.invoke(Method.java:498)
 at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
 at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
 at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
 at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
 at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
 at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27)
 at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
 at org.junit.rules.RunRules.evaluate(RunRules.java:20)
 at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
 at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
 at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
 at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
 at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
 at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
 at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
 at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
 at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
 at org.junit.runners.Suite.runChild(Suite.java:128)
 at org.junit.runners.Suite.runChild(Suite.java:27)
 at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
 at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
 at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
 at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
 at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
 at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
 at org.junit.runners.Suite.runChild(Suite.java:128)
 at org.junit.runners.Suite.runChild(Suite.java:27)
 at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
 at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
 at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
 at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
 at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
 at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
 at org.apache.maven.surefire.junitcore.JUnitCore.run(JUnitCore.java:55)
 at org.apache.maven.surefire.junitcore.JUnitCoreWrapper.createRequestAndRun(JUnitCoreWrapper.java:137)
 at org.apache.maven.surefire.junitcore.JUnitCoreWrapper.executeEager(JUnitCoreWrapper.java:107)
 at org.apache.maven.surefire.junitcore.JUnitCoreWrapper.execute(JUnitCoreWrapper.java:83)
 at org.apache.maven.surefire.junitcore.JUnitCoreWrapper.execute(JUnitCoreWrapper.java:75)
 at org.apache.maven.surefire.junitcore.JUnitCoreProvider.invoke(JUnitCoreProvider.java:158)
 at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:384)
 at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:345)
 at org.apache.maven.surefire.booter.ForkedBooter.execute(ForkedBooter.java:126)
 at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:418)
Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
 at org.apache.flink.runtime.jobmaster.JobResult.toJobExecutionResult(JobResult.java:146)
 at org.apache.flink.client.ClientUtils.submitJobAndWaitForResult(ClientUtils.java:142)
 ... 48 more
Caused by: java.lang.IllegalStateException: Cannot process mail Report throwable java.io.FileNotFoundException: File file:/home/travis/build/flink-ci/flink/flink-tests/target/target/localfs/fs_tests/..file3.crc does not exist or the user running Flink ('travis') has insufficient permissions to access it.
 at org.apache.flink.streaming.runtime.tasks.mailbox.Mail.run(Mail.java:68)
 at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.processMail(MailboxProcessor.java:213)
 at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:154)
 at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:445)
 at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:702)
 at org.apache.flink.runtime.taskmanager.Task.run(Task.java:527)
 at java.lang.Thread.run(Thread.java:748)
Caused by: org.apache.flink.util.WrappingRuntimeException: java.io.FileNotFoundException: File file:/home/travis/build/flink-ci/flink/flink-tests/target/target/localfs/fs_tests/..file3.crc does not exist or the user running Flink ('travis') has insufficient permissions to access it.
 at org.apache.flink.util.WrappingRuntimeException.wrapIfNecessary(WrappingRuntimeException.java:65)
 at org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.lambda$reportThrowable$0(MailboxProcessor.java:166)
 at org.apache.flink.streaming.runtime.tasks.mailbox.Mail.run(Mail.java:66)
 ... 6 more
Caused by: java.io.FileNotFoundException: File file:/home/travis/build/flink-ci/flink/flink-tests/target/target/localfs/fs_tests/..file3.crc does not exist or the user running Flink ('travis') has insufficient permissions to access it.
 at org.apache.flink.core.fs.local.LocalFileSystem.getFileStatus(LocalFileSystem.java:115)
 at org.apache.flink.core.fs.local.LocalFileSystem.listStatus(LocalFileSystem.java:175)
 at org.apache.flink.api.common.io.FileInputFormat.addFilesInDir(FileInputFormat.java:707)
 at org.apache.flink.api.common.io.FileInputFormat.createInputSplits(FileInputFormat.java:591)
 at org.apache.flink.streaming.api.functions.source.ContinuousFileMonitoringFunction.getInputSplitsSortedByModTime(ContinuousFileMonitoringFunction.java:270)
 at org.apache.flink.streaming.api.functions.source.ContinuousFileMonitoringFunction.monitorDirAndForwardSplits(ContinuousFileMonitoringFunction.java:242)
 at org.apache.flink.streaming.api.functions.source.ContinuousFileMonitoringFunction.run(ContinuousFileMonitoringFunction.java:206)
 at org.apache.flink.streaming.api.operators.StreamSource.run(StreamSource.java:100)
 at org.apache.flink.streaming.api.operators.StreamSource.run(StreamSource.java:63)
 at org.apache.flink.streaming.runtime.tasks.SourceStreamTask$LegacySourceFunctionThread.run(SourceStreamTask.java:191)
10:59:08.637 [ERROR] Tests run: 2, Failures: 1, Errors: 0, Skipped: 1, Time elapsed: 5.791 s <<< FAILURE! - in org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase
10:59:08.637 [ERROR] runCheckpointedProgram[FailoverStrategy: RestartAllStrategy](org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase) Time elapsed: 5.36 s <<< FAILURE!

{noformat}

 

https://api.travis-ci.com/v3/job/259366771/log.txt

> ContinuousFileProcessingCheckpointITCase is Flaky
> -------------------------------------------------
>
>                 Key: FLINK-5125
>                 URL: https://issues.apache.org/jira/browse/FLINK-5125
>             Project: Flink
>          Issue Type: Bug
>          Components: Connectors / Common
>            Reporter: Aljoscha Krettek
>            Assignee: Kostas Kloudas
>            Priority: Critical
>              Labels: test-stability
>
> This is the travis log: https://api.travis-ci.org/jobs/177402367/log.txt?deansi=true
> The relevant sections is:
> {code}
> Running org.apache.flink.test.checkpointing.CoStreamCheckpointingITCase
> Tests run: 3, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 2.571 sec - in org.apache.flink.test.exampleJavaPrograms.EnumTriangleBasicITCase
> Running org.apache.flink.test.checkpointing.EventTimeWindowCheckpointingITCase
> Tests run: 1, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 17.704 sec - in org.apache.flink.test.checkpointing.CoStreamCheckpointingITCase
> Running org.apache.flink.test.checkpointing.EventTimeAllWindowCheckpointingITCase
> Tests run: 5, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 11.805 sec - in org.apache.flink.test.checkpointing.EventTimeAllWindowCheckpointingITCase
> Running org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase
> org.apache.flink.client.program.ProgramInvocationException: The program execution failed: Job execution failed.
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:427)
> 	at org.apache.flink.client.program.StandaloneClusterClient.submitJob(StandaloneClusterClient.java:101)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:400)
> 	at org.apache.flink.client.program.ClusterClient.run(ClusterClient.java:392)
> 	at org.apache.flink.streaming.api.environment.RemoteStreamEnvironment.executeRemotely(RemoteStreamEnvironment.java:209)
> 	at org.apache.flink.streaming.api.environment.RemoteStreamEnvironment.execute(RemoteStreamEnvironment.java:173)
> 	at org.apache.flink.test.util.TestUtils.tryExecute(TestUtils.java:32)
> 	at org.apache.flink.test.checkpointing.StreamFaultToleranceTestBase.runCheckpointedProgram(StreamFaultToleranceTestBase.java:106)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> 	at java.lang.reflect.Method.invoke(Method.java:606)
> 	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
> 	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
> 	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
> 	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
> 	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
> 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
> 	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
> 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
> 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
> 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
> 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
> 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
> 	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
> 	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27)
> 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:283)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:173)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:153)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:128)
> 	at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:203)
> 	at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:155)
> 	at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:103)
> Caused by: org.apache.flink.runtime.client.JobExecutionException: Job execution failed.
> 	at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$handleMessage$1$$anonfun$applyOrElse$6.apply$mcV$sp(JobManager.scala:905)
> 	at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$handleMessage$1$$anonfun$applyOrElse$6.apply(JobManager.scala:848)
> 	at org.apache.flink.runtime.jobmanager.JobManager$$anonfun$handleMessage$1$$anonfun$applyOrElse$6.apply(JobManager.scala:848)
> 	at scala.concurrent.impl.Future$PromiseCompletingRunnable.liftedTree1$1(Future.scala:24)
> 	at scala.concurrent.impl.Future$PromiseCompletingRunnable.run(Future.scala:24)
> 	at akka.dispatch.TaskInvocation.run(AbstractDispatcher.scala:41)
> 	at akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:401)
> 	at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
> 	at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.pollAndExecAll(ForkJoinPool.java:1253)
> 	at scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1346)
> 	at scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
> 	at scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
> Caused by: java.lang.Exception: Task Failure @ elem: 466 / 28
> 	at org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase$TestingSinkFunction.invoke(ContinuousFileProcessingCheckpointITCase.java:226)
> 	at org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase$TestingSinkFunction.invoke(ContinuousFileProcessingCheckpointITCase.java:165)
> 	at org.apache.flink.streaming.api.operators.StreamSink.processElement(StreamSink.java:38)
> 	at org.apache.flink.streaming.runtime.io.StreamInputProcessor.processInput(StreamInputProcessor.java:185)
> 	at org.apache.flink.streaming.runtime.tasks.OneInputStreamTask.run(OneInputStreamTask.java:63)
> 	at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:269)
> 	at org.apache.flink.runtime.taskmanager.Task.run(Task.java:650)
> 	at java.lang.Thread.run(Thread.java:745)
> Tests run: 1, Failures: 1, Errors: 0, Skipped: 0, Time elapsed: 8.211 sec <<< FAILURE! - in org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase
> runCheckpointedProgram(org.apache.flink.test.checkpointing.ContinuousFileProcessingCheckpointITCase)  Time elapsed: 4.74 sec  <<< FAILURE!
> java.lang.AssertionError: Test failed: The program execution failed: Job execution failed.
> 	at org.junit.Assert.fail(Assert.java:88)
> 	at org.apache.flink.test.util.TestUtils.tryExecute(TestUtils.java:42)
> 	at org.apache.flink.test.checkpointing.StreamFaultToleranceTestBase.runCheckpointedProgram(StreamFaultToleranceTestBase.java:106)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> 	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> 	at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> 	at java.lang.reflect.Method.invoke(Method.java:606)
> 	at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:50)
> 	at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
> 	at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
> 	at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
> 	at org.junit.rules.TestWatcher$1.evaluate(TestWatcher.java:55)
> 	at org.junit.rules.RunRules.evaluate(RunRules.java:20)
> 	at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:325)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:78)
> 	at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:57)
> 	at org.junit.runners.ParentRunner$3.run(ParentRunner.java:290)
> 	at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:71)
> 	at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:288)
> 	at org.junit.runners.ParentRunner.access$000(ParentRunner.java:58)
> 	at org.junit.runners.ParentRunner$2.evaluate(ParentRunner.java:268)
> 	at org.junit.internal.runners.statements.RunBefores.evaluate(RunBefores.java:26)
> 	at org.junit.internal.runners.statements.RunAfters.evaluate(RunAfters.java:27)
> 	at org.junit.runners.ParentRunner.run(ParentRunner.java:363)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.execute(JUnit4Provider.java:283)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeWithRerun(JUnit4Provider.java:173)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.executeTestSet(JUnit4Provider.java:153)
> 	at org.apache.maven.surefire.junit4.JUnit4Provider.invoke(JUnit4Provider.java:128)
> 	at org.apache.maven.surefire.booter.ForkedBooter.invokeProviderInSameClassLoader(ForkedBooter.java:203)
> 	at org.apache.maven.surefire.booter.ForkedBooter.runSuitesInProcess(ForkedBooter.java:155)
> 	at org.apache.maven.surefire.booter.ForkedBooter.main(ForkedBooter.java:103)
> Running org.apache.flink.test.cancelling.MapCancelingITCase
> Tests run: 4, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 24.723 sec - in org.apache.flink.test.cancelling.MapCancelingITCase
> Running org.apache.flink.test.actions.CountCollectITCase
> Tests run: 4, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 2.247 sec - in org.apache.flink.test.actions.CountCollectITCase
> Running org.apache.flink.test.io.InputOutputITCase
> Tests run: 3, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 2.254 sec - in org.apache.flink.test.io.InputOutputITCase
> Running org.apache.flink.test.io.CsvReaderITCase
> Tests run: 10, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 2.102 sec - in org.apache.flink.test.io.CsvReaderITCase
> Running org.apache.flink.test.failingPrograms.JobSubmissionFailsITCase
> Tests run: 6, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 2.307 sec - in org.apache.flink.test.failingPrograms.JobSubmissionFailsITCase
> Tests run: 18, Failures: 0, Errors: 0, Skipped: 0, Time elapsed: 116.455 sec - in org.apache.flink.test.checkpointing.EventTimeWindowCheckpointingITCase
> Results :
> Failed tests: 
>   ContinuousFileProcessingCheckpointITCase>StreamFaultToleranceTestBase.runCheckpointedProgram:106 Test failed: The program execution failed: Job execution failed.
> {code}



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