[ https://issues.apache.org/jira/browse/HUDI-4541?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ethan Guo updated HUDI-4541: ---------------------------- Issue Type: Bug (was: Improvement) > Flink job fails with column stats enabled in metadata table due to > NotSerializableException > -------------------------------------------------------------------------------------------- > > Key: HUDI-4541 > URL: https://issues.apache.org/jira/browse/HUDI-4541 > Project: Apache Hudi > Issue Type: Bug > Components: flink-sql > Reporter: Ethan Guo > Priority: Blocker > Fix For: 0.12.0 > > > Environment: EMR 6.7.0 Flink 1.14.2 > Reproducible steps: Build h > > Exception: > {code:java} > 2022-08-04 17:04:41org.apache.flink.runtime.JobException: Recovery is > suppressed by NoRestartBackoffTimeStrategy at > org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:138) > at > org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getFailureHandlingResult(ExecutionFailureHandler.java:82) > at > org.apache.flink.runtime.scheduler.DefaultScheduler.handleTaskFailure(DefaultScheduler.java:228) > at > org.apache.flink.runtime.scheduler.DefaultScheduler.maybeHandleTaskFailure(DefaultScheduler.java:218) > at > org.apache.flink.runtime.scheduler.DefaultScheduler.updateTaskExecutionStateInternal(DefaultScheduler.java:209) > at > org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:679) > at > org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:79) > at > org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:444) > at sun.reflect.GeneratedMethodAccessor35.invoke(Unknown Source) at > sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) > at java.lang.reflect.Method.invoke(Method.java:498) at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.lambda$handleRpcInvocation$1(AkkaRpcActor.java:316) > at > org.apache.flink.runtime.concurrent.akka.ClassLoadingUtils.runWithContextClassLoader(ClassLoadingUtils.java:83) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcInvocation(AkkaRpcActor.java:314) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:217) > at > org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:78) > at > org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:163) > at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:24) at > akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:20) at > scala.PartialFunction.applyOrElse(PartialFunction.scala:123) at > scala.PartialFunction.applyOrElse$(PartialFunction.scala:122) at > akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:20) at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171) at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) at > scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:172) at > akka.actor.Actor.aroundReceive(Actor.scala:537) at > akka.actor.Actor.aroundReceive$(Actor.scala:535) at > akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:220) at > akka.actor.ActorCell.receiveMessage(ActorCell.scala:580) at > akka.actor.ActorCell.invoke(ActorCell.scala:548) at > akka.dispatch.Mailbox.processMailbox(Mailbox.scala:270) at > akka.dispatch.Mailbox.run(Mailbox.scala:231) at > akka.dispatch.Mailbox.exec(Mailbox.scala:243) at > java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289) at > java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056) > at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692) at > java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)Caused > by: org.apache.flink.util.FlinkRuntimeException: Cannot serialize operator > event at > org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:111) > at > org.apache.hudi.sink.StreamWriteFunction.flushRemaining(StreamWriteFunction.java:479) > at > org.apache.hudi.sink.StreamWriteFunction.endInput(StreamWriteFunction.java:152) > at > org.apache.hudi.sink.common.AbstractWriteOperator.endInput(AbstractWriteOperator.java:48) > at > org.apache.flink.streaming.runtime.tasks.StreamOperatorWrapper.endOperatorInput(StreamOperatorWrapper.java:91) > at > org.apache.flink.streaming.runtime.tasks.RegularOperatorChain.endInput(RegularOperatorChain.java:100) > at > org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:68) > at > org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:496) > at > org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:203) > at > org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:809) > at > org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:761) > at > org.apache.flink.runtime.taskmanager.Task.runWithSystemExitMonitoring(Task.java:958) > at > org.apache.flink.runtime.taskmanager.Task.restoreAndInvoke(Task.java:937) > at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:766) at > org.apache.flink.runtime.taskmanager.Task.run(Task.java:575) at > java.lang.Thread.run(Thread.java:750)Caused by: > java.io.NotSerializableException: org.apache.hudi.org.apache.avro.util.Utf8 > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1184) > at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348) at > java.util.HashMap.internalWriteEntries(HashMap.java:1817) at > java.util.HashMap.writeObject(HashMap.java:1364) 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 > java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348) at > java.util.ArrayList.writeObject(ArrayList.java:768) 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 > java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at > java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548) > at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509) > at > java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432) > at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178) > at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348) at > org.apache.flink.util.InstantiationUtil.serializeObject(InstantiationUtil.java:632) > at org.apache.flink.util.SerializedValue.<init>(SerializedValue.java:62) > at > org.apache.flink.streaming.runtime.tasks.OperatorEventDispatcherImpl$OperatorEventGatewayImpl.sendEventToCoordinator(OperatorEventDispatcherImpl.java:107) > ... 15 more > {code} -- This message was sent by Atlassian Jira (v8.20.10#820010)