flink 1.12 standalone cluster,定时batch 模式 insert overwrite 到 hive 表,会随机出现找不到
.staging_xxxx 文件的错误,完整错误信息如下:org.apache.flink.runtime.JobException: Recovery
is suppressed by NoRestartBackoffTimeStrategy   at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.handleFailure(ExecutionFailureHandler.java:116)
at
org.apache.flink.runtime.executiongraph.failover.flip1.ExecutionFailureHandler.getGlobalFailureHandlingResult(ExecutionFailureHandler.java:89)
at
org.apache.flink.runtime.scheduler.DefaultScheduler.handleGlobalFailure(DefaultScheduler.java:240)
at
org.apache.flink.runtime.scheduler.UpdateSchedulerNgOnInternalFailuresListener.notifyGlobalFailure(UpdateSchedulerNgOnInternalFailuresListener.java:65)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.failGlobal(ExecutionGraph.java:1055)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.vertexFinished(ExecutionGraph.java:1305)
at
org.apache.flink.runtime.executiongraph.ExecutionVertex.executionFinished(ExecutionVertex.java:849)
at
org.apache.flink.runtime.executiongraph.Execution.markFinished(Execution.java:1127)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.updateStateInternal(ExecutionGraph.java:1512)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.updateState(ExecutionGraph.java:1485)
at
org.apache.flink.runtime.scheduler.SchedulerBase.updateTaskExecutionState(SchedulerBase.java:604)
at
org.apache.flink.runtime.scheduler.SchedulerNG.updateTaskExecutionState(SchedulerNG.java:89)
at
org.apache.flink.runtime.jobmaster.JobMaster.updateTaskExecutionState(JobMaster.java:419)
at sun.reflect.GeneratedMethodAccessor56.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.handleRpcInvocation(AkkaRpcActor.java:286)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleRpcMessage(AkkaRpcActor.java:201)
at
org.apache.flink.runtime.rpc.akka.FencedAkkaRpcActor.handleRpcMessage(FencedAkkaRpcActor.java:74)
at
org.apache.flink.runtime.rpc.akka.AkkaRpcActor.handleMessage(AkkaRpcActor.java:154)
at akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:26)        at
akka.japi.pf.UnitCaseStatement.apply(CaseStatements.scala:21)   at
scala.PartialFunction$class.applyOrElse(PartialFunction.scala:123)      at
akka.japi.pf.UnitCaseStatement.applyOrElse(CaseStatements.scala:21)     at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:170)     at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)     at
scala.PartialFunction$OrElse.applyOrElse(PartialFunction.scala:171)     at
akka.actor.Actor$class.aroundReceive(Actor.scala:517)   at
akka.actor.AbstractActor.aroundReceive(AbstractActor.scala:225) at
akka.actor.ActorCell.receiveMessage(ActorCell.scala:592)        at
akka.actor.ActorCell.invoke(ActorCell.scala:561)        at
akka.dispatch.Mailbox.processMailbox(Mailbox.scala:258) at
akka.dispatch.Mailbox.run(Mailbox.scala:225)    at
akka.dispatch.Mailbox.exec(Mailbox.scala:235)   at
akka.dispatch.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)       at
akka.dispatch.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at akka.dispatch.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)        
at
akka.dispatch.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)Caused
by: java.lang.Exception: Failed to finalize execution on master ... 33
moreCaused by: org.apache.flink.table.api.TableException: Exception in
finalizeGlobal  at
org.apache.flink.table.filesystem.FileSystemOutputFormat.finalizeGlobal(FileSystemOutputFormat.java:97)
at
org.apache.flink.runtime.jobgraph.InputOutputFormatVertex.finalizeOnMaster(InputOutputFormatVertex.java:131)
at
org.apache.flink.runtime.executiongraph.ExecutionGraph.vertexFinished(ExecutionGraph.java:1299)
... 32 moreCaused by: java.io.FileNotFoundException: File
hdfs://service1/user/hive/warehouse/snmpprobe.db/p_port_packet_loss_5m/.staging_1609040810292
does not exist. at
org.apache.hadoop.hdfs.DistributedFileSystem.listStatusInternal(DistributedFileSystem.java:901)
at
org.apache.hadoop.hdfs.DistributedFileSystem.access$600(DistributedFileSystem.java:112)
at
org.apache.hadoop.hdfs.DistributedFileSystem$22.doCall(DistributedFileSystem.java:961)
at
org.apache.hadoop.hdfs.DistributedFileSystem$22.doCall(DistributedFileSystem.java:958)
at
org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
at
org.apache.hadoop.hdfs.DistributedFileSystem.listStatus(DistributedFileSystem.java:958)
at
org.apache.flink.hive.shaded.fs.hdfs.HadoopFileSystem.listStatus(HadoopFileSystem.java:165)
at
org.apache.flink.table.filesystem.PartitionTempFileManager.headCheckpoints(PartitionTempFileManager.java:140)
at
org.apache.flink.table.filesystem.FileSystemCommitter.commitUpToCheckpoint(FileSystemCommitter.java:98)
at
org.apache.flink.table.filesystem.FileSystemOutputFormat.finalizeGlobal(FileSystemOutputFormat.java:95)
... 34 more



--
Sent from: http://apache-flink.147419.n8.nabble.com/

回复