AWS EMR с приложением Flink для бегуна Apache_beam, ошибка java.nio.channels.ClosedByInterruptException при чтении файлов из GCS Задать вопрос - PullRequest
0 голосов
/ 18 апреля 2019

У меня кластер EMR с приложением flink.Запуск Apache-Beam с помощью Flink Runner.Кластер начал читать и отлично работает в течение 30-40 минут.Затем канал внезапно закрывается и прерывается.Это ошибка, которую я получаю.

Я уже установил ключ учетной записи службы в json_configrations и скопировал учетную запись службы json в сценарий начальной загрузки.

Также тайм-аут доступа к файлу gcs до бесконечности.Хотя файл в маленьком размере

Apr 18, 2019 4:15:45 PM com.google.cloud.hadoop.gcsio.GoogleCloudStorageReadChannel read
WARNING: Failed read retry #1/10 for 'gs://files/1_26_00000000000000021016.gz'. Sleeping...
java.nio.channels.ClosedByInterruptException
    at java.nio.channels.spi.AbstractInterruptibleChannel.end(AbstractInterruptibleChannel.java:202)
    at java.nio.channels.Channels$ReadableByteChannelImpl.read(Channels.java:387)
    at com.google.cloud.hadoop.gcsio.GoogleCloudStorageReadChannel.read(GoogleCloudStorageReadChannel.java:348)
    at org.apache.beam.sdk.io.CompressedSource$CompressedReader$CountingChannel.read(CompressedSource.java:382)
    at sun.nio.ch.ChannelInputStream.read(ChannelInputStream.java:65)
    at sun.nio.ch.ChannelInputStream.read(ChannelInputStream.java:109)
    at sun.nio.ch.ChannelInputStream.read(ChannelInputStream.java:103)
    at java.io.FilterInputStream.read(FilterInputStream.java:133)
    at java.io.PushbackInputStream.read(PushbackInputStream.java:186)
    at org.apache.beam.vendor.guava.v20_0.com.google.common.io.ByteStreams.read(ByteStreams.java:859)
    at org.apache.beam.sdk.io.Compression$3.readDecompressed(Compression.java:82)
    at org.apache.beam.sdk.io.CompressedSource$CompressionMode.createDecompressingChannel(CompressedSource.java:110)
    at org.apache.beam.sdk.io.CompressedSource$CompressedReader.startReading(CompressedSource.java:417)
    at org.apache.beam.sdk.io.FileBasedSource$FileBasedReader.startImpl(FileBasedSource.java:476)
    at org.apache.beam.sdk.io.OffsetBasedSource$OffsetBasedReader.start(OffsetBasedSource.java:249)
    at org.apache.beam.sdk.io.ReadAllViaFileBasedSource$ReadFileRangesFn.process(ReadAllViaFileBasedSource.java:108)
    at org.apache.beam.sdk.io.ReadAllViaFileBasedSource$ReadFileRangesFn$DoFnInvoker.invokeProcessElement(Unknown Source)
    at org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:275)
    at org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:240)
    at org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate.processElement(DoFnRunnerWithMetricsUpdate.java:63)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator.processElement(DoFnOperator.java:462)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:712)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:690)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.emit(DoFnOperator.java:818)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.output(DoFnOperator.java:795)
    at org.apache.beam.runners.core.SimpleDoFnRunner.outputWindowedValue(SimpleDoFnRunner.java:309)
    at org.apache.beam.runners.core.SimpleDoFnRunner.access$700(SimpleDoFnRunner.java:77)
    at org.apache.beam.runners.core.SimpleDoFnRunner$DoFnProcessContext.output(SimpleDoFnRunner.java:621)
    at org.apache.beam.sdk.transforms.DoFnOutputReceivers$WindowedContextOutputReceiver.output(DoFnOutputReceivers.java:71)
    at org.apache.beam.sdk.transforms.MapElements$1.processElement(MapElements.java:122)
    at org.apache.beam.sdk.transforms.MapElements$1$DoFnInvoker.invokeProcessElement(Unknown Source)
    at org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:275)
    at org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:240)
    at org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate.processElement(DoFnRunnerWithMetricsUpdate.java:63)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator.processElement(DoFnOperator.java:462)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:712)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:690)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.emit(DoFnOperator.java:818)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.output(DoFnOperator.java:795)
    at org.apache.beam.runners.core.SimpleDoFnRunner.outputWindowedValue(SimpleDoFnRunner.java:309)
    at org.apache.beam.runners.core.SimpleDoFnRunner.access$700(SimpleDoFnRunner.java:77)
    at org.apache.beam.runners.core.SimpleDoFnRunner$DoFnProcessContext.outputWithTimestamp(SimpleDoFnRunner.java:628)
    at org.apache.beam.sdk.transforms.DoFnOutputReceivers$WindowedContextOutputReceiver.outputWithTimestamp(DoFnOutputReceivers.java:80)
    at org.apache.beam.sdk.transforms.Reify$ExtractTimestampsFromValues$1.processElement(Reify.java:203)
    at org.apache.beam.sdk.transforms.Reify$ExtractTimestampsFromValues$1$DoFnInvoker.invokeProcessElement(Unknown Source)
    at org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:275)
    at org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:240)
    at org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate.processElement(DoFnRunnerWithMetricsUpdate.java:63)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator.processElement(DoFnOperator.java:462)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:712)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:690)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.emit(DoFnOperator.java:818)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.output(DoFnOperator.java:795)
    at org.apache.beam.runners.core.SimpleDoFnRunner.outputWindowedValue(SimpleDoFnRunner.java:309)
    at org.apache.beam.runners.core.SimpleDoFnRunner.access$700(SimpleDoFnRunner.java:77)
    at org.apache.beam.runners.core.SimpleDoFnRunner$DoFnProcessContext.output(SimpleDoFnRunner.java:621)
    at org.apache.beam.sdk.transforms.DoFnOutputReceivers$WindowedContextOutputReceiver.output(DoFnOutputReceivers.java:71)
    at org.apache.beam.sdk.transforms.ReifyTimestamps$RemoveWildcard$1.process(ReifyTimestamps.java:70)
    at org.apache.beam.sdk.transforms.ReifyTimestamps$RemoveWildcard$1$DoFnInvoker.invokeProcessElement(Unknown Source)
    at org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:275)
    at org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:240)
    at org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate.processElement(DoFnRunnerWithMetricsUpdate.java:63)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator.processElement(DoFnOperator.java:462)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:712)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:690)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.emit(DoFnOperator.java:818)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.output(DoFnOperator.java:795)
    at org.apache.beam.runners.core.SimpleDoFnRunner.outputWindowedValue(SimpleDoFnRunner.java:309)
    at org.apache.beam.runners.core.SimpleDoFnRunner.access$700(SimpleDoFnRunner.java:77)
    at org.apache.beam.runners.core.SimpleDoFnRunner$DoFnProcessContext.output(SimpleDoFnRunner.java:621)
    at org.apache.beam.sdk.transforms.DoFnOutputReceivers$WindowedContextOutputReceiver.output(DoFnOutputReceivers.java:71)
    at org.apache.beam.sdk.transforms.Reshuffle$1.processElement(Reshuffle.java:101)
    at org.apache.beam.sdk.transforms.Reshuffle$1$DoFnInvoker.invokeProcessElement(Unknown Source)
    at org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:275)
    at org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:240)
    at org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate.processElement(DoFnRunnerWithMetricsUpdate.java:63)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator.processElement(DoFnOperator.java:462)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.pushToOperator(OperatorChain.java:579)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:554)
    at org.apache.flink.streaming.runtime.tasks.OperatorChain$CopyingChainingOutput.collect(OperatorChain.java:534)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:712)
    at org.apache.flink.streaming.api.operators.AbstractStreamOperator$CountingOutput.collect(AbstractStreamOperator.java:690)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.emit(DoFnOperator.java:818)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator$BufferedOutputManager.output(DoFnOperator.java:795)
    at org.apache.beam.runners.core.GroupAlsoByWindowViaWindowSetNewDoFn$1.outputWindowedValue(GroupAlsoByWindowViaWindowSetNewDoFn.java:99)
    at org.apache.beam.runners.core.GroupAlsoByWindowViaWindowSetNewDoFn$1.outputWindowedValue(GroupAlsoByWindowViaWindowSetNewDoFn.java:92)
    at org.apache.beam.runners.core.ReduceFnRunner.lambda$onTrigger$1(ReduceFnRunner.java:1057)
    at org.apache.beam.runners.core.ReduceFnContextFactory$OnTriggerContextImpl.output(ReduceFnContextFactory.java:438)
    at org.apache.beam.runners.core.SystemReduceFn.onTrigger(SystemReduceFn.java:125)
    at org.apache.beam.runners.core.ReduceFnRunner.onTrigger(ReduceFnRunner.java:1060)
    at org.apache.beam.runners.core.ReduceFnRunner.emit(ReduceFnRunner.java:930)
    at org.apache.beam.runners.core.ReduceFnRunner.processElements(ReduceFnRunner.java:368)
    at org.apache.beam.runners.core.GroupAlsoByWindowViaWindowSetNewDoFn.processElement(GroupAlsoByWindowViaWindowSetNewDoFn.java:136)
    at org.apache.beam.runners.core.GroupAlsoByWindowViaWindowSetNewDoFn$DoFnInvoker.invokeProcessElement(Unknown Source)
    at org.apache.beam.runners.core.SimpleDoFnRunner.invokeProcessElement(SimpleDoFnRunner.java:275)
    at org.apache.beam.runners.core.SimpleDoFnRunner.processElement(SimpleDoFnRunner.java:240)
    at org.apache.beam.runners.core.LateDataDroppingDoFnRunner.processElement(LateDataDroppingDoFnRunner.java:80)
    at org.apache.beam.runners.flink.metrics.DoFnRunnerWithMetricsUpdate.processElement(DoFnRunnerWithMetricsUpdate.java:63)
    at org.apache.beam.runners.flink.translation.wrappers.streaming.DoFnOperator.processElement(DoFnOperator.java:462)
    at org.apache.flink.streaming.runtime.io.StreamInputProcessor.processInput(StreamInputProcessor.java:202)
    at org.apache.flink.streaming.runtime.tasks.OneInputStreamTask.run(OneInputStreamTask.java:105)
    at org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:300)
    at org.apache.flink.runtime.taskmanager.Task.run(Task.java:711)
    at java.lang.Thread.run(Thread.java:748)
...