Piotr Nowojski created FLINK-17663:
--------------------------------------
Summary: CheckpointBarrierUnaligner.getFlattenedChannelIndex can
throw ArrayIndexOutOfBoundsException
Key: FLINK-17663
URL: https://issues.apache.org/jira/browse/FLINK-17663
Project: Flink
Issue Type: Bug
Components: Runtime / Network
Reporter: Piotr Nowojski
Fix For: 1.11.0
{{KeyedStateCheckpointingITCase}} with enabled unaligned checkpoints always
life locks because of infinite failure loop caused by the following exception:
{noformat}
java.io.IOException: java.lang.ArrayIndexOutOfBoundsException: 1
at
org.apache.flink.runtime.io.network.partition.consumer.InputChannel.checkError(InputChannel.java:224)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.RemoteInputChannel.getNextBuffer(RemoteInputChannel.java:173)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.waitAndGetNextData(SingleInputGate.java:637)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.getNextBufferOrEvent(SingleInputGate.java:615)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.SingleInputGate.pollNext(SingleInputGate.java:603)
~[classes/:?]
at
org.apache.flink.runtime.taskmanager.InputGateWithMetrics.pollNext(InputGateWithMetrics.java:105)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.UnionInputGate.waitAndGetNextData(UnionInputGate.java:193)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.UnionInputGate.getNextBufferOrEvent(UnionInputGate.java:168)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.UnionInputGate.pollNext(UnionInputGate.java:160)
~[classes/:?]
at
org.apache.flink.streaming.runtime.io.CheckpointedInputGate.pollNext(CheckpointedInputGate.java:110)
~[classes/:?]
at
org.apache.flink.streaming.runtime.io.StreamTaskNetworkInput.emitNext(StreamTaskNetworkInput.java:136)
~[classes/:?]
at
org.apache.flink.streaming.runtime.io.StreamOneInputProcessor.processInput(StreamOneInputProcessor.java:66)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.StreamTask.processInput(StreamTask.java:340)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxStep(MailboxProcessor.java:206)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.mailbox.MailboxProcessor.runMailboxLoop(MailboxProcessor.java:196)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.StreamTask.runMailboxLoop(StreamTask.java:553)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:525)
~[classes/:?]
at org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:713)
[classes/:?]
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:539)
[classes/:?]
at java.lang.Thread.run(Thread.java:748) [?:1.8.0_131]
Suppressed: java.lang.AssertionError: Test ineffective: Function
cleanly finished without ever failing.
at org.junit.Assert.fail(Assert.java:88) ~[junit-4.12.jar:4.12]
at
org.apache.flink.test.checkpointing.KeyedStateCheckpointingITCase$OnceFailingPartitionedSum.close(KeyedStateCheckpointingITCase.java:325)
~[test-classes/:?]
at
org.apache.flink.api.common.functions.util.FunctionUtils.closeFunction(FunctionUtils.java:43)
~[classes/:?]
at
org.apache.flink.streaming.api.operators.AbstractUdfStreamOperator.dispose(AbstractUdfStreamOperator.java:117)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.StreamTask.disposeAllOperators(StreamTask.java:698)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.StreamTask.cleanUpInvoke(StreamTask.java:630)
~[classes/:?]
at
org.apache.flink.streaming.runtime.tasks.StreamTask.invoke(StreamTask.java:537)
~[classes/:?]
at
org.apache.flink.runtime.taskmanager.Task.doRun(Task.java:713) [classes/:?]
at org.apache.flink.runtime.taskmanager.Task.run(Task.java:539)
[classes/:?]
at java.lang.Thread.run(Thread.java:748) [?:1.8.0_131]
Caused by: java.lang.ArrayIndexOutOfBoundsException: 1
at
org.apache.flink.streaming.runtime.io.CheckpointBarrierUnaligner.getFlattenedChannelIndex(CheckpointBarrierUnaligner.java:256)
~[classes/:?]
at
org.apache.flink.streaming.runtime.io.CheckpointBarrierUnaligner.access$000(CheckpointBarrierUnaligner.java:55)
~[classes/:?]
at
org.apache.flink.streaming.runtime.io.CheckpointBarrierUnaligner$ThreadSafeUnaligner.notifyBarrierReceived(CheckpointBarrierUnaligner.java:311)
~[classes/:?]
at
org.apache.flink.runtime.io.network.partition.consumer.RemoteInputChannel.onBuffer(RemoteInputChannel.java:472)
~[classes/:?]
at
org.apache.flink.runtime.io.network.netty.CreditBasedPartitionRequestClientHandler.decodeBufferOrEvent(CreditBasedPartitionRequestClientHandler.java:303)
~[classes/:?]
at
org.apache.flink.runtime.io.network.netty.CreditBasedPartitionRequestClientHandler.decodeMsg(CreditBasedPartitionRequestClientHandler.java:267)
~[classes/:?]
at
org.apache.flink.runtime.io.network.netty.CreditBasedPartitionRequestClientHandler.channelRead(CreditBasedPartitionRequestClientHandler.java:182)
~[classes/:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:374)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:360)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:352)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.runtime.io.network.netty.NettyMessageClientDecoderDelegate.channelRead(NettyMessageClientDecoderDelegate.java:115)
~[classes/:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:374)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:360)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.fireChannelRead(AbstractChannelHandlerContext.java:352)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.DefaultChannelPipeline$HeadContext.channelRead(DefaultChannelPipeline.java:1421)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:374)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.AbstractChannelHandlerContext.invokeChannelRead(AbstractChannelHandlerContext.java:360)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.DefaultChannelPipeline.fireChannelRead(DefaultChannelPipeline.java:930)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.nio.AbstractNioByteChannel$NioByteUnsafe.read(AbstractNioByteChannel.java:163)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKey(NioEventLoop.java:697)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeysOptimized(NioEventLoop.java:632)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.processSelectedKeys(NioEventLoop.java:549)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.channel.nio.NioEventLoop.run(NioEventLoop.java:511)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.util.concurrent.SingleThreadEventExecutor$5.run(SingleThreadEventExecutor.java:918)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
at
org.apache.flink.shaded.netty4.io.netty.util.internal.ThreadExecutorMap$2.run(ThreadExecutorMap.java:74)
~[flink-shaded-netty-4.1.39.Final-10.0.jar:?]
... 1 more
{noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)