[ 
https://issues.apache.org/jira/browse/HDFS-15643?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17222785#comment-17222785
 ] 

Akira Ajisaka commented on HDFS-15643:
--------------------------------------


Error log:
{noformat}
2020-10-29 04:55:00,418 [DataXceiver for client /127.0.0.1:60824 [Getting 
checksum for block 
groupBP-406455512-192.168.249.5-1603947295509:blk_-9223372036854775792_1001]] 
ERROR datanode.DataNode (DataXceiver.java:run(3
24)) - 127.0.0.1:36907:DataXceiver error processing BLOCK_GROUP_CHECKSUM 
operation  src: /127.0.0.1:60824 dst: /127.0.0.1:36907
java.lang.UnsupportedOperationException
        at java.nio.ByteBuffer.array(ByteBuffer.java:994)
        at 
org.apache.hadoop.hdfs.server.datanode.erasurecode.StripedBlockChecksumReconstructor.reconstruct(StripedBlockChecksumReconstructor.java:90)
        at 
org.apache.hadoop.hdfs.server.datanode.BlockChecksumHelper$BlockGroupNonStripedChecksumComputer.recalculateChecksum(BlockChecksumHelper.java:711)
        at 
org.apache.hadoop.hdfs.server.datanode.BlockChecksumHelper$BlockGroupNonStripedChecksumComputer.compute(BlockChecksumHelper.java:489)
        at 
org.apache.hadoop.hdfs.server.datanode.DataXceiver.blockGroupChecksum(DataXceiver.java:1047)
        at 
org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.opStripedBlockChecksum(Receiver.java:327)
        at 
org.apache.hadoop.hdfs.protocol.datatransfer.Receiver.processOp(Receiver.java:119)
        at 
org.apache.hadoop.hdfs.server.datanode.DataXceiver.run(DataXceiver.java:292)
        at java.lang.Thread.run(Thread.java:748)
2020-10-29 04:55:00,418 [Time-limited test] WARN  hdfs.FileChecksumHelper 
(FileChecksumHelper.java:checksumBlockGroup(679)) - 
src=/striped/stripedFileChecksum1, 
datanodes[1]=DatanodeInfoWithStorage[127.0.0.1:36907,DS-e9365b1c-9803-4d66-ac04-9aa2de6181cd,DISK]
java.io.EOFException: Unexpected EOF while trying to read response from server
        at 
org.apache.hadoop.hdfs.protocolPB.PBHelperClient.vintPrefixed(PBHelperClient.java:528)
        at 
org.apache.hadoop.hdfs.FileChecksumHelper$StripedFileNonStripedChecksumComputer.tryDatanode(FileChecksumHelper.java:709)
        at 
org.apache.hadoop.hdfs.FileChecksumHelper$StripedFileNonStripedChecksumComputer.checksumBlockGroup(FileChecksumHelper.java:664)
        at 
org.apache.hadoop.hdfs.FileChecksumHelper$StripedFileNonStripedChecksumComputer.checksumBlocks(FileChecksumHelper.java:638)
        at 
org.apache.hadoop.hdfs.FileChecksumHelper$FileChecksumComputer.compute(FileChecksumHelper.java:252)
        at 
org.apache.hadoop.hdfs.DFSClient.getFileChecksumInternal(DFSClient.java:1851)
        at 
org.apache.hadoop.hdfs.DFSClient.getFileChecksumWithCombineMode(DFSClient.java:1871)
        at 
org.apache.hadoop.hdfs.DistributedFileSystem$34.doCall(DistributedFileSystem.java:1903)
        at 
org.apache.hadoop.hdfs.DistributedFileSystem$34.doCall(DistributedFileSystem.java:1900)
        at 
org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
        at 
org.apache.hadoop.hdfs.DistributedFileSystem.getFileChecksum(DistributedFileSystem.java:1917)
        at 
org.apache.hadoop.hdfs.TestFileChecksum.getFileChecksum(TestFileChecksum.java:602)
        at 
org.apache.hadoop.hdfs.TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery(TestFileChecksum.java:318)
        at 
org.apache.hadoop.hdfs.TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery11(TestFileChecksum.java:444)
        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$1.runReflectiveCall(FrameworkMethod.java:50)
        at 
org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
        at 
org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
        at 
org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
        at 
org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:298)
        at 
org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:292)
        at java.util.concurrent.FutureTask.run(FutureTask.java:266)
        at java.lang.Thread.run(Thread.java:748) {noformat}

> TestFileChecksumCompositeCrc fails intermittently
> -------------------------------------------------
>
>                 Key: HDFS-15643
>                 URL: https://issues.apache.org/jira/browse/HDFS-15643
>             Project: Hadoop HDFS
>          Issue Type: Sub-task
>            Reporter: Ahmed Hussein
>            Assignee: Ahmed Hussein
>            Priority: Critical
>              Labels: pull-request-available
>         Attachments: 
> TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery17.log, 
> org.apache.hadoop.hdfs.TestFileChecksum-output.txt, 
> org.apache.hadoop.hdfs.TestFileChecksum.txt
>
>          Time Spent: 3h 40m
>  Remaining Estimate: 0h
>
> There are many failures in {{TestFileChecksumCompositeCrc}}. The test cases 
> {{testStripedFileChecksumWithMissedDataBlocksRangeQueryXX}} fail. The 
> following is a sample of the stack trace in two of them Query7 and Query8.
> {code:bash}
> org.apache.hadoop.fs.PathIOException: `/striped/stripedFileChecksum1': Fail 
> to get block checksum for 
> LocatedStripedBlock{BP-1812707539-172.17.0.3-1602771351154:blk_-9223372036854775792_1001;
>  getBlockSize()=37748736; corrupt=false; offset=0; 
> locs=[DatanodeInfoWithStorage[127.0.0.1:36687,DS-b00139f0-4f28-4870-8f72-b726bd339e23,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:36303,DS-49a3c58e-da4a-4256-b1f9-893e4003ec94,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:43975,DS-ac278858-b6c8-424f-9e20-58d718dabe31,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:37507,DS-17f9d8d8-f8d3-443b-8df7-29416a2f5cb0,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:36441,DS-7e9d19b5-6220-465f-b33e-f8ed0e60fb07,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:42555,DS-ce679f5e-19fe-45b0-a0cd-8d8bec2f4735,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:39093,DS-4a7f54bb-dd39-4b5b-8dee-31a1b565cd7f,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:41699,DS-e1f939f3-37e7-413e-a522-934243477d81,DISK]];
>  indices=[1, 2, 3, 4, 5, 6, 7, 8]}
>       at 
> org.apache.hadoop.hdfs.FileChecksumHelper$StripedFileNonStripedChecksumComputer.checksumBlocks(FileChecksumHelper.java:640)
>       at 
> org.apache.hadoop.hdfs.FileChecksumHelper$FileChecksumComputer.compute(FileChecksumHelper.java:252)
>       at 
> org.apache.hadoop.hdfs.DFSClient.getFileChecksumInternal(DFSClient.java:1851)
>       at 
> org.apache.hadoop.hdfs.DFSClient.getFileChecksumWithCombineMode(DFSClient.java:1871)
>       at 
> org.apache.hadoop.hdfs.DistributedFileSystem$34.doCall(DistributedFileSystem.java:1902)
>       at 
> org.apache.hadoop.hdfs.DistributedFileSystem$34.doCall(DistributedFileSystem.java:1899)
>       at 
> org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
>       at 
> org.apache.hadoop.hdfs.DistributedFileSystem.getFileChecksum(DistributedFileSystem.java:1916)
>       at 
> org.apache.hadoop.hdfs.TestFileChecksum.getFileChecksum(TestFileChecksum.java:584)
>       at 
> org.apache.hadoop.hdfs.TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery(TestFileChecksum.java:295)
>       at 
> org.apache.hadoop.hdfs.TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery7(TestFileChecksum.java:377)
>       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$1.runReflectiveCall(FrameworkMethod.java:50)
>       at 
> org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
>       at 
> org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
>       at 
> org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
>       at 
> org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:298)
>       at 
> org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:292)
>       at java.util.concurrent.FutureTask.run(FutureTask.java:266)
>       at java.lang.Thread.run(Thread.java:748)
> {code}
>  
> {code:bash}
> Error Message
> `/striped/stripedFileChecksum1': Fail to get block checksum for 
> LocatedStripedBlock{BP-1299291876-172.17.0.3-1602771356932:blk_-9223372036854775792_1001;
>  getBlockSize()=37748736; corrupt=false; offset=0; 
> locs=[DatanodeInfoWithStorage[127.0.0.1:42217,DS-6c29e4b7-e4f1-4302-ad23-fb078f37d783,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:41307,DS-3d824f14-3cd0-46b1-bef1-caa808bf278d,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:37193,DS-eeb44ff5-fdf1-4774-b6cf-5be7c40147a9,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:39897,DS-36d2fbfc-64bc-405c-8360-735f1ad92e30,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:35545,DS-6fd42817-efea-416e-92fb-3e9034705142,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:39945,DS-501deff8-b6df-4cf0-9ac1-154a4253eec8,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:41359,DS-9b0449f5-377b-4a76-9eb6-0bcf2984b4bb,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:36123,DS-4184ab4a-079d-4b1c-a8cb-2ba22b0baafb,DISK]];
>  indices=[0, 1, 2, 3, 4, 6, 7, 8]}
> Stacktrace
> org.apache.hadoop.fs.PathIOException: `/striped/stripedFileChecksum1': Fail 
> to get block checksum for 
> LocatedStripedBlock{BP-1299291876-172.17.0.3-1602771356932:blk_-9223372036854775792_1001;
>  getBlockSize()=37748736; corrupt=false; offset=0; 
> locs=[DatanodeInfoWithStorage[127.0.0.1:42217,DS-6c29e4b7-e4f1-4302-ad23-fb078f37d783,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:41307,DS-3d824f14-3cd0-46b1-bef1-caa808bf278d,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:37193,DS-eeb44ff5-fdf1-4774-b6cf-5be7c40147a9,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:39897,DS-36d2fbfc-64bc-405c-8360-735f1ad92e30,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:35545,DS-6fd42817-efea-416e-92fb-3e9034705142,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:39945,DS-501deff8-b6df-4cf0-9ac1-154a4253eec8,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:41359,DS-9b0449f5-377b-4a76-9eb6-0bcf2984b4bb,DISK],
>  
> DatanodeInfoWithStorage[127.0.0.1:36123,DS-4184ab4a-079d-4b1c-a8cb-2ba22b0baafb,DISK]];
>  indices=[0, 1, 2, 3, 4, 6, 7, 8]}
>       at 
> org.apache.hadoop.hdfs.FileChecksumHelper$StripedFileNonStripedChecksumComputer.checksumBlocks(FileChecksumHelper.java:640)
>       at 
> org.apache.hadoop.hdfs.FileChecksumHelper$FileChecksumComputer.compute(FileChecksumHelper.java:252)
>       at 
> org.apache.hadoop.hdfs.DFSClient.getFileChecksumInternal(DFSClient.java:1851)
>       at 
> org.apache.hadoop.hdfs.DFSClient.getFileChecksumWithCombineMode(DFSClient.java:1871)
>       at 
> org.apache.hadoop.hdfs.DistributedFileSystem$34.doCall(DistributedFileSystem.java:1902)
>       at 
> org.apache.hadoop.hdfs.DistributedFileSystem$34.doCall(DistributedFileSystem.java:1899)
>       at 
> org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
>       at 
> org.apache.hadoop.hdfs.DistributedFileSystem.getFileChecksum(DistributedFileSystem.java:1916)
>       at 
> org.apache.hadoop.hdfs.TestFileChecksum.getFileChecksum(TestFileChecksum.java:584)
>       at 
> org.apache.hadoop.hdfs.TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery(TestFileChecksum.java:295)
>       at 
> org.apache.hadoop.hdfs.TestFileChecksum.testStripedFileChecksumWithMissedDataBlocksRangeQuery8(TestFileChecksum.java:388)
>       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$1.runReflectiveCall(FrameworkMethod.java:50)
>       at 
> org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
>       at 
> org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:47)
>       at 
> org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
>       at 
> org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:298)
>       at 
> org.junit.internal.runners.statements.FailOnTimeout$CallableStatement.call(FailOnTimeout.java:292)
>       at java.util.concurrent.FutureTask.run(FutureTask.java:266)
>       at java.lang.Thread.run(Thread.java:748)
> {code}
>  



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

---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to