You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@beam.apache.org by "liyuntian (JIRA)" <ji...@apache.org> on 2017/04/28 08:16:04 UTC
[jira] [Closed] (BEAM-2109) No Route to Host from
etl-dev-05/xx.xx.xx.xx to bchcluster:8020
[ https://issues.apache.org/jira/browse/BEAM-2109?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
liyuntian closed BEAM-2109.
---------------------------
Resolution: Not A Problem
Fix Version/s: 0.6.0
> No Route to Host from etl-dev-05/xx.xx.xx.xx to bchcluster:8020
> ----------------------------------------------------------------
>
> Key: BEAM-2109
> URL: https://issues.apache.org/jira/browse/BEAM-2109
> Project: Beam
> Issue Type: Bug
> Components: runner-spark
> Environment: spark1.6.2 Hadoop 2.6.0
> Reporter: liyuntian
> Assignee: Amit Sela
> Fix For: 0.6.0
>
>
> I submit a spark job using "spark-submit --class test.testspark --executor-memory 10g artifactid.jar jobname spark://10.139.7.28:7077",It run well and I can see it run in my 5 worker,but when I submit a beam job using the same data ,I always get the error:
> 17/04/28 11:27:00 INFO scheduler.TaskSetManager: Starting task 1.1 in stage 1.0 (TID 37, etl-dev-02, partition 1,PROCESS_LOCAL, 3331 bytes)
> 17/04/28 11:27:01 WARN scheduler.TaskSetManager: Lost task 0.3 in stage 1.0 (TID 36, etl-dev-01): java.lang.RuntimeException: java.net.NoRouteToHostException: No Route to Host from etl-dev-01/10.139.7.26 to bchcluster:8020 failed on socket timeout exception: java.net.NoRouteToHostException: No route to host; For more details see: http://wiki.apache.org/hadoop/NoRouteToHost
> at org.apache.beam.sdk.io.hdfs.HDFSFileSource.validate(HDFSFileSource.java:351)
> at org.apache.beam.sdk.io.hdfs.HDFSFileSource.createReader(HDFSFileSource.java:330)
> at org.apache.beam.runners.spark.io.SourceRDD$Bounded.createReader(SourceRDD.java:169)
> at org.apache.beam.runners.spark.io.SourceRDD$Bounded.access$000(SourceRDD.java:54)
> at org.apache.beam.runners.spark.io.SourceRDD$Bounded$1.<init>(SourceRDD.java:114)
> at org.apache.beam.runners.spark.io.SourceRDD$Bounded.compute(SourceRDD.java:111)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.CacheManager.getOrCompute(CacheManager.scala:69)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:268)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:227)
> at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> at java.lang.Thread.run(Thread.java:745)
> Caused by: java.net.NoRouteToHostException: No Route to Host from etl-dev-01/10.139.7.26 to bchcluster:8020 failed on socket timeout exception: java.net.NoRouteToHostException: No route to host; For more details see: http://wiki.apache.org/hadoop/NoRouteToHost
> at sun.reflect.NativeConstructorAccessorImpl.newInstance0(Native Method)
> at sun.reflect.NativeConstructorAccessorImpl.newInstance(NativeConstructorAccessorImpl.java:57)
> at sun.reflect.DelegatingConstructorAccessorImpl.newInstance(DelegatingConstructorAccessorImpl.java:45)
> at java.lang.reflect.Constructor.newInstance(Constructor.java:526)
> at org.apache.hadoop.net.NetUtils.wrapWithMessage(NetUtils.java:791)
> at org.apache.hadoop.net.NetUtils.wrapException(NetUtils.java:757)
> at org.apache.hadoop.ipc.Client.call(Client.java:1472)
> at org.apache.hadoop.ipc.Client.call(Client.java:1399)
> at org.apache.hadoop.ipc.ProtobufRpcEngine$Invoker.invoke(ProtobufRpcEngine.java:232)
> at com.sun.proxy.$Proxy44.getFileInfo(Unknown Source)
> at org.apache.hadoop.hdfs.protocolPB.ClientNamenodeProtocolTranslatorPB.getFileInfo(ClientNamenodeProtocolTranslatorPB.java:752)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:606)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:187)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:102)
> at com.sun.proxy.$Proxy45.getFileInfo(Unknown Source)
> at org.apache.hadoop.hdfs.DFSClient.getFileInfo(DFSClient.java:1988)
> at org.apache.hadoop.hdfs.DistributedFileSystem$18.doCall(DistributedFileSystem.java:1118)
> at org.apache.hadoop.hdfs.DistributedFileSystem$18.doCall(DistributedFileSystem.java:1114)
> at org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81)
> at org.apache.hadoop.hdfs.DistributedFileSystem.getFileStatus(DistributedFileSystem.java:1114)
> at org.apache.hadoop.fs.Globber.getFileStatus(Globber.java:57)
> at org.apache.hadoop.fs.Globber.glob(Globber.java:252)
> at org.apache.hadoop.fs.FileSystem.globStatus(FileSystem.java:1625)
> at org.apache.beam.sdk.io.hdfs.HDFSFileSource$7.run(HDFSFileSource.java:343)
> at org.apache.beam.sdk.io.hdfs.HDFSFileSource$7.run(HDFSFileSource.java:338)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:415)
> at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1628)
> at org.apache.beam.sdk.io.hdfs.HDFSFileSource.validate(HDFSFileSource.java:338)
> ... 36 more
> Caused by: java.net.NoRouteToHostException: No route to host
> at sun.nio.ch.SocketChannelImpl.checkConnect(Native Method)
> at sun.nio.ch.SocketChannelImpl.finishConnect(SocketChannelImpl.java:739)
> at org.apache.hadoop.net.SocketIOWithTimeout.connect(SocketIOWithTimeout.java:206)
> at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:530)
> at org.apache.hadoop.net.NetUtils.connect(NetUtils.java:494)
> at org.apache.hadoop.ipc.Client$Connection.setupConnection(Client.java:607)
> at org.apache.hadoop.ipc.Client$Connection.setupIOstreams(Client.java:705)
> at org.apache.hadoop.ipc.Client$Connection.access$2800(Client.java:368)
> at org.apache.hadoop.ipc.Client.getConnection(Client.java:1521)
> at org.apache.hadoop.ipc.Client.call(Client.java:1438)
> ... 61 more
> 17/04/28 11:27:01 ERROR scheduler.TaskSetManager: Task 0 in stage 1.0 failed 4 times; aborting job
> 17/04/28 11:27:01 INFO scheduler.TaskSchedulerImpl: Cancelling stage 1
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)