You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Martin Provencher (JIRA)" <ji...@apache.org> on 2011/03/31 20:22:05 UTC
[jira] [Updated] (MAHOUT-646) Cannot run Wikipedia example on
Amazon Elastic MapReduce (EMR)
[ https://issues.apache.org/jira/browse/MAHOUT-646?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Martin Provencher updated MAHOUT-646:
-------------------------------------
Status: Patch Available (was: Open)
To fix it, I've applied this patch :
===================================================================
--- examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java (revision 1087334)
+++ examples/src/main/java/org/apache/mahout/classifier/bayes/WikipediaDatasetCreatorDriver.java (working copy)
@@ -185,7 +185,7 @@
//TODO: job.setNumMapTasks(100);
job.setInputFormatClass(XmlInputFormat.class);
job.setReducerClass(WikipediaDatasetCreatorReducer.class);
- job.setOutputFormatClass(WikipediaDatasetCreatorOutputFormat.class);
+ //job.setOutputFormatClass(WikipediaDatasetCreatorOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path(input));
Path outPath = new Path(output);
> Cannot run Wikipedia example on Amazon Elastic MapReduce (EMR)
> --------------------------------------------------------------
>
> Key: MAHOUT-646
> URL: https://issues.apache.org/jira/browse/MAHOUT-646
> Project: Mahout
> Issue Type: Bug
> Components: Classification
> Affects Versions: 0.5
> Reporter: Martin Provencher
> Priority: Minor
>
> When I tried to run the Wikipedia example on EMR with all the categories existing in the Wikipedia dump, I got this error :
> org.apache.hadoop.ipc.RemoteException: org.apache.hadoop.hdfs.protocol.AlreadyBeingCreatedException: failed to create file /yatter.tagger/wikipedia/input/_temporary/_attempt__0000_r_000000_0/part-r-00000 for DFSClient_attempt_201103292134_0010_r_000000_0 on client 10.240.10.157 because current leaseholder is trying to recreate file.
> at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:1045)
> at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:981)
> at org.apache.hadoop.hdfs.server.namenode.NameNode.create(NameNode.java:377)
> at sun.reflect.GeneratedMethodAccessor7.invoke(Unknown Source)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
> at java.lang.reflect.Method.invoke(Method.java:597)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:508)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:961)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:957)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:396)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:955)
> at org.apache.hadoop.ipc.Client.call(Client.java:740)
> at org.apache.hadoop.ipc.RPC$Invoker.invoke(RPC.java:220)
> at $Proxy1.create(Unknown Source)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
> at java.lang.reflect.Method.invoke(Method.java:597)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:82)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:59)
> at $Proxy1.create(Unknown Source)
> at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream.<init>(DFSClient.java:2709)
> at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:491)
> at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:195)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:524)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:505)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:412)
> at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:128)
> at org.apache.mahout.classifier.bayes.MultipleTextOutputFormat.getBaseRecordWriter(MultipleTextOutputFormat.java:41)
> at org.apache.mahout.classifier.bayes.MultipleOutputFormat$1.write(MultipleOutputFormat.java:81)
> at org.apache.hadoop.mapred.ReduceTask$NewTrackingRecordWriter.write(ReduceTask.java:517)
> at org.apache.hadoop.mapreduce.TaskInputOutputContext.write(TaskInputOutputContext.java:80)
> at org.apache.mahout.classifier.bayes.WikipediaDatasetCreatorReducer.reduce(WikipediaDatasetCreatorReducer.java:35)
> at org.apache.mahout.classifier.bayes.WikipediaDatasetCreatorReducer.reduce(WikipediaDatasetCreatorReducer.java:28)
> at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:176)
> at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:575)
> at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:412)
> at org.apache.hadoop.mapred.Child.main(Child.java:170)
> org.apache.hadoop.ipc.RemoteException: java.io.IOException: failed to create file /yatter.tagger/wikipedia/input/_temporary/_attempt__0000_r_000000_0/part-r-00000 on client 10.240.10.157 either because the filename is invalid or the file exists
> at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFileInternal(FSNamesystem.java:1092)
> at org.apache.hadoop.hdfs.server.namenode.FSNamesystem.startFile(FSNamesystem.java:981)
> at org.apache.hadoop.hdfs.server.namenode.NameNode.create(NameNode.java:377)
> at sun.reflect.GeneratedMethodAccessor7.invoke(Unknown Source)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
> at java.lang.reflect.Method.invoke(Method.java:597)
> at org.apache.hadoop.ipc.RPC$Server.call(RPC.java:508)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:961)
> at org.apache.hadoop.ipc.Server$Handler$1.run(Server.java:957)
> at java.security.AccessController.doPrivileged(Native Method)
> at javax.security.auth.Subject.doAs(Subject.java:396)
> at org.apache.hadoop.ipc.Server$Handler.run(Server.java:955)
> at org.apache.hadoop.ipc.Client.call(Client.java:740)
> at org.apache.hadoop.ipc.RPC$Invoker.invoke(RPC.java:220)
> at $Proxy1.create(Unknown Source)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:25)
> at java.lang.reflect.Method.invoke(Method.java:597)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invokeMethod(RetryInvocationHandler.java:82)
> at org.apache.hadoop.io.retry.RetryInvocationHandler.invoke(RetryInvocationHandler.java:59)
> at $Proxy1.create(Unknown Source)
> at org.apache.hadoop.hdfs.DFSClient$DFSOutputStream.<init>(DFSClient.java:2709)
> at org.apache.hadoop.hdfs.DFSClient.create(DFSClient.java:491)
> at org.apache.hadoop.hdfs.DistributedFileSystem.create(DistributedFileSystem.java:195)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:524)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:505)
> at org.apache.hadoop.fs.FileSystem.create(FileSystem.java:412)
> at org.apache.hadoop.mapreduce.lib.output.TextOutputFormat.getRecordWriter(TextOutputFormat.java:128)
> at org.apache.mahout.classifier.bayes.MultipleTextOutputFormat.getBaseRecordWriter(MultipleTextOutputFormat.java:41)
> at org.apache.mahout.classifier.bayes.MultipleOutputFormat$1.write(MultipleOutputFormat.java:81)
> at org.apache.hadoop.mapred.ReduceTask$NewTrackingRecordWriter.write(ReduceTask.java:517)
> at org.apache.hadoop.mapreduce.TaskInputOutputContext.write(TaskInputOutputContext.java:80)
> at org.apache.mahout.classifier.bayes.WikipediaDatasetCreatorReducer.reduce(WikipediaDatasetCreatorReducer.java:35)
> at org.apache.mahout.classifier.bayes.WikipediaDatasetCreatorReducer.reduce(WikipediaDatasetCreatorReducer.java:28)
> at org.apache.hadoop.mapreduce.Reducer.run(Reducer.java:176)
> at org.apache.hadoop.mapred.ReduceTask.runNewReducer(ReduceTask.java:575)
> at org.apache.hadoop.mapred.ReduceTask.run(ReduceTask.java:412)
> at org.apache.hadoop.mapred.Child.main(Child.java:170)
> 4 more :
> org.apache.hadoop.ipc.RemoteException: java.io.IOException: failed to create file /yatter.tagger/wikipedia/input/_temporary/_attempt__0000_r_000000_0/part-r-00000 on client 10.240.10.157 either because the filename is invalid or the file exists
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira