[
https://issues.apache.org/jira/browse/MAPREDUCE-778?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13171008#comment-13171008
]
Hudson commented on MAPREDUCE-778:
----------------------------------
Integrated in Hadoop-Mapreduce-trunk-Commit #1468 (See
[https://builds.apache.org/job/Hadoop-Mapreduce-trunk-Commit/1468/])
MAPREDUCE-778. Rumen Anonymizer. (Amar Kamat and Chris Douglas via amarrk)
amarrk : http://svn.apache.org/viewcvs.cgi/?root=Apache-SVN&view=rev&rev=1215141
Files :
* /hadoop/common/trunk/hadoop-mapreduce-project/CHANGES.txt
* /hadoop/common/trunk/hadoop-mapreduce-project/ivy.xml
* /hadoop/common/trunk/hadoop-mapreduce-project/ivy/libraries.properties
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/contrib/gridmix/src/java/org/apache/hadoop/mapred/gridmix/GridmixJob.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/docs/src/documentation/content/xdocs/rumen.xml
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/tools/rumen/TestRumenAnonymization.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/tools/rumen/TestRumenFolder.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/test/mapred/org/apache/hadoop/tools/rumen/TestRumenJobTraces.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/Anonymizer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/Folder.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/HadoopLogsAnalyzer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/JobBuilder.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/JsonObjectMapperWriter.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/LoggedJob.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/LoggedLocation.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/LoggedNetworkTopology.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/LoggedTask.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/LoggedTaskAttempt.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/ParsedHost.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/ZombieCluster.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/ZombieJob.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/anonymization
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/anonymization/DataAnonymizer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/anonymization/WordList.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/anonymization/WordListAnonymizerUtility.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/AnonymizableDataType.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/ClassName.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/DataType.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/DefaultAnonymizableDataType.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/DefaultDataType.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/FileName.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/JobName.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/JobProperties.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/NodeName.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/QueueName.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/UserName.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/util
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/util/DefaultJobPropertiesParser.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/util/JobPropertyParser.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/datatypes/util/MapReduceJobPropertiesParser.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/serializers
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/serializers/BlockingSerializer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/serializers/DefaultAnonymizingRumenSerializer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/serializers/DefaultRumenSerializer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/serializers/ObjectStringSerializer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/state
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/state/State.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/state/StateDeserializer.java
*
/hadoop/common/trunk/hadoop-mapreduce-project/src/tools/org/apache/hadoop/tools/rumen/state/StatePool.java
> [Rumen] Need a standalone JobHistory log anonymizer
> ---------------------------------------------------
>
> Key: MAPREDUCE-778
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-778
> Project: Hadoop Map/Reduce
> Issue Type: New Feature
> Components: tools/rumen
> Affects Versions: 0.24.0
> Reporter: Hong Tang
> Assignee: Amar Kamat
> Labels: anonymization, rumen
> Fix For: 0.24.0
>
> Attachments: anonymizer.patch, anonymizer.py,
> mapreduce-778-v1.14-12.patch, mapreduce-778-v1.14-14.patch,
> mapreduce-778-v1.2-2.patch, same.py
>
>
> Job history logs contain a rich set of information that can help understand
> and characterize cluster workload and individual job execution. Examples of
> work that parses or utilizes job history include HADOOP-3585, MAPREDUCE-534,
> HDFS-459, MAPREDUCE-728, and MAPREDUCE-776. Some of the parsing tools
> developed in previous work already contains a component to anonymize the
> logs. It would be nice to combine these effort and have a common standalone
> tool that can anonymizes job history logs and preserve much of the structure
> of the files so that existing tools on top of job history logs continue work
> with no modification.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
