[
https://issues.apache.org/jira/browse/MAPREDUCE-5225?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Zhijie Shen updated MAPREDUCE-5225:
-----------------------------------
Attachment: MAPREDUCE-5225.1.patch
The patch makes SplitSampler jump by sampling step when it does sampling. Then,
the behavior of SplitSampler in both mapred and mapreduce is identical.
> SplitSampler in mapreduce.lib should use a SPLIT_STEP to jump around splits
> ---------------------------------------------------------------------------
>
> Key: MAPREDUCE-5225
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-5225
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Reporter: Zhijie Shen
> Assignee: Zhijie Shen
> Attachments: MAPREDUCE-5225.1.patch
>
>
> Now, SplitSampler only samples the first maxSplitsSampled splits, caused by
> MAPREDUCE-1820. However, jumping around all splits is in general preferable
> than the first N splits.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
