[
https://issues.apache.org/jira/browse/MAPREDUCE-3685?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13232701#comment-13232701
]
anty.rao commented on MAPREDUCE-3685:
-------------------------------------
The bugs i reported are very clear on a glance for anyone who know the nuts and
bolts of mapreduce implementation.As for the attached patch is also very simple
and straight.
I have done A LOG OF tests comparing the overall mapreduce performance in
hadoop-0.23.0 and hadoop-0.20.*,,,the results is dispointing for me, mapreduce
performance in hadoop-0.23.0 is worse than that in hadoop-0.20.*,,
after digging through the code of hadoop-0.23.0, i was astonished by so many
bugs that i reported.
i was wondering that do they do any performance evaluation before release these
codes? Maybe hadoop-0.23.0 isn't used in production cases, currently no one
care about the performance of mapreduce.
Which version should i generate patch against? directly against the trunk
> There are some bugs in implementation of MergeManager
> -----------------------------------------------------
>
> Key: MAPREDUCE-3685
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3685
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: mrv2
> Affects Versions: 0.23.1
> Reporter: anty.rao
> Assignee: Zhihong Yu
> Priority: Minor
> Fix For: 0.24.0
>
> Attachments: MAPREDUCE-3685-branch-0.23.1.patch,
> MAPREDUCE-3685-branch-0.23.1.patch, MAPREDUCE-3685.patch
>
>
--
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
