[
https://issues.apache.org/jira/browse/MAPREDUCE-4815?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14363745#comment-14363745
]
Ivan Bella commented on MAPREDUCE-4815:
---------------------------------------
[~l201514] I work with Dave and it appears after reviewing the last patch that
the basic problem we reported still exists. Basically if mergePaths is called
from two reducers at the same time, and they have output files in the same
subdirectory (the key is subdirectory here) then we will get the situation as
previously described. So say the working directory is dir.1, and two reducers
are putting files in dir.1/dir.2, then this will non-deterministically result
in one of the reducers creating a dir.1/dir.2/dir.2. We were in addition
seeing that files were being put in dir.1/dir.2/dir.2 which should have been
moved into dir.1/dir.2. We will deploy this patch and confirm.
> Speed up FileOutputCommitter#commitJob for many output files
> ------------------------------------------------------------
>
> Key: MAPREDUCE-4815
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-4815
> Project: Hadoop Map/Reduce
> Issue Type: Improvement
> Components: mrv2
> Affects Versions: 0.23.3, 2.0.1-alpha, 2.4.1
> Reporter: Jason Lowe
> Assignee: Siqi Li
> Labels: perfomance
> Fix For: 2.7.0
>
> Attachments: MAPREDUCE-4815.v10.patch, MAPREDUCE-4815.v11.patch,
> MAPREDUCE-4815.v12.patch, MAPREDUCE-4815.v13.patch, MAPREDUCE-4815.v14.patch,
> MAPREDUCE-4815.v15.patch, MAPREDUCE-4815.v16.patch, MAPREDUCE-4815.v17.patch,
> MAPREDUCE-4815.v3.patch, MAPREDUCE-4815.v4.patch, MAPREDUCE-4815.v5.patch,
> MAPREDUCE-4815.v6.patch, MAPREDUCE-4815.v7.patch, MAPREDUCE-4815.v8.patch,
> MAPREDUCE-4815.v9.patch
>
>
> If a job generates many files to commit then the commitJob method call at the
> end of the job can take minutes. This is a performance regression from 1.x,
> as 1.x had the tasks commit directly to the final output directory as they
> were completing and commitJob had very little to do. The commit work was
> processed in parallel and overlapped the processing of outstanding tasks. In
> 0.23/2.x, the commit is single-threaded and waits until all tasks have
> completed before commencing.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
