[
https://issues.apache.org/jira/browse/HADOOP-910?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12571301#action_12571301
]
Devaraj Das commented on HADOOP-910:
------------------------------------
Code looks good. Some comments:
1) The path returned by the localfs merge need not be converted to a fully
qualified path since these files are guaranteed to be in the localfs
2) The localfs merge is passed an array of paths to merge. The paths are
initially stored in a List and an array is then obtained from that List. The
List can be eliminated.
3) The check for where a map output file finally went to should be based on the
filesystem of the path returned.
> Reduces can do merges for the on-disk map output files in parallel with their
> copying
> -------------------------------------------------------------------------------------
>
> Key: HADOOP-910
> URL: https://issues.apache.org/jira/browse/HADOOP-910
> Project: Hadoop Core
> Issue Type: Improvement
> Components: mapred
> Reporter: Devaraj Das
> Assignee: Amar Kamat
> Attachments: HADOOP-910-review.patch, HADOOP-910.patch
>
>
> Proposal to extend the parallel in-memory-merge/copying, that is being done
> as part of HADOOP-830, to the on-disk files.
> Today, the Reduces dump the map output files to disk and the final merge
> happens only after all the map outputs have been collected. It might make
> sense to parallelize this part. That is, whenever a Reduce has collected
> io.sort.factor number of segments on disk, it initiates a merge of those and
> creates one big segment. If the rate of copying is faster than the merge, we
> can probably have multiple threads doing parallel merges of independent sets
> of io.sort.factor number of segments. If the rate of copying is not as fast
> as merge, we stand to gain a lot - at the end of copying of all the map
> outputs, we will be left with a small number of segments for the final merge
> (which hopefully will feed the reduce directly (via the RawKeyValueIterator)
> without having to hit the disk for writing additional output segments).
> If the disk bandwidth is higher than the network bandwidth, we have a good
> story, I guess, to do such a thing.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
