Mailing-List: contact hadoop-dev-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hadoop-dev@lucene.apache.org
Message-ID: <32393664.1173815829459.JavaMail.jira@brutus>
Date: Tue, 13 Mar 2007 12:57:09 -0700 (PDT)
From: "Sameer Paranjpye (JIRA)" <jira@apache.org>
To: hadoop-dev@lucene.apache.org
Subject: [jira] Commented: (HADOOP-910) Reduces can do merges for the
 on-disk map output files in parallel with their copying
In-Reply-To: <1830903.1169189129949.JavaMail.jira@brutus>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/HADOOP-910?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12480530 ] 

Sameer Paranjpye commented on HADOOP-910:
-----------------------------------------

What was your specific observation Runping? We're already doing a lot of in-memory merges in parallel with the shuffle and from all the runs we've seen it looks like the shuffle/merge tracks the maps pretty closely.  Can we get some real data here because this feels like premature optimization.

> 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
>          Issue Type: Improvement
>          Components: mapred
>            Reporter: Devaraj Das
>         Assigned To: Gautam Kowshik
>
> 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.