Mailing-List: contact mapreduce-issues-help@hadoop.apache.org; run by ezmlm
Precedence: bulk
Reply-To: mapreduce-issues@hadoop.apache.org
Date: Mon, 21 Jan 2013 21:18:14 +0000 (UTC)
From: "Siddharth Seth (JIRA)" <jira@apache.org>
To: mapreduce-issues@hadoop.apache.org
Message-ID: <JIRA.12628073.1358443637841.169832.1358803094445@arcas>
In-Reply-To: <JIRA.12628073.1358443637841@arcas>
References: <JIRA.12628073.1358443637841@arcas>
Subject: [jira] [Commented] (MAPREDUCE-4946) Type conversion of map
 completion events leads to performance problems with large jobs
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 7bit


    [ https://issues.apache.org/jira/browse/MAPREDUCE-4946?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13559107#comment-13559107 ] 

Siddharth Seth commented on MAPREDUCE-4946:
-------------------------------------------

The change looks good to me. Jason, could you please post a patch for branch-0.23 as well.

Agreed. TaskUmbilical using TaskAttemptCompletionEvents seems like a longer term change - the conversions ends up getting pushed to individual tasks, unless Task itself is change to work with mrv2 constructs.
                
> Type conversion of map completion events leads to performance problems with large jobs
> --------------------------------------------------------------------------------------
>
>                 Key: MAPREDUCE-4946
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-4946
>             Project: Hadoop Map/Reduce
>          Issue Type: Bug
>          Components: mr-am
>    Affects Versions: 2.0.2-alpha, 0.23.5
>            Reporter: Jason Lowe
>            Assignee: Jason Lowe
>            Priority: Critical
>         Attachments: MAPREDUCE-4946.patch
>
>
> We've seen issues with large jobs (e.g.: 13,000 maps and 3,500 reduces) where reducers fail to connect back to the AM after being launched due to connection timeout.  Looking at stack traces of the AM during this time we see a lot of IPC servers stuck waiting for a lock to get the application ID while type converting the map completion events.  What's odd is that normally getting the application ID should be very cheap, but in this case we're type-converting thousands of map completion events for *each* reducer connecting.  That means we end up type-converting the map completion events over 45 million times during the lifetime of the example job (13,000 * 3,500).
> We either need to make the type conversion much cheaper (i.e.: lockless or at least read-write locked) or, even better, store the completion events in a form that does not require type conversion when serving them up to reducers.

--
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