Mailing-List: contact hadoop-dev-help@lucene.apache.org; run by ezmlm
Precedence: bulk
Reply-To: hadoop-dev@lucene.apache.org
Message-ID: <12044047.1178903475455.JavaMail.jira@brutus>
Date: Fri, 11 May 2007 10:11:15 -0700 (PDT)
From: "Devaraj Das (JIRA)" <jira@apache.org>
To: hadoop-dev@lucene.apache.org
Subject: [jira] Commented: (HADOOP-1350) Shuffle started taking a very long
 time after the HADOOP-1176 fix
In-Reply-To: <18319695.1178854095748.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-1350?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12495098 ] 

Devaraj Das commented on HADOOP-1350:
-------------------------------------

Investigation in progress. Should have something soon. Worst case is that we go back to the hack where we don't do chunked encoding for content-length < 2GB. That will handle all typical cases and also handle the extreme cases of large content-lengths with some performance loss.

> Shuffle started taking a very long time after the HADOOP-1176 fix
> -----------------------------------------------------------------
>
>                 Key: HADOOP-1350
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1350
>             Project: Hadoop
>          Issue Type: Bug
>          Components: mapred
>    Affects Versions: 0.13.0
>            Reporter: Devaraj Das
>         Assigned To: Devaraj Das
>            Priority: Blocker
>             Fix For: 0.13.0
>
>
> Shuffle phase started taking a very long time after the fix for HADOOP-1176.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.