hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hadoop QA (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-1042) Improve the handling of failed map output fetches
Date Tue, 27 Feb 2007 22:22:06 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-1042?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12476420
] 

Hadoop QA commented on HADOOP-1042:
-----------------------------------

+1, because http://issues.apache.org/jira/secure/attachment/12352150/1042.new.patch applied
and successfully tested against trunk revision http://svn.apache.org/repos/asf/lucene/hadoop/trunk/512006.
Results are at http://lucene.zones.apache.org:8080/hudson/job/Hadoop-Patch

> Improve the handling of failed map output fetches
> -------------------------------------------------
>
>                 Key: HADOOP-1042
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1042
>             Project: Hadoop
>          Issue Type: Improvement
>          Components: mapred
>    Affects Versions: 0.11.2
>            Reporter: Devaraj Das
>         Assigned To: Devaraj Das
>         Attachments: 1042.new.patch, 1042.patch
>
>
> Currently, whenever fetch of a map output fails the corresponding MapOutputLocation is
added to a List datastructure for later retrial. But, if the failure was due to a lost task,
the entry that was added is not deleted. For such cases, unnecessary retrials will happen.
This situation should be prevented.

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


Mime
View raw message