hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Owen O'Malley (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-4063) Separate spill thresholds for serialization/accounting in MapTask
Date Fri, 05 Sep 2008 04:41:44 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-4063?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12628547#action_12628547
] 

Owen O'Malley commented on HADOOP-4063:
---------------------------------------

I don't understand the motivation for this patch. It is an incompatible change that I wouldn't
expect anyone to need. What is the use case?

> Separate spill thresholds for serialization/accounting in MapTask
> -----------------------------------------------------------------
>
>                 Key: HADOOP-4063
>                 URL: https://issues.apache.org/jira/browse/HADOOP-4063
>             Project: Hadoop Core
>          Issue Type: Improvement
>          Components: mapred
>            Reporter: Chris Douglas
>            Assignee: Chris Douglas
>            Priority: Minor
>             Fix For: 0.19.0
>
>         Attachments: 4063-0.patch, 4063-1.patch
>
>
> In MapTask, there is a single parameter controlling the threshold for starting a spill
thread concurrently with collection. However, some users may want to set different thresholds
for the serialization buffer (holding record bytes) and the accounting buffer (holding record
metadata).

-- 
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