hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Sandy Ryza (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAPREDUCE-5487) In task processes, JobConf is unnecessarily loaded again in Limits
Date Wed, 04 Dec 2013 01:52:35 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-5487?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13838478#comment-13838478
] 

Sandy Ryza commented on MAPREDUCE-5487:
---------------------------------------

Yup, there should be no changes in those cases I missed something.  In task processes, we
create a JobConf with the cluster configs, use it to initialize Limits, and then load the
user configs.  So the user configs do not have a chance to affect Limits.  In all other cases,
the limits are loaded from the cluster config exactly as before.


> In task processes, JobConf is unnecessarily loaded again in Limits
> ------------------------------------------------------------------
>
>                 Key: MAPREDUCE-5487
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-5487
>             Project: Hadoop Map/Reduce
>          Issue Type: Improvement
>          Components: performance, task
>    Affects Versions: 2.1.0-beta
>            Reporter: Sandy Ryza
>            Assignee: Sandy Ryza
>             Fix For: 2.4.0
>
>         Attachments: MAPREDUCE-5487-1.patch, MAPREDUCE-5487.patch
>
>
> Limits statically loads a JobConf, which incurs costs of reading files from disk and
parsing XML.  The contents of this JobConf are identical to the one loaded by YarnChild (before
adding job.xml as a resource).  Allowing Limits to initialize with the JobConf loaded in YarnChild
would reduce task startup time.



--
This message was sent by Atlassian JIRA
(v6.1#6144)

Mime
View raw message