hadoop-mapreduce-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Vinod Kumar Vavilapalli (Commented) (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAPREDUCE-3813) RackResolver should maintain a cache to avoid repetitive lookups.
Date Mon, 06 Feb 2012 19:15:59 GMT

    [ https://issues.apache.org/jira/browse/MAPREDUCE-3813?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13201480#comment-13201480
] 

Vinod Kumar Vavilapalli commented on MAPREDUCE-3813:
----------------------------------------------------

Allen, this is not for hostname resolution. This is the rack resolver plugin which finds out
the racks for a given set of hosts. Not every rack resolver plugin is fast enough, so we need
a cache to keep track of hosts whose racks are already resolved.
                
> RackResolver should maintain a cache to avoid repetitive lookups.
> -----------------------------------------------------------------
>
>                 Key: MAPREDUCE-3813
>                 URL: https://issues.apache.org/jira/browse/MAPREDUCE-3813
>             Project: Hadoop Map/Reduce
>          Issue Type: Sub-task
>          Components: mrv2, performance
>    Affects Versions: 0.23.0
>            Reporter: Vinod Kumar Vavilapalli
>            Assignee: Vinod Kumar Vavilapalli
>             Fix For: 0.23.1
>
>         Attachments: MAPREDUCE-3813-20120205.txt
>
>
> With the current code, during task creation, we repeatedly resolve hosts and RackResolver
doesn't cache any of the results. Caching will improve performance.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message