hive-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Brock Noland (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HIVE-4936) PTest increase performance by parallelizing rsync
Date Thu, 25 Jul 2013 20:47:50 GMT

    [ https://issues.apache.org/jira/browse/HIVE-4936?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13720032#comment-13720032
] 

Brock Noland commented on HIVE-4936:
------------------------------------

I implemented a fix for this by rsyncing master \-> slave (thread 0) once and then executing
rsync on the slave (thread 0) \-> slave (thread 1 and 2) and achieved significant speedup.
I will post a patch soon.
                
> PTest increase performance by parallelizing rsync
> -------------------------------------------------
>
>                 Key: HIVE-4936
>                 URL: https://issues.apache.org/jira/browse/HIVE-4936
>             Project: Hive
>          Issue Type: Bug
>            Reporter: Brock Noland
>            Assignee: Brock Noland
>
> Currently the bottom neck in PTest2 when adding hosts is the rsync to the slaves. Today
if we have 3 "threads" which will execute on a slave we rsync the source from the master to
the slave 3 times. This causes the process to be CPU bound on the master.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message