You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@tajo.apache.org by "ASF GitHub Bot (JIRA)" <ji...@apache.org> on 2015/07/22 04:50:04 UTC

[jira] [Commented] (TAJO-1696) Resource calculator should consider the requested disk resource at the first stage

    [ https://issues.apache.org/jira/browse/TAJO-1696?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14636141#comment-14636141 ] 

ASF GitHub Bot commented on TAJO-1696:
--------------------------------------

GitHub user jihoonson opened a pull request:

    https://github.com/apache/tajo/pull/640

    TAJO-1696: Resource calculator should consider the requested disk resource at the first stage

    

You can merge this pull request into a Git repository by running:

    $ git pull https://github.com/jihoonson/tajo-2 TAJO-1696

Alternatively you can review and apply these changes as the patch at:

    https://github.com/apache/tajo/pull/640.patch

To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:

    This closes #640
    
----
commit e231945aebb7c3302fa8b4af4934da21de46a999
Author: Jihoon Son <ji...@apache.org>
Date:   2015-07-22T02:47:26Z

    TAJO-1696

----


> Resource calculator should consider the requested disk resource at the first stage
> ----------------------------------------------------------------------------------
>
>                 Key: TAJO-1696
>                 URL: https://issues.apache.org/jira/browse/TAJO-1696
>             Project: Tajo
>          Issue Type: Improvement
>            Reporter: Jihoon Son
>            Assignee: Jihoon Son
>             Fix For: 0.11.0
>
>
> Resource calculator currently considers only cpu and memory. However, disk is an important resource in the first stage, so should be considered for available resource calculation.
> In addition, in the current implementation, a worker sends a heartbeat whenever it finishes processing half of the assigned tasks. So, the problem of ignoring disk resource makes the first heartbeat delayed during the first stage, thereby making the query execution slow.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)