You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@hive.apache.org by "Lefty Leverenz (JIRA)" <ji...@apache.org> on 2016/04/30 10:44:13 UTC

[jira] [Commented] (HIVE-12623) Add an option to force allocation of fragments on requested nodes

    [ https://issues.apache.org/jira/browse/HIVE-12623?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15265248#comment-15265248 ] 

Lefty Leverenz commented on HIVE-12623:
---------------------------------------

HIVE-13469 modifies the description of *hive.llap.task.scheduler.locality.delay* in release 2.1.0, and the new description is appropriate for 2.0.0 as well so I suggest using it in the wiki rather than documenting both versions of the description.

Here's the LLAP section of Configuration Properties:

* [Configuration Properties -- LLAP | https://cwiki.apache.org/confluence/display/Hive/Configuration+Properties#ConfigurationProperties-LLAP]

> Add an option to force allocation of fragments on requested nodes
> -----------------------------------------------------------------
>
>                 Key: HIVE-12623
>                 URL: https://issues.apache.org/jira/browse/HIVE-12623
>             Project: Hive
>          Issue Type: Improvement
>          Components: llap
>            Reporter: Siddharth Seth
>            Assignee: Siddharth Seth
>              Labels: TODOC2.0
>             Fix For: 2.0.0
>
>         Attachments: HIVE-12623.1.patch, HIVE-12623.1.txt, HIVE-12623.1.wip.txt
>
>
> Currently, fragments are sent to random nodes if the requested node does not have capacity. In certain situations there's more to be gained by sending the fragments to the requested node only.



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