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

Posted to issues@impala.apache.org by "Matthew Jacobs (JIRA)" <ji...@apache.org> on 2017/08/14 16:15:01 UTC

[jira] [Resolved] (IMPALA-4833) Use scheduling information to make per-node memory reservation tight

     [ https://issues.apache.org/jira/browse/IMPALA-4833?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Matthew Jacobs resolved IMPALA-4833.
------------------------------------
       Resolution: Fixed
    Fix Version/s: Impala 2.10.0

https://github.com/apache/incubator-impala/commit/6c1254656186b62e90674b4fe093a6864ccbbde5

> Use scheduling information to make per-node memory reservation tight
> --------------------------------------------------------------------
>
>                 Key: IMPALA-4833
>                 URL: https://issues.apache.org/jira/browse/IMPALA-4833
>             Project: IMPALA
>          Issue Type: Improvement
>          Components: Backend
>    Affects Versions: Impala 2.9.0
>            Reporter: Tim Armstrong
>            Assignee: Matthew Jacobs
>              Labels: resource-management
>             Fix For: Impala 2.10.0
>
>
> Following on from IMPALA-3748, we should consider combining the resource estimates with the schedule to accurate compute the minimum buffer requirement per daemon. Different daemons may have different resource requirements because not every fragment runs on every daemon (e.g. unpartitioned fragments, fragments with fewer scan ranges than daemons).



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)