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

Posted to issues@tajo.apache.org by "Jihoon Son (JIRA)" <ji...@apache.org> on 2015/11/12 06:11:10 UTC

[jira] [Updated] (TAJO-1975) Gathering fine-grained column statistics for range shuffle

     [ https://issues.apache.org/jira/browse/TAJO-1975?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jihoon Son updated TAJO-1975:
-----------------------------
    Summary: Gathering fine-grained column statistics for range shuffle  (was: Gathering fine-grained column statistics)

> Gathering fine-grained column statistics for range shuffle
> ----------------------------------------------------------
>
>                 Key: TAJO-1975
>                 URL: https://issues.apache.org/jira/browse/TAJO-1975
>             Project: Tajo
>          Issue Type: Task
>            Reporter: Jihoon Son
>            Assignee: Jihoon Son
>             Fix For: 0.12.0, 0.11.1
>
>
> One of the stages where statistics is very useful is the shuffle stage during query execution.Tajo also utilizes statistics for range shuffle. 
> Currently, once gathering statistics is enabled, it is collected on every column of the input schema rather than the shuffle key columns. This may cause unnecessary overhead, so we need to collect statistics on only the shuffle keys.



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