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

Posted to issues@kylin.apache.org by "Shaofeng SHI (JIRA)" <ji...@apache.org> on 2018/07/15 10:00:02 UTC

[jira] [Updated] (KYLIN-3452) Optimize spark cubing memory footprint

     [ https://issues.apache.org/jira/browse/KYLIN-3452?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Shaofeng SHI updated KYLIN-3452:
--------------------------------
    Description: 
Noticed that there are some steps can be optimized:

1) Cuboid.findForMandatory() will create new object each time, which this can be cached;

2) Executor repeatedly load dictionary, not hit the cache;

3) NDCuboidBuilder and RowkeyEncoder, can optimize for less array copy;

> Optimize spark cubing memory footprint
> --------------------------------------
>
>                 Key: KYLIN-3452
>                 URL: https://issues.apache.org/jira/browse/KYLIN-3452
>             Project: Kylin
>          Issue Type: Improvement
>          Components: Spark Engine
>            Reporter: Shaofeng SHI
>            Priority: Major
>
> Noticed that there are some steps can be optimized:
> 1) Cuboid.findForMandatory() will create new object each time, which this can be cached;
> 2) Executor repeatedly load dictionary, not hit the cache;
> 3) NDCuboidBuilder and RowkeyEncoder, can optimize for less array copy;



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)