You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Cheng Lian (JIRA)" <ji...@apache.org> on 2014/08/29 06:30:08 UTC
[jira] [Commented] (SPARK-3294) Avoid boxing/unboxing when handling
in-memory columnar storage
[ https://issues.apache.org/jira/browse/SPARK-3294?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14114836#comment-14114836 ]
Cheng Lian commented on SPARK-3294:
-----------------------------------
[~marmbrus], would you mind to assign this issue to me?
> Avoid boxing/unboxing when handling in-memory columnar storage
> --------------------------------------------------------------
>
> Key: SPARK-3294
> URL: https://issues.apache.org/jira/browse/SPARK-3294
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 1.0.2, 1.1.0
> Reporter: Cheng Lian
> Priority: Critical
>
> When Spark SQL in-memory columnar storage was implemented, we tried to avoid boxing/unboxing costs as much as possible, but {{javap}} shows that there still exist code that involves boxing/unboxing on critical paths due to type erasure, especially methods of sub-classes of {{ColumnType}}. Should eliminate them whenever possible for better performance.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org