You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Josh Rosen (JIRA)" <ji...@apache.org> on 2014/10/21 20:38:34 UTC
[jira] [Commented] (SPARK-3740) Use a compressed bitmap to track
zero sized blocks in HighlyCompressedMapStatus
[ https://issues.apache.org/jira/browse/SPARK-3740?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14178807#comment-14178807 ]
Josh Rosen commented on SPARK-3740:
-----------------------------------
This isn't just an optimization; it's required for correctness; see SPARK-4019
> Use a compressed bitmap to track zero sized blocks in HighlyCompressedMapStatus
> -------------------------------------------------------------------------------
>
> Key: SPARK-3740
> URL: https://issues.apache.org/jira/browse/SPARK-3740
> Project: Spark
> Issue Type: Improvement
> Components: Shuffle, Spark Core
> Reporter: Reynold Xin
> Assignee: Josh Rosen
> Labels: starter
>
> HighlyCompressedMapStatus uses a single long to track the average block size. However, if a stage has a lot of zero sized outputs, this leads to inefficiency because executors would need to send requests to fetch zero sized blocks.
> We can use a compressed bitmap to track the zero-sized blocks.
> See discussion in https://github.com/apache/spark/pull/2470
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org