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

Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2018/10/30 12:44:00 UTC

[jira] [Commented] (SPARK-25885) HighlyCompressedMapStatus deserialization optimization

    [ https://issues.apache.org/jira/browse/SPARK-25885?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16668646#comment-16668646 ] 

Apache Spark commented on SPARK-25885:
--------------------------------------

User 'Koraseg' has created a pull request for this issue:
https://github.com/apache/spark/pull/22894

> HighlyCompressedMapStatus deserialization optimization
> ------------------------------------------------------
>
>                 Key: SPARK-25885
>                 URL: https://issues.apache.org/jira/browse/SPARK-25885
>             Project: Spark
>          Issue Type: Improvement
>          Components: Spark Core
>    Affects Versions: 2.2.0
>            Reporter: Artem Kupchinskiy
>            Priority: Minor
>
> HighlyCompressedMapStatus uses unnecessary indirection level during deserialization and construction. It uses ArrayBuffer, as an interim storage, before the actual map construction. Since both methods could be application hot spots under certain workloads, it is worth to get rid of that intermediate level.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org