spark-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Takeshi Yamamuro (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (SPARK-6521) Bypass network shuffle read if both endpoints are local
Date Tue, 01 Dec 2015 03:43:10 GMT

    [ https://issues.apache.org/jira/browse/SPARK-6521?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15033016#comment-15033016
] 

Takeshi Yamamuro commented on SPARK-6521:
-----------------------------------------

Performance of the current Spark heavily depends on CPU, so this shuffle optimization has
little effect on that ( benchmark results could be found in pullreq #9478). For a while, this
ticket needs not to be considered and

> Bypass network shuffle read if both endpoints are local
> -------------------------------------------------------
>
>                 Key: SPARK-6521
>                 URL: https://issues.apache.org/jira/browse/SPARK-6521
>             Project: Spark
>          Issue Type: Improvement
>          Components: Shuffle, Spark Core
>    Affects Versions: 1.2.0
>            Reporter: xukun
>
> In the past, executor read other executor's shuffle file in the same node by net. This
pr make that executors in the same node read local shuffle file In sort-based Shuffle. It
will reduce net transport.



--
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


Mime
View raw message