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 2015/05/24 06:44:17 UTC

[jira] [Resolved] (SPARK-912) Take stage breakdown functionality and runLocally out of the main event loop in DAGScheduler

     [ https://issues.apache.org/jira/browse/SPARK-912?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Josh Rosen resolved SPARK-912.
------------------------------
    Resolution: Fixed

It looks like the task result deserialization code was moved out of the main loop in SPARK-7655.  It also looks like the {{runLocally}} was moved into a separate thread a long time ago (pre-1.0?).  Given this, I'm going to resolve this as fixed; I'm not quite sure what the "stage breakdown" in the title is referring to but I think that code has been significantly optimized since 0.8, so it's probably no longer relevant.

> Take stage breakdown functionality and runLocally out of the main event loop in DAGScheduler
> --------------------------------------------------------------------------------------------
>
>                 Key: SPARK-912
>                 URL: https://issues.apache.org/jira/browse/SPARK-912
>             Project: Spark
>          Issue Type: Improvement
>          Components: Scheduler
>    Affects Versions: 0.8.0
>            Reporter: Reynold Xin
>
> This can reduce the complexity of the main event loop and improve performance (since the main event loop is single threaded).
> We can also take the result task deserialization code out of the main loop (maybe Kay is already working on this?).



--
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