[
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: [email protected]
For additional commands, e-mail: [email protected]
