[
https://issues.apache.org/jira/browse/SPARK-10842?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
SuYan updated SPARK-10842:
--------------------------
Affects Version/s: 1.5.0
Priority: Minor (was: Major)
Description: When we traverse RDD, to generate Stage DAG, Spark will
skip judge the stage whether it add into *shuffleIdToStage* in some condition:
get shuffleDep from *getAncestorShuffleDependency*
Component/s: Scheduler
Summary: Eliminate create duplicate stage while generate job dag
(was: liminate duplicate stage )
> Eliminate create duplicate stage while generate job dag
> -------------------------------------------------------
>
> Key: SPARK-10842
> URL: https://issues.apache.org/jira/browse/SPARK-10842
> Project: Spark
> Issue Type: Improvement
> Components: Scheduler
> Affects Versions: 1.5.0
> Reporter: SuYan
> Priority: Minor
>
> When we traverse RDD, to generate Stage DAG, Spark will skip judge the stage
> whether it add into *shuffleIdToStage* in some condition: get shuffleDep from
> *getAncestorShuffleDependency*
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
