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

Posted to issues@spark.apache.org by "Jiang Xingbo (JIRA)" <ji...@apache.org> on 2018/08/09 12:33:00 UTC

[jira] [Created] (SPARK-25074) Implement maxNumConcurrentTasks() in MesosFineGrainedSchedulerBackend

Jiang Xingbo created SPARK-25074:
------------------------------------

             Summary: Implement maxNumConcurrentTasks() in MesosFineGrainedSchedulerBackend
                 Key: SPARK-25074
                 URL: https://issues.apache.org/jira/browse/SPARK-25074
             Project: Spark
          Issue Type: Task
          Components: Spark Core
    Affects Versions: 2.4.0
            Reporter: Jiang Xingbo


We added a new method `maxNumConcurrentTasks()` to `SchedulerBackend` to get the max number of tasks that can be concurrent launched currently. However the method is not implemented in `MesosFineGrainedSchedulerBackend`, so submit a job containing barrier stage shall always fail fast with `MesosFineGrainedSchedulerBackend` resource manager.



--
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