You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Apache Spark (JIRA)" <ji...@apache.org> on 2016/10/21 17:06:58 UTC
[jira] [Assigned] (SPARK-18039) ReceiverTracker run dummyjob too
fast cause receiver scheduling unbalaced
[ https://issues.apache.org/jira/browse/SPARK-18039?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Apache Spark reassigned SPARK-18039:
------------------------------------
Assignee: (was: Apache Spark)
> ReceiverTracker run dummyjob too fast cause receiver scheduling unbalaced
> -------------------------------------------------------------------------
>
> Key: SPARK-18039
> URL: https://issues.apache.org/jira/browse/SPARK-18039
> Project: Spark
> Issue Type: Bug
> Components: Scheduler
> Affects Versions: 2.0.1
> Reporter: astralidea
> Priority: Minor
>
> receiver scheduling balance is important for me
> for instance
> if I have 2 executor, each executor has 1 receiver, calc time is 0.1s per batch.
> but if I have 2 executor, one executor has 2 receiver and another is 0 receiver ,calc time is increase 3s per batch.
> In my cluster executor init is slow I need about 30s to wait.
> but dummy job only run 4s to wait, I add conf spark.scheduler.maxRegisteredResourcesWaitingTime it does not work.
--
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