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 2018/04/13 03:00:00 UTC
[jira] [Commented] (SPARK-23974) Do not allocate more containers as
expected in dynamic allocation
[ https://issues.apache.org/jira/browse/SPARK-23974?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16436726#comment-16436726 ]
Apache Spark commented on SPARK-23974:
--------------------------------------
User 'sadhen' has created a pull request for this issue:
https://github.com/apache/spark/pull/21059
> Do not allocate more containers as expected in dynamic allocation
> -----------------------------------------------------------------
>
> Key: SPARK-23974
> URL: https://issues.apache.org/jira/browse/SPARK-23974
> Project: Spark
> Issue Type: Bug
> Components: Spark Core
> Affects Versions: 2.1.1
> Reporter: Darcy Shen
> Priority: Major
>
> Using Yarn with dynamic allocation enabled, spark does not allocate more containers when current containers(executors) number is less than the max executor num.
> For example, we only have 7 executors working, while our cluster is not busy, and I have set
> {{ spark.dynamicAllocation.maxExecutors = 600}}
> {{and the current jobs of the context are executed slowly.}}
--
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