[
https://issues.apache.org/jira/browse/SPARK-4341?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14206263#comment-14206263
]
Hong Shen commented on SPARK-4341:
----------------------------------
There must be some relation between inputSplits, num-executors and spark
parallelism, for example, if inputSplits (determine partitions of input rdd) is
less than num-executors, it will lead to a waste of resources, if inputSplits
much bigger than num-executor, job will last a long time. It's the same to
num-executors and spark parallelism. So if we want spark widely used, it's
should set by spark automatically.
> Spark need to set num-executors automatically
> ---------------------------------------------
>
> Key: SPARK-4341
> URL: https://issues.apache.org/jira/browse/SPARK-4341
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
> Affects Versions: 1.1.0
> Reporter: Hong Shen
>
> The mapreduce job can set maptask automaticlly, but in spark, we have to set
> num-executors, executor memory and cores. It's difficult for users to set
> these args, especially for the users want to use spark sql. So when user
> havn't set num-executors, spark should set num-executors automatically
> accroding to the input partitions.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org
