[
https://issues.apache.org/jira/browse/SPARK-4845?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
wangfei updated SPARK-4845:
---------------------------
Description:
Adding parallelismRatio to control the partitions num of shuffledRDD, the rule
is:
Math.max(1, parallelismRatio * number of partitions of the largest upstream
RDD)
The ratio is 1.0 by default to make it compatible with the old version.
When we have a good experience on it, we can change this.
was:
Adding parallelismRatio to control the partitions num of shuffledRDD, the rule
is:
Math.max(1, parallelismRatio * number of partitions of the largest upstream
RDD)
The ratio is 1.0 by default to make it compatible with the old version. When we
have a good experience on it, we can change this.
> Adding a parallelismRatio to control the partitions num of shuffledRDD
> ----------------------------------------------------------------------
>
> Key: SPARK-4845
> URL: https://issues.apache.org/jira/browse/SPARK-4845
> Project: Spark
> Issue Type: Improvement
> Components: Spark Core
> Affects Versions: 1.1.0
> Reporter: wangfei
> Fix For: 1.3.0
>
>
> Adding parallelismRatio to control the partitions num of shuffledRDD, the
> rule is:
> Math.max(1, parallelismRatio * number of partitions of the largest upstream
> RDD)
> The ratio is 1.0 by default to make it compatible with the old version.
> When we have a good experience on it, we can change this.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
