wangfei created SPARK-4845:
------------------------------
Summary: 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]
