[jira] [Commented] (SPARK-8695) TreeAggregation shouldn't be triggered for 5 partitions

["Perinkulam I Ganesh (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/SPARK-8695?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14606582#comment-14606582 ] 

Perinkulam I Ganesh commented on SPARK-8695:
--------------------------------------------

Looks like a simple change

while (numPartitions > scale + numPartitions / scale + 1 ) {

or

while (numPartitions > 5 && (numPartitions > scale + numPartitions / scale)) {

should correct the behaviour

thanks

> TreeAggregation shouldn't be triggered for 5 partitions
> -------------------------------------------------------
>
>                 Key: SPARK-8695
>                 URL: https://issues.apache.org/jira/browse/SPARK-8695
>             Project: Spark
>          Issue Type: Improvement
>          Components: MLlib, Spark Core
>    Affects Versions: 1.5.0
>            Reporter: Xiangrui Meng
>            Assignee: Xiangrui Meng
>            Priority: Minor
>
> If an RDD has 5 partitions, tree aggregation doesn't reduce the wall-clock time. Instead, it introduces scheduling and shuffling overhead. We should update the condition to use tree aggregation (code attached):
> {code}
>       while (numPartitions > scale + numPartitions / scale) {
> {code}



--
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