[
https://issues.apache.org/jira/browse/HIVE-10458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14539875#comment-14539875
]
Xuefu Zhang commented on HIVE-10458:
------------------------------------
Hi [~lirui], it doesn't seem making sense to have parallel order and then
reduce again with one reducer. Thus, disabling parallel order for order by +
limit seems better.
As a side question, I remember that you mentioned that parallel order doesn't
help much on performance. Could you quantify that? If so, maybe we shouldn't
consider parallel order at all.
> Enable parallel order by for spark [Spark Branch]
> -------------------------------------------------
>
> Key: HIVE-10458
> URL: https://issues.apache.org/jira/browse/HIVE-10458
> Project: Hive
> Issue Type: Sub-task
> Components: Spark
> Reporter: Rui Li
> Assignee: Rui Li
> Attachments: HIVE-10458.1-spark.patch
>
>
> We don't have to force reducer# to 1 as spark supports parallel sorting.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
