[
https://issues.apache.org/jira/browse/HIVE-8486?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14174292#comment-14174292
]
Chao commented on HIVE-8486:
----------------------------
1) I discussed with [~szehon] about this, and seems we cannot change the
calculation now, since it will affect the way how the buckets are calculated.
2) In the Spark branch, we are not doing anything to estimate the number of
reducers. In MR, in case this number is not set, it will estimate and set it at
runtime. This is done in {{MapRedTask}}. Tez also uses "Auto Reducer
Parallelism" (see HIVE-7158) to control this. As result, I think we should do
something to resolve this.
> TPC-DS Query 96 parallelism is not set correcly
> -----------------------------------------------
>
> Key: HIVE-8486
> URL: https://issues.apache.org/jira/browse/HIVE-8486
> Project: Hive
> Issue Type: Sub-task
> Components: Spark
> Reporter: Brock Noland
> Assignee: Chao
>
> When we run the query on a 20B we only have a parallelism factor of 1.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
