[jira] [Comment Edited] (HIVE-16998) Add config to enable HoS DPP only for map-joins

["Sahil Takiar (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HIVE-16998?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16104042#comment-16104042 ] 

Sahil Takiar edited comment on HIVE-16998 at 7/27/17 11:11 PM:
---------------------------------------------------------------

You'll probably need to rebase this too, since I just merged HIVE-17087.


was (Author: stakiar):
You'll probably need to rebase this too, since I just merged HIVE-16923.

> Add config to enable HoS DPP only for map-joins
> -----------------------------------------------
>
>                 Key: HIVE-16998
>                 URL: https://issues.apache.org/jira/browse/HIVE-16998
>             Project: Hive
>          Issue Type: Sub-task
>          Components: Logical Optimizer, Spark
>            Reporter: Sahil Takiar
>            Assignee: Janaki Lahorani
>         Attachments: HIVE16998.1.patch, HIVE16998.2.patch, HIVE16998.3.patch, HIVE16998.4.patch
>
>
> HoS DPP will split a given operator tree in two under the following conditions: it has detected that the query can benefit from DPP, and the filter is not a map-join (see SplitOpTreeForDPP).
> This can hurt performance if the the non-partitioned side of the join involves a complex operator tree - e.g. the query {{select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)}} will require running the subquery twice, once in each Spark job.
> Queries with map-joins don't get split into two operator trees and thus don't suffer from this drawback. Thus, it would be nice to have a config key that just enables DPP on HoS for map-joins.



--
This message was sent by Atlassian JIRA
(v6.4.14#64029)