You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@ignite.apache.org by "Yury Gerzhedovich (Jira)" <ji...@apache.org> on 2022/12/12 11:15:00 UTC

[jira] [Commented] (IGNITE-18224) Sql. Allow hash output distribution for SET relations

    [ https://issues.apache.org/jira/browse/IGNITE-18224?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17646039#comment-17646039 ] 

Yury Gerzhedovich commented on IGNITE-18224:
--------------------------------------------

[~xtern] , LGTM

> Sql. Allow hash output distribution for SET relations
> -----------------------------------------------------
>
>                 Key: IGNITE-18224
>                 URL: https://issues.apache.org/jira/browse/IGNITE-18224
>             Project: Ignite
>          Issue Type: Improvement
>          Components: sql
>            Reporter: Konstantin Orlov
>            Assignee: Pavel Pereslegin
>            Priority: Major
>              Labels: ignite-3
>          Time Spent: 50m
>  Remaining Estimate: 0h
>
> Currently, we allow only single output distribution for SET operations, but looks like if we have hash input distribution and projected columns contains all of the distribution keys we can execute SET operator on remote nodes and produce hash output distribution with the same keys. This will reduce memory consumption on the initiator node and make some other optimizations possible.
> Reference implementation can be found here: IGNITE-16396



--
This message was sent by Atlassian Jira
(v8.20.10#820010)