You are viewing a plain text version of this content. The canonical link for it is here.
Posted to jira@arrow.apache.org by "Andrew Lamb (Jira)" <ji...@apache.org> on 2020/12/30 11:38:00 UTC

[jira] [Commented] (ARROW-11068) [Rust] [DataFusion] Wrap more operators in CoalesceBatchExec

    [ https://issues.apache.org/jira/browse/ARROW-11068?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17256477#comment-17256477 ] 

Andrew Lamb commented on ARROW-11068:
-------------------------------------

I have some suggestions here: https://github.com/apache/arrow/pull/9043#discussion_r550163707

TLDR -- I think incorporating the coalescing logic into the operators themselves (so they don't produce small baches in the first place) might be better

> [Rust] [DataFusion] Wrap more operators in CoalesceBatchExec
> ------------------------------------------------------------
>
>                 Key: ARROW-11068
>                 URL: https://issues.apache.org/jira/browse/ARROW-11068
>             Project: Apache Arrow
>          Issue Type: Improvement
>          Components: Rust - DataFusion
>            Reporter: Andy Grove
>            Assignee: Andy Grove
>            Priority: Major
>             Fix For: 3.0.0
>
>
> Once [https://github.com/apache/arrow/pull/9043] is merged, we should extend this to wrap HashJoinExec and HashAggregateExec as well since they can both produce small batches.
> Rather than hard-code a list of operators that need to be wrapped, we should find a more generic mechanism so that plans can declare if their input and/or output batches should be coalesced (similar to how we handle partitioning) and this would allow custom operators outside of DataFusion to benefit from this optimization.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)