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

Posted to issues-all@impala.apache.org by "Joe McDonnell (JIRA)" <ji...@apache.org> on 2018/10/04 17:09:00 UTC

[jira] [Commented] (IMPALA-4625) Parquet Row Group Size optimization

    [ https://issues.apache.org/jira/browse/IMPALA-4625?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16638552#comment-16638552 ] 

Joe McDonnell commented on IMPALA-4625:
---------------------------------------

Marking as related to IMPALA-5843 (Parquet page skipping). 

> Parquet Row Group Size optimization
> -----------------------------------
>
>                 Key: IMPALA-4625
>                 URL: https://issues.apache.org/jira/browse/IMPALA-4625
>             Project: IMPALA
>          Issue Type: Improvement
>          Components: Backend
>    Affects Versions: Impala 2.2.4
>            Reporter: Alan Choi
>            Priority: Major
>
> For highly selective query, once we can narrow it down to a single Parquet file that matches the predicate, Impala still has to process that single file. Right now, a single Parquet file generated by Impala has only 1 row group and its default size is 256MB. A row group is processed in serial cannot be parallelized at this moment. Processing a 256MB row group can takes several sec, even for a very simple predicate. To improve the response time of such highly selective query, the row group must be smaller.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-all-unsubscribe@impala.apache.org
For additional commands, e-mail: issues-all-help@impala.apache.org