phoenix-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Abhishek Singh Chouhan (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (PHOENIX-4686) Phoenix stats does not account for server side limit push downs
Date Wed, 18 Apr 2018 14:10:00 GMT

    [ https://issues.apache.org/jira/browse/PHOENIX-4686?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16442565#comment-16442565
] 

Abhishek Singh Chouhan commented on PHOENIX-4686:
-------------------------------------------------

[~jamestaylor] Have attached a WIP patch. Please have a look and let me know if this is in
the right direction :)

Basic idea of the patch is to handle the two cases using stats for parallelization(and in
turn having scans b/w guide posts that will have the page filter with the limit specified)
and no stats parallelization (where we'll have a scan spanning multiple gps in which case
adjust the estimates that we've collected in the loop above). For adjustment of stats in both
the cases i've used the simple method of estimating single row size (bytes in gp/rows in gp)
and multiplying by the perscan limit that we're pushing down in the scan.

> Phoenix stats does not account for server side limit push downs
> ---------------------------------------------------------------
>
>                 Key: PHOENIX-4686
>                 URL: https://issues.apache.org/jira/browse/PHOENIX-4686
>             Project: Phoenix
>          Issue Type: Bug
>            Reporter: Abhishek Singh Chouhan
>            Assignee: Abhishek Singh Chouhan
>            Priority: Major
>         Attachments: PHOENIX-4686-wip.master.patch
>
>
> For a query like SELECT * FROM FOO LIMIT 10 the EST_BYTES_READ does not take into account
a limit correctly when there's no WHERE clause (or a WHERE clause that gets compiled out into
start/stop row key on the scan).



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

Mime
View raw message