drill-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Khurram Faraaz (JIRA)" <j...@apache.org>
Subject [jira] [Comment Edited] (DRILL-4589) Reduce planning time for file system partition pruning by reducing filter evaluation overhead
Date Thu, 14 Apr 2016 18:16:25 GMT

    [ https://issues.apache.org/jira/browse/DRILL-4589?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15241661#comment-15241661
] 

Khurram Faraaz edited comment on DRILL-4589 at 4/14/16 6:15 PM:
----------------------------------------------------------------

The following tests will be executed to verify this change.

{noformat}
There are 25 directories (1990 through 2015), and each directory has 4 sub directories (Q1,
Q2, Q3 and Q4)
and each of those sub directories has 2000 parquet files (each being ~2KB in size)

REFRESH TABLE METADATA `DRILL_4589`
will be executed over the root directory and tests similar to those listed below (and more)
will be executed.

explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 IS NOT
NULL;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 IS NULL;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 >= 25
AND c1 <= 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 >= 53;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 <= 97;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 >= 25
AND c1 < 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 > 25
AND c1 <= 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 > 25
AND c1 < 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c4 LIKE 'orb%';
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c4 LIKE 'orb%'
AND c7 = '1958-04-24';
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c4 IN (...)
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND LENGTH(c5)
>= 1 AND LENGTH(c5) <= 172;
{noformat}


was (Author: khfaraaz):
The following tests will be executed to verify this change.

{noformat}
There are 25 directories (1990 THROUGH 2015), and each directory has 4 sub directories (Q1,
Q2, Q3 and Q4)
and each of those sub directories has 2000 parquet files (each being ~2KB in size)

REFRESH TABLE METADATA `DRILL_4589`
will be executed over the root directory and tests similar to those listed below (and more)
will be executed.

explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 IS NOT
NULL;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 IS NULL;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 >= 25
AND c1 <= 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 >= 53;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 <= 97;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 >= 25
AND c1 < 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 > 25
AND c1 <= 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c1 > 25
AND c1 < 135;
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c4 LIKE 'orb%';
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c4 LIKE 'orb%'
AND c7 = '1958-04-24';
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND c4 IN (...)
explain plan for select * from `DRILL_4589` WHERE dir0='2000' AND dir1='Q2' AND LENGTH(c5)
>= 1 AND LENGTH(c5) <= 172;
{noformat}

> Reduce planning time for file system partition pruning by reducing filter evaluation
overhead
> ---------------------------------------------------------------------------------------------
>
>                 Key: DRILL-4589
>                 URL: https://issues.apache.org/jira/browse/DRILL-4589
>             Project: Apache Drill
>          Issue Type: Bug
>          Components: Query Planning & Optimization
>            Reporter: Jinfeng Ni
>            Assignee: Jinfeng Ni
>
> When Drill is used to query hundreds of thousands, or even millions of files organized
into multi-level directories, user typically will provide a partition filter like  : dir0
= something and dir1 = something2 and .. .  
> For such queries, we saw the query planning time could be unacceptable long, due to three
main overheads: 1) to expand and get the list of files, 2) to evaluate the partition filter,
3) to get the metadata, in the case of parquet files for which metadata cache file is not
available. 
> DRILL-2517 targets at the 3rd part of overhead. As a follow-up work after DRILL-2517,
we plan to reduce the filter evaluation overhead. For now, the partition filter evaluation
is applied to file level. In many cases, we saw that the number of leaf subdirectories is
significantly lower than that of files. Since all the files under the same leaf subdirecctory
share the same directory metadata, we should apply the filter evaluation at the leaf subdirectory.
By doing that, we could reduce the cpu overhead to evaluate the filter, and the memory overhead
as well.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message