You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hive.apache.org by "Ashutosh Chauhan (Jira)" <ji...@apache.org> on 2020/10/20 18:55:00 UTC
[jira] [Commented] (HIVE-24262) Optimise NullScanTaskDispatcher for
cloud storage
[ https://issues.apache.org/jira/browse/HIVE-24262?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17217872#comment-17217872 ]
Ashutosh Chauhan commented on HIVE-24262:
-----------------------------------------
I don't see any advantage of scanning the FS to determine if path is empty or not.
Queries under considerations are select count(distinct part_col) from t. Such queries since don't reference any non-partition column are applicable to metadataonly optimizer. Now, where partition objects exist in HMS but there is no data on FS, question is whether to return empty resultset or to return actual values from HMS. I think this is a corner-case which I am not sure if standard has a clear answer. I think we can chose to return resultset containing partition column. If we do that, we don't need to determine if dirs are empty or not and can skip this expensive operation.
Also, there already is config for this, so for some reason alternative resultset is desired that's also possible by turning off optimization completely.
> Optimise NullScanTaskDispatcher for cloud storage
> -------------------------------------------------
>
> Key: HIVE-24262
> URL: https://issues.apache.org/jira/browse/HIVE-24262
> Project: Hive
> Issue Type: Improvement
> Reporter: Rajesh Balamohan
> Assignee: Mustafa Iman
> Priority: Major
>
> {noformat}
> select count(DISTINCT ss_sold_date_sk) from store_sales;
> ----------------------------------------------------------------------------------------------
> VERTICES MODE STATUS TOTAL COMPLETED RUNNING PENDING FAILED KILLED
> ----------------------------------------------------------------------------------------------
> Map 1 .......... container SUCCEEDED 1 1 0 0 0 0
> Reducer 2 ...... container SUCCEEDED 1 1 0 0 0 0
> ----------------------------------------------------------------------------------------------
> VERTICES: 02/02 [==========================>>] 100% ELAPSED TIME: 5.55 s
> ----------------------------------------------------------------------------------------------
> INFO : Status: DAG finished successfully in 5.44 seconds
> INFO :
> INFO : Query Execution Summary
> INFO : ----------------------------------------------------------------------------------------------
> INFO : OPERATION DURATION
> INFO : ----------------------------------------------------------------------------------------------
> INFO : Compile Query 102.02s
> INFO : Prepare Plan 0.51s
> INFO : Get Query Coordinator (AM) 0.01s
> INFO : Submit Plan 0.33s
> INFO : Start DAG 0.56s
> INFO : Run DAG 5.44s
> INFO : ----------------------------------------------------------------------------------------------
> {noformat}
> Reason for "102 seconds" compilation time is that, it ends up doing "isEmptyPath" check for every partition path and takes lot of time in compilation phase.
> If the parent directory of all paths belong to the same path, we could just do a recursive listing just once (instead of listing each directory one at a time sequentially) in cloud storage systems.
> https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/NullScanTaskDispatcher.java#L158
> https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/NullScanTaskDispatcher.java#L121
> https://github.com/apache/hive/blob/master/ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/NullScanTaskDispatcher.java#L101
> With a temp hacky fix, it comes down to 2 seconds from 100+ seconds.
> {noformat}
> INFO : Dag name: select count(DISTINCT ss_sold_...store_sales (Stage-1)
> INFO : Status: Running (Executing on YARN cluster with App id application_1602500203747_0003)
> ----------------------------------------------------------------------------------------------
> VERTICES MODE STATUS TOTAL COMPLETED RUNNING PENDING FAILED KILLED
> ----------------------------------------------------------------------------------------------
> Map 1 .......... container SUCCEEDED 1 1 0 0 0 0
> Reducer 2 ...... container SUCCEEDED 1 1 0 0 0 0
> ----------------------------------------------------------------------------------------------
> VERTICES: 02/02 [==========================>>] 100% ELAPSED TIME: 1.23 s
> ----------------------------------------------------------------------------------------------
> INFO : Status: DAG finished successfully in 1.20 seconds
> INFO :
> INFO : Query Execution Summary
> INFO : ----------------------------------------------------------------------------------------------
> INFO : OPERATION DURATION
> INFO : ----------------------------------------------------------------------------------------------
> INFO : Compile Query 0.85s
> INFO : Prepare Plan 0.17s
> INFO : Get Query Coordinator (AM) 0.00s
> INFO : Submit Plan 0.03s
> INFO : Start DAG 0.03s
> INFO : Run DAG 1.20s
> INFO : ----------------------------------------------------------------------------------------------
> {noformat}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)