[jira] [Commented] (HIVE-6872) Explore options of optimizing FileSinkOperator-->getDynOutPaths()

["Rajesh Balamohan (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HIVE-6872?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13964022#comment-13964022 ] 

Rajesh Balamohan commented on HIVE-6872:
----------------------------------------

This should be applicable for tables with "partition" + "sorted data" as well.

> Explore options of optimizing FileSinkOperator-->getDynOutPaths()
> -----------------------------------------------------------------
>
>                 Key: HIVE-6872
>                 URL: https://issues.apache.org/jira/browse/HIVE-6872
>             Project: Hive
>          Issue Type: Bug
>            Reporter: Rajesh Balamohan
>            Priority: Critical
>
> 1. Download hive-testbench from https://github.com/cartershanklin/hive-testbench
> 2. Generate data using "./tpcds-setup.sh 10 /user/hive/external partitioned" 
> 3. Most of the data population for tables with "partition + bucket + sorted data" will run a lot slower even with scale factor of 10 on 20 node cluster.
> Bottleneck seems to be in FileSinkOperator-->getDynOutPaths() where it tries to close FSPath writers.  Every call takes almost 150-200 ms. 
> set hive.enforce.bucketing=true;
> set hive.exec.dynamic.partition.mode=nonstrict;
> set hive.exec.max.dynamic.partitions.pernode=4096;
> With the above setting, one of the data loading (for web_sales table) took almost 4096 * 150 = 600 seconds in closing the writers sequentially.  
> Purpose of this jira is to figure out options of optimizing this code path.



--
This message was sent by Atlassian JIRA
(v6.2#6252)