[ 
https://issues.apache.org/jira/browse/SPARK-26155?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16700228#comment-16700228
 ] 

Liang-Chi Hsieh commented on SPARK-26155:
-----------------------------------------

Is there possibly any other thing affecting the time?

I find there are many places in two DAGs with time difference.

For example, in the DAG with L486&487, the first WholeStageCodegen costs 4.9m, 
but in another DAG, it costs 45.3s. However, in this WholeStageCodegen there is 
no hash join.

And, in one WholeStageCodegen which contains SortMergeJoin + BroadcastHashJoin 
+ HashAggregate, the time is the same 2.1m.


> Spark SQL  performance degradation after apply SPARK-21052 with Q19 of TPC-DS 
> in 3TB scale
> ------------------------------------------------------------------------------------------
>
>                 Key: SPARK-26155
>                 URL: https://issues.apache.org/jira/browse/SPARK-26155
>             Project: Spark
>          Issue Type: Improvement
>          Components: SQL
>    Affects Versions: 2.3.0, 2.3.1, 2.3.2, 2.4.0
>            Reporter: Ke Jia
>            Priority: Major
>         Attachments: Q19 analysis in Spark2.3 with L486&487.pdf, Q19 analysis 
> in Spark2.3 without L486 & 487.pdf, q19.sql
>
>
> In our test environment, we found a serious performance degradation issue in 
> Spark2.3 when running TPC-DS on SKX 8180. Several queries have serious 
> performance degradation. For example, TPC-DS Q19 needs 126 seconds with Spark 
> 2.3 while it needs only 29 seconds with Spark2.1 on 3TB data. We investigated 
> this problem and figured out the root cause is in community patch SPARK-21052 
> which add metrics to hash join process. And the impact code is 
> [L486|https://github.com/apache/spark/blob/1d3dd58d21400b5652b75af7e7e53aad85a31528/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala#L486]
>  and 
> [L487|https://github.com/apache/spark/blob/1d3dd58d21400b5652b75af7e7e53aad85a31528/sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashedRelation.scala#L487]
>   . Q19 costs about 30 seconds without these two lines code and 126 seconds 
> with these code.



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

---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org
For additional commands, e-mail: issues-h...@spark.apache.org

Reply via email to