You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Maxim Gekk (Jira)" <ji...@apache.org> on 2020/01/18 17:22:00 UTC
[jira] [Commented] (SPARK-30564) Regression in the wide schema
benchmark
[ https://issues.apache.org/jira/browse/SPARK-30564?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17018652#comment-17018652 ]
Maxim Gekk commented on SPARK-30564:
------------------------------------
Here, regression is ~8 times [https://github.com/apache/spark/pull/27078/files#diff-8d27bbf2f73a68bf0c2025f0702f7332R74]
> Regression in the wide schema benchmark
> ---------------------------------------
>
> Key: SPARK-30564
> URL: https://issues.apache.org/jira/browse/SPARK-30564
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 3.0.0
> Reporter: Maxim Gekk
> Priority: Minor
>
> New results of WideSchemaBenchmark generated in the PR: https://github.com/apache/spark/pull/27078 show regressions up to 2 times.
> Before:
> {code}
> 2500 select expressions 103 / 107 0.0 102962705.0 0.1X
> {code}
> https://github.com/apache/spark/pull/27078/files#diff-8d27bbf2f73a68bf0c2025f0702f7332L11
> After:
> {code}
> 2500 select expressions 211 214 4 0.0 210927791.0 0.0X
> {code}
> https://github.com/apache/spark/pull/27078/files#diff-8d27bbf2f73a68bf0c2025f0702f7332R11
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org