[
https://issues.apache.org/jira/browse/SPARK-29169?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Dongjoon Hyun updated SPARK-29169:
----------------------------------
Affects Version/s: (was: 3.0.0)
3.1.0
> Performance regression in ORC Vectorized on TINYINT scans
> ---------------------------------------------------------
>
> Key: SPARK-29169
> URL: https://issues.apache.org/jira/browse/SPARK-29169
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 3.1.0
> Reporter: Maxim Gekk
> Priority: Major
>
> The updated benchmark results show performance regression *(almost 2 times
> slower)* in ORC Vectorized on scanning Single TINYINT Column, see
> https://github.com/apache/spark/pull/25828/files#diff-e37c3433287c7371ff9c2404db821095R13
> . Need to find out the root cause of this and fix it.
> Old results:
> {code}
> SQL Single TINYINT Column Scan: Best/Avg Time(ms) Rate(M/s) Per
> Row(ns) Relative
> SQL ORC Vectorized 167 / 174 94.2
> 10.6 157.9X
> {code}
> New results:
> {code}
> SQL Single TINYINT Column Scan: Best Time(ms) Avg Time(ms)
> Stdev(ms) Rate(M/s) Per Row(ns) Relative
> SQL ORC Vectorized 329 347
> 25 47.9 20.9 72.9X
> {code}
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
