[
https://issues.apache.org/jira/browse/SPARK-49725?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Yuming Wang updated SPARK-49725:
--------------------------------
Attachment: driver.svg
> Increase PerMethodRecompilationCutoff and PerBytecodeRecompilationCutoff
> ------------------------------------------------------------------------
>
> Key: SPARK-49725
> URL: https://issues.apache.org/jira/browse/SPARK-49725
> Project: Spark
> Issue Type: Improvement
> Components: SQL
> Affects Versions: 4.0.0
> Reporter: Yuming Wang
> Priority: Major
> Attachments: driver.svg, executor.svg
>
>
> Cluster becomes slower and slower if do not disable
> {{spark.sql.codegen.wholeStage}}.
> {noformat}
> java -XX:+PrintFlagsFinal -version | grep Cutoff
> intx LiveNodeCountInliningCutoff = 40000
> {C2 product} {default}
> intx PerBytecodeRecompilationCutoff = 200
> {product} {default}
> intx PerMethodRecompilationCutoff = 400
> {product} {default}
> openjdk version "17.0.6" 2023-01-17 LTS
> OpenJDK Runtime Environment Zulu17.40+20-SA (build 17.0.6+10-LTS)
> OpenJDK 64-Bit Server VM Zulu17.40+20-SA (build 17.0.6+10-LTS, mixed mode,
> sharing)
> {noformat}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
