[
https://issues.apache.org/jira/browse/HADOOP-19875?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18078404#comment-18078404
]
Steve Loughran commented on HADOOP-19875:
-----------------------------------------
we cannot redistribute it, which != cannot use. parquet-benchmarks is an
example of a benchmark-only module; iceberg spark modules have their own.
I've been busy there, and it works well for microbenchmarks of things like
marshalling and unmarshalling, as there you can use flame graphs to identify
problems. More complex operations: you can show things are slow, you will show
when they've got faster (or slower!), but won't be so easy to track down *why*
https://steveloughran.github.io/benchmarking-variants/benchmarking-variants.html
> Further improve CrcComposer performance
> ---------------------------------------
>
> Key: HADOOP-19875
> URL: https://issues.apache.org/jira/browse/HADOOP-19875
> Project: Hadoop Common
> Issue Type: Improvement
> Components: common
> Reporter: Tsz-wo Sze
> Assignee: Tsz-wo Sze
> Priority: Major
> Attachments: screenshot-2.png
>
>
> In HDDS-10489, we found that using LongToIntFunction instead of
> ToIntFunction<Long> can further improve the performance.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
