pan3793 commented on PR #3114:
URL: https://github.com/apache/celeborn/pull/3114#issuecomment-2677924137

   I suppose the upgrade should have perf improvements for the Celeborn client 
because the default  value of `celeborn.client.push.buffer.max.size` is `64k`
   
https://github.com/apache/celeborn/blob/f09482108fe91f986b9cfceebd4b050379bf6f64/common/src/main/scala/org/apache/celeborn/common/CelebornConf.scala#L4457
   
   and zstd [v1.5.7](https://github.com/facebook/zstd/releases/tag/v1.5.7) 
release notes say
   
   > Enhanced Compression Speed for Small Data Blocks
   
   Note: Celeborn Spark shaded client does not ship the zstd-jni and always 
uses Spark's built-in zstd-jni, if someone wants to test the perf improvement, 
he/she should upgrade the Spark Spark's built-in zstd-jni first.
   


-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: [email protected]

For queries about this service, please contact Infrastructure at:
[email protected]

Reply via email to