[GitHub] [spark] mridulm commented on pull request #40193: [SPARK-42528] Optimize PercentileHeap further by removing averaging

["mridulm (via GitHub)" <gi...@apache.org>]

mridulm commented on PR #40193:
URL: https://github.com/apache/spark/pull/40193#issuecomment-1447649892

   My main concern is for tasksets with very low number of tasks, where the change can result in nontrivial difference.
   Given the performance impact is minimal overall, I am not convinced whether we want to make this change.


-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org