You are viewing a plain text version of this content. The canonical link for it is here.

Posted to reviews@spark.apache.org by GitBox <gi...@apache.org> on 2021/02/25 21:18:10 UTC

[GitHub] [spark] ekoifman edited a comment on pull request #31653: SPARK-33832 v2. move OptimzieSkewedJoin to query stage preparation

ekoifman edited a comment on pull request #31653:
URL: https://github.com/apache/spark/pull/31653#issuecomment-786218496


   Hi @cloud-fan, @maryannxue 
   this is a rewrite based on the discussion in https://github.com/apache/spark/pull/30829.
   I created a new PR to make the differences between the 2 approaches easier to see.
   
   This is not fully polished but please take a look and provide feedback.  This solution moves `OptimizeSkewedJoin` to query stage preparation, adjusts the costing of new shuffles and enables `CoalesceShufflePartitions` to run after `OptimizeSkewedJoin`.  The amount of change here doesn't seem any less than in the original solution.  Please let me know if this looks like what you expected.


----------------------------------------------------------------
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.

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