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 2020/09/01 01:48:38 UTC

[GitHub] [spark] manuzhang commented on pull request #29593: [SPARK-32753][SQL] Update logical link when eliminating Exchange with same partitioning with AQE

manuzhang commented on pull request #29593:
URL: https://github.com/apache/spark/pull/29593#issuecomment-684142596


   https://github.com/apache/spark/blob/701e5934140e477426cf2a68f2c5746be67418d6/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala#L494-L514
   
   The query stage to replace, `ShuffleQueryStage`, is linked to logical node `Aggregate(...)` instead of `RepartitionByExpression(Aggregate(...))` without update in eliminating Exchange.  That lead to a new physical node of `ShuffleQueryStage` which will replace `HashAggregate(ShuffleQueryStage...)` where the final aggregate is lost


----------------------------------------------------------------
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