cloud-fan commented on a change in pull request #31984:
URL: https://github.com/apache/spark/pull/31984#discussion_r607540865
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala
##########
@@ -160,8 +160,7 @@ object PartitionPruning extends Rule[LogicalPlan] with
PredicateHelper with Join
// We can't reuse the broadcast because the join type doesn't support
broadcast,
// and doing DPP means running an extra query that may have significant
overhead.
// We need to make sure the pruning side is very big so that DPP is
still worthy.
- canBroadcastBySize(otherPlan, conf) &&
Review comment:
Previously, we only check `canBroadcastBySize` in the else branch. That
means, if broadcastOnly=false, we can do DPP if the join type allows doing
broadcast, and we don't care if the size is large or not, we only care the cost
`estimatePruningSideSize > overhead`.
This is a bit aggressive but it was the behavior since the beginning. Shall
we restore the behavior? @wangyum
--
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
