maropu commented on a change in pull request #29104:
URL: https://github.com/apache/spark/pull/29104#discussion_r454744947
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/BroadcastNestedLoopJoinExec.scala
##########
@@ -205,6 +226,117 @@ case class BroadcastNestedLoopJoinExec(
}
}
+ case class NotInSubquerySingleColumnOptimizeParams(
+ buildSideHashSet: mutable.HashSet[AnyRef],
+ isNullExists: Boolean,
+ isBuildRowsEmpty: Boolean)
+
+ private def notInSubquerySingleColumnOptimizeEnabled: Boolean = {
+ if (SQLConf.get.notInSubquerySingleColumnOptimizeEnabled &&
right.output.length == 1) {
+ // buildSide must be single column
+ // and condition must be either of following pattern
+ // or(a=b,isnull(a=b))
+ // or(isnull(a=b),a=b)
+ condition.get match {
+ case _@Or(_@EqualTo(leftAttr: AttributeReference, rightAttr:
AttributeReference),
+ _@IsNull(_@EqualTo(tmpLeft: AttributeReference, tmpRight:
AttributeReference)))
+ if leftAttr.semanticEquals(tmpLeft) &&
rightAttr.semanticEquals(tmpRight) =>
+ notInSubquerySingleColumnOptimizeSetStreamedKey(leftAttr, rightAttr)
+ if (notInSubquerySingleColumnOptimizeStreamedKeyIndex != -1) {
+ true
+ } else {
+ logWarning(s"failed to find
notInSubquerySingleColumnOptimizeStreamedKeyIndex," +
+ s" fallback to leftExistenceJoin.")
+ false
+ }
+ case _@Or(_@IsNull(_@EqualTo(tmpLeft: AttributeReference, tmpRight:
AttributeReference)),
+ _@EqualTo(leftAttr: AttributeReference, rightAttr:
AttributeReference))
+ if leftAttr.semanticEquals(tmpLeft) &&
rightAttr.semanticEquals(tmpRight) =>
+ notInSubquerySingleColumnOptimizeSetStreamedKey(leftAttr, rightAttr)
+ if (notInSubquerySingleColumnOptimizeStreamedKeyIndex != -1) {
+ true
+ } else {
+ logWarning(s"failed to find
notInSubquerySingleColumnOptimizeStreamedKeyIndex," +
+ s" fallback to leftExistenceJoin.")
+ false
Review comment:
This code block is the same with the line244-251? If so, could you merge
them? How about defining an extractor object for the case?
----------------------------------------------------------------
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]
