c21 commented on a change in pull request #32210:
URL: https://github.com/apache/spark/pull/32210#discussion_r619988615
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoinExec.scala
##########
@@ -81,11 +83,22 @@ case class ShuffledHashJoinExec(
protected override def doExecute(): RDD[InternalRow] = {
val numOutputRows = longMetric("numOutputRows")
+ val spillThreshold = getSpillThreshold
+ val inMemoryThreshold = getInMemoryThreshold
+ val streamSortPlan = getStreamSortPlan
+ val buildSortPlan = getBuildSortPlan
+ val fallbackSMJPlan = SortMergeJoinExec(leftKeys, rightKeys, joinType,
condition, left, right)
+
streamedPlan.execute().zipPartitions(buildPlan.execute()) { (streamIter,
buildIter) =>
- val hashed = buildHashedRelation(buildIter)
- joinType match {
- case FullOuter => fullOuterJoin(streamIter, hashed, numOutputRows)
- case _ => join(streamIter, hashed, numOutputRows)
+ buildHashedRelation(buildIter) match {
+ case r: UnfinishedUnsafeHashedRelation =>
+ joinWithSortFallback(streamIter, buildIter, r.destructiveValues(),
streamSortPlan,
Review comment:
> is there any other faster ballback logic than the current approach.
@maropu - yes, I am open and welcome any suggestion as well. Thanks for more
insights from @sigmod and you @maropu . I will take a deeper look of hybrid
join as in documentations you guys provided, and get back to you guys later.
--
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]
