maropu commented on a change in pull request #32210:
URL: https://github.com/apache/spark/pull/32210#discussion_r619981709
##########
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:
> @maropu - yes, more data is in #32210 (comment) .
Ah, thanks. I missed that comment. It looks nice.
--
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]
