ulysses-you commented on code in PR #6093:
URL: https://github.com/apache/incubator-gluten/pull/6093#discussion_r1642691198
##########
gluten-core/src/main/scala/org/apache/gluten/execution/JoinExecTransformer.scala:
##########
@@ -370,6 +371,66 @@ abstract class ShuffledHashJoinExecTransformerBase(
}
}
+object ShuffledHashJoinExecTransformerBase {
+
+ private def getBuildSide(sj: ShuffledJoin, buildSide: BuildSide = null):
BuildSide = {
+ val leftBuildable =
+
BackendsApiManager.getSettings.supportHashBuildJoinTypeOnLeft(sj.joinType)
+ val rightBuildable =
+
BackendsApiManager.getSettings.supportHashBuildJoinTypeOnRight(sj.joinType)
+ if (!leftBuildable) {
+ BuildRight
+ } else if (!rightBuildable) {
+ BuildLeft
+ } else {
+ sj.logicalLink match {
+ case Some(join: Join) =>
+ val leftSize = join.left.stats.sizeInBytes
+ val rightSize = join.right.stats.sizeInBytes
+ if (rightSize <= leftSize) BuildRight else BuildLeft
+ // Only the ShuffledHashJoinExec generated directly in some spark
tests is not link
+ // logical plan, such as OuterJoinSuite.
+ case _ => Option(buildSide).getOrElse(BuildRight)
+ }
+ }
+ }
+
+ private def dropPartialSort(plan: SparkPlan): SparkPlan = plan match {
+ case sort: SortExecTransformer if !sort.global =>
+ sort.child
+ case sort: SortExec if !sort.global =>
+ sort.child
+ case _ => plan
+ }
+
+ def from(shj: ShuffledHashJoinExec): ShuffledHashJoinExecTransformerBase = {
+ BackendsApiManager.getSparkPlanExecApiInstance
+ .genShuffledHashJoinExecTransformer(
+ shj.leftKeys,
+ shj.rightKeys,
+ shj.joinType,
+ getBuildSide(shj, shj.buildSide),
+ shj.condition,
+ shj.left,
+ shj.right,
+ shj.isSkewJoin)
+ }
+
+ def from(smj: SortMergeJoinExec): ShuffledHashJoinExecTransformerBase = {
+ BackendsApiManager.getSparkPlanExecApiInstance
+ .genShuffledHashJoinExecTransformer(
+ smj.leftKeys,
+ smj.rightKeys,
+ smj.joinType,
+ getBuildSide(smj),
+ smj.condition,
+ dropPartialSort(smj.left),
Review Comment:
see PullOutPreProject
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
