cloud-fan commented on a change in pull request #26289:
[SPARK-28560][SQL][followup] support the build side to local shuffle reader as
far as possible in BroadcastHashJoin
URL: https://github.com/apache/spark/pull/26289#discussion_r340524707
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeLocalShuffleReader.scala
##########
@@ -56,16 +68,27 @@ case class OptimizeLocalShuffleReader(conf: SQLConf)
extends Rule[SparkPlan] {
case e: ShuffleExchangeExec => e
}.length
}
-
+ // Check whether additional shuffle introduced. If introduced, revert the
local reader.
val numExchangeBefore = numExchanges(EnsureRequirements(conf).apply(plan))
- val numExchangeAfter =
numExchanges(EnsureRequirements(conf).apply(optimizedPlan))
-
- if (numExchangeAfter > numExchangeBefore) {
- logDebug("OptimizeLocalShuffleReader rule is not applied due" +
+ val numExchangeAfter =
numExchanges(EnsureRequirements(conf).apply(withProbeSideLocalReader))
+ val optimizedPlan = if (numExchangeAfter > numExchangeBefore) {
+ logDebug("OptimizeLocalShuffleReader rule is not applied in the probe
side due" +
" to additional shuffles will be introduced.")
plan
} else {
- optimizedPlan
+ withProbeSideLocalReader
+ }
+ // Add the local reader in build side and and do not need to check whether
+ // additional shuffle introduced.
+ optimizedPlan.transformDown {
+ case join: BroadcastHashJoinExec if (join.buildSide == BuildLeft &&
Review comment:
nit: we can unify the condition check some how
```
object BroadcastJoinWithShuffleLeft {
def unapply(plan: LogicalPlan): Option[(QueryStageExec, BuildSide)] = plan
match {
case join: BroadcastHashJoinExec if
ShuffleQueryStageExec.isShuffleQueryStageExec(join.left) =>
Some((join.left.asInstanceOf[QueryStageExec], join.buildSide))
}
}
object BroadcastJoinWithShuffleRight ...
// add probe side local reader
case join @ BroadcastJoinWithShuffleLeft(shuffleStage, BuildRight) =>
val localReader = ...
join.copy(left = localReader)
...
// add build side local reader
case join @ BroadcastJoinWithShuffleLeft(shuffleStage, BuildLeft) =>
...
```
----------------------------------------------------------------
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]
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
