Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

chore: Don't transform the HashAggregate to CometHashAggregate if Comet shuffle is disabled #991

Merged
merged 1 commit into from
Oct 1, 2024
+13 −5
Merged

chore: Don't transform the HashAggregate to CometHashAggregate if Comet shuffle is disabled #991

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 13 additions & 5 deletions spark/src/main/scala/org/apache/comet/CometSparkSessionExtensions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -439,7 +439,11 @@ class CometSparkSessionExtensions

case op: BaseAggregateExec
if op.isInstanceOf[HashAggregateExec] ||
op.isInstanceOf[ObjectHashAggregateExec] =>
op.isInstanceOf[ObjectHashAggregateExec] &&
// When Comet shuffle is disabled, we don't want to transform the HashAggregate
// to CometHashAggregate. Otherwise, we probably get partial Comet aggregation
// and final Spark aggregation.
isCometShuffleEnabled(conf) =>
val groupingExprs = op.groupingExpressions
val aggExprs = op.aggregateExpressions
val resultExpressions = op.resultExpressions
Expand All @@ -451,8 +455,10 @@ class CometSparkSessionExtensions
// Fallback to Spark nevertheless here.
op
} else {
// For a final mode HashAggregate, we only need to transform the HashAggregate
// if there is Comet partial aggregation.
val sparkFinalMode = {
!modes.isEmpty && modes.head == Final && findPartialAgg(child).isEmpty
!modes.isEmpty && modes.head == Final && findCometPartialAgg(child).isEmpty
}

if (sparkFinalMode) {
Expand Down Expand Up @@ -995,13 +1001,15 @@ class CometSparkSessionExtensions
* Find the first Comet partial aggregate in the plan. If it reaches a Spark HashAggregate
* with partial mode, it will return None.
*/
def findPartialAgg(plan: SparkPlan): Option[CometHashAggregateExec] = {
def findCometPartialAgg(plan: SparkPlan): Option[CometHashAggregateExec] = {
plan.collectFirst {
case agg: CometHashAggregateExec if agg.aggregateExpressions.forall(_.mode == Partial) =>
Some(agg)
case agg: HashAggregateExec if agg.aggregateExpressions.forall(_.mode == Partial) => None
case a: AQEShuffleReadExec => findPartialAgg(a.child)
case s: ShuffleQueryStageExec => findPartialAgg(s.plan)
case agg: ObjectHashAggregateExec if agg.aggregateExpressions.forall(_.mode == Partial) =>
None
case a: AQEShuffleReadExec => findCometPartialAgg(a.child)
case s: ShuffleQueryStageExec => findCometPartialAgg(s.plan)
}.flatten
}

Expand Down
Loading