Skip to content

[SPARK-32220][SQL][3.0][FOLLOW-UP]SHUFFLE_REPLICATE_NL Hint should not change Non-Cartesian Product join result #29093

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

Closed
AngersZhuuuu wants to merge 1 commit into from
Closed

[SPARK-32220][SQL][3.0][FOLLOW-UP]SHUFFLE_REPLICATE_NL Hint should not change Non-Cartesian Product join result #29093

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
14 changes: 8 additions & 6 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/SparkStrategies.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -244,7 +244,7 @@ abstract class SparkStrategies extends QueryPlanner[SparkPlan] {
// 4. Pick cartesian product if join type is inner like.
// 5. Pick broadcast nested loop join as the final solution. It may OOM but we don't have
// other choice.
case p @ ExtractEquiJoinKeys(joinType, leftKeys, rightKeys, condition, left, right, hint) =>
case j @ ExtractEquiJoinKeys(joinType, leftKeys, rightKeys, nonEquiCond, left, right, hint) =>
def createBroadcastHashJoin(buildLeft: Boolean, buildRight: Boolean) = {
val wantToBuildLeft = canBuildLeft(joinType) && buildLeft
val wantToBuildRight = canBuildRight(joinType) && buildRight
Expand All @@ -254,7 +254,7 @@ abstract class SparkStrategies extends QueryPlanner[SparkPlan] {
rightKeys,
joinType,
buildSide,
condition,
nonEquiCond,
planLater(left),
planLater(right)))
}
Expand All @@ -269,7 +269,7 @@ abstract class SparkStrategies extends QueryPlanner[SparkPlan] {
rightKeys,
joinType,
buildSide,
condition,
nonEquiCond,
planLater(left),
planLater(right)))
}
Expand All @@ -278,15 +278,17 @@ abstract class SparkStrategies extends QueryPlanner[SparkPlan] {
def createSortMergeJoin() = {
if (RowOrdering.isOrderable(leftKeys)) {
Some(Seq(joins.SortMergeJoinExec(
leftKeys, rightKeys, joinType, condition, planLater(left), planLater(right))))
leftKeys, rightKeys, joinType, nonEquiCond, planLater(left), planLater(right))))
} else {
None
}
}

def createCartesianProduct() = {
if (joinType.isInstanceOf[InnerLike]) {
Some(Seq(joins.CartesianProductExec(planLater(left), planLater(right), p.condition)))
// `CartesianProductExec` can't implicitly evaluate equal join condition, here we should
// pass the original condition which includes both equal and non-equal conditions.
Some(Seq(joins.CartesianProductExec(planLater(left), planLater(right), j.condition)))
} else {
None
}
Expand All @@ -311,7 +313,7 @@ abstract class SparkStrategies extends QueryPlanner[SparkPlan] {
// This join could be very slow or OOM
val buildSide = getSmallerSide(left, right)
Seq(joins.BroadcastNestedLoopJoinExec(
planLater(left), planLater(right), buildSide, joinType, condition))
planLater(left), planLater(right), buildSide, joinType, nonEquiCond))
}
}

Expand Down