Skip to content

[SPARK-32268][SQL][FOLLOWUP] Add ColumnPruning in injectBloomFilter #36047

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
Flyangz wants to merge 1 commit into from
Closed

[SPARK-32268][SQL][FOLLOWUP] Add ColumnPruning in injectBloomFilter #36047

Show file tree
Hide file tree
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
3 changes: 2 additions & 1 deletion ...catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/InjectRuntimeFilter.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,8 @@ object InjectRuntimeFilter extends Rule[LogicalPlan] with PredicateHelper with J
}
val aggExp = AggregateExpression(bloomFilterAgg, Complete, isDistinct = false, None)
val alias = Alias(aggExp, "bloomFilter")()
val aggregate = ConstantFolding(Aggregate(Nil, Seq(alias), filterCreationSidePlan))
val aggregate =
ConstantFolding(ColumnPruning(Aggregate(Nil, Seq(alias), filterCreationSidePlan)))
val bloomFilterSubquery = ScalarSubquery(aggregate, Nil)
val filter = BloomFilterMightContain(bloomFilterSubquery,
new XxHash64(Seq(filterApplicationSideExp)))
Expand Down
15 changes: 15 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/InjectRuntimeFilterSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -255,6 +255,7 @@ class InjectRuntimeFilterSuite extends QueryTest with SQLTestUtils with SharedSp
planEnabled = sql(query).queryExecution.optimizedPlan
checkAnswer(sql(query), expectedAnswer)
if (shouldReplace) {
assert(!columnPruningTakesEffect(planEnabled))
assert(getNumBloomFilters(planEnabled) > getNumBloomFilters(planDisabled))
} else {
assert(getNumBloomFilters(planEnabled) == getNumBloomFilters(planDisabled))
Expand Down Expand Up @@ -288,6 +289,20 @@ class InjectRuntimeFilterSuite extends QueryTest with SQLTestUtils with SharedSp
numMightContains
}

def columnPruningTakesEffect(plan: LogicalPlan): Boolean = {
def takesEffect(plan: LogicalPlan): Boolean = {
val result = org.apache.spark.sql.catalyst.optimizer.ColumnPruning.apply(plan)
!result.fastEquals(plan)
}

plan.collectFirst {
case Filter(condition, _) if condition.collectFirst {
case subquery: org.apache.spark.sql.catalyst.expressions.ScalarSubquery
if takesEffect(subquery.plan) => true
}.nonEmpty => true
}.nonEmpty
}

def assertRewroteSemiJoin(query: String): Unit = {
checkWithAndWithoutFeatureEnabled(query, testSemiJoin = true, shouldReplace = true)
}
Expand Down