Skip to content

[SPARK-46037][SQL] Correctness fix for Shuffled Hash Join build left without codegen #47905

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
cloud-fan wants to merge 1 commit into from
Closed

[SPARK-46037][SQL] Correctness fix for Shuffled Hash Join build left without codegen #47905

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
5 changes: 2 additions & 3 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/joins/HashJoin.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -138,9 +138,8 @@ trait HashJoin extends JoinCodegenSupport {
UnsafeProjection.create(streamedBoundKeys)

@transient protected[this] lazy val boundCondition = if (condition.isDefined) {
if (joinType == FullOuter && buildSide == BuildLeft) {
// Put join left side before right side. This is to be consistent with
// `ShuffledHashJoinExec.fullOuterJoin`.
if ((joinType == FullOuter || joinType == LeftOuter) && buildSide == BuildLeft) {
// Put join left side before right side.
Predicate.create(condition.get, buildPlan.output ++ streamedPlan.output).eval _
} else {
Predicate.create(condition.get, streamedPlan.output ++ buildPlan.output).eval _
Expand Down
22 changes: 20 additions & 2 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/joins/OuterJoinSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,11 +26,12 @@ import org.apache.spark.sql.catalyst.plans.logical.{Join, JoinHint}
import org.apache.spark.sql.execution.{SparkPlan, SparkPlanTest}
import org.apache.spark.sql.execution.exchange.EnsureRequirements
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.test.SharedSparkSession
import org.apache.spark.sql.test.{SharedSparkSession, SQLTestData}
import org.apache.spark.sql.types.{DoubleType, IntegerType, StructType}

class OuterJoinSuite extends SparkPlanTest with SharedSparkSession {
class OuterJoinSuite extends SparkPlanTest with SharedSparkSession with SQLTestData {
import testImplicits.toRichColumn
setupTestData()

private val EnsureRequirements = new EnsureRequirements()

Expand Down Expand Up @@ -326,4 +327,21 @@ class OuterJoinSuite extends SparkPlanTest with SharedSparkSession {
(null, null, 7, 7.0)
)
)

testWithWholeStageCodegenOnAndOff(
"SPARK-46037: ShuffledHashJoin build left with left outer join, codegen off") { _ =>
def join(hint: String): DataFrame = {
sql(
s"""
|SELECT /*+ $hint */ *
|FROM testData t1
|LEFT OUTER JOIN
|testData2 t2
|ON key = a AND concat(value, b) = '12'
|""".stripMargin)
}
val df1 = join("SHUFFLE_HASH(t1)")
val df2 = join("SHUFFLE_MERGE(t1)")
checkAnswer(df1, identity, df2.collect().toSeq)
}
}