[GitHub] [spark] imback82 commented on a change in pull request #29074: [SPARK-32282][SQL] Improve EnsureRquirement.reorderJoinKeys to handle more scenarios such as PartitioningCollection

[GitBox <gi...@apache.org>]

imback82 commented on a change in pull request #29074:
URL: https://github.com/apache/spark/pull/29074#discussion_r500687979



##########
File path: sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/EnsureRequirements.scala
##########
@@ -171,19 +176,54 @@ case class EnsureRequirements(conf: SQLConf) extends Rule[SparkPlan] {
       leftPartitioning: Partitioning,
       rightPartitioning: Partitioning): (Seq[Expression], Seq[Expression]) = {
     if (leftKeys.forall(_.deterministic) && rightKeys.forall(_.deterministic)) {
-      (leftPartitioning, rightPartitioning) match {
-        case (HashPartitioning(leftExpressions, _), _) =>
-          reorder(leftKeys.toIndexedSeq, rightKeys.toIndexedSeq, leftExpressions, leftKeys)
-        case (_, HashPartitioning(rightExpressions, _)) =>
-          reorder(leftKeys.toIndexedSeq, rightKeys.toIndexedSeq, rightExpressions, rightKeys)
-        case _ =>
-          (leftKeys, rightKeys)
-      }
+      reorderJoinKeysRecursively(
+        leftKeys,
+        rightKeys,
+        Some(leftPartitioning),
+        Some(rightPartitioning))
+        .getOrElse((leftKeys, rightKeys))
     } else {
       (leftKeys, rightKeys)
     }
   }
 
+  /**
+   * Recursively reorders the join keys based on partitioning. It starts reordering the
+   * join keys to match HashPartitioning on either side, followed by PartitioningCollection.
+   */
+  private def reorderJoinKeysRecursively(
+      leftKeys: Seq[Expression],
+      rightKeys: Seq[Expression],
+      leftPartitioning: Option[Partitioning],
+      rightPartitioning: Option[Partitioning]): Option[(Seq[Expression], Seq[Expression])] = {
+    (leftPartitioning, rightPartitioning) match {
+      case (Some(HashPartitioning(leftExpressions, _)), _) =>
+        reorder(leftKeys.toIndexedSeq, rightKeys.toIndexedSeq, leftExpressions, leftKeys)
+          .orElse(reorderJoinKeysRecursively(
+            leftKeys, rightKeys, None, rightPartitioning))
+      case (_, Some(HashPartitioning(rightExpressions, _))) =>
+        reorder(leftKeys.toIndexedSeq, rightKeys.toIndexedSeq, rightExpressions, rightKeys)
+          .orElse(reorderJoinKeysRecursively(
+            leftKeys, rightKeys, leftPartitioning, None))
+      case (Some(PartitioningCollection(partitionings)), _) =>
+        partitionings.foreach { p =>
+          reorderJoinKeysRecursively(leftKeys, rightKeys, Some(p), rightPartitioning).map { k =>
+            return Some(k)

Review comment:
       Thanks, updated.

##########
File path: sql/core/src/test/scala/org/apache/spark/sql/execution/exchange/EnsureRequirementsSuite.scala
##########
@@ -0,0 +1,146 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements.  See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License.  You may obtain a copy of the License at
+ *
+ *    http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.execution.exchange
+
+import org.apache.spark.sql.catalyst.expressions.Literal
+import org.apache.spark.sql.catalyst.plans.Inner
+import org.apache.spark.sql.catalyst.plans.physical.{HashPartitioning, PartitioningCollection}
+import org.apache.spark.sql.execution.{DummySparkPlan, SortExec}
+import org.apache.spark.sql.execution.joins.SortMergeJoinExec
+import org.apache.spark.sql.test.SharedSparkSession
+
+class EnsureRequirementsSuite extends SharedSparkSession {
+  private val exprA = Literal(1)
+  private val exprB = Literal(2)
+  private val exprC = Literal(3)
+
+  test("reorder should handle PartitioningCollection") {
+    val plan1 = DummySparkPlan(
+      outputPartitioning = PartitioningCollection(Seq(
+        HashPartitioning(exprA :: exprB :: Nil, 5),
+        HashPartitioning(exprA :: Nil, 5))))
+    val plan2 = DummySparkPlan()
+
+    // Test PartitioningCollection on the left side of join.
+    val smjExec1 = SortMergeJoinExec(
+      exprB :: exprA :: Nil, exprA :: exprB :: Nil, Inner, None, plan1, plan2)
+    EnsureRequirements(spark.sessionState.conf).apply(smjExec1) match {
+      case SortMergeJoinExec(leftKeys, rightKeys, _, _,
+        SortExec(_, _,
+          DummySparkPlan(_, _, PartitioningCollection(leftPartitionings), _, _), _),
+        SortExec(_, _,
+          ShuffleExchangeExec(HashPartitioning(rightPartitioningExpressions, _), _, _), _), _) =>
+        assert(leftKeys !== smjExec1.leftKeys)
+        assert(rightKeys !== smjExec1.rightKeys)
+        assert(leftKeys === leftPartitionings.head.asInstanceOf[HashPartitioning].expressions)

Review comment:
       OK. I simplified the checks in this test.




----------------------------------------------------------------
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:
users@infra.apache.org



---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org