Create a trait ShuffledJoin for SMJ and SHJ

Author: c21

sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledHashJoinExec.scala

@@ -40,27 +40,14 @@ case class ShuffledHashJoinExec(
     condition: Option[Expression],
     left: SparkPlan,
     right: SparkPlan)
-  extends HashJoin {
+  extends HashJoin with ShuffledJoin {
 
   override lazy val metrics = Map(
     "numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows"),
     "buildDataSize" -> SQLMetrics.createSizeMetric(sparkContext, "data size of build side"),
     "buildTime" -> SQLMetrics.createTimingMetric(sparkContext, "time to build hash map"))
 
-  override def outputPartitioning: Partitioning = joinType match {
-    case _: InnerLike =>
-      PartitioningCollection(Seq(left.outputPartitioning, right.outputPartitioning))
-    // For left and right outer joins, the output is partitioned by the streamed input's join keys.
-    case LeftOuter => left.outputPartitioning
-    case RightOuter => right.outputPartitioning
-    case LeftExistence(_) => left.outputPartitioning
-    case x =>
-      throw new IllegalArgumentException(
-        s"${getClass.getSimpleName} should not take $x as the JoinType")
-  }
-
-  override def requiredChildDistribution: Seq[Distribution] =
-    HashClusteredDistribution(leftKeys) :: HashClusteredDistribution(rightKeys) :: Nil
+  override def outputPartitioning: Partitioning = super[ShuffledJoin].outputPartitioning
 
   private def buildHashedRelation(iter: Iterator[InternalRow]): HashedRelation = {
     val buildDataSize = longMetric("buildDataSize")

sql/core/src/main/scala/org/apache/spark/sql/execution/joins/ShuffledJoin.scala

@@ -0,0 +1,43 @@
+/*
+ * 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.joins
+
+import org.apache.spark.sql.catalyst.plans.{FullOuter, InnerLike, LeftExistence, LeftOuter, RightOuter}
+import org.apache.spark.sql.catalyst.plans.physical.{Distribution, HashClusteredDistribution, Partitioning, PartitioningCollection, UnknownPartitioning}
+
+/**
+ * Holds common logic for join operators by shuffling two child relations
+ * using the join keys.
+ */
+trait ShuffledJoin extends BaseJoinExec {
+  override def requiredChildDistribution: Seq[Distribution] = {
+    HashClusteredDistribution(leftKeys) :: HashClusteredDistribution(rightKeys) :: Nil
+  }
+
+  override def outputPartitioning: Partitioning = joinType match {
+    case _: InnerLike =>
+      PartitioningCollection(Seq(left.outputPartitioning, right.outputPartitioning))
+    case LeftOuter => left.outputPartitioning
+    case RightOuter => right.outputPartitioning
+    case FullOuter => UnknownPartitioning(left.outputPartitioning.numPartitions)
+    case LeftExistence(_) => left.outputPartitioning
+    case x =>
+      throw new IllegalArgumentException(
+        s"ShuffledJoin should not take $x as the JoinType")
+  }
+}

sql/core/src/main/scala/org/apache/spark/sql/execution/joins/SortMergeJoinExec.scala

@@ -41,7 +41,7 @@ case class SortMergeJoinExec(
     condition: Option[Expression],
     left: SparkPlan,
     right: SparkPlan,
-    isSkewJoin: Boolean = false) extends BaseJoinExec with CodegenSupport {
+    isSkewJoin: Boolean = false) extends ShuffledJoin with CodegenSupport {
 
   override lazy val metrics = Map(
     "numOutputRows" -> SQLMetrics.createMetric(sparkContext, "number of output rows"))
@@ -72,26 +72,13 @@ case class SortMergeJoinExec(
     }
   }
 
-  override def outputPartitioning: Partitioning = joinType match {
-    case _: InnerLike =>
-      PartitioningCollection(Seq(left.outputPartitioning, right.outputPartitioning))
-    // For left and right outer joins, the output is partitioned by the streamed input's join keys.
-    case LeftOuter => left.outputPartitioning
-    case RightOuter => right.outputPartitioning
-    case FullOuter => UnknownPartitioning(left.outputPartitioning.numPartitions)
-    case LeftExistence(_) => left.outputPartitioning
-    case x =>
-      throw new IllegalArgumentException(
-        s"${getClass.getSimpleName} should not take $x as the JoinType")
-  }
-
   override def requiredChildDistribution: Seq[Distribution] = {
     if (isSkewJoin) {
       // We re-arrange the shuffle partitions to deal with skew join, and the new children
       // partitioning doesn't satisfy `HashClusteredDistribution`.
       UnspecifiedDistribution :: UnspecifiedDistribution :: Nil
     } else {
-      HashClusteredDistribution(leftKeys) :: HashClusteredDistribution(rightKeys) :: Nil
+      super.requiredChildDistribution
     }
   }