Github user JoshRosen commented on a diff in the pull request:
https://github.com/apache/spark/pull/11403#discussion_r55435156
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/exchange/Exchange.scala
---
@@ -0,0 +1,91 @@
+/*
+ * 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 scala.collection.mutable
+import scala.collection.mutable.ArrayBuffer
+
+import org.apache.spark.broadcast
+import org.apache.spark.rdd.RDD
+import org.apache.spark.sql.SQLContext
+import org.apache.spark.sql.catalyst.InternalRow
+import org.apache.spark.sql.catalyst.expressions.Attribute
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.execution.{LeafNode, SparkPlan, UnaryNode}
+import org.apache.spark.sql.types.StructType
+
+/**
+ * An interface for exchanges.
+ */
+abstract class Exchange extends UnaryNode {
+ override def output: Seq[Attribute] = child.output
+}
+
+/**
+ * A wrapper for reused exchange to have different output, which is
required to resolve the
+ * attributes in following plans.
+ */
+case class ReusedExchange(override val output: Seq[Attribute], child:
Exchange) extends LeafNode {
+
+ override def sameResult(plan: SparkPlan): Boolean = {
+ // Ignore this wrapper. `plan` could also be a ReusedExchange, so we
reverse the order here.
+ plan.sameResult(child)
+ }
+
+ def doExecute(): RDD[InternalRow] = {
+ child.execute()
+ }
+
+ override protected[sql] def doExecuteBroadcast[T]():
broadcast.Broadcast[T] = {
+ child.executeBroadcast()
+ }
+
+ // Do not repeat the same tree in explain.
+ override def treeChildren: Seq[SparkPlan] = Nil
+}
+
+/**
+ * Find out duplicated exchanges in the spark plan, then use the same
exchange for all the
+ * references.
+ */
+private[sql] case class ReuseExchange(sqlContext: SQLContext) extends
Rule[SparkPlan] {
+
+ def apply(plan: SparkPlan): SparkPlan = {
+ if (!sqlContext.conf.exchangeReuseEnabled) {
+ return plan
+ }
+ // Build a hash map using schema of exchanges to avoid O(N*N)
sameResult calls.
+ val exchanges = mutable.HashMap[StructType, ArrayBuffer[Exchange]]()
+ plan.transformUp {
+ case exchange: Exchange =>
+ val sameSchema = exchanges.getOrElseUpdate(exchange.schema,
ArrayBuffer[Exchange]())
+ val samePlan = sameSchema.find { e =>
+ exchange.sameResult(e)
+ }
+ if (samePlan.isDefined) {
+ // Keep the output of this exchange, the following plans require
that to resolve
+ // attributes.
+ val reused = ReusedExchange(exchange.output, samePlan.get)
--- End diff --
Don't need to assign to this intermediate variable.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastruct...@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
