peter-toth commented on a change in pull request #28885:
URL: https://github.com/apache/spark/pull/28885#discussion_r654293110
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/ExplainUtils.scala
##########
@@ -41,22 +38,15 @@ object ExplainUtils extends AdaptiveSparkPlanHelper {
*
* @param plan Input query plan to process
* @param append function used to append the explain output
- * @param startOperatorID The start value of operation id. The subsequent
operations will
- * be assigned higher value.
*
* @return The last generated operation id for this input plan. This is to
ensure we
Review comment:
Fixed in
https://github.com/apache/spark/pull/28885/commits/7187ebd2e053570d92017100dba4a0738fa2f014.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/reuse/ReuseExchangeAndSubquery.scala
##########
@@ -0,0 +1,61 @@
+/*
+ * 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.reuse
+
+import org.apache.spark.sql.catalyst.rules.Rule
+import org.apache.spark.sql.catalyst.trees.TreePattern._
+import org.apache.spark.sql.execution.{BaseSubqueryExec,
ExecSubqueryExpression, ReusedSubqueryExec, SparkPlan}
+import org.apache.spark.sql.execution.exchange.{Exchange, ReusedExchangeExec}
+import org.apache.spark.sql.util.ReuseMap
+
+/**
+ * Find out duplicated exchanges and subqueries in the whole spark plan
including subqueries, then
+ * use the same exchange or subquery for all the references.
Review comment:
Ok, added the explanation in
https://github.com/apache/spark/pull/28885/commits/7187ebd2e053570d92017100dba4a0738fa2f014
##########
File path: sql/catalyst/src/main/scala/org/apache/spark/sql/util/ReuseMap.scala
##########
@@ -0,0 +1,73 @@
+/*
+ * 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.util
+
+import scala.collection.mutable.{ArrayBuffer, Map}
+
+import org.apache.spark.sql.catalyst.plans.QueryPlan
+import org.apache.spark.sql.types.StructType
+
+/**
+ * Map of canonicalized plans that can be used to find reuse possibilities.
+ *
+ * To avoid costly canonicalization of a plan:
+ * - we use its schema first to check if it can be replaced to a reused one at
all
+ * - we insert it into the map of canonicalized plans only when at least 2
have the same schema
+ *
+ * @tparam T the type of the node we want to reuse
+ * @tparam T2 the type of the canonicalized node
+ */
+class ReuseMap[T <: T2, T2 <: QueryPlan[T2]] {
+ private val map = Map[StructType, ArrayBuffer[T]]()
+
+ /**
+ * Find a matching plan with the same canonicalized form in the map or add
the new plan to the
+ * map otherwise.
+ *
+ * @param plan the input plan
+ * @return the matching plan or the input plan
+ */
+ def lookupOrElseAdd(plan: T): T = {
Review comment:
Fixed in
https://github.com/apache/spark/pull/28885/commits/7187ebd2e053570d92017100dba4a0738fa2f014
--
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
