gatorsmile commented on a change in pull request #24706: [SPARK-23128][SQL] A 
new approach to do adaptive execution in Spark SQL
URL: https://github.com/apache/spark/pull/24706#discussion_r292898739
 
 

 ##########
 File path: 
sql/core/src/test/scala/org/apache/spark/sql/execution/adaptive/AdaptiveQueryExecSuite.scala
 ##########
 @@ -0,0 +1,275 @@
+/*
+ * 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.adaptive
+
+import org.apache.spark.sql.QueryTest
+import org.apache.spark.sql.execution.{ReusedSubqueryExec, SparkPlan}
+import org.apache.spark.sql.execution.joins.{BroadcastHashJoinExec, 
SortMergeJoinExec}
+import org.apache.spark.sql.internal.SQLConf
+import org.apache.spark.sql.test.SharedSQLContext
+
+class AdaptiveQueryExecSuite extends QueryTest with SharedSQLContext {
+
+  setupTestData()
+
+  private def runAdaptiveAndVerifyResult(query: String): (SparkPlan, 
SparkPlan) = {
+    val dfAdaptive = sql(query)
+    val result = dfAdaptive.collect()
+    withSQLConf(SQLConf.RUNTIME_REOPTIMIZATION_ENABLED.key -> "false") {
+      val df = sql(query)
+      QueryTest.sameRows(result.toSeq, df.collect().toSeq)
+    }
+    val plan = dfAdaptive.queryExecution.executedPlan
+    assert(plan.isInstanceOf[AdaptiveSparkPlanExec])
+    val adaptivePlan = plan.asInstanceOf[AdaptiveSparkPlanExec].executedPlan
+    (dfAdaptive.queryExecution.sparkPlan, adaptivePlan)
+  }
+
+  private def findTopLevelBroadcastHashJoin(plan: SparkPlan): 
Seq[BroadcastHashJoinExec] = {
+    plan.collect {
+      case j: BroadcastHashJoinExec => Seq(j)
+      case s: QueryStageExec => findTopLevelBroadcastHashJoin(s.plan)
+    }.flatten
+  }
+
+  private def findTopLevelSortMergeJoin(plan: SparkPlan): 
Seq[SortMergeJoinExec] = {
+    plan.collect {
+      case j: SortMergeJoinExec => Seq(j)
+      case s: QueryStageExec => findTopLevelSortMergeJoin(s.plan)
+    }.flatten
+  }
+
+  private def findReusedExchange(plan: SparkPlan): Seq[ReusedQueryStageExec] = 
{
+    plan.collect {
+      case e: ReusedQueryStageExec => Seq(e)
+      case a: AdaptiveSparkPlanExec => findReusedExchange(a.executedPlan)
+      case s: QueryStageExec => findReusedExchange(s.plan)
+      case p: SparkPlan => p.subqueries.flatMap(findReusedExchange)
+    }.flatten
+  }
+
+  private def findReusedSubquery(plan: SparkPlan): Seq[ReusedSubqueryExec] = {
+    plan.collect {
+      case e: ReusedSubqueryExec => Seq(e)
+      case s: QueryStageExec => findReusedSubquery(s.plan)
+      case p: SparkPlan => p.subqueries.flatMap(findReusedSubquery)
+    }.flatten
+  }
+
+  test("Change merge join to broadcast join") {
+    withSQLConf(
+        SQLConf.RUNTIME_REOPTIMIZATION_ENABLED.key -> "true",
+        SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "80") {
+      val (plan, adaptivePlan) = runAdaptiveAndVerifyResult(
+        "SELECT * FROM testData join testData2 ON key = a where value = '1'")
 
 Review comment:
   ```Scala
       withSQLConf(
           SQLConf.RUNTIME_REOPTIMIZATION_ENABLED.key -> "true",
           SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "80") {
         spark.sql(
           "SELECT * FROM testData join testData2 ON key = a where value = 
'1'").explain()
       }
   
       withSQLConf(
         SQLConf.RUNTIME_REOPTIMIZATION_ENABLED.key -> "false",
         SQLConf.AUTO_BROADCASTJOIN_THRESHOLD.key -> "80") {
         spark.sql(
           "SELECT * FROM testData join testData2 ON key = a where value = 
'1'").explain()
       }
   ```
   
   Try these? It sounds like the WholeStage codegen ID is lost after we turn on 
the adaptive query execution.

----------------------------------------------------------------
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:
us...@infra.apache.org


With regards,
Apache Git Services

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

Reply via email to