xuanyuanking commented on a change in pull request #20303: [SPARK-23128][SQL] A new approach to do adaptive execution in Spark SQL URL: https://github.com/apache/spark/pull/20303#discussion_r251890917
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlan.scala ########## @@ -0,0 +1,126 @@ +/* + * 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 java.util.concurrent.CountDownLatch + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.SparkSession +import org.apache.spark.sql.catalyst.InternalRow +import org.apache.spark.sql.catalyst.expressions.Attribute +import org.apache.spark.sql.execution.{LeafExecNode, SparkPlan, SparkPlanInfo, SQLExecution} +import org.apache.spark.sql.execution.ui.SparkListenerSQLAdaptiveExecutionUpdate + +/** + * A root node to trigger query stages and execute the query plan adaptively. It incrementally + * updates the query plan when a query stage is materialized and provides accurate runtime + * statistics. + */ +case class AdaptiveSparkPlan(initialPlan: ResultQueryStage, session: SparkSession) + extends LeafExecNode{ + + override def output: Seq[Attribute] = initialPlan.output + + @volatile private var currentQueryStage: QueryStage = initialPlan + @volatile private var error: Throwable = null + private val readyLock = new CountDownLatch(1) + + private def replaceStage(oldStage: QueryStage, newStage: QueryStage): QueryStage = { + if (oldStage.id == newStage.id) { + newStage + } else { + val newPlanForOldStage = oldStage.plan.transform { + case q: QueryStage => replaceStage(q, newStage) + } + oldStage.withNewPlan(newPlanForOldStage) + } + } + + private def createCallback(executionId: Option[Long]): QueryStageTriggerCallback = { + new QueryStageTriggerCallback { + override def onStageUpdated(stage: QueryStage): Unit = { + updateCurrentQueryStage(stage, executionId) + if (stage.isInstanceOf[ResultQueryStage]) readyLock.countDown() + } + + override def onStagePlanningFailed(stage: QueryStage, e: Throwable): Unit = { + error = new RuntimeException( Review comment: Make sense, RuntimeException will kill the whole executor. ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
