[SPARK-23128][SQL] A new approach to do adaptive execution in Spark SQL #20303
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,115 @@ | ||
| /* | ||
| * 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.SparkException | ||
| 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 execute the query plan adaptively. It splits the query plan into independent | ||
| * stages and executes them in order according to their dependencies. The query stage | ||
| * materializes its output at the end. When one stage completes, the data statistics of its | ||
| * materialized output will be used to optimize the subsequent stages. | ||
| * This is called mid-query re-optimization in database literature. | ||
| */ | ||
| case class AdaptiveSparkPlanExec(initialPlan: SparkPlan, session: SparkSession) | ||
| extends LeafExecNode{ | ||
|
|
||
| override def output: Seq[Attribute] = initialPlan.output | ||
|
|
||
| @volatile private var currentPlan: SparkPlan = initialPlan | ||
| @volatile private var error: Throwable = null | ||
|
|
||
| // We will release the lock when all the query stages are completed, or we fail to | ||
| // optimize/execute query stages. Getting `finalPlan` will be blocked until the lock is release. | ||
| // This is better than wait()/notify(), as we can easily check if the computation has completed, | ||
| // by calling `readyLock.getCount()`. | ||
| private val readyLock = new CountDownLatch(1) | ||
|
|
||
| private def createCallback(executionId: Option[Long]) = new QueryStageManagerCallback { | ||
| override def onPlanUpdate(updatedPlan: SparkPlan): Unit = { | ||
| updateCurrentPlan(updatedPlan, executionId) | ||
| } | ||
|
|
||
| override def onFinalPlan(finalPlan: SparkPlan): Unit = { | ||
| updateCurrentPlan(finalPlan, executionId) | ||
| readyLock.countDown() | ||
| } | ||
|
|
||
| override def onStageMaterializationFailed(stage: QueryStageExec, e: Throwable): Unit = { | ||
| error = new SparkException( | ||
| s""" | ||
| |Fail to materialize query stage ${stage.id}: | ||
| |${stage.plan.treeString} | ||
| """.stripMargin, e) | ||
| readyLock.countDown() | ||
| } | ||
|
|
||
| override def onError(e: Throwable): Unit = { | ||
| error = e | ||
| readyLock.countDown() | ||
| } | ||
| } | ||
|
|
||
| private def updateCurrentPlan(newPlan: SparkPlan, executionId: Option[Long]): Unit = { | ||
| currentPlan = newPlan | ||
| executionId.foreach { id => | ||
| session.sparkContext.listenerBus.post(SparkListenerSQLAdaptiveExecutionUpdate( | ||
| id, | ||
| SQLExecution.getQueryExecution(id).toString, | ||
| SparkPlanInfo.fromSparkPlan(currentPlan))) | ||
| } | ||
| } | ||
|
|
||
| def finalPlan: SparkPlan = { | ||
| if (readyLock.getCount > 0) { | ||
| val sc = session.sparkContext | ||
| val executionId = Option(sc.getLocalProperty(SQLExecution.EXECUTION_ID_KEY)).map(_.toLong) | ||
| val stageManager = new QueryStageManager(initialPlan, session, createCallback(executionId)) | ||
| stageManager.start() | ||
| readyLock.await() | ||
| stageManager.stop() | ||
| } | ||
|
|
||
| if (error != null) throw error | ||
| currentPlan | ||
| } | ||
|
|
||
| override def executeCollect(): Array[InternalRow] = finalPlan.executeCollect() | ||
| override def executeTake(n: Int): Array[InternalRow] = finalPlan.executeTake(n) | ||
| override def executeToIterator(): Iterator[InternalRow] = finalPlan.executeToIterator() | ||
| override def doExecute(): RDD[InternalRow] = finalPlan.execute() | ||
| override def generateTreeString( | ||
| depth: Int, | ||
| lastChildren: Seq[Boolean], | ||
| append: String => Unit, | ||
| verbose: Boolean, | ||
| prefix: String = "", | ||
| addSuffix: Boolean = false, | ||
| maxFields: Int): Unit = { | ||
| currentPlan.generateTreeString( | ||
| depth, lastChildren, append, verbose, "", false, maxFields) | ||
| } | ||
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,39 @@ | ||
| /* | ||
| * 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.SparkSession | ||
| import org.apache.spark.sql.catalyst.rules.Rule | ||
| import org.apache.spark.sql.execution.SparkPlan | ||
| import org.apache.spark.sql.execution.command.ExecutedCommandExec | ||
|
|
||
| /** | ||
| * This rule wraps the query plan with an [[AdaptiveSparkPlanExec]], which executes the query plan | ||
| * adaptively with runtime data statistics. Note that this rule must be run after | ||
| * [[org.apache.spark.sql.execution.exchange.EnsureRequirements]], so that the exchange nodes are | ||
| * already inserted. | ||
| */ | ||
| case class InsertAdaptiveSparkPlan(session: SparkSession) extends Rule[SparkPlan] { | ||
|
|
||
| override def apply(plan: SparkPlan): SparkPlan = plan match { | ||
| case _: ExecutedCommandExec => plan | ||
| case _ if session.sessionState.conf.adaptiveExecutionEnabled => | ||
| AdaptiveSparkPlanExec(plan, session.cloneSession()) | ||
| case _ => plan | ||
| } | ||
| } |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
super nit: we can simply write
_ > 0