spark LogicalQueryStage 源码

  • 2022-10-20
  • 浏览 (212)

spark LogicalQueryStage 代码

文件路径:/sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/LogicalQueryStage.scala

/*
 * 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.catalyst.expressions.{Attribute, SortOrder}
import org.apache.spark.sql.catalyst.plans.logical.{LeafNode, LogicalPlan, RepartitionOperation, Statistics}
import org.apache.spark.sql.catalyst.trees.TreePattern.{LOGICAL_QUERY_STAGE, REPARTITION_OPERATION, TreePattern}
import org.apache.spark.sql.execution.SparkPlan

/**
 * The LogicalPlan wrapper for a [[QueryStageExec]], or a snippet of physical plan containing
 * a [[QueryStageExec]], in which all ancestor nodes of the [[QueryStageExec]] are linked to
 * the same logical node.
 *
 * For example, a logical Aggregate can be transformed into FinalAgg - Shuffle - PartialAgg, in
 * which the Shuffle will be wrapped into a [[QueryStageExec]], thus the [[LogicalQueryStage]]
 * will have FinalAgg - QueryStageExec as its physical plan.
 */
// TODO we can potentially include only [[QueryStageExec]] in this class if we make the aggregation
// planning aware of partitioning.
case class LogicalQueryStage(
    logicalPlan: LogicalPlan,
    physicalPlan: SparkPlan) extends LeafNode {

  override def output: Seq[Attribute] = logicalPlan.output
  override val isStreaming: Boolean = logicalPlan.isStreaming
  override val outputOrdering: Seq[SortOrder] = physicalPlan.outputOrdering
  override protected val nodePatterns: Seq[TreePattern] = {
    // Repartition is a special node that it represents a shuffle exchange,
    // then in AQE the repartition will be always wrapped into `LogicalQueryStage`
    val repartitionPattern = logicalPlan match {
      case _: RepartitionOperation => Some(REPARTITION_OPERATION)
      case _ => None
    }
    Seq(LOGICAL_QUERY_STAGE) ++ repartitionPattern
  }

  override def computeStats(): Statistics = {
    // TODO this is not accurate when there is other physical nodes above QueryStageExec.
    val physicalStats = physicalPlan.collectFirst {
      case s: QueryStageExec => s
    }.flatMap(_.computeStats())
    if (physicalStats.isDefined) {
      logDebug(s"Physical stats available as ${physicalStats.get} for plan: $physicalPlan")
    } else {
      logDebug(s"Physical stats not available for plan: $physicalPlan")
    }
    physicalStats.getOrElse(logicalPlan.stats)
  }

  override def maxRows: Option[Long] = stats.rowCount.map(_.min(Long.MaxValue).toLong)
}

相关信息

spark 源码目录

相关文章

spark AQEOptimizer 源码

spark AQEPropagateEmptyRelation 源码

spark AQEShuffleReadExec 源码

spark AQEShuffleReadRule 源码

spark AQEUtils 源码

spark AdaptiveRulesHolder 源码

spark AdaptiveSparkPlanExec 源码

spark AdaptiveSparkPlanHelper 源码

spark AdjustShuffleExchangePosition 源码

spark CoalesceShufflePartitions 源码

0  赞