Skip to content

[SPARK-28560][SQL][followup] change the local shuffle reader from leaf node to unary node #26250

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
JkSelf wants to merge 2 commits into from
Closed

[SPARK-28560][SQL][followup] change the local shuffle reader from leaf node to unary node #26250

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
06847fe
change the leaf node to unary node about local shuffle reader exec
JkSelf Oct 25, 2019
b5eb977
resolve the comments
JkSelf Oct 28, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion sql/core/src/main/scala/org/apache/spark/sql/execution/SparkPlanInfo.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,6 @@ private[execution] object SparkPlanInfo {
case ReusedSubqueryExec(child) => child :: Nil
case a: AdaptiveSparkPlanExec => a.executedPlan :: Nil
case stage: QueryStageExec => stage.plan :: Nil
case localReader: LocalShuffleReaderExec => localReader.child :: Nil
case _ => plan.children ++ plan.subqueries
}
val metrics = plan.metrics.toSeq.map { case (key, metric) =>
Expand Down
1 change: 0 additions & 1 deletion ...core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanHelper.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,7 +125,6 @@ trait AdaptiveSparkPlanHelper {
private def allChildren(p: SparkPlan): Seq[SparkPlan] = p match {
case a: AdaptiveSparkPlanExec => Seq(a.executedPlan)
case s: QueryStageExec => Seq(s.plan)
case l: LocalShuffleReaderExec => Seq(l.child)
case _ => p.children
}
}
4 changes: 2 additions & 2 deletions ...e/src/main/scala/org/apache/spark/sql/execution/adaptive/OptimizeLocalShuffleReader.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.plans.physical.{Partitioning, UnknownPartitioning}
import org.apache.spark.sql.catalyst.rules.Rule
import org.apache.spark.sql.execution.{LeafExecNode, SparkPlan}
import org.apache.spark.sql.execution.{SparkPlan, UnaryExecNode}
import org.apache.spark.sql.execution.exchange.{EnsureRequirements, ShuffleExchangeExec}
import org.apache.spark.sql.execution.joins.{BroadcastHashJoinExec, BuildLeft, BuildRight}
import org.apache.spark.sql.internal.SQLConf
Expand Down Expand Up @@ -70,7 +70,7 @@ case class OptimizeLocalShuffleReader(conf: SQLConf) extends Rule[SparkPlan] {
}
}

case class LocalShuffleReaderExec(child: QueryStageExec) extends LeafExecNode {
case class LocalShuffleReaderExec(child: QueryStageExec) extends UnaryExecNode {

override def output: Seq[Attribute] = child.output

Expand Down
12 changes: 8 additions & 4 deletions ...e/src/main/scala/org/apache/spark/sql/execution/adaptive/ReduceNumShufflePartitions.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.plans.physical.{Partitioning, UnknownPartitioning}
import org.apache.spark.sql.catalyst.rules.Rule
import org.apache.spark.sql.execution.{ShuffledRowRDD, SparkPlan, UnaryExecNode}
import org.apache.spark.sql.execution.adaptive.{QueryStageExec, ReusedQueryStageExec, ShuffleQueryStageExec}
import org.apache.spark.sql.execution.adaptive.{LocalShuffleReaderExec, QueryStageExec, ReusedQueryStageExec, ShuffleQueryStageExec}
import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.util.ThreadUtils

Expand Down Expand Up @@ -64,10 +64,14 @@ case class ReduceNumShufflePartitions(conf: SQLConf) extends Rule[SparkPlan] {
return plan
}

val shuffleStages = plan.collect {
case stage: ShuffleQueryStageExec => stage
case ReusedQueryStageExec(_, stage: ShuffleQueryStageExec, _) => stage
def collectShuffleStages(plan: SparkPlan): Seq[ShuffleQueryStageExec] = plan match {
case _: LocalShuffleReaderExec => Nil
case stage: ShuffleQueryStageExec => Seq(stage)
case ReusedQueryStageExec(_, stage: ShuffleQueryStageExec, _) => Seq(stage)
case _ => plan.children.flatMap(collectShuffleStages)
}

val shuffleStages = collectShuffleStages(plan)
// ShuffleExchanges introduced by repartition do not support changing the number of partitions.
// We change the number of partitions in the stage only if all the ShuffleExchanges support it.
if (!shuffleStages.forall(_.plan.canChangeNumPartitions)) {
Copy link
Contributor

@cloud-fan cloud-fan Oct 25, 2019

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We can change the logic of collecting shuffle stages:

def collectShuffleStages(plan: SparkPlan): Seq[ShuffleQueryStageExec] = plan match {
  case _: LocalShuffleReaderExec = Nil
  case stage: ShuffleQueryStageExec => Seq(stage)
  case ReusedQueryStageExec(_, stage: ShuffleQueryStageExec, _) => Seq(stage) 
  case _ => plan.children.flatMap(collectShuffleStages)
}

val shuffleStages = collectShuffleStages(plan)

Expand Down