JkSelf commented on a change in pull request #31756:
URL: https://github.com/apache/spark/pull/31756#discussion_r614025183
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/AdaptiveSparkPlanExec.scala
##########
@@ -310,6 +310,11 @@ case class AdaptiveSparkPlanExec(
rdd
}
+ override def doExecuteBroadcast[T](): broadcast.Broadcast[T] = {
+ val broadcastPlan = getFinalPhysicalPlan()
+ broadcastPlan.doExecuteBroadcast()
Review comment:
Updated.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PlanAdaptiveDynamicPruningFilters.scala
##########
@@ -17,19 +17,18 @@
package org.apache.spark.sql.execution.adaptive
-import scala.collection.concurrent.TrieMap
-
import org.apache.spark.sql.catalyst.expressions.{BindReferences,
DynamicPruningExpression, Literal}
+import org.apache.spark.sql.catalyst.optimizer.{BuildLeft, BuildRight}
import org.apache.spark.sql.catalyst.rules.Rule
import org.apache.spark.sql.execution._
import org.apache.spark.sql.execution.exchange.BroadcastExchangeExec
-import org.apache.spark.sql.execution.joins.{HashedRelationBroadcastMode,
HashJoin}
+import org.apache.spark.sql.execution.joins.{BroadcastHashJoinExec,
HashedRelationBroadcastMode, HashJoin}
/**
* A rule to insert dynamic pruning predicates in order to reuse the results
of broadcast.
*/
case class PlanAdaptiveDynamicPruningFilters(
- stageCache: TrieMap[SparkPlan, QueryStageExec]) extends Rule[SparkPlan] {
+ originalPlan: SparkPlan) extends Rule[SparkPlan] {
Review comment:
Updated.
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/PlanAdaptiveDynamicPruningFilters.scala
##########
@@ -41,15 +40,26 @@ case class PlanAdaptiveDynamicPruningFilters(
adaptivePlan: AdaptiveSparkPlanExec), exprId, _)) =>
val packedKeys = BindReferences.bindReferences(
HashJoin.rewriteKeyExpr(buildKeys), adaptivePlan.executedPlan.output)
- val mode = HashedRelationBroadcastMode(packedKeys)
- // plan a broadcast exchange of the build side of the join
- val exchange = BroadcastExchangeExec(mode, adaptivePlan.executedPlan)
- val existingStage = stageCache.get(exchange.canonicalized)
- if (existingStage.nonEmpty && conf.exchangeReuseEnabled) {
- val name = s"dynamicpruning#${exprId.id}"
- val reuseQueryStage = existingStage.get.newReuseInstance(0,
exchange.output)
- val broadcastValues =
- SubqueryBroadcastExec(name, index, buildKeys, reuseQueryStage)
+
+ val canReuseExchange = conf.exchangeReuseEnabled && buildKeys.nonEmpty
&&
+ originalPlan.find {
+ case BroadcastHashJoinExec(_, _, _, BuildLeft, _, left, _, _) =>
+ left.sameResult(adaptivePlan.executedPlan)
+ case BroadcastHashJoinExec(_, _, _, BuildRight, _, _, right, _) =>
+ right.sameResult(adaptivePlan.executedPlan)
+ case _ => false
+ }.isDefined
+
+ if(canReuseExchange) {
Review comment:
Updated.
--
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
