cloud-fan commented on a change in pull request #31258: URL: https://github.com/apache/spark/pull/31258#discussion_r561945532
########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/InsertAdaptiveSparkPlan.scala ########## @@ -129,6 +129,33 @@ case class InsertAdaptiveSparkPlan( verifyAdaptivePlan(executedPlan, query) val subquery = SubqueryExec(s"subquery#${exprId.id}", executedPlan) subqueryMap.put(exprId.id, subquery) + case expressions.DynamicPruningSubquery(value, buildPlan, + buildKeys, broadcastKeyIndex, onlyInBroadcast, exprId) + if !subqueryMap.contains(exprId.id) => + val executedPlan = compileSubquery(buildPlan) + verifyAdaptivePlan(executedPlan, buildPlan) + val adaptivePlan = executedPlan.asInstanceOf[AdaptiveSparkPlanExec] + + // Insert the broadcast exchange + val packedKeys = + BindReferences.bindReferences(HashJoin.rewriteKeyExpr(buildKeys), + adaptivePlan.inputPlan.output) + val mode = HashedRelationBroadcastMode(packedKeys) + // plan a broadcast exchange of the build side of the join + val exchange = BroadcastExchangeExec(mode, adaptivePlan.inputPlan) + val name = s"dynamicpruning#${exprId.id}" + + // place the broadcast adaptor for reusing the broadcast results on the probe side + val broadcastValues = + SubqueryBroadcastExec(name, broadcastKeyIndex, buildKeys, exchange) + + // Update the inputPlan and the currentPhysicalPlan of the adaptivePlan. + adaptivePlan.inputPlan = broadcastValues Review comment: can we wrap the `adaptivePlan` with subquery broadcast? Then we don't need to mutate `adaptivePlan.inputPlan` annd keep it as immutable. ########## File path: sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/InsertAdaptiveSparkPlan.scala ########## @@ -129,6 +129,33 @@ case class InsertAdaptiveSparkPlan( verifyAdaptivePlan(executedPlan, query) val subquery = SubqueryExec(s"subquery#${exprId.id}", executedPlan) subqueryMap.put(exprId.id, subquery) + case expressions.DynamicPruningSubquery(value, buildPlan, + buildKeys, broadcastKeyIndex, onlyInBroadcast, exprId) + if !subqueryMap.contains(exprId.id) => + val executedPlan = compileSubquery(buildPlan) + verifyAdaptivePlan(executedPlan, buildPlan) + val adaptivePlan = executedPlan.asInstanceOf[AdaptiveSparkPlanExec] + + // Insert the broadcast exchange + val packedKeys = + BindReferences.bindReferences(HashJoin.rewriteKeyExpr(buildKeys), + adaptivePlan.inputPlan.output) + val mode = HashedRelationBroadcastMode(packedKeys) + // plan a broadcast exchange of the build side of the join + val exchange = BroadcastExchangeExec(mode, adaptivePlan.inputPlan) + val name = s"dynamicpruning#${exprId.id}" + + // place the broadcast adaptor for reusing the broadcast results on the probe side + val broadcastValues = + SubqueryBroadcastExec(name, broadcastKeyIndex, buildKeys, exchange) + + // Update the inputPlan and the currentPhysicalPlan of the adaptivePlan. + adaptivePlan.inputPlan = broadcastValues Review comment: can we wrap the `adaptivePlan` with subquery broadcast? Then we don't need to mutate `adaptivePlan.inputPlan` here and keep `inputPlan` as immutable. ---------------------------------------------------------------- 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: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org For additional commands, e-mail: reviews-h...@spark.apache.org