spark-reviews mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From GitBox <...@apache.org>
Subject [GitHub] [spark] maropu commented on a change in pull request #27077: [SPARK-30408][SQL] Should not remove orderBy in sortBy clause in Optimizer
Date Wed, 08 Jan 2020 07:55:47 GMT
maropu commented on a change in pull request #27077: [SPARK-30408][SQL] Should not remove orderBy
in sortBy clause in Optimizer
URL: https://github.com/apache/spark/pull/27077#discussion_r364100529
 
 

 ##########
 File path: sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
 ##########
 @@ -980,15 +980,25 @@ object EliminateSorts extends Rule[LogicalPlan] {
       if (newOrders.isEmpty) child else s.copy(order = newOrders)
     case Sort(orders, true, child) if SortOrder.orderingSatisfies(child.outputOrdering, orders)
=>
       child
-    case s @ Sort(_, _, child) => s.copy(child = recursiveRemoveSort(child))
+    case s @ Sort(_, _, child) => s.copy(child = recursiveRemoveSort(s, child))
     case j @ Join(originLeft, originRight, _, cond, _) if cond.forall(_.deterministic) =>
       j.copy(left = recursiveRemoveSort(originLeft), right = recursiveRemoveSort(originRight))
     case g @ Aggregate(_, aggs, originChild) if isOrderIrrelevantAggs(aggs) =>
       g.copy(child = recursiveRemoveSort(originChild))
   }
 
+  private def recursiveRemoveSort(parent: Sort, plan: LogicalPlan): LogicalPlan = plan match
{
+    case s @ Sort(_, _, child) =>
+      if (parent.global == s.global) {
+        recursiveRemoveSort(child)
+      } else {
+        s.copy(child = recursiveRemoveSort(child))
+      }
+    case _ => recursiveRemoveSort(plan)
+  }
+
   private def recursiveRemoveSort(plan: LogicalPlan): LogicalPlan = plan match {
-    case Sort(_, _, child) => recursiveRemoveSort(child)
+    case s @ Sort(_, _, child) => recursiveRemoveSort(s, child)
 
 Review comment:
   How about the case , `global sort => project/filter => local sort`?

----------------------------------------------------------------
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:
users@infra.apache.org


With regards,
Apache Git Services

---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org


Mime
View raw message