cloud-fan commented on code in PR #37250:
URL: https://github.com/apache/spark/pull/37250#discussion_r927777533
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala:
##########
@@ -1528,28 +1528,44 @@ object EliminateSorts extends Rule[LogicalPlan] {
}
case Sort(orders, false, child) if
SortOrder.orderingSatisfies(child.outputOrdering, orders) =>
applyLocally.lift(child).getOrElse(child)
- case s @ Sort(_, _, child) => s.copy(child = recursiveRemoveSort(child))
+ case s @ Sort(_, global, child) => s.copy(child =
recursiveRemoveSort(child, global))
case j @ Join(originLeft, originRight, _, cond, _) if
cond.forall(_.deterministic) =>
- j.copy(left = recursiveRemoveSort(originLeft), right =
recursiveRemoveSort(originRight))
+ j.copy(left = recursiveRemoveSort(originLeft, true),
+ right = recursiveRemoveSort(originRight, true))
case g @ Aggregate(_, aggs, originChild) if isOrderIrrelevantAggs(aggs) =>
- g.copy(child = recursiveRemoveSort(originChild))
+ g.copy(child = recursiveRemoveSort(originChild, true))
}
- private def recursiveRemoveSort(plan: LogicalPlan): LogicalPlan = {
+ /**
+ * If the upper sort is global then we can remove the global or local sort
recursively.
+ * If the upper sort is local then we can only remove the local sort
recursively.
Review Comment:
Think about what if we remove all the `Repartition` nodes, will users
complain? They will even if `Repartition` does not change the data, but only
change the partitioning. Data partitioning is also a user expectation that we
shouldn't break.
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
