ulysses-you commented on a change in pull request #30368:
URL: https://github.com/apache/spark/pull/30368#discussion_r524804089
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -1452,11 +1452,27 @@ object PushPredicateThroughJoin extends
Rule[LogicalPlan] with PredicateHelper {
}
/**
- * Combines two adjacent [[Limit]] operators into one, merging the
- * expressions into one single expression.
+ * 1. Eliminate [[Limit]] operators if it's child max row <= limit.
+ * 2. Combines two adjacent [[Limit]] operators into one, merging the
+ * expressions into one single expression.
*/
-object CombineLimits extends Rule[LogicalPlan] {
- def apply(plan: LogicalPlan): LogicalPlan = plan transform {
+object EliminateLimits extends Rule[LogicalPlan] {
+ private def canEliminate(limitExpr: Expression, child: LogicalPlan): Boolean
= {
+ // We skip such case that Sort is after Limit since
+ // SparkStrategies will convert them to TakeOrderedAndProjectExec
+ val skipEliminate = child match {
+ case Sort(_, true, _) => true
Review comment:
BTW, also add the shuffle benchmark
```
runBenchmark("Sort and Limit") {
val N = 100000
val benchmark = new Benchmark("benchmark sort and limit", N)
benchmark.addCase("TakeOrderedAndProject", 3) { _ =>
spark.range(N).toDF("c").repartition(200).sort("c").take(200000)
}
benchmark.addCase("Sort And Limit", 3) { _ =>
withSQLConf("spark.sql.execution.topKSortFallbackThreshold" -> "-1")
{
spark.range(N).toDF("c").repartition(200).sort("c").take(200000)
}
}
benchmark.addCase("Sort", 3) { _ =>
spark.range(N).toDF("c").repartition(200).sort("c").collect()
}
benchmark.run()
}
```
and the result is
```
Java HotSpot(TM) 64-Bit Server VM 1.8.0_191-b12 on Mac OS X 10.15.6
Intel(R) Core(TM) i5-5257U CPU @ 2.70GHz
benchmark sort and limit: Best Time(ms) Avg Time(ms)
Stdev(ms) Rate(M/s) Per Row(ns) Relative
------------------------------------------------------------------------------------------------------------------------
TakeOrderedAndProject 1833 2259
382 0.1 18327.1 1.0X
Sort And Limit 1417 1658
285 0.1 14167.5 1.3X
Sort 1324 1484
225 0.1 13238.3 1.4X
```
----------------------------------------------------------------
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]
