ulysses-you commented on code in PR #39377:
URL: https://github.com/apache/spark/pull/39377#discussion_r1062152134
##########
sql/core/src/main/scala/org/apache/spark/sql/execution/dynamicpruning/PartitionPruning.scala:
##########
@@ -167,44 +167,10 @@ object PartitionPruning extends Rule[LogicalPlan] with
PredicateHelper with Join
}
val estimatePruningSideSize = filterRatio *
partPlan.stats.sizeInBytes.toFloat
- val overhead = calculatePlanOverhead(otherPlan)
+ val overhead = collectLeafPlanOverhead(otherPlan).sum.toFloat
estimatePruningSideSize > overhead
}
- /**
- * Calculates a heuristic overhead of a logical plan. Normally it returns
the total
- * size in bytes of all scan relations. We don't count in-memory relation
which uses
- * only memory.
- */
- private def calculatePlanOverhead(plan: LogicalPlan): Float = {
- val (cached, notCached) = plan.collectLeaves().partition(p => p match {
- case _: InMemoryRelation => true
- case _ => false
- })
- val scanOverhead = notCached.map(_.stats.sizeInBytes).sum.toFloat
- val cachedOverhead = cached.map {
- case m: InMemoryRelation if m.cacheBuilder.storageLevel.useDisk &&
Review Comment:
this method moved into the new trait.
--
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]
