gatorsmile commented on a change in pull request #24623: [SPARK-27739][SQL]
df.persist should save stats from optimized plan
URL: https://github.com/apache/spark/pull/24623#discussion_r311373968
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala
##########
@@ -146,17 +146,17 @@ object InMemoryRelation {
storageLevel: StorageLevel,
child: SparkPlan,
tableName: Option[String],
- logicalPlan: LogicalPlan): InMemoryRelation = {
+ optimizedPlan: LogicalPlan): InMemoryRelation = {
val cacheBuilder = CachedRDDBuilder(useCompression, batchSize,
storageLevel, child, tableName)
- val relation = new InMemoryRelation(child.output, cacheBuilder,
logicalPlan.outputOrdering)
- relation.statsOfPlanToCache = logicalPlan.stats
+ val relation = new InMemoryRelation(child.output, cacheBuilder,
optimizedPlan.outputOrdering)
+ relation.statsOfPlanToCache = optimizedPlan.stats
relation
}
- def apply(cacheBuilder: CachedRDDBuilder, logicalPlan: LogicalPlan):
InMemoryRelation = {
+ def apply(cacheBuilder: CachedRDDBuilder, optimizedPlan: LogicalPlan):
InMemoryRelation = {
val relation = new InMemoryRelation(
- cacheBuilder.cachedPlan.output, cacheBuilder, logicalPlan.outputOrdering)
- relation.statsOfPlanToCache = logicalPlan.stats
+ cacheBuilder.cachedPlan.output, cacheBuilder,
optimizedPlan.outputOrdering)
+ relation.statsOfPlanToCache = optimizedPlan.stats
Review comment:
If the stats of analyzed plan is the same as the optimized plan, please hold
this PR until they become different.
----------------------------------------------------------------
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
With regards,
Apache Git Services
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
