aokolnychyi commented on code in PR #57487:
URL: https://github.com/apache/spark/pull/57487#discussion_r3687098673
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/execution/datasources/v2/DataSourceV2Relation.scala:
##########
@@ -199,15 +201,33 @@ case class DataSourceV2ScanRelation(
}
override def computeStats(): Statistics = {
- scan match {
- case r: SupportsReportStatistics =>
- val statistics = r.estimateStatistics()
- DataSourceV2Relation.transformV2Stats(statistics, None,
conf.defaultSizeInBytes, output)
- case _ =>
- Statistics(sizeInBytes = conf.defaultSizeInBytes)
+ if (conf.cboEnabled || conf.planStatsEnabled) {
+ computeFullStats()
+ } else {
+ computeSizeOnlyStats()
+ }
+ }
+
+ private def computeFullStats(): Statistics = {
+ V2StatisticsUtils.computeStats(scan) match {
+ case Some(v2Stats) =>
+ DataSourceV2Relation.transformV2Stats(v2Stats,
conf.defaultSizeInBytes, output)
+ case _ => defaultSizeOnlyStats
+ }
+ }
+
+ private def computeSizeOnlyStats(): Statistics = {
+ val avgRowSize = EstimationUtils.getSizePerRow(output)
Review Comment:
It was my bad to suggest an extra variable, given that we have `=>
avgRowSize` as argument. Can you revert to what you had before?
--
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]
