cloud-fan commented on a change in pull request #32689:
URL: https://github.com/apache/spark/pull/32689#discussion_r641327805
##########
File path:
sql/core/src/main/scala/org/apache/spark/sql/execution/adaptive/QueryStageExec.scala
##########
@@ -95,18 +95,21 @@ abstract class QueryStageExec extends LeafExecNode {
/**
* Compute the statistics of the query stage if executed, otherwise None.
*/
- def computeStats(): Option[Statistics] = resultOption.get().map { _ =>
+ def computeStats(): Option[Statistics] = if (isMaterialized) {
val runtimeStats = getRuntimeStatistics
val dataSize = runtimeStats.sizeInBytes.max(0)
val numOutputRows = runtimeStats.rowCount.map(_.max(0))
- Statistics(dataSize, numOutputRows, isRuntime = true)
+ Some(Statistics(dataSize, numOutputRows, isRuntime = true))
+ } else {
+ None
}
@transient
@volatile
protected var _resultOption = new AtomicReference[Option[Any]](None)
private[adaptive] def resultOption: AtomicReference[Option[Any]] =
_resultOption
+ private[adaptive] def isMaterialized: Boolean = resultOption.get().isDefined
Review comment:
`materialize` is a public method, I think it makes more sense to make
`isMaterialized` public as well.
--
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
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscr...@spark.apache.org
For additional commands, e-mail: reviews-h...@spark.apache.org
