Github user gatorsmile commented on a diff in the pull request:
https://github.com/apache/spark/pull/21189#discussion_r185043356
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/SizeInBytesOnlyStatsPlanVisitor.scala
---
@@ -33,8 +33,8 @@ object SizeInBytesOnlyStatsPlanVisitor extends
LogicalPlanVisitor[Statistics] {
private def visitUnaryNode(p: UnaryNode): Statistics = {
// There should be some overhead in Row object, the size should not be
zero when there is
// no columns, this help to prevent divide-by-zero error.
- val childRowSize = p.child.output.map(_.dataType.defaultSize).sum + 8
- val outputRowSize = p.output.map(_.dataType.defaultSize).sum + 8
+ val childRowSize = EstimationUtils.getSizePerRow(p.child.output)
+ val outputRowSize = EstimationUtils.getSizePerRow(p.output)
--- End diff --
cc @juliuszsompolski @cloud-fan
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
