singhpk234 commented on code in PR #37083:
URL: https://github.com/apache/spark/pull/37083#discussion_r918544779
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/BasicStatsPlanVisitor.scala:
##########
@@ -17,16 +17,40 @@
package org.apache.spark.sql.catalyst.plans.logical.statsEstimation
+import org.apache.spark.sql.catalyst.expressions.AttributeMap
import org.apache.spark.sql.catalyst.plans.logical._
/**
- * A [[LogicalPlanVisitor]] that computes the statistics for the cost-based
optimizer.
+ * An [[LogicalPlanVisitor]] that computes a single dimension for plan stats:
size in bytes.
*/
object BasicStatsPlanVisitor extends LogicalPlanVisitor[Statistics] {
- /** Falls back to the estimation computed by
[[SizeInBytesOnlyStatsPlanVisitor]]. */
- private def fallback(p: LogicalPlan): Statistics =
SizeInBytesOnlyStatsPlanVisitor.visit(p)
+ /**
+ * A default, commonly used estimation for unary nodes. We assume the input
row number is the
+ * same as the output row number, and compute sizes based on the column
types.
+ */
+ 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 = EstimationUtils.getSizePerRow(p.child.output)
+ val outputRowSize = EstimationUtils.getSizePerRow(p.output)
+ // Assume there will be the same number of rows as child has.
+ var sizeInBytes = (p.child.stats.sizeInBytes * outputRowSize) /
childRowSize
+ if (sizeInBytes == 0) {
+ // sizeInBytes can't be zero, or sizeInBytes of BinaryNode will also be
zero
+ // (product of children).
+ sizeInBytes = 1
+ }
+
+ // v2 sources can bubble-up rowCount, so always propagate.
+ // Don't propagate attributeStats, since they are not estimated here.
+ Statistics(sizeInBytes = sizeInBytes, rowCount = p.child.stats.rowCount)
Review Comment:
for dsv2 sources rowCount can be passed from the relation itself without
running `analyze`, hence BasicStatsPlanVisitor which will be our default now,
post this change will take rowcount into consideration.
--
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]
