singhpk234 commented on code in PR #37083:
URL: https://github.com/apache/spark/pull/37083#discussion_r918534436
##########
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:
In this estimator, we adjust the size by scaling it by (input row size /
output row size) but since we don't have much info (in terms of min / max / ndv
etc) to estimate the row count we just say the node output's child output row
count which is mostly true for operators like project etc.
Since we were just computing sizeInBytes and propagating rowCounts as it is
I left the comment as it is.
Should I rephrase it to let's say :
- `estimates size in bytes, row count for plan stats`
##########
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/plans/logical/statsEstimation/AdvancedStatsPlanVisitor.scala:
##########
@@ -0,0 +1,90 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one or more
+ * contributor license agreements. See the NOTICE file distributed with
+ * this work for additional information regarding copyright ownership.
+ * The ASF licenses this file to You under the Apache License, Version 2.0
+ * (the "License"); you may not use this file except in compliance with
+ * the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing, software
+ * distributed under the License is distributed on an "AS IS" BASIS,
+ * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ * See the License for the specific language governing permissions and
+ * limitations under the License.
+ */
+
+package org.apache.spark.sql.catalyst.plans.logical.statsEstimation
+
+import org.apache.spark.sql.catalyst.plans.logical._
+
+/**
+ * A [[LogicalPlanVisitor]] that computes the statistics for the cost-based
optimizer.
+ */
+object AdvancedStatsPlanVisitor extends LogicalPlanVisitor[Statistics] {
+
+ /** Falls back to the estimation computed by [[BasicStatsPlanVisitor]]. */
+ private def fallback(p: LogicalPlan): Statistics =
BasicStatsPlanVisitor.visit(p)
+
+ override def default(p: LogicalPlan): Statistics = fallback(p)
+
+ override def visitAggregate(p: Aggregate): Statistics = {
+ AggregateEstimation.estimate(p).getOrElse(fallback(p))
+ }
+
+ override def visitDistinct(p: Distinct): Statistics = {
+ val child = p.child
+ visitAggregate(Aggregate(child.output, child.output, child))
+ }
+
+ override def visitExcept(p: Except): Statistics = fallback(p)
+
+ override def visitExpand(p: Expand): Statistics = fallback(p)
+
+ override def visitFilter(p: Filter): Statistics = {
+ FilterEstimation(p).estimate.getOrElse(fallback(p))
+ }
+
+ override def visitGenerate(p: Generate): Statistics = default(p)
+
+ override def visitGlobalLimit(p: GlobalLimit): Statistics = fallback(p)
+
+ override def visitOffset(p: Offset): Statistics = fallback(p)
+
+ override def visitIntersect(p: Intersect): Statistics = fallback(p)
+
+ override def visitJoin(p: Join): Statistics = fallback(p)
Review Comment:
fallback here would endup calling BasicStatsPlanVisitor.visit(p) which, will
in turn call BasicStatsPlanVisitor#visitJoin which will be
`JoinEstimation(p).estimate.getOrElse(default(p))`. Hence added the same.
--
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: reviews-unsubscr...@spark.apache.org
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
