dongjoon-hyun commented on a change in pull request #29950:
URL: https://github.com/apache/spark/pull/29950#discussion_r502311982
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/internal/SQLConf.scala
##########
@@ -1926,6 +1926,19 @@ object SQLConf {
.booleanConf
.createWithDefault(true)
+ val MAX_COMMON_EXPRS_IN_COLLAPSE_PROJECT =
+ buildConf("spark.sql.optimizer.maxCommonExprsInCollapseProject")
+ .doc("An integer number indicates the maximum allowed number of a common
expression " +
+ "can be collapsed into upper Project from lower Project by optimizer
rule " +
+ "`CollapseProject`. Normally `CollapseProject` will collapse adjacent
Project " +
+ "and merge expressions. But in some edge cases, expensive expressions
might be " +
+ "duplicated many times in merged Project by this optimization. This
config sets " +
+ "a maximum number. Once an expression is duplicated more than this
number " +
+ "if merging two Project, Spark SQL will skip the merging.")
+ .version("3.1.0")
+ .intConf
+ .createWithDefault(20)
Review comment:
Just a question. Is there a reason to choose `20`?
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -732,10 +732,12 @@ object ColumnPruning extends Rule[LogicalPlan] {
* `GlobalLimit(LocalLimit)` pattern is also considered.
Review comment:
Could you update the optimizer description according to the new conf?
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/optimizer/Optimizer.scala
##########
@@ -732,10 +732,12 @@ object ColumnPruning extends Rule[LogicalPlan] {
* `GlobalLimit(LocalLimit)` pattern is also considered.
*/
object CollapseProject extends Rule[LogicalPlan] {
-
def apply(plan: LogicalPlan): LogicalPlan = plan transformUp {
case p1 @ Project(_, p2: Project) =>
- if (haveCommonNonDeterministicOutput(p1.projectList, p2.projectList)) {
+ val maxCommonExprs = SQLConf.get.maxCommonExprsInCollapseProject
+
+ if (haveCommonNonDeterministicOutput(p1.projectList, p2.projectList) ||
+ getLargestNumOfCommonOutput(p1.projectList, p2.projectList) >
maxCommonExprs) {
Review comment:
indentation?
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala
##########
@@ -124,14 +128,34 @@ object ScanOperation extends OperationHelper with
PredicateHelper {
}.exists(!_.deterministic))
}
+ def moreThanMaxAllowedCommonOutput(
+ expr: Seq[NamedExpression],
Review comment:
indentation?
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala
##########
@@ -124,14 +128,34 @@ object ScanOperation extends OperationHelper with
PredicateHelper {
}.exists(!_.deterministic))
}
+ def moreThanMaxAllowedCommonOutput(
+ expr: Seq[NamedExpression],
Review comment:
indentation? It seems that there is one more space here.
##########
File path:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/planning/patterns.scala
##########
@@ -124,14 +128,34 @@ object ScanOperation extends OperationHelper with
PredicateHelper {
}.exists(!_.deterministic))
}
+ def moreThanMaxAllowedCommonOutput(
+ expr: Seq[NamedExpression],
+ aliases: AttributeMap[Expression]): Boolean = {
+ val exprMap = mutable.HashMap.empty[Attribute, Int]
+
+ expr.foreach(_.collect {
+ case a: Attribute if aliases.contains(a) => exprMap.update(a,
exprMap.getOrElse(a, 0) + 1)
+ })
+
+ val commonOutputs = if (exprMap.size > 0) {
+ exprMap.maxBy(_._2)._2
+ } else {
+ 0
+ }
+
+ commonOutputs > maxCommonExprs
+ }
+
private def collectProjectsAndFilters(plan: LogicalPlan): ScanReturnType = {
plan match {
case Project(fields, child) =>
collectProjectsAndFilters(child) match {
case Some((_, filters, other, aliases)) =>
// Follow CollapseProject and only keep going if the collected
Projects
- // do not have common non-deterministic expressions.
- if (!hasCommonNonDeterministic(fields, aliases)) {
+ // do not have common non-deterministic expressions, or do not
have equal to/more than
+ // maximum allowed common outputs.
+ if (!hasCommonNonDeterministic(fields, aliases)
+ || !moreThanMaxAllowedCommonOutput(fields, aliases)) {
Review comment:
nit, you may want to move `||` into line 157.
----------------------------------------------------------------
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:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
