Github user rxin commented on a diff in the pull request:
https://github.com/apache/spark/pull/12047#discussion_r58290224
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegen.scala
---
@@ -434,12 +435,20 @@ case class CollapseCodegenStages(conf: SQLConf)
extends Rule[SparkPlan] {
case _ => true
}
+ private def numOfNestedFields(dataType: DataType): Int = dataType match {
+ case dt: StructType => dt.fields.map(f =>
numOfNestedFields(f.dataType)).sum
+ case m: MapType => numOfNestedFields(m.keyType) +
numOfNestedFields(m.valueType)
+ case a: ArrayType => numOfNestedFields(a.elementType) + 1
+ case u: UserDefinedType[_] => numOfNestedFields(u.sqlType)
+ case _ => 1
+ }
+
private def supportCodegen(plan: SparkPlan): Boolean = plan match {
case plan: CodegenSupport if plan.supportCodegen =>
val willFallback = plan.expressions.exists(_.find(e =>
!supportCodegen(e)).isDefined)
// the generated code will be huge if there are too many columns
- val haveManyColumns = plan.output.length > 200
- !willFallback && !haveManyColumns
+ val haveManyFields = numOfNestedFields(plan.schema) >
conf.wholeStageMaxNumFields
--- End diff --
haveTooManyFields
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
