Github user kiszk commented on a diff in the pull request:
https://github.com/apache/spark/pull/19082#discussion_r136090141
--- Diff:
sql/core/src/main/scala/org/apache/spark/sql/execution/aggregate/HashAggregateExec.scala
---
@@ -244,6 +246,92 @@ case class HashAggregateExec(
protected override val shouldStopRequired = false
+ // We assume a prefix has lower cases and a name has camel cases
+ private val variableName = "^[a-z]+_[a-zA-Z]+[0-9]*".r
+
+ // Returns true if a given name id belongs to this `CodegenContext`
+ private def isVariable(nameId: String): Boolean = nameId match {
+ case variableName() => true
+ case _ => false
+ }
+
+ // Extracts all the outer references for a given `aggExpr`. This result
will be used to split
+ // aggregation into small functions.
+ private def getOuterReferences(
+ ctx: CodegenContext,
+ aggExpr: Expression,
+ subExprs: Map[Expression, SubExprEliminationState]): Set[(String,
String)] = {
+ val stack = mutable.Stack[Expression](aggExpr)
+ val argSet = mutable.Set[(String, String)]()
+ val addIfNotLiteral = (value: String, tpe: String) => {
+ if (isVariable(value)) {
+ argSet += ((tpe, value))
+ }
+ }
+ while (stack.nonEmpty) {
+ stack.pop() match {
+ case e if subExprs.contains(e) =>
+ val exprCode = subExprs(e)
+ addIfNotLiteral(exprCode.value, ctx.javaType(e.dataType))
+ addIfNotLiteral(exprCode.isNull, "boolean")
+ // Since the children possibly has common expressions, we push
them here
+ stack.pushAll(e.children)
+ case ref: BoundReference
+ if ctx.currentVars != null && ctx.currentVars(ref.ordinal) !=
null =>
+ val argVal = ctx.currentVars(ref.ordinal).value
+ addIfNotLiteral(argVal, ctx.javaType(ref.dataType))
+ addIfNotLiteral(ctx.currentVars(ref.ordinal).isNull, "boolean")
+ case _: BoundReference =>
+ argSet += (("InternalRow", ctx.INPUT_ROW))
+ case e =>
+ stack.pushAll(e.children)
+ }
+ }
+
+ argSet.toSet
+ }
+
+ // Splits the aggregation into small functions because the HotSpot does
not compile
+ // too long functions.
+ private def splitAggregateExpressions(
+ ctx: CodegenContext,
+ aggExprs: Seq[Expression],
+ evalAndUpdateCodes: Seq[String],
+ subExprs: Map[Expression, SubExprEliminationState],
+ otherArgs: Seq[(String, String)] = Seq.empty): Seq[String] = {
+ aggExprs.zipWithIndex.map { case (aggExpr, i) =>
+ // The maximum number of parameters in Java methods is 255, so this
method gives up splitting
+ // the code if the number goes over the limit.
+ // You can find more information about the limit in the JVM
specification:
+ // - The number of method parameters is limited to 255 by the
definition of a method
+ // descriptor, where the limit includes one unit for this in the
case of instance
+ // or interface method invocations.
+ val args = (getOuterReferences(ctx, aggExpr, subExprs) ++
otherArgs).toSeq
+
+ // This is for testing/benchmarking only
+ val maxParamNumInJavaMethod =
+
sqlContext.getConf("spark.sql.codegen.aggregate.maxParamNumInJavaMethod", null)
match {
+ case null | "" => 256
--- End diff --
Since `$doAggVal` is [non-static
method](https://stackoverflow.com/questions/30581531/maximum-number-of-parameters-in-java-method-declaration),
this number should be `255`.
---
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]
