Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SPARK-26680][SQL] Eagerly create inputVars while conditions are appropriate #23617

Closed
wants to merge 2 commits into from
Closed

[SPARK-26680][SQL] Eagerly create inputVars while conditions are appropriate #23617

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
367b6e8
Initial commit
bersprockets Jan 22, 2019
5f27005
Review feedback
bersprockets Jan 22, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/WholeStageCodegenExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,14 +143,11 @@ trait CodegenSupport extends SparkPlan {
* Note that `outputVars` and `row` can't both be null.
*/
final def consume(ctx: CodegenContext, outputVars: Seq[ExprCode], row: String = null): String = {
val inputVars =
val inputVarsCandidate =
if (outputVars != null) {
assert(outputVars.length == output.length)
// outputVars will be used to generate the code for UnsafeRow, so we should copy them
outputVars.map(_.copy()) match {
case stream: Stream[ExprCode] => stream.force
case other => other
}
outputVars.map(_.copy())
} else {
assert(row != null, "outputVars and row cannot both be null.")
ctx.currentVars = null
Expand All @@ -160,6 +157,11 @@ trait CodegenSupport extends SparkPlan {
}
}

val inputVars = inputVarsCandidate match {
case stream: Stream[ExprCode] => stream.force
case other => other
}

val rowVar = prepareRowVar(ctx, row, outputVars)

// Set up the `currentVars` in the codegen context, as we generate the code of `inputVars`
Expand Down
9 changes: 9 additions & 0 deletions sql/core/src/test/scala/org/apache/spark/sql/execution/WholeStageCodegenSuite.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -330,4 +330,13 @@ class WholeStageCodegenSuite extends QueryTest with SharedSQLContext {

checkAnswer(abc, Row(1, "a"))
}

test("SPARK-26680: Stream in groupBy does not cause StackOverflowError") {
val groupByCols = Stream(col("key"))
val df = Seq((1, 2), (2, 3), (1, 3)).toDF("key", "value")
.groupBy(groupByCols: _*)
.max("value")

checkAnswer(df, Seq(Row(1, 3), Row(2, 3)))
}
}