-
Notifications
You must be signed in to change notification settings - Fork 28.1k
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.
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-22498][SQL] Fix 64KB JVM bytecode limit problem with concat #19728
Changes from 8 commits
bc97d41
0ed8d16
366f721
6fdb451
e6b73ab
cd20410
e668b98
555575e
22019b1
b9ca4ff
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -63,15 +63,28 @@ case class Concat(children: Seq[Expression]) extends Expression with ImplicitCas | |
|
||
override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = { | ||
val evals = children.map(_.genCode(ctx)) | ||
val inputs = evals.map { eval => | ||
s"${eval.isNull} ? null : ${eval.value}" | ||
}.mkString(", ") | ||
ev.copy(evals.map(_.code).mkString("\n") + s""" | ||
boolean ${ev.isNull} = false; | ||
UTF8String ${ev.value} = UTF8String.concat($inputs); | ||
if (${ev.value} == null) { | ||
${ev.isNull} = true; | ||
} | ||
val numArgs = evals.length | ||
val args = ctx.freshName("args") | ||
|
||
val inputs = evals.zipWithIndex.map { case (eval, index) => | ||
s""" | ||
${eval.code} | ||
if (!${eval.isNull}) { | ||
$args[$index] = ${eval.value}; | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. If There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. good catch |
||
} | ||
""" | ||
} | ||
val codes = if (ctx.INPUT_ROW != null && ctx.currentVars == null) { | ||
ctx.splitExpressions(inputs, "valueConcat", | ||
("InternalRow", ctx.INPUT_ROW) :: ("UTF8String[]", args) :: Nil) | ||
} else { | ||
inputs.mkString("\n") | ||
} | ||
ev.copy(s""" | ||
UTF8String[] $args = new UTF8String[$numArgs]; | ||
$codes | ||
UTF8String ${ev.value} = UTF8String.concat($args); | ||
boolean ${ev.isNull} = ${ev.value} == null; | ||
""") | ||
} | ||
} | ||
|
@@ -125,19 +138,43 @@ case class ConcatWs(children: Seq[Expression]) | |
if (children.forall(_.dataType == StringType)) { | ||
// All children are strings. In that case we can construct a fixed size array. | ||
val evals = children.map(_.genCode(ctx)) | ||
|
||
val inputs = evals.map { eval => | ||
s"${eval.isNull} ? (UTF8String) null : ${eval.value}" | ||
}.mkString(", ") | ||
|
||
ev.copy(evals.map(_.code).mkString("\n") + s""" | ||
UTF8String ${ev.value} = UTF8String.concatWs($inputs); | ||
val separator = evals.head | ||
val strings = evals.tail | ||
val argNums = strings.length | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. nit: |
||
val args = ctx.freshName("args") | ||
|
||
val inputs = strings.zipWithIndex.map { case (eval, index) => | ||
if (eval.isNull != "true") { | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Same issue as https://github.com/apache/spark/pull/19728/files#r150441287. |
||
s""" | ||
${eval.code} | ||
if (!${eval.isNull}) { | ||
$args[$index] = ${eval.value}; | ||
} | ||
""" | ||
} else { | ||
"" | ||
} | ||
} | ||
val codes = s"${separator.code}\n" + | ||
(if (ctx.INPUT_ROW != null && ctx.currentVars == null) { | ||
ctx.splitExpressions(inputs, "valueConcatWs", | ||
("InternalRow", ctx.INPUT_ROW) :: ("UTF8String[]", args) :: Nil) | ||
} else { | ||
inputs.mkString("\n") | ||
}) | ||
ev.copy(s""" | ||
UTF8String[] $args = new UTF8String[$argNums]; | ||
$codes | ||
UTF8String ${ev.value} = UTF8String.concatWs(${separator.value}, $args); | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. nit:
|
||
boolean ${ev.isNull} = ${ev.value} == null; | ||
""") | ||
} else { | ||
val array = ctx.freshName("array") | ||
ctx.addMutableState("UTF8String[]", array, "") | ||
val varargNum = ctx.freshName("varargNum") | ||
ctx.addMutableState("int", varargNum, "") | ||
val idxInVararg = ctx.freshName("idxInVararg") | ||
ctx.addMutableState("int", idxInVararg, "") | ||
|
||
val evals = children.map(_.genCode(ctx)) | ||
val (varargCount, varargBuild) = children.tail.zip(evals.tail).map { case (child, eval) => | ||
|
@@ -163,13 +200,17 @@ case class ConcatWs(children: Seq[Expression]) | |
} | ||
}.unzip | ||
|
||
ev.copy(evals.map(_.code).mkString("\n") + | ||
val codes = ctx.splitExpressions(ctx.INPUT_ROW, evals.map(_.code)) | ||
val varargCounts = ctx.splitExpressions(ctx.INPUT_ROW, varargCount) | ||
val varargBuilds = ctx.splitExpressions(ctx.INPUT_ROW, varargBuild) | ||
ev.copy( | ||
s""" | ||
int $varargNum = ${children.count(_.dataType == StringType) - 1}; | ||
int $idxInVararg = 0; | ||
${varargCount.mkString("\n")} | ||
UTF8String[] $array = new UTF8String[$varargNum]; | ||
${varargBuild.mkString("\n")} | ||
$codes | ||
$varargNum = ${children.count(_.dataType == StringType) - 1}; | ||
$idxInVararg = 0; | ||
$varargCounts | ||
$array = new UTF8String[$varargNum]; | ||
$varargBuilds | ||
UTF8String ${ev.value} = UTF8String.concatWs(${evals.head.value}, $array); | ||
boolean ${ev.isNull} = ${ev.value} == null; | ||
""") | ||
|
@@ -224,22 +265,55 @@ case class Elt(children: Seq[Expression]) | |
override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = { | ||
val index = indexExpr.genCode(ctx) | ||
val strings = stringExprs.map(_.genCode(ctx)) | ||
val indexVal = ctx.freshName("index") | ||
val stringVal = ctx.freshName("stringVal") | ||
val assignStringValue = strings.zipWithIndex.map { case (eval, index) => | ||
s""" | ||
case ${index + 1}: | ||
${ev.value} = ${eval.isNull} ? null : ${eval.value}; | ||
${eval.code} | ||
$stringVal = ${eval.isNull} ? null : ${eval.value}; | ||
break; | ||
""" | ||
}.mkString("\n") | ||
val indexVal = ctx.freshName("index") | ||
val stringArray = ctx.freshName("strings"); | ||
} | ||
|
||
ev.copy(index.code + "\n" + strings.map(_.code).mkString("\n") + s""" | ||
final int $indexVal = ${index.value}; | ||
UTF8String ${ev.value} = null; | ||
switch ($indexVal) { | ||
$assignStringValue | ||
val cases = ctx.splitCodes(assignStringValue) | ||
val codes = if (cases.length == 1) { | ||
s""" | ||
UTF8String $stringVal = null; | ||
switch ($indexVal) { | ||
${cases.head} | ||
} | ||
""" | ||
} else { | ||
var fullFuncName = "" | ||
cases.reverse.zipWithIndex.map { case (s, index) => | ||
val prevFunc = if (index == 0) { | ||
"null" | ||
} else { | ||
s"$fullFuncName(${ctx.INPUT_ROW}, $indexVal)" | ||
} | ||
val funcName = ctx.freshName("eltFunc") | ||
val funcBody = s""" | ||
private UTF8String $funcName(InternalRow ${ctx.INPUT_ROW}, int $indexVal) { | ||
UTF8String $stringVal = null; | ||
switch ($indexVal) { | ||
$s | ||
default: | ||
return $prevFunc; | ||
} | ||
return $stringVal; | ||
} | ||
""" | ||
fullFuncName = ctx.addNewFunction(funcName, funcBody) | ||
} | ||
s"UTF8String $stringVal = $fullFuncName(${ctx.INPUT_ROW}, ${indexVal});" | ||
} | ||
|
||
ev.copy(index.code + "\n" + | ||
s""" | ||
final int $indexVal = ${index.value}; | ||
$codes | ||
UTF8String ${ev.value} = $stringVal; | ||
final boolean ${ev.isNull} = ${ev.value} == null; | ||
""") | ||
} | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
nit: we can inline it