diff options
author | Takuya UESHIN <ueshin@happy-camper.st> | 2016-09-30 17:31:59 -0700 |
---|---|---|
committer | Reynold Xin <rxin@databricks.com> | 2016-09-30 17:31:59 -0700 |
commit | 81455a9cd963098613bad10182e3fafc83a6e352 (patch) | |
tree | 14811a2f6cd6adad242a3e8d2e1f0d69ea45bcc3 | |
parent | f327e16863371076dbd2a7f22c8895ae07f8274b (diff) | |
download | spark-81455a9cd963098613bad10182e3fafc83a6e352.tar.gz spark-81455a9cd963098613bad10182e3fafc83a6e352.tar.bz2 spark-81455a9cd963098613bad10182e3fafc83a6e352.zip |
[SPARK-17703][SQL] Add unnamed version of addReferenceObj for minor objects.
## What changes were proposed in this pull request?
There are many minor objects in references, which are extracted to the generated class field, e.g. `errMsg` in `GetExternalRowField` or `ValidateExternalType`, but number of fields in class is limited so we should reduce the number.
This pr adds unnamed version of `addReferenceObj` for these minor objects not to store the object into field but refer it from the `references` field at the time of use.
## How was this patch tested?
Existing tests.
Author: Takuya UESHIN <ueshin@happy-camper.st>
Closes #15276 from ueshin/issues/SPARK-17703.
3 files changed, 28 insertions, 4 deletions
diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala index 33b9b804fc..cb808e375a 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/codegen/CodeGenerator.scala @@ -85,6 +85,21 @@ class CodegenContext { val references: mutable.ArrayBuffer[Any] = new mutable.ArrayBuffer[Any]() /** + * Add an object to `references`. + * + * Returns the code to access it. + * + * This is for minor objects not to store the object into field but refer it from the references + * field at the time of use because number of fields in class is limited so we should reduce it. + */ + def addReferenceObj(obj: Any): String = { + val idx = references.length + references += obj + val clsName = obj.getClass.getName + s"(($clsName) references[$idx])" + } + + /** * Add an object to `references`, create a class member to access it. * * Returns the name of class member. diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala index 92f8fb85fc..dbb52a4bb1 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala @@ -517,7 +517,10 @@ case class AssertTrue(child: Expression) extends UnaryExpression with ImplicitCa override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = { val eval = child.genCode(ctx) - val errMsgField = ctx.addReferenceObj("errMsg", errMsg) + + // Use unnamed reference that doesn't create a local field here to reduce the number of fields + // because errMsgField is used only when the value is null or false. + val errMsgField = ctx.addReferenceObj(errMsg) ExprCode(code = s"""${eval.code} |if (${eval.isNull} || !${eval.value}) { | throw new RuntimeException($errMsgField); diff --git a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala index faf8fecd79..50e2ac3c36 100644 --- a/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala +++ b/sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/objects/objects.scala @@ -906,7 +906,9 @@ case class AssertNotNull(child: Expression, walkedTypePath: Seq[String]) override protected def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = { val childGen = child.genCode(ctx) - val errMsgField = ctx.addReferenceObj("errMsg", errMsg) + // Use unnamed reference that doesn't create a local field here to reduce the number of fields + // because errMsgField is used only when the value is null. + val errMsgField = ctx.addReferenceObj(errMsg) val code = s""" ${childGen.code} @@ -941,7 +943,9 @@ case class GetExternalRowField( private val errMsg = s"The ${index}th field '$fieldName' of input row cannot be null." override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = { - val errMsgField = ctx.addReferenceObj("errMsg", errMsg) + // Use unnamed reference that doesn't create a local field here to reduce the number of fields + // because errMsgField is used only when the field is null. + val errMsgField = ctx.addReferenceObj(errMsg) val row = child.genCode(ctx) val code = s""" ${row.code} @@ -979,7 +983,9 @@ case class ValidateExternalType(child: Expression, expected: DataType) private val errMsg = s" is not a valid external type for schema of ${expected.simpleString}" override def doGenCode(ctx: CodegenContext, ev: ExprCode): ExprCode = { - val errMsgField = ctx.addReferenceObj("errMsg", errMsg) + // Use unnamed reference that doesn't create a local field here to reduce the number of fields + // because errMsgField is used only when the type doesn't match. + val errMsgField = ctx.addReferenceObj(errMsg) val input = child.genCode(ctx) val obj = input.value |