Skip to content

[GLUTEN-10818][VL] Implement KnownSizeEstimation for buildSideRelation #10817

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

Merged
zhztheplayer merged 3 commits into from
Oct 13, 2025
Merged

[GLUTEN-10818][VL] Implement KnownSizeEstimation for buildSideRelation #10817

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
1346345
[VL]Implement KnownSizeEstimation for buildSideRelation
zjuwangg Sep 29, 2025
0f1734f
fix style
zjuwangg Sep 29, 2025
9857f49
address comments
zjuwangg Oct 11, 2025
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
11 changes: 10 additions & 1 deletion backends-velox/src/main/scala/org/apache/spark/sql/execution/ColumnarBuildSideRelation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,7 @@ import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.utils.SparkArrowUtil
import org.apache.spark.sql.vectorized.ColumnarBatch
import org.apache.spark.task.TaskResources
import org.apache.spark.util.KnownSizeEstimation

import org.apache.arrow.c.ArrowSchema

Expand Down Expand Up @@ -61,7 +62,8 @@ case class ColumnarBuildSideRelation(
output: Seq[Attribute],
batches: Array[Array[Byte]],
safeBroadcastMode: SafeBroadcastMode)
extends BuildSideRelation {
extends BuildSideRelation
with KnownSizeEstimation {

// Rebuild the real BroadcastMode on demand; never serialize it.
@transient override lazy val mode: BroadcastMode =
Expand Down Expand Up @@ -236,4 +238,11 @@ case class ColumnarBuildSideRelation(
}
iterator.toArray
}
override def estimatedSize: Long = {
if (batches != null) {
batches.map(_.length.toLong).sum
} else {
0L
}
}
}
13 changes: 11 additions & 2 deletions ...rc/main/scala/org/apache/spark/sql/execution/unsafe/UnsafeColumnarBuildSideRelation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -36,7 +36,7 @@ import org.apache.spark.sql.internal.SQLConf
import org.apache.spark.sql.utils.SparkArrowUtil
import org.apache.spark.sql.vectorized.ColumnarBatch
import org.apache.spark.task.TaskResources
import org.apache.spark.util.Utils
import org.apache.spark.util.{KnownSizeEstimation, Utils}

import com.esotericsoftware.kryo.{Kryo, KryoSerializable}
import com.esotericsoftware.kryo.io.{Input, Output}
Expand Down Expand Up @@ -102,7 +102,8 @@ case class UnsafeColumnarBuildSideRelation(
extends BuildSideRelation
with Externalizable
with Logging
with KryoSerializable {
with KryoSerializable
with KnownSizeEstimation {

// Rebuild the real BroadcastMode on demand; never serialize it.
@transient override lazy val mode: BroadcastMode =
Expand Down Expand Up @@ -366,4 +367,12 @@ case class UnsafeColumnarBuildSideRelation(
}
iterator.toArray
}

override def estimatedSize: Long = {
if (batches != null) {
batches.totalBytes
} else {
0L
}
}
}
Loading