Skip to content

perf: [iceberg] reduce nativeIcebergScanMetadata serialization points #3243

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
mbutrovich merged 1 commit into from
Jan 22, 2026
Merged

perf: [iceberg] reduce nativeIcebergScanMetadata serialization points #3243

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
15 changes: 6 additions & 9 deletions spark/src/main/scala/org/apache/spark/sql/comet/CometBatchScanExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ import org.apache.comet.iceberg.CometIcebergNativeScanMetadata
case class CometBatchScanExec(
wrapped: BatchScanExec,
runtimeFilters: Seq[Expression],
nativeIcebergScanMetadata: Option[CometIcebergNativeScanMetadata] = None)
@transient nativeIcebergScanMetadata: Option[CometIcebergNativeScanMetadata] = None)
extends DataSourceV2ScanExecBase
with CometPlan {
def ordering: Option[Seq[SortOrder]] = wrapped.ordering
Expand Down Expand Up @@ -99,26 +99,23 @@ case class CometBatchScanExec(
override def equals(other: Any): Boolean = other match {
case other: CometBatchScanExec =>
// `wrapped` in `this` and `other` could reference to the same `BatchScanExec` object,
// check `runtimeFilters` and `nativeIcebergScanMetadata` equality too.
this.wrappedScan == other.wrappedScan && this.runtimeFilters == other.runtimeFilters &&
this.nativeIcebergScanMetadata == other.nativeIcebergScanMetadata
// check `runtimeFilters` equality too.
this.wrappedScan == other.wrappedScan && this.runtimeFilters == other.runtimeFilters
case _ =>
false
}

override def hashCode(): Int = {
Objects.hashCode(
wrappedScan,
runtimeFilters,
Integer.valueOf(nativeIcebergScanMetadata.map(_.hashCode()).getOrElse(0)))
Objects.hashCode(wrappedScan, runtimeFilters)
}

override def doCanonicalize(): CometBatchScanExec = {
this.copy(
wrapped = wrappedScan.doCanonicalize(),
runtimeFilters = QueryPlan.normalizePredicates(
runtimeFilters.filterNot(_ == DynamicPruningExpression(Literal.TrueLiteral)),
output))
output),
nativeIcebergScanMetadata = None)
}

override def nodeName: String = {
Expand Down
6 changes: 2 additions & 4 deletions spark/src/main/scala/org/apache/spark/sql/comet/CometIcebergNativeScanExec.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -166,8 +166,7 @@ case class CometIcebergNativeScanExec(
this.metadataLocation == other.metadataLocation &&
this.output == other.output &&
this.serializedPlanOpt == other.serializedPlanOpt &&
this.numPartitions == other.numPartitions &&
this.nativeIcebergScanMetadata == other.nativeIcebergScanMetadata
this.numPartitions == other.numPartitions
case _ =>
false
}
Expand All @@ -178,8 +177,7 @@ case class CometIcebergNativeScanExec(
metadataLocation,
output.asJava,
serializedPlanOpt,
numPartitions: java.lang.Integer,
nativeIcebergScanMetadata)
numPartitions: java.lang.Integer)
}

object CometIcebergNativeScanExec {
Expand Down
Loading