Skip to content

[SPARK-58232][SQL] Simplify cached-batch column-index resolution with a map lookup #57395

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

Open
ganeshashree wants to merge 2 commits into
base: master
Choose a base branch
from
+21 −7
Open

[SPARK-58232][SQL] Simplify cached-batch column-index resolution with a map lookup #57395

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
a53d4c7
[SPARK-58232][SQL] Resolve cached-batch column indices via a map inst…
ganeshas-db Jul 21, 2026
3bd5b1d
[SPARK-58232][SQL] Address review: reuse AttributeSeq.indexOf and cov…
ganeshas-db Jul 21, 2026
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: 11 additions & 4 deletions ...e/src/main/scala/org/apache/spark/sql/execution/columnar/ArrowCachedBatchSerializer.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ import org.apache.arrow.vector.ipc.message.{ArrowRecordBatch, MessageSerializer}
import org.apache.spark.{SparkException, TaskContext}
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.catalyst.InternalRow
import org.apache.spark.sql.catalyst.expressions.Attribute
import org.apache.spark.sql.catalyst.expressions.{Attribute, AttributeSeq}
import org.apache.spark.sql.catalyst.expressions.codegen.UnsafeRowWriter
import org.apache.spark.sql.catalyst.types.DataTypeUtils
import org.apache.spark.sql.columnar.{CachedBatch, SimpleMetricsCachedBatchSerializer}
Expand Down Expand Up @@ -144,8 +144,12 @@ class ArrowCachedBatchSerializer extends SimpleMetricsCachedBatchSerializer {
conf: SQLConf): RDD[ColumnarBatch] = {
val cacheSchema = DataTypeUtils.fromAttributes(cacheAttributes)
val selectedSchema = DataTypeUtils.fromAttributes(selectedAttributes)
// Use AttributeSeq's cached exprId -> ordinal map so each selected attribute is a
// constant-time lookup, instead of rebuilding the exprId list and linear-scanning it
// per selected attribute.
val cacheAttributeSeq = AttributeSeq(cacheAttributes)
val columnIndices =
selectedAttributes.map(a => cacheAttributes.map(o => o.exprId).indexOf(a.exprId)).toArray
selectedAttributes.map(a => cacheAttributeSeq.indexOf(a.exprId)).toArray
// Capture config on driver
val timeZoneId = conf.sessionLocalTimeZone
val prefetchEnabled = conf.arrowCachePrefetchEnabled
Expand All @@ -170,9 +174,12 @@ class ArrowCachedBatchSerializer extends SimpleMetricsCachedBatchSerializer {
val selectedSchema = DataTypeUtils.fromAttributes(selectedAttributes)
val timeZoneId = conf.sessionLocalTimeZone

// Calculate column indices for projection
// Calculate column indices for projection. Use AttributeSeq's cached exprId -> ordinal
// map so each selected attribute is a constant-time lookup, instead of linear-scanning
// the cache attributes per selected attribute.
val cacheAttributeSeq = AttributeSeq(cacheAttributes)
val selectedIndices = selectedAttributes.map { attr =>
cacheAttributes.indexWhere(_.exprId == attr.exprId)
cacheAttributeSeq.indexOf(attr.exprId)
}.toArray

// Check if all selected types can use the fast path.
Expand Down
13 changes: 10 additions & 3 deletions sql/core/src/main/scala/org/apache/spark/sql/execution/columnar/InMemoryRelation.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -197,8 +197,12 @@ class DefaultCachedBatchSerializer extends SimpleMetricsCachedBatchSerializer {
conf: SQLConf): RDD[ColumnarBatch] = {
val offHeapColumnVectorEnabled = conf.offHeapColumnVectorEnabled
val outputSchema = DataTypeUtils.fromAttributes(selectedAttributes)
// Use AttributeSeq's cached exprId -> ordinal map so each selected attribute is a
// constant-time lookup, instead of rebuilding the exprId list and linear-scanning it
// per selected attribute.
val cacheAttributeSeq = AttributeSeq(cacheAttributes)
val columnIndices =
selectedAttributes.map(a => cacheAttributes.map(o => o.exprId).indexOf(a.exprId)).toArray
selectedAttributes.map(a => cacheAttributeSeq.indexOf(a.exprId)).toArray

def createAndDecompressColumn(cb: CachedBatch): ColumnarBatch = {
val cachedColumnarBatch = cb.asInstanceOf[DefaultCachedBatch]
Expand Down Expand Up @@ -230,10 +234,13 @@ class DefaultCachedBatchSerializer extends SimpleMetricsCachedBatchSerializer {
cacheAttributes: Seq[Attribute],
selectedAttributes: Seq[Attribute],
conf: SQLConf): RDD[InternalRow] = {
// Find the ordinals and data types of the requested columns.
// Find the ordinals and data types of the requested columns. Use AttributeSeq's cached
// exprId -> ordinal map so each requested column is a constant-time lookup, instead of
// rebuilding the exprId list and linear-scanning it per requested column.
val cacheAttributeSeq = AttributeSeq(cacheAttributes)
val (requestedColumnIndices, requestedColumnDataTypes) =
selectedAttributes.map { a =>
cacheAttributes.map(_.exprId).indexOf(a.exprId) -> a.dataType
cacheAttributeSeq.indexOf(a.exprId) -> a.dataType
}.unzip

val columnTypes = requestedColumnDataTypes.map {
Expand Down