Skip to content

[SPARK-17528][SQL][followup] remove unnecessary data copy in object hash aggregate #18712

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

Closed
cloud-fan wants to merge 1 commit into from
Closed

[SPARK-17528][SQL][followup] remove unnecessary data copy in object hash aggregate #18712

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
20 changes: 4 additions & 16 deletions ...e/src/main/scala/org/apache/spark/sql/execution/aggregate/ObjectAggregationIterator.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,10 +70,6 @@ class ObjectAggregationIterator(
generateProcessRow(newExpressions, newFunctions, newInputAttributes)
}

// A safe projection used to do deep clone of input rows to prevent false sharing.
private[this] val safeProjection: Projection =
FromUnsafeProjection(outputAttributes.map(_.dataType))

/**
* Start processing input rows.
*/
Expand Down Expand Up @@ -151,12 +147,11 @@ class ObjectAggregationIterator(
val groupingKey = groupingProjection.apply(null)
val buffer: InternalRow = getAggregationBufferByKey(hashMap, groupingKey)
while (inputRows.hasNext) {
val newInput = safeProjection(inputRows.next())
processRow(buffer, newInput)
processRow(buffer, inputRows.next())
}
} else {
while (inputRows.hasNext && !sortBased) {
val newInput = safeProjection(inputRows.next())
val newInput = inputRows.next()
val groupingKey = groupingProjection.apply(newInput)
val buffer: InternalRow = getAggregationBufferByKey(hashMap, groupingKey)
processRow(buffer, newInput)
Expand Down Expand Up @@ -266,9 +261,7 @@ class SortBasedAggregator(
// Firstly, update the aggregation buffer with input rows.
while (hasNextInput &&
groupingKeyOrdering.compare(inputIterator.getKey, groupingKey) == 0) {
// Since `inputIterator.getValue` is an `UnsafeRow` whose underlying buffer will be
// overwritten when `inputIterator` steps forward, we need to do a deep copy here.
processRow(result.aggregationBuffer, inputIterator.getValue.copy())
processRow(result.aggregationBuffer, inputIterator.getValue)
hasNextInput = inputIterator.next()
}

Expand All @@ -277,12 +270,7 @@ class SortBasedAggregator(
// be called after calling processRow.
while (hasNextAggBuffer &&
groupingKeyOrdering.compare(initialAggBufferIterator.getKey, groupingKey) == 0) {
mergeAggregationBuffers(
result.aggregationBuffer,
// Since `inputIterator.getValue` is an `UnsafeRow` whose underlying buffer will be
// overwritten when `inputIterator` steps forward, we need to do a deep copy here.
initialAggBufferIterator.getValue.copy()
)
mergeAggregationBuffers(result.aggregationBuffer, initialAggBufferIterator.getValue)
hasNextAggBuffer = initialAggBufferIterator.next()
}

Expand Down