Skip to content

Add in the missing RmmSpark calls for the coalescing reader #14026

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
firestarman merged 2 commits into from
Dec 17, 2025
Merged

Add in the missing RmmSpark calls for the coalescing reader #14026

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
88c57d3
Monitor pool threads for coalescing readers
firestarman Dec 16, 2025
253fd17
address comments
firestarman Dec 17, 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
3 changes: 3 additions & 0 deletions sql-plugin/src/main/scala/com/nvidia/spark/rapids/GpuOrcScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2640,9 +2640,12 @@ class MultiFileOrcPartitionReader(

override def callImpl(): (Seq[DataBlockBase], Long) = {
TrampolineUtil.setTaskContext(taskContext)
// Mark the async thread as a pool thread within the RetryFramework
RmmSpark.poolThreadWorkingOnTask(taskContext.taskAttemptId())
try {
doRead()
} finally {
RmmSpark.poolThreadFinishedForTask(taskContext.taskAttemptId())
TrampolineUtil.unsetTaskContext()
}
}
Expand Down
3 changes: 3 additions & 0 deletions sql-plugin/src/main/scala/com/nvidia/spark/rapids/parquet/GpuParquetScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2261,6 +2261,8 @@ class MultiFileParquetPartitionReader(

override def callImpl(): (Seq[DataBlockBase], Long) = {
TrampolineUtil.setTaskContext(taskContext)
// Mark the async thread as a pool thread within the RetryFramework
RmmSpark.poolThreadWorkingOnTask(taskContext.taskAttemptId())
try {
val startBytesRead = fileSystemBytesRead()
val outputBlocks = withResource(outhmb) { _ =>
Expand All @@ -2287,6 +2289,7 @@ class MultiFileParquetPartitionReader(
// the corrupted file. But it should be ok since there is no meta pointing to that "hole"
(Seq.empty, 0)
} finally {
RmmSpark.poolThreadFinishedForTask(taskContext.taskAttemptId())
TrampolineUtil.unsetTaskContext()
}
}
Expand Down
3 changes: 3 additions & 0 deletions sql-plugin/src/main/scala/org/apache/spark/sql/rapids/GpuAvroScan.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1013,6 +1013,8 @@ class GpuMultiFileAvroPartitionReader(

override def callImpl(): (Seq[DataBlockBase], Long) = {
TrampolineUtil.setTaskContext(taskContext)
// Mark the async thread as a pool thread within the RetryFramework
RmmSpark.poolThreadWorkingOnTask(taskContext.taskAttemptId())
try {
val startBytesRead = fileSystemBytesRead()
val res = withResource(outhmb) { _ =>
Expand All @@ -1025,6 +1027,7 @@ class GpuMultiFileAvroPartitionReader(
val bytesRead = fileSystemBytesRead() - startBytesRead
(res, bytesRead)
} finally {
RmmSpark.poolThreadFinishedForTask(taskContext.taskAttemptId())
TrampolineUtil.unsetTaskContext()
}
}
Expand Down