Skip to content

[GLUTEN-9215][VL] Release buffered input stream in native ShuffleReader on EOS to avoid OOM #9216

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
marin-ma wants to merge 1 commit into from
Closed

[GLUTEN-9215][VL] Release buffered input stream in native ShuffleReader on EOS to avoid OOM #9216

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
25 changes: 20 additions & 5 deletions cpp/velox/shuffle/VeloxShuffleReader.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -317,13 +317,13 @@ std::shared_ptr<ColumnarBatch> VeloxHashShuffleReaderDeserializer::next() {
auto arrowBuffers,
BlockPayload::deserialize(in_.get(), codec_, memoryPool_, numRows, deserializeTime_, decompressTime_));
if (arrowBuffers.empty()) {
// Reach EOS.
reachEos();
return nullptr;
}
return makeColumnarBatch(rowType_, numRows, std::move(arrowBuffers), veloxPool_, deserializeTime_);
}

if (reachEos_) {
if (reachedEos_) {
if (merged_) {
return makeColumnarBatch(rowType_, std::move(merged_), veloxPool_, deserializeTime_);
}
Expand All @@ -337,7 +337,7 @@ std::shared_ptr<ColumnarBatch> VeloxHashShuffleReaderDeserializer::next() {
arrowBuffers,
BlockPayload::deserialize(in_.get(), codec_, memoryPool_, numRows, deserializeTime_, decompressTime_));
if (arrowBuffers.empty()) {
reachEos_ = true;
reachEos();
break;
}
if (!merged_) {
Expand All @@ -356,7 +356,7 @@ std::shared_ptr<ColumnarBatch> VeloxHashShuffleReaderDeserializer::next() {
}

// Reach EOS.
if (reachEos_ && !merged_) {
if (reachedEos_ && !merged_) {
return nullptr;
}

Expand All @@ -369,6 +369,11 @@ std::shared_ptr<ColumnarBatch> VeloxHashShuffleReaderDeserializer::next() {
return columnarBatch;
}

void VeloxHashShuffleReaderDeserializer::reachEos() {
reachedEos_ = true;
in_.reset();
}

VeloxSortShuffleReaderDeserializer::VeloxSortShuffleReaderDeserializer(
std::shared_ptr<arrow::io::InputStream> in,
const std::shared_ptr<arrow::Schema>& schema,
Expand Down Expand Up @@ -410,7 +415,7 @@ std::shared_ptr<ColumnarBatch> VeloxSortShuffleReaderDeserializer::next() {
BlockPayload::deserialize(in_.get(), codec_, arrowPool_, numRows, deserializeTime_, decompressTime_));

if (arrowBuffers.empty()) {
reachedEos_ = true;
reachEos();
if (cachedRows_ > 0) {
return deserializeToBatch();
}
Expand Down Expand Up @@ -493,6 +498,11 @@ void VeloxSortShuffleReaderDeserializer::readLargeRow(std::vector<std::shared_pt
cachedRows_++;
}

void VeloxSortShuffleReaderDeserializer::reachEos() {
reachedEos_ = true;
in_.reset();
}

class VeloxRssSortShuffleReaderDeserializer::VeloxInputStream : public facebook::velox::GlutenByteInputStream {
public:
VeloxInputStream(std::shared_ptr<arrow::io::InputStream> input, facebook::velox::BufferPtr buffer);
Expand Down Expand Up @@ -561,6 +571,7 @@ std::shared_ptr<ColumnarBatch> VeloxRssSortShuffleReaderDeserializer::next() {
}

if (!in_->hasNext()) {
reachEos();
return nullptr;
}

Expand All @@ -582,6 +593,10 @@ std::shared_ptr<ColumnarBatch> VeloxRssSortShuffleReaderDeserializer::next() {
return std::make_shared<VeloxColumnarBatch>(std::move(rowVector));
}

void VeloxRssSortShuffleReaderDeserializer::reachEos() {
in_.reset();
}

size_t VeloxRssSortShuffleReaderDeserializer::VeloxInputStream::remainingSize() const {
return std::numeric_limits<unsigned long>::max();
}
Expand Down
8 changes: 7 additions & 1 deletion cpp/velox/shuffle/VeloxShuffleReader.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,8 @@ class VeloxHashShuffleReaderDeserializer final : public ColumnarBatchIterator {
std::shared_ptr<ColumnarBatch> next() override;

private:
void reachEos();

std::shared_ptr<arrow::io::InputStream> in_;
std::shared_ptr<arrow::Schema> schema_;
std::shared_ptr<arrow::util::Codec> codec_;
Expand All @@ -60,7 +62,7 @@ class VeloxHashShuffleReaderDeserializer final : public ColumnarBatchIterator {
int64_t& decompressTime_;

std::unique_ptr<InMemoryPayload> merged_{nullptr};
bool reachEos_{false};
bool reachedEos_{false};
};

class VeloxSortShuffleReaderDeserializer final : public ColumnarBatchIterator {
Expand All @@ -86,6 +88,8 @@ class VeloxSortShuffleReaderDeserializer final : public ColumnarBatchIterator {

void readLargeRow(std::vector<std::shared_ptr<arrow::Buffer>>& arrowBuffers);

void reachEos();

std::shared_ptr<arrow::io::InputStream> in_;
std::shared_ptr<arrow::Schema> schema_;
std::shared_ptr<arrow::util::Codec> codec_;
Expand Down Expand Up @@ -119,6 +123,8 @@ class VeloxRssSortShuffleReaderDeserializer : public ColumnarBatchIterator {
private:
class VeloxInputStream;

void reachEos();

std::shared_ptr<facebook::velox::memory::MemoryPool> veloxPool_;
facebook::velox::RowTypePtr rowType_;
std::vector<facebook::velox::RowVectorPtr> batches_;
Expand Down
Loading