Skip to content

[GLUTEN-8072][VL] Add close method to close the hdfs connection #10593

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
JkSelf merged 2 commits into from
Sep 22, 2025
Merged

[GLUTEN-8072][VL] Add close method to close the hdfs connection #10593

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
e03d0b7
Call HdfsFileSystem#close() method to close the hdfs connection prior…
JkSelf Sep 22, 2025
907fdd5
Fix the compile issue
JkSelf Sep 22, 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
28 changes: 28 additions & 0 deletions cpp/velox/compute/VeloxBackend.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,6 +44,7 @@
#include "velox/connectors/hive/HiveDataSource.h"
#include "velox/connectors/hive/storage_adapters/abfs/RegisterAbfsFileSystem.h" // @manual
#include "velox/connectors/hive/storage_adapters/gcs/RegisterGcsFileSystem.h" // @manual
#include "velox/connectors/hive/storage_adapters/hdfs/HdfsFileSystem.h"
#include "velox/connectors/hive/storage_adapters/hdfs/RegisterHdfsFileSystem.h" // @manual
#include "velox/connectors/hive/storage_adapters/s3fs/RegisterS3FileSystem.h" // @manual
#include "velox/dwio/orc/reader/OrcReader.h"
Expand Down Expand Up @@ -331,4 +332,31 @@ VeloxBackend* VeloxBackend::get() {
}
return instance_.get();
}

void VeloxBackend::tearDown() {
#ifdef ENABLE_HDFS
for (const auto& [_, filesystem] : facebook::velox::filesystems::registeredFilesystems) {
filesystem->close();
}
#endif

// Destruct IOThreadPoolExecutor will join all threads.
// On threads exit, thread local variables can be constructed with referencing global variables.
// So, we need to destruct IOThreadPoolExecutor and stop the threads before global variables get destructed.
ioExecutor_.reset();
globalMemoryManager_.reset();

// dump cache stats on exit if enabled
if (dynamic_cast<facebook::velox::cache::AsyncDataCache*>(asyncDataCache_.get())) {
LOG(INFO) << asyncDataCache_->toString();
for (const auto& entry : std::filesystem::directory_iterator(cachePathPrefix_)) {
if (entry.path().filename().string().find(cacheFilePrefix_) != std::string::npos) {
LOG(INFO) << "Removing cache file " << entry.path().filename().string();
std::filesystem::remove(cachePathPrefix_ + "/" + entry.path().filename().string());
}
}
asyncDataCache_->shutdown();
}
}

} // namespace gluten
20 changes: 1 addition & 19 deletions cpp/velox/compute/VeloxBackend.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,25 +56,7 @@ class VeloxBackend {
return globalMemoryManager_.get();
}

void tearDown() {
// Destruct IOThreadPoolExecutor will join all threads.
// On threads exit, thread local variables can be constructed with referencing global variables.
// So, we need to destruct IOThreadPoolExecutor and stop the threads before global variables get destructed.
ioExecutor_.reset();
globalMemoryManager_.reset();

// dump cache stats on exit if enabled
if (dynamic_cast<facebook::velox::cache::AsyncDataCache*>(asyncDataCache_.get())) {
LOG(INFO) << asyncDataCache_->toString();
for (const auto& entry : std::filesystem::directory_iterator(cachePathPrefix_)) {
if (entry.path().filename().string().find(cacheFilePrefix_) != std::string::npos) {
LOG(INFO) << "Removing cache file " << entry.path().filename().string();
std::filesystem::remove(cachePathPrefix_ + "/" + entry.path().filename().string());
}
}
asyncDataCache_->shutdown();
}
}
void tearDown();

private:
explicit VeloxBackend(
Expand Down
1 change: 0 additions & 1 deletion cpp/velox/operators/writer/VeloxParquetDataSource.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,6 @@
#include "velox/connectors/hive/storage_adapters/gcs/GcsFileSystem.h"
#endif
#ifdef ENABLE_HDFS
#include "velox/connectors/hive/storage_adapters/hdfs/HdfsFileSystem.h"
#include "velox/connectors/hive/storage_adapters/hdfs/HdfsUtil.h"
#endif
#ifdef ENABLE_ABFS
Expand Down