rocksdb-native 2.2.0 → 2.3.0

package/vendor/librocksdb/vendor/rocksdb/env/fs_on_demand.h

@@ -0,0 +1,139 @@
+// Copyright (c) 2024-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+#include <string>
+
+#include "rocksdb/file_system.h"
+
+namespace ROCKSDB_NAMESPACE {
+// A FileSystem that links files to a local (destination) directory from a
+// corresponding remote (source) directory on demand. The decision to link
+// depends on the file type, with appendable or rename-able files, such as,
+// descriptors, logs, CURRENT, being read in place in the remote directory,
+// and SST files being linked. In the future, files read in place may be
+// mirrored to the local directory, so the local dir has a complete database
+// for troubleshooting purposes.
+
+class OnDemandFileSystem : public FileSystemWrapper {
+ public:
+  OnDemandFileSystem(const std::shared_ptr<FileSystem>& target,
+                     const std::string& remote_path,
+                     const std::string& local_path)
+      : FileSystemWrapper(target),
+        remote_path_(remote_path),
+        local_path_(local_path) {}
+
+  const char* Name() const override { return "OnDemandFileSystem"; }
+
+  IOStatus NewSequentialFile(const std::string& fname,
+                             const FileOptions& file_opts,
+                             std::unique_ptr<FSSequentialFile>* result,
+                             IODebugContext* dbg) override;
+
+  IOStatus NewRandomAccessFile(const std::string& fname,
+                               const FileOptions& file_opts,
+                               std::unique_ptr<FSRandomAccessFile>* result,
+                               IODebugContext* dbg) override;
+
+  IOStatus NewWritableFile(const std::string& fname,
+                           const FileOptions& file_opts,
+                           std::unique_ptr<FSWritableFile>* result,
+                           IODebugContext* dbg) override;
+
+  IOStatus ReuseWritableFile(const std::string& /*fname*/,
+                             const std::string& /*old_fname*/,
+                             const FileOptions& /*fopts*/,
+                             std::unique_ptr<FSWritableFile>* /*result*/,
+                             IODebugContext* /*dbg*/) override {
+    return IOStatus::NotSupported("ReuseWritableFile");
+  }
+
+  IOStatus NewDirectory(const std::string& name, const IOOptions& io_opts,
+                        std::unique_ptr<FSDirectory>* result,
+                        IODebugContext* dbg) override;
+
+  IOStatus FileExists(const std::string& fname, const IOOptions& options,
+                      IODebugContext* dbg) override;
+
+  IOStatus GetChildren(const std::string& dir, const IOOptions& options,
+                       std::vector<std::string>* result,
+                       IODebugContext* dbg) override;
+
+  IOStatus GetChildrenFileAttributes(const std::string& dir,
+                                     const IOOptions& options,
+                                     std::vector<FileAttributes>* result,
+                                     IODebugContext* dbg) override;
+
+  IOStatus GetFileSize(const std::string& fname, const IOOptions& options,
+                       uint64_t* file_size, IODebugContext* dbg) override;
+
+ private:
+  bool CheckPathAndAdjust(const std::string& orig, const std::string& replace,
+                          std::string& path);
+  bool LookupFileType(const std::string& name, FileType* type);
+
+  const std::string remote_path_;
+  const std::string local_path_;
+};
+
+// A wrapper class around an FSSequentialFile object. Its mainly
+// intended to be used for appendable files like MANIFEST and logs.
+// Beneath the covers, it tracks when EOF is reached, and reopens
+// the file in order to read the latest appended data. This is
+// necessary on some distributed file systems as they may have
+// stale metadata about the file.
+// TODO: Mirror the data read to a local file for troubleshooting
+//       purposes, as well as recovery in case the source dir is
+//       deleted.
+class OnDemandSequentialFile : public FSSequentialFile {
+ public:
+  OnDemandSequentialFile(std::unique_ptr<FSSequentialFile>&& file,
+                         OnDemandFileSystem* fs, const FileOptions& file_opts,
+                         const std::string& path)
+      : file_(std::move(file)),
+        fs_(fs),
+        file_opts_(file_opts),
+        path_(path),
+        eof_(false),
+        offset_(0) {}
+
+  virtual ~OnDemandSequentialFile() {}
+
+  IOStatus Read(size_t n, const IOOptions& options, Slice* result,
+                char* scratch, IODebugContext* dbg) override;
+
+  IOStatus Skip(uint64_t n) override;
+
+  bool use_direct_io() const override;
+
+  size_t GetRequiredBufferAlignment() const override;
+
+  IOStatus InvalidateCache(size_t /*offset*/, size_t /*length*/) override {
+    return IOStatus::NotSupported("InvalidateCache not supported.");
+  }
+
+  IOStatus PositionedRead(uint64_t /*offset*/, size_t /*n*/,
+                          const IOOptions& /*options*/, Slice* /*result*/,
+                          char* /*scratch*/, IODebugContext* /*dbg*/) override {
+    return IOStatus::NotSupported("PositionedRead");
+  }
+
+  Temperature GetTemperature() const override;
+
+ private:
+  std::unique_ptr<FSSequentialFile> file_;
+  OnDemandFileSystem* fs_;
+  const FileOptions file_opts_;
+  const std::string path_;
+  bool eof_;
+  uint64_t offset_;
+};
+
+std::shared_ptr<FileSystem> NewOnDemandFileSystem(
+    const std::shared_ptr<FileSystem>& fs, std::string remote_path,
+    std::string local_path);
+
+}  // namespace ROCKSDB_NAMESPACE

package/vendor/librocksdb/vendor/rocksdb/env/io_posix.cc

@@ -28,7 +28,7 @@
 #include <cstdio>
 #include <cstdlib>
 #include <cstring>
-#ifdef OS_LINUX
+#if defined(OS_LINUX) || defined(OS_ANDROID)
 #include <sys/statfs.h>
 #include <sys/sysmacros.h>
 #endif
@@ -457,7 +457,6 @@ Status PosixHelper::GetLogicalBlockSizeOfDirectory(const std::string& directory,
                                                    size_t* size) {
   int fd = open(directory.c_str(), O_DIRECTORY | O_RDONLY);
   if (fd == -1) {
-    close(fd);
     return Status::IOError("Cannot open directory " + directory);
   }
   *size = PosixHelper::GetLogicalBlockSizeOfFd(fd);
@@ -1377,9 +1376,10 @@ IOStatus PosixWritableFile::Close(const IOOptions& /*opts*/,
     // After ftruncate, we check whether ftruncate has the correct behavior.
     // If not, we should hack it with FALLOC_FL_PUNCH_HOLE
     if (result == 0 &&
-        (file_stats.st_size + file_stats.st_blksize - 1) /
-                file_stats.st_blksize !=
-            file_stats.st_blocks / (file_stats.st_blksize / 512)) {
+        static_cast<size_t>((file_stats.st_size + file_stats.st_blksize - 1) /
+                            file_stats.st_blksize) !=
+            static_cast<size_t>(file_stats.st_blocks /
+                                (file_stats.st_blksize / 512))) {
       IOSTATS_TIMER_GUARD(allocate_nanos);
       if (allow_fallocate_) {
         fallocate(fd_, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, filesize_,
@@ -1441,10 +1441,12 @@ void PosixWritableFile::SetWriteLifeTimeHint(Env::WriteLifeTimeHint hint) {
 #ifdef OS_LINUX
 // Suppress Valgrind "Unimplemented functionality" error.
 #ifndef ROCKSDB_VALGRIND_RUN
+  uint64_t fcntl_hint = hint;
+
   if (hint == write_hint_) {
     return;
   }
-  if (fcntl(fd_, F_SET_RW_HINT, &hint) == 0) {
+  if (fcntl(fd_, F_SET_RW_HINT, &fcntl_hint) == 0) {
     write_hint_ = hint;
   }
 #else

package/vendor/librocksdb/vendor/rocksdb/env/io_posix.h

@@ -30,7 +30,7 @@
 // For non linux platform, the following macros are used only as place
 // holder.
 #if !(defined OS_LINUX) && !(defined OS_FREEBSD) && !(defined CYGWIN) && \
-    !(defined OS_AIX)
+    !(defined OS_AIX) && !(defined OS_ANDROID)
 #define POSIX_FADV_NORMAL 0     /* [MC1] no further special treatment */
 #define POSIX_FADV_RANDOM 1     /* [MC1] expect random page refs */
 #define POSIX_FADV_SEQUENTIAL 2 /* [MC1] expect sequential page refs */

package/vendor/librocksdb/vendor/rocksdb/file/delete_scheduler.cc

@@ -31,6 +31,7 @@ DeleteScheduler::DeleteScheduler(SystemClock* clock, FileSystem* fs,
       total_trash_size_(0),
       rate_bytes_per_sec_(rate_bytes_per_sec),
       pending_files_(0),
+      next_trash_bucket_(0),
       bytes_max_delete_chunk_(bytes_max_delete_chunk),
       closing_(false),
       cv_(&mu_),
@@ -60,30 +61,72 @@ DeleteScheduler::~DeleteScheduler() {
 Status DeleteScheduler::DeleteFile(const std::string& file_path,
                                    const std::string& dir_to_sync,
                                    const bool force_bg) {
+  uint64_t total_size = sst_file_manager_->GetTotalSize();
   if (rate_bytes_per_sec_.load() <= 0 ||
       (!force_bg &&
-       total_trash_size_.load() >
-           sst_file_manager_->GetTotalSize() * max_trash_db_ratio_.load())) {
+       total_trash_size_.load() > total_size * max_trash_db_ratio_.load())) {
     // Rate limiting is disabled or trash size makes up more than
     // max_trash_db_ratio_ (default 25%) of the total DB size
-    TEST_SYNC_POINT("DeleteScheduler::DeleteFile");
-    Status s = fs_->DeleteFile(file_path, IOOptions(), nullptr);
+    Status s = DeleteFileImmediately(file_path, /*accounted=*/true);
     if (s.ok()) {
-      s = sst_file_manager_->OnDeleteFile(file_path);
       ROCKS_LOG_INFO(info_log_,
                      "Deleted file %s immediately, rate_bytes_per_sec %" PRIi64
-                     ", total_trash_size %" PRIu64 " max_trash_db_ratio %lf",
+                     ", total_trash_size %" PRIu64 ", total_size %" PRIi64
+                     ", max_trash_db_ratio %lf",
                      file_path.c_str(), rate_bytes_per_sec_.load(),
-                     total_trash_size_.load(), max_trash_db_ratio_.load());
-      InstrumentedMutexLock l(&mu_);
-      RecordTick(stats_.get(), FILES_DELETED_IMMEDIATELY);
+                     total_trash_size_.load(), total_size,
+                     max_trash_db_ratio_.load());
+    }
+    return s;
+  }
+  return AddFileToDeletionQueue(file_path, dir_to_sync, /*bucket=*/std::nullopt,
+                                /*accounted=*/true);
+}
+
+Status DeleteScheduler::DeleteUnaccountedFile(const std::string& file_path,
+                                              const std::string& dir_to_sync,
+                                              const bool force_bg,
+                                              std::optional<int32_t> bucket) {
+  uint64_t num_hard_links = 1;
+  fs_->NumFileLinks(file_path, IOOptions(), &num_hard_links, nullptr)
+      .PermitUncheckedError();
+
+  // We can tolerate rare races where we might immediately delete both links
+  // to a file.
+  if (rate_bytes_per_sec_.load() <= 0 || (!force_bg && num_hard_links > 1)) {
+    Status s = DeleteFileImmediately(file_path, /*accounted=*/false);
+    if (s.ok()) {
+      ROCKS_LOG_INFO(info_log_,
+                     "Deleted file %s immediately, rate_bytes_per_sec %" PRIi64,
+                     file_path.c_str(), rate_bytes_per_sec_.load());
     }
     return s;
   }
+  return AddFileToDeletionQueue(file_path, dir_to_sync, bucket,
+                                /*accounted=*/false);
+}
 
+Status DeleteScheduler::DeleteFileImmediately(const std::string& file_path,
+                                              bool accounted) {
+  TEST_SYNC_POINT("DeleteScheduler::DeleteFile");
+  TEST_SYNC_POINT_CALLBACK("DeleteScheduler::DeleteFile::cb",
+                           const_cast<std::string*>(&file_path));
+  Status s = fs_->DeleteFile(file_path, IOOptions(), nullptr);
+  if (s.ok()) {
+    s = OnDeleteFile(file_path, accounted);
+    InstrumentedMutexLock l(&mu_);
+    RecordTick(stats_.get(), FILES_DELETED_IMMEDIATELY);
+  }
+  return s;
+}
+
+Status DeleteScheduler::AddFileToDeletionQueue(const std::string& file_path,
+                                               const std::string& dir_to_sync,
+                                               std::optional<int32_t> bucket,
+                                               bool accounted) {
   // Move file to trash
   std::string trash_file;
-  Status s = MarkAsTrash(file_path, &trash_file);
+  Status s = MarkAsTrash(file_path, accounted, &trash_file);
   ROCKS_LOG_INFO(info_log_, "Mark file: %s as trash -- %s", trash_file.c_str(),
                  s.ToString().c_str());
 
@@ -92,7 +135,7 @@ Status DeleteScheduler::DeleteFile(const std::string& file_path,
                     file_path.c_str(), s.ToString().c_str());
     s = fs_->DeleteFile(file_path, IOOptions(), nullptr);
     if (s.ok()) {
-      s = sst_file_manager_->OnDeleteFile(file_path);
+      s = OnDeleteFile(file_path, accounted);
       ROCKS_LOG_INFO(info_log_, "Deleted file %s immediately",
                      trash_file.c_str());
       InstrumentedMutexLock l(&mu_);
@@ -102,11 +145,13 @@ Status DeleteScheduler::DeleteFile(const std::string& file_path,
   }
 
   // Update the total trash size
-  uint64_t trash_file_size = 0;
-  IOStatus io_s =
-      fs_->GetFileSize(trash_file, IOOptions(), &trash_file_size, nullptr);
-  if (io_s.ok()) {
-    total_trash_size_.fetch_add(trash_file_size);
+  if (accounted) {
+    uint64_t trash_file_size = 0;
+    IOStatus io_s =
+        fs_->GetFileSize(trash_file, IOOptions(), &trash_file_size, nullptr);
+    if (io_s.ok()) {
+      total_trash_size_.fetch_add(trash_file_size);
+    }
   }
   //**TODO: What should we do if we failed to
   // get the file size?
@@ -115,8 +160,15 @@ Status DeleteScheduler::DeleteFile(const std::string& file_path,
   {
     InstrumentedMutexLock l(&mu_);
     RecordTick(stats_.get(), FILES_MARKED_TRASH);
-    queue_.emplace(trash_file, dir_to_sync);
+    queue_.emplace(trash_file, dir_to_sync, accounted, bucket);
     pending_files_++;
+    if (bucket.has_value()) {
+      auto iter = pending_files_in_buckets_.find(bucket.value());
+      assert(iter != pending_files_in_buckets_.end());
+      if (iter != pending_files_in_buckets_.end()) {
+        iter->second++;
+      }
+    }
     if (pending_files_ == 1) {
       cv_.SignalAll();
     }
@@ -175,7 +227,7 @@ Status DeleteScheduler::CleanupDirectory(Env* env, SstFileManagerImpl* sfm,
 }
 
 Status DeleteScheduler::MarkAsTrash(const std::string& file_path,
-                                    std::string* trash_file) {
+                                    bool accounted, std::string* trash_file) {
   // Sanity check of the path
   size_t idx = file_path.rfind('/');
   if (idx == std::string::npos || idx == file_path.size() - 1) {
@@ -209,7 +261,7 @@ Status DeleteScheduler::MarkAsTrash(const std::string& file_path,
     }
     cnt++;
   }
-  if (s.ok()) {
+  if (s.ok() && accounted) {
     s = sst_file_manager_->OnMoveFile(file_path, *trash_file);
   }
   return s;
@@ -233,6 +285,8 @@ void DeleteScheduler::BackgroundEmptyTrash() {
     uint64_t total_deleted_bytes = 0;
     int64_t current_delete_rate = rate_bytes_per_sec_.load();
     while (!queue_.empty() && !closing_) {
+      // Satisfy static analysis.
+      std::optional<int32_t> bucket = std::nullopt;
       if (current_delete_rate != rate_bytes_per_sec_.load()) {
         // User changed the delete rate
         current_delete_rate = rate_bytes_per_sec_.load();
@@ -245,14 +299,17 @@ void DeleteScheduler::BackgroundEmptyTrash() {
       // Get new file to delete
       const FileAndDir& fad = queue_.front();
       std::string path_in_trash = fad.fname;
+      std::string dir_to_sync = fad.dir;
+      bool accounted = fad.accounted;
+      bucket = fad.bucket;
 
       // We don't need to hold the lock while deleting the file
       mu_.Unlock();
       uint64_t deleted_bytes = 0;
       bool is_complete = true;
       // Delete file from trash and update total_penlty value
-      Status s =
-          DeleteTrashFile(path_in_trash, fad.dir, &deleted_bytes, &is_complete);
+      Status s = DeleteTrashFile(path_in_trash, dir_to_sync, accounted,
+                                 &deleted_bytes, &is_complete);
       total_deleted_bytes += deleted_bytes;
       mu_.Lock();
       if (is_complete) {
@@ -286,12 +343,20 @@ void DeleteScheduler::BackgroundEmptyTrash() {
       TEST_SYNC_POINT_CALLBACK("DeleteScheduler::BackgroundEmptyTrash:Wait",
                                &total_penalty);
 
+      int32_t pending_files_in_bucket = std::numeric_limits<int32_t>::max();
       if (is_complete) {
         pending_files_--;
+        if (bucket.has_value()) {
+          auto iter = pending_files_in_buckets_.find(bucket.value());
+          assert(iter != pending_files_in_buckets_.end());
+          if (iter != pending_files_in_buckets_.end()) {
+            pending_files_in_bucket = iter->second--;
+          }
+        }
       }
-      if (pending_files_ == 0) {
-        // Unblock WaitForEmptyTrash since there are no more files waiting
-        // to be deleted
+      if (pending_files_ == 0 || pending_files_in_bucket == 0) {
+        // Unblock WaitForEmptyTrash or WaitForEmptyTrashBucket since there are
+        // no more files waiting to be deleted
         cv_.SignalAll();
       }
     }
@@ -300,12 +365,14 @@ void DeleteScheduler::BackgroundEmptyTrash() {
 
 Status DeleteScheduler::DeleteTrashFile(const std::string& path_in_trash,
                                         const std::string& dir_to_sync,
-                                        uint64_t* deleted_bytes,
+                                        bool accounted, uint64_t* deleted_bytes,
                                         bool* is_complete) {
   uint64_t file_size;
   Status s = fs_->GetFileSize(path_in_trash, IOOptions(), &file_size, nullptr);
   *is_complete = true;
   TEST_SYNC_POINT("DeleteScheduler::DeleteTrashFile:DeleteFile");
+  TEST_SYNC_POINT_CALLBACK("DeleteScheduler::DeleteTrashFile::cb",
+                           const_cast<std::string*>(&path_in_trash));
   if (s.ok()) {
     bool need_full_delete = true;
     if (bytes_max_delete_chunk_ != 0 && file_size > bytes_max_delete_chunk_) {
@@ -372,7 +439,7 @@ Status DeleteScheduler::DeleteTrashFile(const std::string& path_in_trash,
       }
       if (s.ok()) {
         *deleted_bytes = file_size;
-        s = sst_file_manager_->OnDeleteFile(path_in_trash);
+        s = OnDeleteFile(path_in_trash, accounted);
       }
     }
   }
@@ -382,12 +449,24 @@ Status DeleteScheduler::DeleteTrashFile(const std::string& path_in_trash,
                     path_in_trash.c_str(), s.ToString().c_str());
     *deleted_bytes = 0;
   } else {
-    total_trash_size_.fetch_sub(*deleted_bytes);
+    if (accounted) {
+      total_trash_size_.fetch_sub(*deleted_bytes);
+    }
   }
 
   return s;
 }
 
+Status DeleteScheduler::OnDeleteFile(const std::string& file_path,
+                                     bool accounted) {
+  if (accounted) {
+    return sst_file_manager_->OnDeleteFile(file_path);
+  }
+  TEST_SYNC_POINT_CALLBACK("DeleteScheduler::OnDeleteFile",
+                           const_cast<std::string*>(&file_path));
+  return Status::OK();
+}
+
 void DeleteScheduler::WaitForEmptyTrash() {
   InstrumentedMutexLock l(&mu_);
   while (pending_files_ > 0 && !closing_) {
@@ -395,6 +474,30 @@ void DeleteScheduler::WaitForEmptyTrash() {
   }
 }
 
+std::optional<int32_t> DeleteScheduler::NewTrashBucket() {
+  if (rate_bytes_per_sec_.load() <= 0) {
+    return std::nullopt;
+  }
+  InstrumentedMutexLock l(&mu_);
+  int32_t bucket_number = next_trash_bucket_++;
+  pending_files_in_buckets_.emplace(bucket_number, 0);
+  return bucket_number;
+}
+
+void DeleteScheduler::WaitForEmptyTrashBucket(int32_t bucket) {
+  InstrumentedMutexLock l(&mu_);
+  if (bucket >= next_trash_bucket_) {
+    return;
+  }
+  auto iter = pending_files_in_buckets_.find(bucket);
+  while (iter != pending_files_in_buckets_.end() && iter->second > 0 &&
+         !closing_) {
+    cv_.Wait();
+    iter = pending_files_in_buckets_.find(bucket);
+  }
+  pending_files_in_buckets_.erase(bucket);
+}
+
 void DeleteScheduler::MaybeCreateBackgroundThread() {
   if (bg_thread_ == nullptr && rate_bytes_per_sec_.load() > 0) {
     bg_thread_.reset(

package/vendor/librocksdb/vendor/rocksdb/file/delete_scheduler.h

@@ -7,6 +7,7 @@
 
 
 #include <map>
+#include <optional>
 #include <queue>
 #include <string>
 #include <thread>
@@ -48,16 +49,45 @@ class DeleteScheduler {
     MaybeCreateBackgroundThread();
   }
 
-  // Mark file as trash directory and schedule its deletion. If force_bg is
-  // set, it forces the file to always be deleted in the background thread,
-  // except when rate limiting is disabled
+  // Delete an accounted file that is tracked by `SstFileManager` and should be
+  // tracked by this `DeleteScheduler` when it's deleted.
+  // The file is deleted immediately if slow deletion is disabled. If force_bg
+  // is not set and trash to db size ratio exceeded the configured threshold,
+  // it is immediately deleted too. In all other cases, the file will be moved
+  // to a trash directory and scheduled for deletion by a background thread.
   Status DeleteFile(const std::string& fname, const std::string& dir_to_sync,
                     const bool force_bg = false);
 
-  // Wait for all files being deleteing in the background to finish or for
+  // Delete an unaccounted file that is not tracked by `SstFileManager` and
+  // should not be tracked by this `DeleteScheduler` when it's deleted.
+  // The file is deleted immediately if slow deletion is disabled. If force_bg
+  // is not set and the file have more than 1 hard link, it is immediately
+  // deleted too. In all other cases, the file will be moved to a trash
+  // directory and scheduled for deletion by a background thread.
+  // This API also supports assign a file to a specified bucket created by
+  // `NewTrashBucket` when delete files in the background. So the caller can
+  // wait for a specific bucket to be empty by checking the
+  // `WaitForEmptyTrashBucket` API.
+  Status DeleteUnaccountedFile(const std::string& file_path,
+                               const std::string& dir_to_sync,
+                               const bool force_bg = false,
+                               std::optional<int32_t> bucket = std::nullopt);
+
+  // Wait for all files being deleted in the background to finish or for
   // destructor to be called.
   void WaitForEmptyTrash();
 
+  // Creates a new trash bucket. A bucket is only created and returned when slow
+  // deletion is enabled.
+  // For each bucket that is created, the user should also call
+  // `WaitForEmptyTrashBucket` after scheduling file deletions to make sure the
+  // trash files are all cleared.
+  std::optional<int32_t> NewTrashBucket();
+
+  // Wait for all the files in the specified bucket to be deleted in the
+  // background or for the destructor to be called.
+  void WaitForEmptyTrashBucket(int32_t bucket);
+
   // Return a map containing errors that happened in BackgroundEmptyTrash
   // file_path => error status
   std::map<std::string, Status> GetBackgroundErrors();
@@ -87,12 +117,21 @@ class DeleteScheduler {
   }
 
  private:
-  Status MarkAsTrash(const std::string& file_path, std::string* path_in_trash);
+  Status DeleteFileImmediately(const std::string& file_path, bool accounted);
+
+  Status AddFileToDeletionQueue(const std::string& file_path,
+                                const std::string& dir_to_sync,
+                                std::optional<int32_t> bucket, bool accounted);
+
+  Status MarkAsTrash(const std::string& file_path, bool accounted,
+                     std::string* path_in_trash);
 
   Status DeleteTrashFile(const std::string& path_in_trash,
-                         const std::string& dir_to_sync,
+                         const std::string& dir_to_sync, bool accounted,
                          uint64_t* deleted_bytes, bool* is_complete);
 
+  Status OnDeleteFile(const std::string& file_path, bool accounted);
+
   void BackgroundEmptyTrash();
 
   void MaybeCreateBackgroundThread();
@@ -104,19 +143,28 @@ class DeleteScheduler {
   std::atomic<uint64_t> total_trash_size_;
   // Maximum number of bytes that should be deleted per second
   std::atomic<int64_t> rate_bytes_per_sec_;
-  // Mutex to protect queue_, pending_files_, bg_errors_, closing_, stats_
+  // Mutex to protect queue_, pending_files_, next_trash_bucket_,
+  // pending_files_in_buckets_, bg_errors_, closing_, stats_
   InstrumentedMutex mu_;
 
   struct FileAndDir {
-    FileAndDir(const std::string& f, const std::string& d) : fname(f), dir(d) {}
+    FileAndDir(const std::string& _fname, const std::string& _dir,
+               bool _accounted, std::optional<int32_t> _bucket)
+        : fname(_fname), dir(_dir), accounted(_accounted), bucket(_bucket) {}
     std::string fname;
     std::string dir;  // empty will be skipped.
+    bool accounted;
+    std::optional<int32_t> bucket;
   };
 
   // Queue of trash files that need to be deleted
   std::queue<FileAndDir> queue_;
   // Number of trash files that are waiting to be deleted
   int32_t pending_files_;
+  // Next trash bucket that can be created
+  int32_t next_trash_bucket_;
+  // A mapping from trash bucket to number of pending files in the bucket
+  std::map<int32_t, int32_t> pending_files_in_buckets_;
   uint64_t bytes_max_delete_chunk_;
   // Errors that happened in BackgroundEmptyTrash (file_path => error)
   std::map<std::string, Status> bg_errors_;
@@ -127,6 +175,7 @@ class DeleteScheduler {
   // Condition variable signaled in these conditions
   //    - pending_files_ value change from 0 => 1
   //    - pending_files_ value change from 1 => 0
+  //    - a value in pending_files_in_buckets change from 1 => 0
   //    - closing_ value is set to true
   InstrumentedCondVar cv_;
   // Background thread running BackgroundEmptyTrash
@@ -138,6 +187,10 @@ class DeleteScheduler {
   // If the trash size constitutes for more than this fraction of the total DB
   // size we will start deleting new files passed to DeleteScheduler
   // immediately
+  // Unaccounted files passed for deletion will not cause change in
+  // total_trash_size_ or affect the DeleteScheduler::total_trash_size_ over
+  // SstFileManager::total_size_ ratio. Their slow deletion is not subject to
+  // this configured threshold either.
   std::atomic<double> max_trash_db_ratio_;
   static const uint64_t kMicrosInSecond = 1000 * 1000LL;
   std::shared_ptr<Statistics> stats_;

package/vendor/librocksdb/vendor/rocksdb/file/file_util.cc

@@ -59,7 +59,10 @@ IOStatus CopyFile(FileSystem* fs, const std::string& source,
       return io_s;
     }
     if (slice.size() == 0) {
-      return IOStatus::Corruption("file too small");
+      return IOStatus::Corruption(
+          "File smaller than expected for copy: " + source + " expecting " +
+          std::to_string(size) + " more bytes after " +
+          std::to_string(dest_writer->GetFileSize()));
     }
 
     io_s = dest_writer->Append(opts, slice);
@@ -122,8 +125,8 @@ IOStatus CreateFile(FileSystem* fs, const std::string& destination,
 Status DeleteDBFile(const ImmutableDBOptions* db_options,
                     const std::string& fname, const std::string& dir_to_sync,
                     const bool force_bg, const bool force_fg) {
-  SstFileManagerImpl* sfm =
-      static_cast<SstFileManagerImpl*>(db_options->sst_file_manager.get());
+  SstFileManagerImpl* sfm = static_cast_with_check<SstFileManagerImpl>(
+      db_options->sst_file_manager.get());
   if (sfm && !force_fg) {
     return sfm->ScheduleFileDeletion(fname, dir_to_sync, force_bg);
   } else {
@@ -131,6 +134,21 @@ Status DeleteDBFile(const ImmutableDBOptions* db_options,
   }
 }
 
+Status DeleteUnaccountedDBFile(const ImmutableDBOptions* db_options,
+                               const std::string& fname,
+                               const std::string& dir_to_sync,
+                               const bool force_bg, const bool force_fg,
+                               std::optional<int32_t> bucket) {
+  SstFileManagerImpl* sfm = static_cast_with_check<SstFileManagerImpl>(
+      db_options->sst_file_manager.get());
+  if (sfm && !force_fg) {
+    return sfm->ScheduleUnaccountedFileDeletion(fname, dir_to_sync, force_bg,
+                                                bucket);
+  } else {
+    return db_options->env->DeleteFile(fname);
+  }
+}
+
 // requested_checksum_func_name brings the function name of the checksum
 // generator in checksum_factory. Empty string is permitted, in which case the
 // name of the generator created by the factory is unchecked. When
@@ -226,7 +244,10 @@ IOStatus GenerateOneFileChecksum(
                                   io_s.ToString());
     }
     if (slice.size() == 0) {
-      return IOStatus::Corruption("file too small");
+      return IOStatus::Corruption(
+          "File smaller than expected for checksum: " + file_path +
+          " expecting " + std::to_string(size) + " more bytes after " +
+          std::to_string(offset));
     }
     checksum_generator->Update(slice.data(), slice.size());
     size -= slice.size();