SstFileManager: add bytes_max_delete_chunk

Summary:
Add `bytes_max_delete_chunk` in SstFileManager so that we can drop a large file in multiple batches.
Closes https://github.com/facebook/rocksdb/pull/3640

Differential Revision: D7358679

Pulled By: siying

fbshipit-source-id: ef17f0da2f5723dbece2669485a9b91b3edc0bb7

HISTORY.md

@@ -17,6 +17,7 @@
 * Avoid unnecessarily flushing in `CompactRange()` when the range specified by the user does not overlap unflushed memtables.
 * If `ColumnFamilyOptions::max_subcompactions` is set greater than one, we now parallelize large manual level-based compactions.
 * Add "rocksdb.live-sst-files-size" DB property to return total bytes of all SST files belong to the latest LSM tree.
+* NewSstFileManager to add an argument bytes_max_delete_chunk with default 64MB. With this argument, a file larger than 64MB will be ftruncated multiple times based on this size.
 
 ### Bug Fixes
 * Fix a leak in prepared_section_completed_ where the zeroed entries would not removed from the map.

include/rocksdb/sst_file_manager.h

@@ -96,10 +96,14 @@ class SstFileManager {
 // @param max_trash_db_ratio: 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
+// @param bytes_max_delete_chunk: if a single file is larger than delete chunk,
+//    ftruncate the file by this size each time, rather than dropping the whole
+//    file. 0 means to always delete the whole file.
 extern SstFileManager* NewSstFileManager(
     Env* env, std::shared_ptr<Logger> info_log = nullptr,
     std::string trash_dir = "", int64_t rate_bytes_per_sec = 0,
     bool delete_existing_trash = true, Status* status = nullptr,
-    double max_trash_db_ratio = 0.25);
+    double max_trash_db_ratio = 0.25,
+    uint64_t bytes_max_delete_chunk = 64 * 1024 * 1024);
 
 }  // namespace rocksdb

util/delete_scheduler.cc

@@ -22,11 +22,13 @@ namespace rocksdb {
 DeleteScheduler::DeleteScheduler(Env* env, int64_t rate_bytes_per_sec,
                                  Logger* info_log,
                                  SstFileManagerImpl* sst_file_manager,
-                                 double max_trash_db_ratio)
+                                 double max_trash_db_ratio,
+                                 uint64_t bytes_max_delete_chunk)
     : env_(env),
       total_trash_size_(0),
       rate_bytes_per_sec_(rate_bytes_per_sec),
       pending_files_(0),
+      bytes_max_delete_chunk_(bytes_max_delete_chunk),
       closing_(false),
       cv_(&mu_),
       info_log_(info_log),
@@ -208,15 +210,18 @@ void DeleteScheduler::BackgroundEmptyTrash() {
 
       // Get new file to delete
       std::string path_in_trash = queue_.front();
-      queue_.pop();
 
       // We dont 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,  &deleted_bytes);
+      Status s = DeleteTrashFile(path_in_trash, &deleted_bytes, &is_complete);
       total_deleted_bytes += deleted_bytes;
       mu_.Lock();
+      if (is_complete) {
+        queue_.pop();
+      }
 
       if (!s.ok()) {
         bg_errors_[path_in_trash] = s;
@@ -236,7 +241,9 @@ void DeleteScheduler::BackgroundEmptyTrash() {
       TEST_SYNC_POINT_CALLBACK("DeleteScheduler::BackgroundEmptyTrash:Wait",
                                &total_penlty);
 
-      pending_files_--;
+      if (is_complete) {
+        pending_files_--;
+      }
       if (pending_files_ == 0) {
         // Unblock WaitForEmptyTrash since there are no more files waiting
         // to be deleted
@@ -247,23 +254,49 @@ void DeleteScheduler::BackgroundEmptyTrash() {
 }
 
 Status DeleteScheduler::DeleteTrashFile(const std::string& path_in_trash,
-                                        uint64_t* deleted_bytes) {
+                                        uint64_t* deleted_bytes,
+                                        bool* is_complete) {
   uint64_t file_size;
   Status s = env_->GetFileSize(path_in_trash, &file_size);
+  *is_complete = true;
+  TEST_SYNC_POINT("DeleteScheduler::DeleteTrashFile:DeleteFile");
   if (s.ok()) {
-    TEST_SYNC_POINT("DeleteScheduler::DeleteTrashFile:DeleteFile");
-    s = env_->DeleteFile(path_in_trash);
-  }
+    bool need_full_delete = true;
+    if (bytes_max_delete_chunk_ != 0 && file_size > bytes_max_delete_chunk_) {
+      unique_ptr<WritableFile> wf;
+      Status my_status =
+          env_->ReopenWritableFile(path_in_trash, &wf, EnvOptions());
+      if (my_status.ok()) {
+        my_status = wf->Truncate(file_size - bytes_max_delete_chunk_);
+        if (my_status.ok()) {
+          TEST_SYNC_POINT("DeleteScheduler::DeleteTrashFile:Fsync");
+          my_status = wf->Fsync();
+        }
+      }
+      if (my_status.ok()) {
+        *deleted_bytes = bytes_max_delete_chunk_;
+        need_full_delete = false;
+        *is_complete = false;
+      } else {
+        ROCKS_LOG_WARN(info_log_,
+                       "Failed to partially delete %s from trash -- %s",
+                       path_in_trash.c_str(), my_status.ToString().c_str());
+      }
+    }
 
+    if (need_full_delete) {
+      s = env_->DeleteFile(path_in_trash);
+      *deleted_bytes = file_size;
+      sst_file_manager_->OnDeleteFile(path_in_trash);
+    }
+  }
   if (!s.ok()) {
     // Error while getting file size or while deleting
     ROCKS_LOG_ERROR(info_log_, "Failed to delete %s from trash -- %s",
                     path_in_trash.c_str(), s.ToString().c_str());
     *deleted_bytes = 0;
   } else {
-    *deleted_bytes = file_size;
-    total_trash_size_.fetch_sub(file_size);
-    sst_file_manager_->OnDeleteFile(path_in_trash);
+    total_trash_size_.fetch_sub(*deleted_bytes);
   }
 
   return s;

util/delete_scheduler.h

@@ -34,7 +34,7 @@ class DeleteScheduler {
  public:
   DeleteScheduler(Env* env, int64_t rate_bytes_per_sec, Logger* info_log,
                   SstFileManagerImpl* sst_file_manager,
-                  double max_trash_db_ratio);
+                  double max_trash_db_ratio, uint64_t bytes_max_delete_chunk);
 
   ~DeleteScheduler();
 
@@ -82,7 +82,7 @@ class DeleteScheduler {
   Status MarkAsTrash(const std::string& file_path, std::string* path_in_trash);
 
   Status DeleteTrashFile(const std::string& path_in_trash,
-                         uint64_t* deleted_bytes);
+                         uint64_t* deleted_bytes, bool* is_complete);
 
   void BackgroundEmptyTrash();
 
@@ -97,6 +97,7 @@ class DeleteScheduler {
   std::queue<std::string> queue_;
   // Number of trash files that are waiting to be deleted
   int32_t pending_files_;
+  uint64_t bytes_max_delete_chunk_;
   // Errors that happened in BackgroundEmptyTrash (file_path => error)
   std::map<std::string, Status> bg_errors_;
   // Set to true in ~DeleteScheduler() to force BackgroundEmptyTrash to stop

util/delete_scheduler_test.cc

@@ -99,7 +99,7 @@ class DeleteSchedulerTest : public testing::Test {
     // 25%)
     sst_file_mgr_.reset(
         new SstFileManagerImpl(env_, nullptr, rate_bytes_per_sec_,
-                               /* max_trash_db_ratio= */ 1.1));
+                               /* max_trash_db_ratio= */ 1.1, 128 * 1024));
     delete_scheduler_ = sst_file_mgr_->delete_scheduler();
   }
 
@@ -436,6 +436,34 @@ TEST_F(DeleteSchedulerTest, StartBGEmptyTrashMultipleTimes) {
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 }
 
+TEST_F(DeleteSchedulerTest, DeletePartialFile) {
+  int bg_delete_file = 0;
+  int bg_fsync = 0;
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DeleteScheduler::DeleteTrashFile:DeleteFile",
+      [&](void*) { bg_delete_file++; });
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DeleteScheduler::DeleteTrashFile:Fsync", [&](void*) { bg_fsync++; });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  rate_bytes_per_sec_ = 1024 * 1024;  // 1 MB / sec
+  NewDeleteScheduler();
+
+  // Should delete in 4 batch
+  ASSERT_OK(delete_scheduler_->DeleteFile(NewDummyFile("data_1", 500 * 1024)));
+  ASSERT_OK(delete_scheduler_->DeleteFile(NewDummyFile("data_2", 100 * 1024)));
+  // Should delete in 2 batch
+  ASSERT_OK(delete_scheduler_->DeleteFile(NewDummyFile("data_2", 200 * 1024)));
+
+  delete_scheduler_->WaitForEmptyTrash();
+
+  auto bg_errors = delete_scheduler_->GetBackgroundErrors();
+  ASSERT_EQ(bg_errors.size(), 0);
+  ASSERT_EQ(7, bg_delete_file);
+  ASSERT_EQ(4, bg_fsync);
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+}
+
 // 1- Create a DeleteScheduler with very slow rate limit (1 Byte / sec)
 // 2- Delete 100 files using DeleteScheduler
 // 3- Delete the DeleteScheduler (call the destructor while queue is not empty)

util/sst_file_manager_impl.cc

@@ -18,7 +18,8 @@ namespace rocksdb {
 #ifndef ROCKSDB_LITE
 SstFileManagerImpl::SstFileManagerImpl(Env* env, std::shared_ptr<Logger> logger,
                                        int64_t rate_bytes_per_sec,
-                                       double max_trash_db_ratio)
+                                       double max_trash_db_ratio,
+                                       uint64_t bytes_max_delete_chunk)
     : env_(env),
       logger_(logger),
       total_files_size_(0),
@@ -26,7 +27,7 @@ SstFileManagerImpl::SstFileManagerImpl(Env* env, std::shared_ptr<Logger> logger,
       cur_compactions_reserved_size_(0),
       max_allowed_space_(0),
       delete_scheduler_(env, rate_bytes_per_sec, logger.get(), this,
-                        max_trash_db_ratio) {}
+                        max_trash_db_ratio, bytes_max_delete_chunk) {}
 
 SstFileManagerImpl::~SstFileManagerImpl() {}
 
@@ -196,10 +197,11 @@ SstFileManager* NewSstFileManager(Env* env, std::shared_ptr<Logger> info_log,
                                   std::string trash_dir,
                                   int64_t rate_bytes_per_sec,
                                   bool delete_existing_trash, Status* status,
-                                  double max_trash_db_ratio) {
+                                  double max_trash_db_ratio,
+                                  uint64_t bytes_max_delete_chunk) {
   SstFileManagerImpl* res =
       new SstFileManagerImpl(env, info_log, rate_bytes_per_sec,
-                             max_trash_db_ratio);
+                             max_trash_db_ratio, bytes_max_delete_chunk);
 
   // trash_dir is deprecated and not needed anymore, but if user passed it
   // we will still remove files in it.
@@ -236,7 +238,8 @@ SstFileManager* NewSstFileManager(Env* env, std::shared_ptr<Logger> info_log,
                                   std::string trash_dir,
                                   int64_t rate_bytes_per_sec,
                                   bool delete_existing_trash, Status* status,
-                                  double max_trash_db_ratio) {
+                                  double max_trash_db_ratio,
+                                  uint64_t bytes_max_delete_chunk) {
   if (status) {
     *status =
       Status::NotSupported("SstFileManager is not supported in ROCKSDB_LITE");

util/sst_file_manager_impl.h

@@ -27,7 +27,8 @@ class SstFileManagerImpl : public SstFileManager {
  public:
   explicit SstFileManagerImpl(Env* env, std::shared_ptr<Logger> logger,
                               int64_t rate_bytes_per_sec,
-                              double max_trash_db_ratio);
+                              double max_trash_db_ratio,
+                              uint64_t bytes_max_delete_chunk);
 
   ~SstFileManagerImpl();