BlobDB::Open() should put all existing trash files to delete scheduler (#5103)

Summary:
Right now, BlobDB::Open() fails to put all trash files to delete scheduler,
which causes some trash files permanently untracked.
Pull Request resolved: https://github.com/facebook/rocksdb/pull/5103

Differential Revision: D14606095

Pulled By: siying

fbshipit-source-id: 41a9437a2948abb235c0ed85f9a04612d0e50183

diff --git a/utilities/blob_db/blob_db_impl.cc b/utilities/blob_db/blob_db_impl.cc
index 7c938c16e4c9ba84f4b0975d07a8fbbfe4aa3a3f..f8e858dd9aabcd6747f5f5eb90e1f1339476e4b4 100644 (file)
--- a/utilities/blob_db/blob_db_impl.cc
+++ b/utilities/blob_db/blob_db_impl.cc
@@ -31,6 +31,7 @@
 #include "util/logging.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
+#include "util/sst_file_manager_impl.h"
 #include "util/stop_watch.h"
 #include "util/sync_point.h"
 #include "util/timer_queue.h"
@@ -180,6 +181,12 @@ Status BlobDBImpl::Open(std::vector<ColumnFamilyHandle*>* handles) {
     return s;
   }
   db_impl_ = static_cast_with_check<DBImpl, DB>(db_->GetRootDB());
+
+  // Add trash files in blob dir to file delete scheduler.
+  SstFileManagerImpl* sfm = static_cast<SstFileManagerImpl*>(
+      db_impl_->immutable_db_options().sst_file_manager.get());
+  DeleteScheduler::CleanupDirectory(env_, sfm, blob_dir_);
+
   UpdateLiveSSTSize();
 
   // Start background jobs.

diff --git a/utilities/blob_db/blob_db_impl.h b/utilities/blob_db/blob_db_impl.h
index 8678ee9d495c9b992e6049c690ea18613184c64c..0a22c0acd9bf4dd4eeeb392a0857130b2d60d2ae 100644 (file)
--- a/utilities/blob_db/blob_db_impl.h
+++ b/utilities/blob_db/blob_db_impl.h
@@ -197,6 +197,8 @@ class BlobDBImpl : public BlobDB {
   void TEST_DeleteObsoleteFiles();
 
   uint64_t TEST_live_sst_size();
+
+  const std::string& TEST_blob_dir() const { return blob_dir_; }
 #endif  //  !NDEBUG
 
  private:

diff --git a/utilities/blob_db/blob_db_test.cc b/utilities/blob_db/blob_db_test.cc
index f9b4063c7aa4dfc6981100e1f5a9aabd2e409633..e5c10f0c2de04f8c8285452dc8d6ff4cd7606499 100644 (file)
--- a/utilities/blob_db/blob_db_test.cc
+++ b/utilities/blob_db/blob_db_test.cc
@@ -18,6 +18,7 @@
 #include "rocksdb/utilities/debug.h"
 #include "util/cast_util.h"
 #include "util/fault_injection_test_env.h"
+#include "util/file_util.h"
 #include "util/random.h"
 #include "util/sst_file_manager_impl.h"
 #include "util/string_util.h"
@@ -810,12 +811,70 @@ TEST_F(BlobDBTest, SstFileManager) {
   ASSERT_EQ(0, files_deleted_directly);
   Destroy();
   // Make sure that DestroyBlobDB() also goes through delete scheduler.
-  ASSERT_GE(2, files_scheduled_to_delete);
+  ASSERT_GE(files_scheduled_to_delete, 2);
   ASSERT_EQ(0, files_deleted_directly);
   SyncPoint::GetInstance()->DisableProcessing();
   sfm->WaitForEmptyTrash();
 }
 
+TEST_F(BlobDBTest, SstFileManagerRestart) {
+  int files_deleted_directly = 0;
+  int files_scheduled_to_delete = 0;
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "SstFileManagerImpl::ScheduleFileDeletion",
+      [&](void * /*arg*/) { files_scheduled_to_delete++; });
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DeleteScheduler::DeleteFile",
+      [&](void * /*arg*/) { files_deleted_directly++; });
+
+  // run the same test for Get(), MultiGet() and Iterator each.
+  std::shared_ptr<SstFileManager> sst_file_manager(
+      NewSstFileManager(mock_env_.get()));
+  sst_file_manager->SetDeleteRateBytesPerSecond(1);
+  SstFileManagerImpl *sfm =
+      static_cast<SstFileManagerImpl *>(sst_file_manager.get());
+
+  BlobDBOptions bdb_options;
+  bdb_options.min_blob_size = 0;
+  Options db_options;
+
+  SyncPoint::GetInstance()->EnableProcessing();
+  db_options.sst_file_manager = sst_file_manager;
+
+  Open(bdb_options, db_options);
+  std::string blob_dir = blob_db_impl()->TEST_blob_dir();
+  blob_db_->Put(WriteOptions(), "foo", "bar");
+  Close();
+
+  // Create 3 dummy trash files under the blob_dir
+  CreateFile(db_options.env, blob_dir + "/000666.blob.trash", "", false);
+  CreateFile(db_options.env, blob_dir + "/000888.blob.trash", "", true);
+  CreateFile(db_options.env, blob_dir + "/something_not_match.trash", "",
+             false);
+
+  // Make sure that reopening the DB rescan the existing trash files
+  Open(bdb_options, db_options);
+  ASSERT_GE(files_scheduled_to_delete, 3);
+  ASSERT_EQ(0, files_deleted_directly);
+
+  sfm->WaitForEmptyTrash();
+
+  // There should be exact one file under the blob dir now.
+  std::vector<std::string> all_files;
+  ASSERT_OK(db_options.env->GetChildren(blob_dir, &all_files));
+  int nfiles = 0;
+  for (const auto &f : all_files) {
+    assert(!f.empty());
+    if (f[0] == '.') {
+      continue;
+    }
+    nfiles++;
+  }
+  ASSERT_EQ(nfiles, 1);
+
+  SyncPoint::GetInstance()->DisableProcessing();
+}
+
 TEST_F(BlobDBTest, SnapshotAndGarbageCollection) {
   BlobDBOptions bdb_options;
   bdb_options.min_blob_size = 0;