@nxtedition/rocksdb 5.2.21 → 5.2.28

package/deps/rocksdb/rocksdb/db/column_family.h

@@ -9,10 +9,10 @@
 
 #pragma once
 
-#include <unordered_map>
+#include <atomic>
 #include <string>
+#include <unordered_map>
 #include <vector>
-#include <atomic>
 
 #include "db/memtable_list.h"
 #include "db/table_cache.h"
@@ -25,6 +25,7 @@
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "trace_replay/block_cache_tracer.h"
+#include "util/hash_containers.h"
 #include "util/thread_local.h"
 
 namespace ROCKSDB_NAMESPACE {
@@ -208,8 +209,6 @@ struct SuperVersion {
   uint64_t version_number;
   WriteStallCondition write_stall_condition;
 
-  InstrumentedMutex* db_mutex;
-
   // should be called outside the mutex
   SuperVersion() = default;
   ~SuperVersion();
@@ -253,13 +252,12 @@ extern Status CheckCFPathsSupported(const DBOptions& db_options,
 
 extern ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                            const ColumnFamilyOptions& src);
-// Wrap user defined table proproties collector factories `from cf_options`
+// Wrap user defined table properties collector factories `from cf_options`
 // into internal ones in int_tbl_prop_collector_factories. Add a system internal
 // one too.
 extern void GetIntTblPropCollectorFactory(
     const ImmutableCFOptions& ioptions,
-    std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-        int_tbl_prop_collector_factories);
+    IntTblPropCollectorFactories* int_tbl_prop_collector_factories);
 
 class ColumnFamilySet;
 
@@ -282,8 +280,7 @@ class ColumnFamilyData {
   // UnrefAndTryDelete() decreases the reference count and do free if needed,
   // return true if this is freed else false, UnrefAndTryDelete() can only
   // be called while holding a DB mutex, or during single-threaded recovery.
-  // sv_under_cleanup is only provided when called from SuperVersion::Cleanup.
-  bool UnrefAndTryDelete(SuperVersion* sv_under_cleanup = nullptr);
+  bool UnrefAndTryDelete();
 
   // SetDropped() can only be called under following conditions:
   // 1) Holding a DB mutex,
@@ -316,7 +313,7 @@ class ColumnFamilyData {
   FlushReason GetFlushReason() const { return flush_reason_; }
   // thread-safe
   const FileOptions* soptions() const;
-  const ImmutableCFOptions* ioptions() const { return &ioptions_; }
+  const ImmutableOptions* ioptions() const { return &ioptions_; }
   // REQUIRES: DB mutex held
   // This returns the MutableCFOptions used by current SuperVersion
   // You should use this API to reference MutableCFOptions most of the time.
@@ -361,6 +358,7 @@ class ColumnFamilyData {
   uint64_t GetNumLiveVersions() const;  // REQUIRE: DB mutex held
   uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
   uint64_t GetLiveSstFilesSize() const;   // REQUIRE: DB mutex held
+  uint64_t GetTotalBlobFileSize() const;  // REQUIRE: DB mutex held
   void SetMemtable(MemTable* new_mem) {
     uint64_t memtable_id = last_memtable_id_.fetch_add(1) + 1;
     new_mem->SetID(memtable_id);
@@ -416,7 +414,8 @@ class ColumnFamilyData {
                            const CompactRangeOptions& compact_range_options,
                            const InternalKey* begin, const InternalKey* end,
                            InternalKey** compaction_end, bool* manual_conflict,
-                           uint64_t max_file_num_to_ignore);
+                           uint64_t max_file_num_to_ignore,
+                           const std::string& trim_ts);
 
   CompactionPicker* compaction_picker() { return compaction_picker_.get(); }
   // thread-safe
@@ -428,8 +427,7 @@ class ColumnFamilyData {
     return internal_comparator_;
   }
 
-  const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-  int_tbl_prop_collector_factories() const {
+  const IntTblPropCollectorFactories* int_tbl_prop_collector_factories() const {
     return &int_tbl_prop_collector_factories_;
   }
 
@@ -441,7 +439,7 @@ class ColumnFamilyData {
   // Get SuperVersion stored in thread local storage. If it does not exist,
   // get a reference from a current SuperVersion.
   SuperVersion* GetThreadLocalSuperVersion(DBImpl* db);
-  // Try to return SuperVersion back to thread local storage. Retrun true on
+  // Try to return SuperVersion back to thread local storage. Return true on
   // success and false on failure. It fails when the thread local storage
   // contains anything other than SuperVersion::kSVInUse flag.
   bool ReturnThreadLocalSuperVersion(SuperVersion* sv);
@@ -455,7 +453,6 @@ class ColumnFamilyData {
   // the clients to allocate SuperVersion outside of mutex.
   // IMPORTANT: Only call this from DBImpl::InstallSuperVersion()
   void InstallSuperVersion(SuperVersionContext* sv_context,
-                           InstrumentedMutex* db_mutex,
                            const MutableCFOptions& mutable_cf_options);
   void InstallSuperVersion(SuperVersionContext* sv_context,
                            InstrumentedMutex* db_mutex);
@@ -475,9 +472,11 @@ class ColumnFamilyData {
     kPendingCompactionBytes,
   };
   static std::pair<WriteStallCondition, WriteStallCause>
-  GetWriteStallConditionAndCause(int num_unflushed_memtables, int num_l0_files,
-                                 uint64_t num_compaction_needed_bytes,
-                                 const MutableCFOptions& mutable_cf_options);
+  GetWriteStallConditionAndCause(
+      int num_unflushed_memtables, int num_l0_files,
+      uint64_t num_compaction_needed_bytes,
+      const MutableCFOptions& mutable_cf_options,
+      const ImmutableCFOptions& immutable_cf_options);
 
   // Recalculate some small conditions, which are changed only during
   // compaction, adding new memtable and/or
@@ -520,19 +519,22 @@ class ColumnFamilyData {
   }
 
   ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
+  WriteBufferManager* write_buffer_mgr() { return write_buffer_manager_; }
+
+  static const uint32_t kDummyColumnFamilyDataId;
 
  private:
   friend class ColumnFamilySet;
-  static const uint32_t kDummyColumnFamilyDataId;
   ColumnFamilyData(uint32_t id, const std::string& name,
                    Version* dummy_versions, Cache* table_cache,
                    WriteBufferManager* write_buffer_manager,
                    const ColumnFamilyOptions& options,
                    const ImmutableDBOptions& db_options,
-                   const FileOptions& file_options,
+                   const FileOptions* file_options,
                    ColumnFamilySet* column_family_set,
                    BlockCacheTracer* const block_cache_tracer,
-                   const std::shared_ptr<IOTracer>& io_tracer);
+                   const std::shared_ptr<IOTracer>& io_tracer,
+                   const std::string& db_session_id);
 
   std::vector<std::string> GetDbPaths() const;
 
@@ -546,11 +548,10 @@ class ColumnFamilyData {
   std::atomic<bool> dropped_;  // true if client dropped it
 
   const InternalKeyComparator internal_comparator_;
-  std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
-      int_tbl_prop_collector_factories_;
+  IntTblPropCollectorFactories int_tbl_prop_collector_factories_;
 
   const ColumnFamilyOptions initial_cf_options_;
-  const ImmutableCFOptions ioptions_;
+  const ImmutableOptions ioptions_;
   MutableCFOptions mutable_cf_options_;
 
   const bool is_delete_range_supported_;
@@ -629,10 +630,8 @@ class ColumnFamilyData {
 // held and it needs to be executed from the write thread. SetDropped() also
 // guarantees that it will be called only from single-threaded LogAndApply(),
 // but this condition is not that important.
-// * Iteration -- hold DB mutex, but you can release it in the body of
-// iteration. If you release DB mutex in body, reference the column
-// family before the mutex and unreference after you unlock, since the column
-// family might get dropped when the DB mutex is released
+// * Iteration -- hold DB mutex. If you want to release the DB mutex in the
+// body of the iteration, wrap in a RefedColumnFamilySet.
 // * GetDefault() -- thread safe
 // * GetColumnFamily() -- either inside of DB mutex or from a write thread
 // * GetNextColumnFamilyID(), GetMaxColumnFamily(), UpdateMaxColumnFamily(),
@@ -644,17 +643,12 @@ class ColumnFamilySet {
    public:
     explicit iterator(ColumnFamilyData* cfd)
         : current_(cfd) {}
+    // NOTE: minimum operators for for-loop iteration
     iterator& operator++() {
-      // dropped column families might still be included in this iteration
-      // (we're only removing them when client drops the last reference to the
-      // column family).
-      // dummy is never dead, so this will never be infinite
-      do {
-        current_ = current_->next_;
-      } while (current_->refs_.load(std::memory_order_relaxed) == 0);
+      current_ = current_->next_;
       return *this;
     }
-    bool operator!=(const iterator& other) {
+    bool operator!=(const iterator& other) const {
       return this->current_ != other.current_;
     }
     ColumnFamilyData* operator*() { return current_; }
@@ -669,7 +663,8 @@ class ColumnFamilySet {
                   WriteBufferManager* _write_buffer_manager,
                   WriteController* _write_controller,
                   BlockCacheTracer* const block_cache_tracer,
-                  const std::shared_ptr<IOTracer>& io_tracer);
+                  const std::shared_ptr<IOTracer>& io_tracer,
+                  const std::string& db_session_id);
   ~ColumnFamilySet();
 
   ColumnFamilyData* GetDefault() const;
@@ -692,10 +687,6 @@ class ColumnFamilySet {
   iterator begin() { return iterator(dummy_cfd_->next_); }
   iterator end() { return iterator(dummy_cfd_); }
 
-  // REQUIRES: DB mutex held
-  // Don't call while iterating over ColumnFamilySet
-  void FreeDeadColumnFamilies();
-
   Cache* get_table_cache() { return table_cache_; }
 
   WriteBufferManager* write_buffer_manager() { return write_buffer_manager_; }
@@ -715,10 +706,12 @@ class ColumnFamilySet {
   // * when reading, at least one condition needs to be satisfied:
   // 1. DB mutex locked
   // 2. accessed from a single-threaded write thread
-  std::unordered_map<std::string, uint32_t> column_families_;
-  std::unordered_map<uint32_t, ColumnFamilyData*> column_family_data_;
+  UnorderedMap<std::string, uint32_t> column_families_;
+  UnorderedMap<uint32_t, ColumnFamilyData*> column_family_data_;
 
   uint32_t max_column_family_;
+  const FileOptions file_options_;
+
   ColumnFamilyData* dummy_cfd_;
   // We don't hold the refcount here, since default column family always exists
   // We are also not responsible for cleaning up default_cfd_cache_. This is
@@ -728,12 +721,61 @@ class ColumnFamilySet {
 
   const std::string db_name_;
   const ImmutableDBOptions* const db_options_;
-  const FileOptions file_options_;
   Cache* table_cache_;
   WriteBufferManager* write_buffer_manager_;
   WriteController* write_controller_;
   BlockCacheTracer* const block_cache_tracer_;
   std::shared_ptr<IOTracer> io_tracer_;
+  std::string db_session_id_;
+};
+
+// A wrapper for ColumnFamilySet that supports releasing DB mutex during each
+// iteration over the iterator, because the cfd is Refed and Unrefed during
+// each iteration to prevent concurrent CF drop from destroying it (until
+// Unref).
+class RefedColumnFamilySet {
+ public:
+  explicit RefedColumnFamilySet(ColumnFamilySet* cfs) : wrapped_(cfs) {}
+
+  class iterator {
+   public:
+    explicit iterator(ColumnFamilySet::iterator wrapped) : wrapped_(wrapped) {
+      MaybeRef(*wrapped_);
+    }
+    ~iterator() { MaybeUnref(*wrapped_); }
+    inline void MaybeRef(ColumnFamilyData* cfd) {
+      if (cfd->GetID() != ColumnFamilyData::kDummyColumnFamilyDataId) {
+        cfd->Ref();
+      }
+    }
+    inline void MaybeUnref(ColumnFamilyData* cfd) {
+      if (cfd->GetID() != ColumnFamilyData::kDummyColumnFamilyDataId) {
+        cfd->UnrefAndTryDelete();
+      }
+    }
+    // NOTE: minimum operators for for-loop iteration
+    inline iterator& operator++() {
+      ColumnFamilyData* old = *wrapped_;
+      ++wrapped_;
+      // Can only unref & potentially free cfd after accessing its next_
+      MaybeUnref(old);
+      MaybeRef(*wrapped_);
+      return *this;
+    }
+    inline bool operator!=(const iterator& other) const {
+      return this->wrapped_ != other.wrapped_;
+    }
+    inline ColumnFamilyData* operator*() { return *wrapped_; }
+
+   private:
+    ColumnFamilySet::iterator wrapped_;
+  };
+
+  iterator begin() { return iterator(wrapped_->begin()); }
+  iterator end() { return iterator(wrapped_->end()); }
+
+ private:
+  ColumnFamilySet* wrapped_;
 };
 
 // We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access

package/deps/rocksdb/rocksdb/db/column_family_test.cc

@@ -56,16 +56,8 @@ class ColumnFamilyTestBase : public testing::Test {
  public:
   explicit ColumnFamilyTestBase(uint32_t format) : rnd_(139), format_(format) {
     Env* base_env = Env::Default();
-#ifndef ROCKSDB_LITE
-    const char* test_env_uri = getenv("TEST_ENV_URI");
-    if (test_env_uri) {
-      Env* test_env = nullptr;
-      Status s = Env::LoadEnv(test_env_uri, &test_env, &env_guard_);
-      base_env = test_env;
-      EXPECT_OK(s);
-      EXPECT_NE(Env::Default(), base_env);
-    }
-#endif  // !ROCKSDB_LITE
+    EXPECT_OK(
+        test::CreateEnvFromSystem(ConfigOptions(), &base_env, &env_guard_));
     EXPECT_NE(nullptr, base_env);
     env_ = new EnvCounter(base_env);
     env_->skip_fsync_ = true;
@@ -562,7 +554,7 @@ class ColumnFamilyTest
 INSTANTIATE_TEST_CASE_P(FormatDef, ColumnFamilyTest,
                         testing::Values(test::kDefaultFormatVersion));
 INSTANTIATE_TEST_CASE_P(FormatLatest, ColumnFamilyTest,
-                        testing::Values(test::kLatestFormatVersion));
+                        testing::Values(kLatestFormatVersion));
 
 TEST_P(ColumnFamilyTest, DontReuseColumnFamilyID) {
   for (int iter = 0; iter < 3; ++iter) {
@@ -754,8 +746,8 @@ INSTANTIATE_TEST_CASE_P(
                     std::make_tuple(test::kDefaultFormatVersion, false)));
 INSTANTIATE_TEST_CASE_P(
     FormatLatest, FlushEmptyCFTestWithParam,
-    testing::Values(std::make_tuple(test::kLatestFormatVersion, true),
-                    std::make_tuple(test::kLatestFormatVersion, false)));
+    testing::Values(std::make_tuple(kLatestFormatVersion, true),
+                    std::make_tuple(kLatestFormatVersion, false)));
 
 TEST_P(ColumnFamilyTest, AddDrop) {
   Open();
@@ -2286,6 +2278,8 @@ TEST_P(ColumnFamilyTest, SanitizeOptions) {
               // not a multiple of 4k, round up 4k
               expected_arena_block_size += 4 * 1024;
             }
+            expected_arena_block_size =
+                std::min(size_t{1024 * 1024}, expected_arena_block_size);
             ASSERT_EQ(expected_arena_block_size, result.arena_block_size);
           }
         }
@@ -2981,7 +2975,8 @@ TEST_P(ColumnFamilyTest, FlushCloseWALFiles) {
   SpecialEnv env(Env::Default());
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  column_family_options_.memtable_factory.reset(new SpecialSkipListFactory(2));
+  column_family_options_.memtable_factory.reset(
+      test::NewSpecialSkipListFactory(2));
   Open();
   CreateColumnFamilies({"one"});
   ASSERT_OK(Put(1, "fodor", "mirko"));
@@ -3026,7 +3021,8 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile1) {
   SpecialEnv env(Env::Default());
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  column_family_options_.memtable_factory.reset(new SpecialSkipListFactory(2));
+  column_family_options_.memtable_factory.reset(
+      test::NewSpecialSkipListFactory(2));
   Open();
   CreateColumnFamilies({"one"});
   ASSERT_OK(Put(1, "fodor", "mirko"));
@@ -3077,7 +3073,8 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile2) {
   env.SetBackgroundThreads(2, Env::HIGH);
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  column_family_options_.memtable_factory.reset(new SpecialSkipListFactory(2));
+  column_family_options_.memtable_factory.reset(
+      test::NewSpecialSkipListFactory(2));
   Open();
   CreateColumnFamilies({"one"});
   ASSERT_OK(Put(1, "fodor", "mirko"));
@@ -3135,7 +3132,8 @@ TEST_P(ColumnFamilyTest, ForwardIteratorCloseWALFile) {
   env.SetBackgroundThreads(2, Env::HIGH);
   db_options_.env = &env;
   db_options_.max_background_flushes = 1;
-  column_family_options_.memtable_factory.reset(new SpecialSkipListFactory(3));
+  column_family_options_.memtable_factory.reset(
+      test::NewSpecialSkipListFactory(3));
   column_family_options_.level0_file_num_compaction_trigger = 2;
   Open();
   CreateColumnFamilies({"one"});
@@ -3409,15 +3407,31 @@ TEST(ColumnFamilyTest, ValidateBlobGCCutoff) {
                   .IsInvalidArgument());
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+TEST(ColumnFamilyTest, ValidateBlobGCForceThreshold) {
+  DBOptions db_options;
+
+  ColumnFamilyOptions cf_options;
+  cf_options.enable_blob_garbage_collection = true;
+
+  cf_options.blob_garbage_collection_force_threshold = -0.5;
+  ASSERT_TRUE(ColumnFamilyData::ValidateOptions(db_options, cf_options)
+                  .IsInvalidArgument());
 
-#ifdef ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
-extern "C" {
-void RegisterCustomObjects(int argc, char** argv);
+  cf_options.blob_garbage_collection_force_threshold = 0.0;
+  ASSERT_OK(ColumnFamilyData::ValidateOptions(db_options, cf_options));
+
+  cf_options.blob_garbage_collection_force_threshold = 0.5;
+  ASSERT_OK(ColumnFamilyData::ValidateOptions(db_options, cf_options));
+
+  cf_options.blob_garbage_collection_force_threshold = 1.0;
+  ASSERT_OK(ColumnFamilyData::ValidateOptions(db_options, cf_options));
+
+  cf_options.blob_garbage_collection_force_threshold = 1.5;
+  ASSERT_TRUE(ColumnFamilyData::ValidateOptions(db_options, cf_options)
+                  .IsInvalidArgument());
 }
-#else
-void RegisterCustomObjects(int /*argc*/, char** /*argv*/) {}
-#endif  // !ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
+
+}  // namespace ROCKSDB_NAMESPACE
 
 int main(int argc, char** argv) {
   ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();

package/deps/rocksdb/rocksdb/db/compact_files_test.cc

@@ -118,6 +118,81 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
   delete db;
 }
 
+TEST_F(CompactFilesTest, MultipleLevel) {
+  Options options;
+  options.create_if_missing = true;
+  options.level_compaction_dynamic_level_bytes = true;
+  options.num_levels = 6;
+  // Add listener
+  FlushedFileCollector* collector = new FlushedFileCollector();
+  options.listeners.emplace_back(collector);
+
+  DB* db = nullptr;
+  DestroyDB(db_name_, options);
+  Status s = DB::Open(options, db_name_, &db);
+  ASSERT_OK(s);
+  ASSERT_NE(db, nullptr);
+
+  // create couple files in L0, L3, L4 and L5
+  for (int i = 5; i > 2; --i) {
+    collector->ClearFlushedFiles();
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i), ""));
+    ASSERT_OK(db->Flush(FlushOptions()));
+    // Ensure background work is fully finished including listener callbacks
+    // before accessing listener state.
+    ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForBackgroundWork());
+    auto l0_files = collector->GetFlushedFiles();
+    ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files, i));
+
+    std::string prop;
+    ASSERT_TRUE(
+        db->GetProperty("rocksdb.num-files-at-level" + ToString(i), &prop));
+    ASSERT_EQ("1", prop);
+  }
+  ASSERT_OK(db->Put(WriteOptions(), ToString(0), ""));
+  ASSERT_OK(db->Flush(FlushOptions()));
+
+  ColumnFamilyMetaData meta;
+  db->GetColumnFamilyMetaData(&meta);
+  // Compact files except the file in L3
+  std::vector<std::string> files;
+  for (int i = 0; i < 6; ++i) {
+    if (i == 3) continue;
+    for (auto& file : meta.levels[i].files) {
+      files.push_back(file.db_path + "/" + file.name);
+    }
+  }
+
+  SyncPoint::GetInstance()->LoadDependency({
+      {"CompactionJob::Run():Start", "CompactFilesTest.MultipleLevel:0"},
+      {"CompactFilesTest.MultipleLevel:1", "CompactFilesImpl:3"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  std::thread thread([&] {
+    TEST_SYNC_POINT("CompactFilesTest.MultipleLevel:0");
+    ASSERT_OK(db->Put(WriteOptions(), "bar", "v2"));
+    ASSERT_OK(db->Put(WriteOptions(), "foo", "v2"));
+    ASSERT_OK(db->Flush(FlushOptions()));
+    TEST_SYNC_POINT("CompactFilesTest.MultipleLevel:1");
+  });
+
+  // Compaction cannot move up the data to higher level
+  // here we have input file from level 5, so the output level has to be >= 5
+  for (int invalid_output_level = 0; invalid_output_level < 5;
+       invalid_output_level++) {
+    s = db->CompactFiles(CompactionOptions(), files, invalid_output_level);
+    std::cout << s.ToString() << std::endl;
+    ASSERT_TRUE(s.IsInvalidArgument());
+  }
+
+  ASSERT_OK(db->CompactFiles(CompactionOptions(), files, 5));
+  SyncPoint::GetInstance()->DisableProcessing();
+  thread.join();
+
+  delete db;
+}
+
 TEST_F(CompactFilesTest, ObsoleteFiles) {
   Options options;
   // to trigger compaction more easily
@@ -224,6 +299,9 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
     ASSERT_OK(db->Flush(FlushOptions()));
   }
 
+  // Ensure background work is fully finished including listener callbacks
+  // before accessing listener state.
+  ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForBackgroundWork());
   auto l0_files = collector->GetFlushedFiles();
   EXPECT_EQ(5, l0_files.size());
 
@@ -342,6 +420,9 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
     ASSERT_OK(db->Put(WriteOptions(), "key", "val"));
     ASSERT_OK(db->Flush(FlushOptions()));
 
+    // Ensure background work is fully finished including listener callbacks
+    // before accessing listener state.
+    ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForBackgroundWork());
     auto l0_files = collector->GetFlushedFiles();
     ASSERT_EQ(1, l0_files.size());