Add async WAL precreation

db/c.cc

@@ -5286,6 +5286,15 @@ size_t rocksdb_options_get_recycle_log_file_num(rocksdb_options_t* opt) {
   return opt->rep.recycle_log_file_num;
 }
 
+void rocksdb_options_set_async_wal_precreate(rocksdb_options_t* opt,
+                                             unsigned char v) {
+  opt->rep.async_wal_precreate = v;
+}
+
+unsigned char rocksdb_options_get_async_wal_precreate(rocksdb_options_t* opt) {
+  return opt->rep.async_wal_precreate;
+}
+
 void rocksdb_options_set_soft_pending_compaction_bytes_limit(
     rocksdb_options_t* opt, size_t v) {
   opt->rep.soft_pending_compaction_bytes_limit = v;

db/c_test.c

@@ -2869,6 +2869,9 @@ int main(int argc, char** argv) {
     rocksdb_options_set_track_and_verify_wals_in_manifest(o, 42);
     CheckCondition(1 ==
                    rocksdb_options_get_track_and_verify_wals_in_manifest(o));
+    CheckCondition(0 == rocksdb_options_get_async_wal_precreate(o));
+    rocksdb_options_set_async_wal_precreate(o, 1);
+    CheckCondition(1 == rocksdb_options_get_async_wal_precreate(o));
 
     /* Blob Options */
     rocksdb_options_set_enable_blob_files(o, 1);

db/db_impl/db_impl.cc

@@ -788,12 +788,27 @@ Status DBImpl::CloseHelper() {
          bg_flush_scheduled_ || bg_purge_scheduled_ ||
          bg_pressure_callback_in_progress_ ||
          bg_async_file_open_state_ == AsyncFileOpenState::kScheduled ||
+         async_wal_precreate_state_ == AsyncWALPrecreateState::kScheduled ||
          pending_purge_obsolete_files_ ||
          error_handler_.IsRecoveryInProgress()) {
     TEST_SYNC_POINT("DBImpl::~DBImpl:WaitJob");
     bg_cv_.Wait();
   }
 
+  // Release any opened-but-unpublished WAL writer after the in-flight worker
+  // has published its result. Clear the DB-owned async slot while holding
+  // mutex_, but destroy the detached writer after dropping mutex_ because
+  // log::Writer / WritableFileWriter destruction can flush and close the file.
+  // The file itself can be left behind as an empty future WAL; recovery already
+  // tolerates it and marks its file number used if observed.
+  UnpublishedWAL unused_async_wal = std::move(async_wal_precreate_wal_);
+  async_wal_precreate_state_ = AsyncWALPrecreateState::kNotScheduled;
+  if (unused_async_wal.writer) {
+    mutex_.Unlock();
+    unused_async_wal.Reset();
+    mutex_.Lock();
+  }
+
   // Ensure subclasses don't forget to schedule async file opening
   assert(!immutable_db_options_.open_files_async || !opened_successfully_ ||
          bg_async_file_open_state_ != AsyncFileOpenState::kNotScheduled);

db/db_impl/db_impl.h

@@ -15,6 +15,8 @@
 #include <limits>
 #include <list>
 #include <map>
+#include <memory>
+#include <optional>
 #include <set>
 #include <string>
 #include <unordered_map>
@@ -2809,7 +2811,68 @@ class DBImpl : public DB {
   size_t GetWalPreallocateBlockSize(uint64_t write_buffer_size) const;
   Env::WriteLifeTimeHint CalculateWALWriteHint() { return Env::WLTH_SHORT; }
 
-  IOStatus CreateWAL(const WriteOptions& write_options, uint64_t log_file_num,
+  // Returns true when async WAL precreation is enabled and compatible with the
+  // active WAL strategy. WAL recycling already avoids file creation latency, so
+  // precreation is disabled when recycle_log_file_num is non-zero.
+  bool AsyncWALPrecreateEnabled() const;
+
+  // A WAL file that has a reserved file number and may have an opened writer,
+  // but has not been added to DBImpl's in-memory logical WAL tracking lists
+  // (logs_ and alive_wal_files_).
+  struct UnpublishedWAL {
+    uint64_t log_number = 0;
+    std::unique_ptr<log::Writer> writer;
+
+    UnpublishedWAL() = default;
+    UnpublishedWAL(const UnpublishedWAL&) = delete;
+    UnpublishedWAL& operator=(const UnpublishedWAL&) = delete;
+
+    UnpublishedWAL(UnpublishedWAL&& other) noexcept {
+      *this = std::move(other);
+    }
+    UnpublishedWAL& operator=(UnpublishedWAL&& other) noexcept {
+      if (this != &other) {
+        log_number = other.log_number;
+        writer = std::move(other.writer);
+        other.Reset();
+      }
+      return *this;
+    }
+
+    void Reset() {
+      log_number = 0;
+      writer.reset();
+    }
+  };
+
+  // Reserves the next WAL file number and schedules a HIGH-priority background
+  // task to precreate that WAL file. A precreated WAL is not a logical WAL
+  // until a foreground WAL rotation consumes it.
+  void MaybeScheduleAsyncWALPrecreate(size_t preallocate_block_size);
+
+  // Background task for opening the reserved future WAL and publishing the
+  // result under mutex_.
+  static void BGWorkAsyncWALPrecreate(void* arg);
+
+  // Waits for an in-flight async WAL precreation and returns a prepared WAL if
+  // one is available. If precreation failed, returns an empty WAL and lets the
+  // foreground rotation create the WAL synchronously. Caller must hold mutex_.
+  UnpublishedWAL WaitForAsyncWALPrecreate();
+
+  // Opens and preallocates a WAL writer without writing logical WAL records.
+  // Used by async WAL precreation and by synchronous WAL creation.
+  IOStatus CreateWALWriter(const DBOptions& db_options, uint64_t log_file_num,
+                           uint64_t recycle_log_number,
+                           size_t preallocate_block_size,
+                           UnpublishedWAL* new_wal);
+
+  // Starts an opened WAL file by writing the initial records required before it
+  // can be installed as the current WAL for foreground writes.
+  IOStatus StartWALFile(const WriteOptions& write_options,
+                        const PredecessorWALInfo& predecessor_wal_info,
+                        log::Writer* new_log);
+  IOStatus CreateWAL(const DBOptions& db_options,
+                     const WriteOptions& write_options, uint64_t log_file_num,
                      uint64_t recycle_log_number, size_t preallocate_block_size,
                      const PredecessorWALInfo& predecessor_wal_info,
                      log::Writer** new_log);
@@ -3282,6 +3345,28 @@ class DBImpl : public DB {
   AsyncFileOpenState bg_async_file_open_state_ =
       AsyncFileOpenState::kNotScheduled;
 
+  // State machine for the single async WAL precreation slot protected by
+  // mutex_. Background precreation failure returns to kNotScheduled; foreground
+  // rotation handles it the same as no prepared WAL and creates one
+  // synchronously. kScheduled owns a reserved file number; kReady owns an
+  // opened writer that has not been started or added to logical WAL tracking.
+  enum class AsyncWALPrecreateState : uint8_t {
+    kNotScheduled = 0,  // No WAL precreate work is in-flight or ready.
+    kScheduled,         // Background task owns creation of the reserved WAL.
+    kReady,             // Reserved WAL writer is open but not logically live.
+  };
+
+  // Protected by mutex_. Tracks at most one background precreated WAL. A
+  // precreated WAL is only reserved empty storage until SwitchMemtable()
+  // consumes it and installs it in DBImpl's in-memory logical WAL tracking
+  // lists (logs_ and alive_wal_files_).
+  AsyncWALPrecreateState async_wal_precreate_state_ =
+      AsyncWALPrecreateState::kNotScheduled;
+
+  // Reserved in-flight/ready precreated WAL. The writer is populated only while
+  // state is kReady.
+  UnpublishedWAL async_wal_precreate_wal_;
+
   std::deque<ManualCompactionState*> manual_compaction_dequeue_;
 
   // shall we disable deletion of obsolete files