rocksdb写流程DBImpl::WriteImpl()源代码分析

---

1. WriteThread的状态

写线程WriteThread会有几种状态，在写memtable的过程中通这几种状态来决定当前w当前执行到哪儿了，下一步该怎么执行。

  enum State : uint8_t {
   
    // The initial state of a writer.  This is a Writer that is
    // waiting in JoinBatchGroup.  This state can be left when another
    // thread informs the waiter that it has become a group leader
    // (-> STATE_GROUP_LEADER), when a leader that has chosen to be
    // non-parallel informs a follower that its writes have been committed
    // (-> STATE_COMPLETED), or when a leader that has chosen to perform
    // updates in parallel and needs this Writer to apply its batch (->
    // STATE_PARALLEL_FOLLOWER).
    STATE_INIT = 1,

    // The state used to inform a waiting Writer that it has become the
    // leader, and it should now build a write batch group.  Tricky:
    // this state is not used if newest_writer_ is empty when a writer
    // enqueues itself, because there is no need to wait (or even to
    // create the mutex and condvar used to wait) in that case.  This is
    // a terminal state unless the leader chooses to make this a parallel
    // batch, in which case the last parallel worker to finish will move
    // the leader to STATE_COMPLETED.
    STATE_GROUP_LEADER = 2,

    // The state used to inform a waiting writer that it has become the
    // leader of memtable writer group. The leader will either write
    // memtable for the whole group, or launch a parallel group write
    // to memtable by calling LaunchParallelMemTableWrite.
    STATE_MEMTABLE_WRITER_LEADER = 4,

    // The state used to inform a waiting writer that it has become a
    // parallel memtable writer. It can be the group leader who launch the
    // parallel writer group, or one of the followers. The writer should then
    // apply its batch to the memtable concurrently and call
    // CompleteParallelMemTableWriter.
    STATE_PARALLEL_MEMTABLE_WRITER = 8,

    // A follower whose writes have been applied, or a parallel leader
    // whose followers have all finished their work.  This is a terminal
    // state.
    STATE_COMPLETED = 16,

    // A state indicating that the thread may be waiting using StateMutex()
    // and StateCondVar()
    STATE_LOCKED_WAITING = 32,
  };

2. write_group结构

3. 写过程WriteImpl()函数源码分析

// The main write queue. This is the only write queue that updates LastSequence.
// When using one write queue, the same sequence also indicates the last
// published sequence.
Status DBImpl::WriteImpl(const WriteOptions& write_options,
                         WriteBatch* my_batch, WriteCallback* callback,
                         uint64_t* log_used, uint64_t log_ref,
                         bool disable_memtable, uint64_t* seq_used,
                         size_t batch_cnt,
                         PreReleaseCallback* pre_release_callback) {
   
  assert(!seq_per_batch_ || batch_cnt != 0);
  if (my_batch == nullptr) {
   
    return Status::Corruption("Batch is nullptr!");
  }
  if (tracer_) {
   
    InstrumentedMutexLock lock(&trace_mutex_);
    if (tracer_) {
   
      tracer_->Write(my_batch);
    }
  }
  if (write_options.sync && write_options.disableWAL) {
   
    return Status::InvalidArgument("Sync writes has to enable WAL.");
  }
  if (two_write_queues_ && immutable_db_options_.enable_pipelined_write) {
   
    return Status::NotSupported(
        "pipelined_writes is not compatible with concurrent prepares");
  }
  if (seq_per_batch_ && immutable_db_options_.enable_pipelined_write) {
   
    // TODO(yiwu): update pipeline write with seq_per_batch and batch_cnt
    return Status::NotSupported(
        "pipelined_writes is not compatible with seq_per_batch");
  }
  if (immutable_db_options_.unordered_write &&
      immutable_db_options_.enable_pipelined_write) {
   
    return Status::NotSupported(
        "pipelined_writes is not compatible with unordered_write");
  }
  // Otherwise IsLatestPersistentState optimization does not make sense
  assert(!WriteBatchInternal::IsLatestPersistentState(my_batch) ||
         disable_memtable);

  Status status;
  IOStatus io_s;
  if (write_options.low_pri) {
   
    status = ThrottleLowPriWritesIfNeeded(write_options, my_batch);
    if (!status.ok()) {
   
      return status;
    }
  }

  /* 
  只写WAL不写memtable
  two_wrote_queues_:
        当设置时，我们使用一个单独的队列来处理不写入memtable的写操作。
        在2PC中，这些是准备阶段的写操作。
  */
  if (two_write_queues_ && disable_memtable) {
   
    AssignOrder assign_order =
        seq_per_batch_ ? kDoAssignOrder : kDontAssignOrder;
    // Otherwise it is WAL-only Prepare batches in WriteCommitted policy and
    // they don't consume sequence.
    return WriteImplWALOnly(&nonmem_write_thread_, write_options, my_batch,
                            callback, log_used, log_ref, seq_used, batch_cnt,
                            pre_release_callback, assign_order,
                            kDontPublishLastSeq, disable_memtable);
  }
  
  // 将unordered_w