LevelDB源码分析9-MemTable

Memtable中存放内存中的key-value,其提供了写入，删除以及读取k-v记录的接口。leveldb在插入时要保证key的顺序性，因此Memtalbe的核心数据结构是一个skip-list,Memtalbe只是一个接口类。Memtalbe为上层调用提供接口。

class MemTable {
 public:
  // MemTables are reference counted.  The initial reference count
  // is zero and the caller must call Ref() at least once.
  explicit MemTable(const InternalKeyComparator& comparator);

  // Increase reference count.
  void Ref() { ++refs_; } //引用计数器

  // Drop reference count.  Delete if no more references exist.
  void Unref() {
    --refs_;
    assert(refs_ >= 0);
    if (refs_ <= 0) {
      delete this;
    }
  }

    // Returns an estimate of the number of bytes of data in use by this
  // data structure.
  //
  // REQUIRES: external synchronization to prevent simultaneous
  // operations on the same MemTable.
  size_t ApproximateMemoryUsage(); //调用Arena的MemoryUsage,因为这里的内存是向arena申请的

  // Return an iterator that yields the contents of the memtable.
  //
  // The caller must ensure that the underlying MemTable remains live
  // while the returned iterator is live.  The keys returned by this
  // iterator are internal keys encoded by AppendInternalKey in the
  // db/format.{h,cc} module.
  Iterator* NewIterator();//新迭代器

  // Add an entry into memtable that maps key to value at the
  // specified sequence number and with the specified type.
  // Typically value will be empty if type==kTypeDeletion.
  //插入
  void Add(SequenceNumber seq, ValueType type,
           const Slice& key,
           const Slice& value);

  // If memtable contains a value for key, store it in *value and return true.
  // If memtable contains a deletion for key, store a NotFound() error
  // in *status and return true.
  // Else, return false.
  //得到一个value
  bool Get(const LookupKey& key, std::string* value, Status* s);

   private:
  ~MemTable();  // Private since only Unref() should be used to delete it

  struct KeyComparator {
    const InternalKeyComparator comparator;
    explicit KeyComparator(const InternalKeyComparator& c) : comparator(c) { }
    int operator()(const char* a, const char* b) const;
  };
  friend class MemTableIterator;
  friend class MemTableBackwardIterator;

  typedef SkipList<const char*, KeyComparator> Table;

  KeyComparator comparator_; //比较器
  int refs_;//ref，引用计数器
  Arena arena_;//内存管理
  Table table_;//table,是一个skip_list

  // No copying allowed
  MemTable(const MemTable&);
  void operator=(const MemTable&);
};

具体实现：

/构造函数
MemTable::MemTable(const InternalKeyComparator& cmp)
    : comparator_(cmp),
      refs_(0),
      table_(comparator_, &arena_) {
}
//析构函数
MemTable::~MemTable() {
  assert(refs_ == 0);
}

//调用arena的MemoryUsage()
size_t MemTable::ApproximateMemoryUsage() { return arena_.MemoryUsage(); }

//MemTable的迭代器结构
//MemTableIterator是SkipList的iterator的封装，底层调用的是SkipList的Iterator
class MemTableIterator: public Iterator {
 public:
  explicit MemTableIterator(MemTable::Table* table) : iter_(table) { }

  virtual bool Valid() const { return iter_.Valid(); }
  virtual void Seek(const Slice& k) { iter_.Seek(EncodeKey(&tmp_, k)); }
  virtual void SeekToFirst() { iter_.SeekToFirst(); }
  virtual void SeekToLast() { iter_.SeekToLast(); }
  virtual void Next() { iter_.Next(); }
  virtual void Prev() { iter_.Prev(); }
  //GetLengthPrefixedSlice函数是把带有长度的前缀去掉，返回Slice.
  virtual Slice key() const { return GetLengthPrefixedSlice(iter_.key()); }
  virtual Slice value() const {
    Slice key_slice = GetLengthPrefixedSlice(iter_.key());
    return GetLengthPrefixedSlice(key_slice.data() + key_slice.size());
  }

  virtual Status status() const { return Status::OK(); }

 private:
  MemTable::Table::Iterator iter_;
  std::string tmp_;       // For passing to EncodeKey

  // No copying allowed
  MemTableIterator(const MemTableIterator&);
  void operator=(const MemTableIterator&);
};
//新建一个迭代器
Iterator* MemTable::NewIterator() {
  return new MemTableIterator(&table_);
}

插入操作：

//插入key，value
void MemTable::Add(SequenceNumber s, ValueType type,
                   const Slice& key,
                   const Slice& value) {
  // Format of an entry is concatenation of:
  //  key_size     : varint32 of internal_key.size()
  //  key bytes    : char[internal_key.size()]
  //  value_size   : varint32 of value.size()
  //  value bytes  : char[value.size()]
  size_t key_size = key.size();
  size_t val_size = value.size();
  //iinternal_key_size包括了8个字节的附加信息
  size_t internal_key_size = key_size + 8;
  const size_t encoded_len =
      VarintLength(internal_key_size) + internal_key_size +
      VarintLength(val_size) + val_size;
  char* buf = arena_.Allocate(encoded_len);
  char* p = EncodeVarint32(buf, internal_key_size);
  memcpy(p, key.data(), key_size);
  p += key_size;
  EncodeFixed64(p, (s << 8) | type);//8字节的信息
  p += 8;
  p = EncodeVarint32(p, val_size);
  memcpy(p, value.data(), val_size);
  assert((p + val_size) - buf == encoded_len);
  table_.Insert(buf);//插入key：key_size+key_data + seq << 8 | type + val_size + val_data
}

查找操作：

//得到查找的内容:key_size+key_data + seq << 8 | type + val_size + val_data
//得到通过key查找的value存放在val中。
bool MemTable::Get(const LookupKey& key, std::string* value, Status* s) {
  Slice memkey = key.memtable_key();
  Table::Iterator iter(&table_);
  iter.Seek(memkey.data());
  if (iter.Valid()) {
    // entry format is:
    //    klength  varint32
    //    userkey  char[klength]
    //    tag      uint64
    //    vlength  varint32
    //    value    char[vlength]
    // Check that it belongs to same user key.  We do not check the
    // sequence number since the Seek() call above should have skipped
    // all entries with overly large sequence numbers.
    const char* entry = iter.key();
    uint32_t key_length;
    //得到长度，这里ertry是转换的下界
    const char* key_ptr = GetVarint32Ptr(entry, entry+5, &key_length);
    //相等...
    if (comparator_.comparator.user_comparator()->Compare(
            Slice(key_ptr, key_length - 8),
            key.user_key()) == 0) {
      // Correct user key
    //得到类型，为kTypeValue说明该值存在，为kDeletion说明该值被删除了(lazy delete)
      const uint64_t tag = DecodeFixed64(key_ptr + key_length - 8);
      switch (static_cast<ValueType>(tag & 0xff)) {
        case kTypeValue: {
          Slice v = GetLengthPrefixedSlice(key_ptr + key_length);
          value->assign(v.data(), v.size());
          return true;
        }
        case kTypeDeletion:
          *s = Status::NotFound(Slice());
          return true;
      }
    }
  }
  //如果key都不能，那么返回false
  return false;
}