leveldb学习：Versionedit和Versionset

VersionEdit:

compact过程中会有一系列改变当前Version的操作（FileNumber添加。删除input的sstable,添加输出的sstable）。为了缩小version切换的时间点，将这些操作封装成versionedit，compact完毕时，将versionedit中的操作一次应用到当前version就可以得到最新状态的version。

versionedit的成员变量：

 private:
  friend class VersionSet;
  typedef std::set< std::pair<int, uint64_t> > DeletedFileSet;
  std::string comparator_;
  uint64_t log_number_;
  uint64_t prev_log_number_;
  uint64_t next_file_number_;
  SequenceNumber last_sequence_;
  bool has_comparator_;
  bool has_log_number_;
  bool has_prev_log_number_;
  bool has_next_file_number_;
  bool has_last_sequence_;
  std::vector< std::pair<int, InternalKey> > compact_pointers_;
  DeletedFileSet deleted_files_;
  std::vector< std::pair<int, FileMetaData> > new_files_;

deleted_files_和new_files_记录的是compact过程的input sstable和output sstable。

每一次compact之后都会讲相应的versionedit encode进入manifest文件。參考函数encodeto。

void VersionEdit::EncodeTo(std::string* dst) const {
  if (has_comparator_) {
    PutVarint32(dst, kComparator);
    PutLengthPrefixedSlice(dst, comparator_);
  }
  if (has_log_number_) {
    PutVarint32(dst, kLogNumber);
    PutVarint64(dst, log_number_);
  }
  if (has_prev_log_number_) {
    PutVarint32(dst, kPrevLogNumber);
    PutVarint64(dst, prev_log_number_);
  }
  if (has_next_file_number_) {
    PutVarint32(dst, kNextFileNumber);
    PutVarint64(dst, next_file_number_);
  }
  if (has_last_sequence_) {
    PutVarint32(dst, kLastSequence);
    PutVarint64(dst, last_sequence_);
  }
  for (size_t i = 0; i < compact_pointers_.size(); i++) {
    PutVarint32(dst, kCompactPointer);
    PutVarint32(dst, compact_pointers_[i].first);  // level
    PutLengthPrefixedSlice(dst, compact_pointers_[i].second.Encode());
  }
  for (DeletedFileSet::const_iterator iter = deleted_files_.begin();
       iter != deleted_files_.end();
       ++iter) {
    PutVarint32(dst, kDeletedFile);
    PutVarint32(dst, iter->first);   // level
    PutVarint64(dst, iter->second);  // file number
  }
  for (size_t i = 0; i < new_files_.size(); i++) {
    const FileMetaData& f = new_files_[i].second;
    PutVarint32(dst, kNewFile);
    PutVarint32(dst, new_files_[i].first);  // level
    PutVarint64(dst, f.number);
    PutVarint64(dst, f.file_size);
    PutLengthPrefixedSlice(dst, f.smallest.Encode());
    PutLengthPrefixedSlice(dst, f.largest.Encode());
  }
}

VersionSet::Builder

将VersionEdit应用到VersionSet上的过程封装成VersionSet::Builder。主要是更新Version::files_[]。

class VersionSet::Builder {
 private:
  // Helper to sort by v->files_[file_number].smallest
//处理version::files_[i]中的filemetadata的排序
  struct BySmallestKey {
    const InternalKeyComparator* internal_comparator;
    bool operator()(FileMetaData* f1, FileMetaData* f2) const {
      int r = internal_comparator->Compare(f1->smallest, f2->smallest);
      if (r != 0) {
        return (r < 0);
      } else {
        // Break ties by file number
        return (f1->number < f2->number);
      }
    }
  };

//排序的sstable集合
  typedef std::set<FileMetaData*, BySmallestKey> FileSet;
//要加入和删除的sstable集合
  struct LevelState {
    std::set<uint64_t> deleted_files;
    FileSet* added_files;
  };
//要更新的versionset
  VersionSet* vset_;
//基准的version，compact后，将current_传入作为base
  Version* base_;
//各个level上要更新的文件集合
  LevelState levels_[config::kNumLevels];

事实上也就是VersionEdit放置sstable修改信息（主要为deleted_files_和new_files_）。Builder依据这些信息完毕files_[]的修改（參见函数Apply、SaveTo和MaybeAddFile）。

VersionSet

在version的博客里。我们说versionset是DB中的version的集合。整个DB的当前状态被VersionSet管理者。器重由当前最新的Version以及其它正在服务的Version链表，全局的SequenceNumber。当前的manifest_file_number，封装sstable的Tablecache。

（详细含义可见“leveldb学习开篇”中转载的一篇博客）每一个level中下一次compact要选取的start_key等等。

private:
  Env* const env_;//about磁盘读写
  const std::string dbname_;
  const Options* const options_;
  TableCache* const table_cache_;//操作sstable的tablecache
  const InternalKeyComparator icmp_;
  uint64_t next_file_number_;//下一个可用的filenumber
  uint64_t manifest_file_number_;//manifest文件
  uint64_t last_sequence_;//最后用过的SequenceNumber
  uint64_t log_number_;//log文件的filenumber
  uint64_t prev_log_number_;  // 0 or backing store for memtable being compacted
  // Opened lazily
  WritableFile* descriptor_file_;
  log::Writer* descriptor_log_;
  Version dummy_versions_;  // version链表，表头  Head of circular doubly-linked list of versions.
  Version* current_;        // 当前最新的Version    == dummy_versions_.prev_
  // Per-level key at which the next compaction at that level should start.
  // Either an empty string, or a valid InternalKey.
  std::string compact_pointer_[config::kNumLevels];

为了尽量均匀compact每一个level，所以会将这一次comapct的end_key作为下一次compact的start_key，compactor_pointer_就保存着每一个level下一次compact的start_key。

以下来看成员函数，versionset的细节在函数中解说：

void VersionSet::AppendVersion(Version* v) {
  // Make "v" current
  assert(v->refs_ == 0);
  assert(v != current_);
  if (current_ != NULL) {
    current_->Unref();
  }
  current_ = v;
  v->Ref();
  // Append to linked list
  v->prev_ = dummy_versions_.prev_;
  v->next_ = &dummy_versions_;
  v->prev_->next_ = v;
  v->next_->prev_ = v;
}

加入version，全部的version是用一个环状链表保存指针的，加入version也就是更新dummy_versions_的前后指针，而且设置V为当前version（current_）

Status VersionSet::LogAndApply(VersionEdit* edit, port::Mutex* mu) {
  if (edit->has_log_number_) {
    assert(edit->log_number_ >= log_number_);
    assert(edit->log_number_ < next_file_number_);
  } else {
    edit->SetLogNumber(log_number_);
  }
  if (!edit->has_prev_log_number_) {
    edit->SetPrevLogNumber(prev_log_number_);
  }
  edit->SetNextFile(next_file_number_);
  edit->SetLastSequence(last_sequence_);
  Version* v = new Version(this);
  {
    Builder builder(this, current_);
    builder.Apply(edit);
    builder.SaveTo(v);
  }
  Finalize(v);
  // Initialize new descriptor log file if necessary by creating
  // a temporary file that contains a snapshot of the current version.
  std::string new_manifest_file;
  Status s;
  if (descriptor_log_ == NULL) {
    // No reason to unlock *mu here since we only hit this path in the
    // first call to LogAndApply (when opening the database).
    assert(descriptor_file_ == NULL);
    new_manifest_file = DescriptorFileName(dbname_, manifest_file_number_);
    edit->SetNextFile(next_file_number_);
    s = env_->NewWritableFile(new_manifest_file, &descriptor_file_);
    if (s.ok()) {
      descriptor_log_ = new log::Writer(descriptor_file_);
      s = WriteSnapshot(descriptor_log_);
    }
  }
  // Unlock during expensive MANIFEST log write
  {
    mu->Unlock();
    // Write new record to MANIFEST log
    if (s.ok()) {
      std::string record;
      edit->EncodeTo(&record);
      s = descriptor_log_->AddRecord(record);
      if (s.ok()) {
        s = descriptor_file_->Sync();
      }
      if (!s.ok()) {
        Log(options_->info_log, "MANIFEST write: %s\n", s.ToString().c_str());
      }
    }
    // If we just created a new descriptor file, install it by writing a
    // new CURRENT file that points to it.
    if (s.ok() && !new_manifest_file.empty()) {
      s = SetCurrentFile(env_, dbname_, manifest_file_number_);
    }
    mu->Lock();
  }
  // Install the new version
  if (s.ok()) {
    AppendVersion(v);
    log_number_ = edit->log_number_;
    prev_log_number_ = edit->prev_log_number_;
  } else {
    delete v;
    if (!new_manifest_file.empty()) {
      delete descriptor_log_;
      delete descriptor_file_;
      descriptor_log_ = NULL;
      descriptor_file_ = NULL;
      env_->DeleteFile(new_manifest_file);
    }
  }
  return s;
}

产生新版本号并更新当中files_[]：

首先输入參数VersionEdit记录了leveldb每次更新的信息，包含新加入的sstable以及要删除的sstable，则仅仅需利用VersionSet::Builder更新新产生的version对象，然后将其加入version的链表中。并指定为current_。

然后还要向manifest文件写入新version的信息（为了重新启动db后能够恢复推出前的状态。须要将db中的状态保存下来。这些信息就保存在manfest文件里）

void VersionSet::Finalize(Version* v)

对version中的每一级sstable做一个评估。选择score最高的level作为须要compact的level（compaction_level_）。评估是依据每一个level上文件的大小（level 你，n>0）和数量(level 0)

uint64_t VersionSet::ApproximateOffsetOf(Version* v, const InternalKey& ikey) {
  uint64_t result = 0;
  for (int level = 0; level < config::kNumLevels; level++) {
    const std::vector<FileMetaData*>& files = v->files_[level];
    for (size_t i = 0; i < files.size(); i++) {
      if (icmp_.Compare(files[i]->largest, ikey) <= 0) {
        // Entire file is before "ikey", so just add the file size
        result += files[i]->file_size;
      } else if (icmp_.Compare(files[i]->smallest, ikey) > 0) {
        // Entire file is after "ikey", so ignore
        if (level > 0) {
          // Files other than level 0 are sorted by meta->smallest, so
          // no further files in this level will contain data for
          // "ikey".
          break;
        }
      } else {
        // "ikey" falls in the range for this table.  Add the
        // approximate offset of "ikey" within the table.
        Table* tableptr;
        Iterator* iter = table_cache_->NewIterator(
            ReadOptions(), files[i]->number, files[i]->file_size, &tableptr);
        if (tableptr != NULL) {
          result += tableptr->ApproximateOffsetOf(ikey.Encode());
        }
        delete iter;
      }
    }
  }
  return result;
}

在version中寻找ikey的记录，返回偏移量，由于sstable间entries是不反复的。所以能够通过推断ikey和largest key的大小得到结果。

void VersionSet::AddLiveFiles(std::set<uint64_t>* live) {
  for (Version* v = dummy_versions_.next_;
       v != &dummy_versions_;
       v = v->next_) {
    for (int level = 0; level < config::kNumLevels; level++) {
      const std::vector<FileMetaData*>& files = v->files_[level];
      for (size_t i = 0; i < files.size(); i++) {
        live->insert(files[i]->number);
      }
    }
  }
}

求得全部version中的sstable的文件节点，放置在lives序列中。

void VersionSet::GetRange(const std::vector<FileMetaData*>& inputs,
                          InternalKey* smallest,
                          InternalKey* largest) {
  assert(!inputs.empty());
  smallest->Clear();
  largest->Clear();
  for (size_t i = 0; i < inputs.size(); i++) {
    FileMetaData* f = inputs[i];
    if (i == 0) {
      *smallest = f->smallest;
      *largest = f->largest;
    } else {
      if (icmp_.Compare(f->smallest, *smallest) < 0) {
        *smallest = f->smallest;
      }
      if (icmp_.Compare(f->largest, *largest) > 0) {
        *largest = f->largest;
      }
    }
  }
}

获得input范围内存储的key范围。保存在smallest和largest内。相似的还有GetRange2函数。不同的是GetRange2获取的是两个输入文件群内的key值范围，先将两个文件群容器合并，在调用GetRange。

好了。加上上篇的关于version的介绍。事实上整个version、versionset的内容我仅仅写了一部分，但对于理解leveldb的版本号控制我想应该有了一个较为清楚的认识，version是有关版本号信息的类，主要成员变量是files_[kNumLevels]的容器，记录这个版本号的全部sstable信息，versionset就是全部历史versions的集合。而versionedit和versionset::builder都是为了更新version的sstable信息。

如有错误，欢迎大家指正。