前往小程序,Get更优阅读体验!
立即前往
首页
学习
活动
专区
工具
TVP
发布
社区首页 >专栏 >leveldb源码分析--日志文件格式

leveldb源码分析--日志文件格式

原创
作者头像
小林帮
发布2021-03-21 21:45:32
7830
发布2021-03-21 21:45:32
举报

使用场景

  • WAL日志文件;
  • MANIFEST版本信息文件;

日志文件格式

log-format.jpg
log-format.jpg

特点:

  1. log文件由连续的block组成,每个block的大小固定为32K;
  2. 每个block由连续的record组成;
  3. 由于用户data的大小可能超过32K,一个block保存不下,故通过type字段来表示日志的类型;

如:

log-format-example.jpg
log-format-example.jpg

日志操作

读日志

代码语言:txt
复制
bool Reader::ReadRecord(Slice* record, std::string* scratch) {
  if (last_record_offset_ < initial_offset_) {
    if (!SkipToInitialBlock()) {
      return false;
    }
  }

  scratch->clear();
  record->clear();
  bool in_fragmented_record = false;
  uint64_t prospective_record_offset = 0;

  Slice fragment;
  while (true) {
    const unsigned int record_type = ReadPhysicalRecord(&fragment);

    uint64_t physical_record_offset =
        end_of_buffer_offset_ - buffer_.size() - kHeaderSize - fragment.size();

    if (resyncing_) {
      if (record_type == kMiddleType) {
        continue;
      } else if (record_type == kLastType) {
        resyncing_ = false;
        continue;
      } else {
        resyncing_ = false;
      }
    }

    switch (record_type) {
      case kFullType:
        if (in_fragmented_record) {
          // Handle bug in earlier versions of log::Writer where
          // it could emit an empty kFirstType record at the tail end
          // of a block followed by a kFullType or kFirstType record
          // at the beginning of the next block.
          if (!scratch->empty()) {
            ReportCorruption(scratch->size(), "partial record without end(1)");
          }
        }
        prospective_record_offset = physical_record_offset;
        scratch->clear();
        *record = fragment;
        last_record_offset_ = prospective_record_offset;
        return true;

      case kFirstType:
        if (in_fragmented_record) {
          // Handle bug in earlier versions of log::Writer where
          // it could emit an empty kFirstType record at the tail end
          // of a block followed by a kFullType or kFirstType record
          // at the beginning of the next block.
          if (!scratch->empty()) {
            ReportCorruption(scratch->size(), "partial record without end(2)");
          }
        }
        prospective_record_offset = physical_record_offset;
        scratch->assign(fragment.data(), fragment.size());
        in_fragmented_record = true;
        break;

      case kMiddleType:
        if (!in_fragmented_record) {
          ReportCorruption(fragment.size(),
                           "missing start of fragmented record(1)");
        } else {
          scratch->append(fragment.data(), fragment.size());
        }
        break;

      case kLastType:
        if (!in_fragmented_record) {
          ReportCorruption(fragment.size(),
                           "missing start of fragmented record(2)");
        } else {
          scratch->append(fragment.data(), fragment.size());
          *record = Slice(*scratch);
          last_record_offset_ = prospective_record_offset;
          return true;
        }
        break;

      case kEof:
        if (in_fragmented_record) {
          // This can be caused by the writer dying immediately after
          // writing a physical record but before completing the next; don't
          // treat it as a corruption, just ignore the entire logical record.
          scratch->clear();
        }
        return false;

      case kBadRecord:
        if (in_fragmented_record) {
          ReportCorruption(scratch->size(), "error in middle of record");
          in_fragmented_record = false;
          scratch->clear();
        }
        break;

      default: {
        char buf[40];
        std::snprintf(buf, sizeof(buf), "unknown record type %u", record_type);
        ReportCorruption(
            (fragment.size() + (in_fragmented_record ? scratch->size() : 0)),
            buf);
        in_fragmented_record = false;
        scratch->clear();
        break;
      }
    }
  }
  return false;
}

// 从磁盘文件中读取一个record数据记录
unsigned int Reader::ReadPhysicalRecord(Slice* result) {
  while (true) {
    if (buffer_.size() < kHeaderSize) {
      if (!eof_) {
        buffer_.clear();
        // 从磁盘文件中读取一个4K的数据块
        Status status = file_->Read(kBlockSize, &buffer_, backing_store_);
        end_of_buffer_offset_ += buffer_.size();
        if (!status.ok()) {
          buffer_.clear();
          ReportDrop(kBlockSize, status);
          eof_ = true;
          return kEof;
        } else if (buffer_.size() < kBlockSize) {
          eof_ = true;
        }
        continue;
      } else {
        buffer_.clear();
        return kEof;
      }
    }

    // 解析record记录的类别和长度
    const char* header = buffer_.data();
    const uint32_t a = static_cast<uint32_t>(header[4]) & 0xff;
    const uint32_t b = static_cast<uint32_t>(header[5]) & 0xff;
    const unsigned int type = header[6];
    const uint32_t length = a | (b << 8);
    if (kHeaderSize + length > buffer_.size()) {
      size_t drop_size = buffer_.size();
      buffer_.clear();
      if (!eof_) {
        ReportCorruption(drop_size, "bad record length");
        return kBadRecord;
      }
      // If the end of the file has been reached without reading |length| bytes
      // of payload, assume the writer died in the middle of writing the record.
      // Don't report a corruption.
      return kEof;
    }

    if (type == kZeroType && length == 0) {
      // Skip zero length record without reporting any drops since
      // such records are produced by the mmap based writing code in
      // env_posix.cc that preallocates file regions.
      buffer_.clear();
      return kBadRecord;
    }

    // Check crc
    if (checksum_) {
      uint32_t expected_crc = crc32c::Unmask(DecodeFixed32(header));
      uint32_t actual_crc = crc32c::Value(header + 6, 1 + length);
      if (actual_crc != expected_crc) {
        // Drop the rest of the buffer since "length" itself may have
        // been corrupted and if we trust it, we could find some
        // fragment of a real log record that just happens to look
        // like a valid log record.
        size_t drop_size = buffer_.size();
        buffer_.clear();
        ReportCorruption(drop_size, "checksum mismatch");
        return kBadRecord;
      }
    }

    buffer_.remove_prefix(kHeaderSize + length);

    // Skip physical record that started before initial_offset_
    if (end_of_buffer_offset_ - buffer_.size() - kHeaderSize - length <
        initial_offset_) {
      result->clear();
      return kBadRecord;
    }

    *result = Slice(header + kHeaderSize, length);
    return type;
  }
}

原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。

如有侵权,请联系 cloudcommunity@tencent.com 删除。

原创声明:本文系作者授权腾讯云开发者社区发表,未经许可,不得转载。

如有侵权,请联系 cloudcommunity@tencent.com 删除。

评论
登录后参与评论
0 条评论
热度
最新
推荐阅读
目录
  • 使用场景
  • 日志文件格式
  • 日志操作
    • 读日志
    领券
    问题归档专栏文章快讯文章归档关键词归档开发者手册归档开发者手册 Section 归档
    http://www.vxiaotou.com