Leveldb source code analysis -- log file format

Use scenarios

• WAL Log files ;
• MANIFEST Version information file ;

Log file format

log-format.jpg

characteristic ：

1. log The file consists of consecutive block form , Every block The size of is fixed to 32K;
2. Every block Continuous record form ;
3. Because of users data May be larger than 32K, One block Cannot save , So through type Field to indicate the type of log ;

Such as ：

log-format-example.jpg

Log operations

Read log

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;
}

//  Read a... From the disk file record Data records 
unsigned int Reader::ReadPhysicalRecord(Slice* result) {
  while (true) {
    if (buffer_.size() < kHeaderSize) {
      if (!eof_) {
        buffer_.clear();
        //  Read a... From the disk file 4K A block of data 
        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;
      }
    }

    //  analysis record Category and length of records 
    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;
  }
}