Demo entry 6636637

compaction

   

Submitted by anonymous on Aug 29, 2017 at 03:31
Language: C++. Code size: 5.9 kB.

Status DBImpl::DoCompactionWork(CompactionState* compact) {
  const uint64_t start_micros = env_->NowMicros();
  int64_t imm_micros = 0;  // Micros spent doing imm_ compactions

  Log(options_.info_log,  "Compacting %d@%d + %d@%d files",
      compact->compaction->num_input_files(0),
      compact->compaction->level(),
      compact->compaction->num_input_files(1),
      compact->compaction->level() + 1);

  assert(versions_->NumLevelFiles(compact->compaction->level()) > 0);
  assert(compact->builder == NULL);
  assert(compact->outfile == NULL);
  if (snapshots_.empty()) {
    compact->smallest_snapshot = versions_->LastSequence();
  } else {
    compact->smallest_snapshot = snapshots_.oldest()->number_;
  }

  // Release mutex while we're actually doing the compaction work
  mutex_.Unlock();

  //// 遍历inputs文件
  Iterator* input = versions_->MakeInputIterator(compact->compaction);
  input->SeekToFirst();
  Status status;
  ParsedInternalKey ikey;
  std::string current_user_key;
  bool has_current_user_key = false;
  SequenceNumber last_sequence_for_key = kMaxSequenceNumber;
  for (; input->Valid() && !shutting_down_.Acquire_Load(); ) {
    // Prioritize immutable compaction work
    /// // 每次都判断如果有memtable 需要compact,先compact memtable
    if (has_imm_.NoBarrier_Load() != NULL) {
      const uint64_t imm_start = env_->NowMicros(); /// 获取当前的时间微秒
      mutex_.Lock();
      if (imm_ != NULL) {
        CompactMemTable();
        bg_cv_.SignalAll();  // Wakeup MakeRoomForWrite() if necessary
      }
      mutex_.Unlock();
      imm_micros += (env_->NowMicros() - imm_start);
    }

    Slice key = input->key();
    /// 判断合适结束合并,当level n+1 的文件和level n+2的文件overlap超过一个20M时,就会停止compact
    if (compact->compaction->ShouldStopBefore(key) &&
        compact->builder != NULL) {
      status = FinishCompactionOutputFile(compact, input);
      if (!status.ok()) {
        break;
      }
    }

    // Handle key/value, add to state, etc.
    bool drop = false;
    if (!ParseInternalKey(key, &ikey)) {
      /// 解码出错Do not hide error keys
      current_user_key.clear();
      has_current_user_key = false;
      last_sequence_for_key = kMaxSequenceNumber;
    } else {
      if (!has_current_user_key ||
          user_comparator()->Compare(ikey.user_key,
                                     Slice(current_user_key)) != 0) {
        // First occurrence of this user key
        current_user_key.assign(ikey.user_key.data(), ikey.user_key.size());
        has_current_user_key = true;
        last_sequence_for_key = kMaxSequenceNumber;
      }

      if (last_sequence_for_key <= compact->smallest_snapshot) {
        // Hidden by an newer entry for same user key
        drop = true;    // (A)
      } else if (ikey.type == kTypeDeletion /**1) 是删除类型*/ &&
                 ikey.sequence <= compact->smallest_snapshot &&
                 compact->compaction->IsBaseLevelForKey(ikey.user_key) /**高的level中没有数据,这样可以保证,在
                高层存在key时,delete的删除标记不会被擦除*/) {
        // For this user key:
        // (1) there is no data in higher levels
        // (2) data in lower levels will have larger sequence numbers
        // (3) data in layers that are being compacted here and have
        //     smaller sequence numbers will be dropped in the next
        //     few iterations of this loop (by rule (A) above).
        // Therefore this deletion marker is obsolete and can be dropped.
        drop = true;
      }

      last_sequence_for_key = ikey.sequence;
    }
#if 0
    Log(options_.info_log,
        "  Compact: %s, seq %d, type: %d %d, drop: %d, is_base: %d, "
        "%d smallest_snapshot: %d",
        ikey.user_key.ToString().c_str(),
        (int)ikey.sequence, ikey.type, kTypeValue, drop,
        compact->compaction->IsBaseLevelForKey(ikey.user_key),
        (int)last_sequence_for_key, (int)compact->smallest_snapshot);
#endif

    if (!drop) {
      // Open output file if necessary
      if (compact->builder == NULL) {
        status = OpenCompactionOutputFile(compact);
        if (!status.ok()) {
          break;
        }
      }
      if (compact->builder->NumEntries() == 0) {
        compact->current_output()->smallest.DecodeFrom(key);
      }
      compact->current_output()->largest.DecodeFrom(key);
      compact->builder->Add(key, input->value());

      // Close output file if it is big enough
      /// 一旦输出超过了阈值(MaxFileSizeForLevel(level)),则生成一个新的sst文件
      if (compact->builder->FileSize() >=
          compact->compaction->MaxOutputFileSize() /**MaxFileSizeForLevel(level)*/) {
        status = FinishCompactionOutputFile(compact, input);
        if (!status.ok()) {
          break;
        }
      }
    }
    /// 继续遍历
    input->Next();
  }

  if (status.ok() && shutting_down_.Acquire_Load()) {
    status = Status::IOError("Deleting DB during compaction");
  }
  if (status.ok() && compact->builder != NULL) {
    status = FinishCompactionOutputFile(compact, input);
  }
  if (status.ok()) {
    status = input->status();
  }
  delete input;
  input = NULL;

  CompactionStats stats;
  stats.micros = env_->NowMicros() - start_micros - imm_micros;
  for (int which = 0; which < 2; which++) {
    for (int i = 0; i < compact->compaction->num_input_files(which); i++) {
      stats.bytes_read += compact->compaction->input(which, i)->file_size;
    }
  }
  for (size_t i = 0; i < compact->outputs.size(); i++) {
    stats.bytes_written += compact->outputs[i].file_size;
  }

  mutex_.Lock();
  stats_[compact->compaction->level() + 1].Add(stats);

  if (status.ok()) {
    status = InstallCompactionResults(compact);
  }
  if (!status.ok()) {
    RecordBackgroundError(status);
  }
  VersionSet::LevelSummaryStorage tmp;
  Log(options_.info_log,
      "compacted to: %s", versions_->LevelSummary(&tmp));
  return status;
}

This snippet took 0.01 seconds to highlight.

Back to the Entry List or Home.

Delete this entry (admin only).