HDFS源码分析数据块复制监控线程ReplicationMonitor（一）

        ReplicationMonitor是HDFS中关于数据块复制的监控线程，它的主要作用就是计算DataNode工作，并将复制请求超时的块重新加入到待调度队列。其定义及作为线程核心的run()方法如下：

  /**
   * Periodically calls computeReplicationWork().
   * 周期性调用computeReplicationWork()方法
   */
  private class ReplicationMonitor implements Runnable {

    @Override
    public void run() {
    	
      // 如果namesystem持续运行，while循环一直进行
      while (namesystem.isRunning()) {
        try {
          // Process replication work only when active NN is out of safe mode.
          if (namesystem.isPopulatingReplQueues()) {
            // 计算数据节点工作
        	computeDatanodeWork();
        	// 将复制请求超时的块重新加入到待调度队列
            processPendingReplications();
          }
          
          // 线程休眠replicationRecheckInterval时间
          Thread.sleep(replicationRecheckInterval);
        } catch (Throwable t) {
          if (!namesystem.isRunning()) {
            LOG.info("Stopping ReplicationMonitor.");
            if (!(t instanceof InterruptedException)) {
              LOG.info("ReplicationMonitor received an exception"
                  + " while shutting down.", t);
            }
            break;
          } else if (!checkNSRunning && t instanceof InterruptedException) {
            LOG.info("Stopping ReplicationMonitor for testing.");
            break;
          }
          LOG.fatal("ReplicationMonitor thread received Runtime exception. ", t);
          terminate(1, t);
        }
      }
    }
  }