jedis客户端网络故障期间redis发生master-slav

客户端控制台一直报一下异常：

redis.clients.jedis.exceptions.JedisDataException: READONLY You can't write against a read only slave.

从字面意思理解的话，意思是写到了只读的从节点。正常情况下是不会出现这个问题的。只会发生在master已经切换，但是client使用的master没有刷新的情况。

可以看下jedis的源码(2.9版本)：

protected class MasterListener extends Thread {
省略一些代码...
 @Override
    public void run() {

      running.set(true);

      while (running.get()) {

        j = new Jedis(host, port);

        try {
          // double check that it is not being shutdown
          if (!running.get()) {
            break;
          }

          j.subscribe(new JedisPubSub() {
            @Override
            public void onMessage(String channel, String message) {
              log.fine("Sentinel " + host + ":" + port + " published: " + message + ".");

              String[] switchMasterMsg = message.split(" ");

              if (switchMasterMsg.length > 3) {

                if (masterName.equals(switchMasterMsg[0])) {
 //正常来说发生master切换，client会收到switchmaster消息，从而重新初始化连接池。                 initPool(toHostAndPort(Arrays.asList(switchMasterMsg[3], switchMasterMsg[4])));
                } else {
                  log.fine("Ignoring message on +switch-master for master name "
                      + switchMasterMsg[0] + ", our master name is " + masterName);
                }

              } else {
                log.severe("Invalid message received on Sentinel " + host + ":" + port
                    + " on channel +switch-master: " + message);
              }
            }
          }, "+switch-master");

        } catch (JedisConnectionException e) {

          if (running.get()) {
            log.log(Level.SEVERE, "Lost connection to Sentinel at " + host + ":" + port
                + ". Sleeping 5000ms and retrying.", e);
            try {
              Thread.sleep(subscribeRetryWaitTimeMillis);
            } catch (InterruptedException e1) {
              log.log(Level.SEVERE, "Sleep interrupted: ", e1);
            }
          } else {
            log.fine("Unsubscribing from Sentinel at " + host + ":" + port);
          }
        } finally {
          j.close();
        }
      }
    }

伴随着往slave节点写的错误还可以看到：

 log.log(Level.SEVERE, "Lost connection to Sentinel at " + host + ":" + port
                + ". Sleeping 5000ms and retrying.", e);

这个错误日志，说明曾经客户端丢失了连接。

查看jedis github相关isuse，果真有相关内容。可以参考：

https://github.com/xetorthio/jedis/pull/1566

https://github.com/xetorthio/jedis/issues/1953

这个问题在2.9.3版本已经得到正确修复：

 @Override
    public void run() {

      running.set(true);

      while (running.get()) {

        j = new Jedis(host, port);

        try {
          // double check that it is not being shutdown
          if (!running.get()) {
            break;
          }
          
          /* 这里就是关键，只要while循环一次则重新初始化一次。正常情况是会阻塞在 j.subscribe 所以不会一直执行。
           * Added code for active refresh
           */
          List<String> masterAddr = j.sentinelGetMasterAddrByName(masterName);  
          if (masterAddr == null || masterAddr.size() != 2) {

            log.warning("Can not get master addr, master name: "+ masterName+". Sentinel: "+host+"："+port+".");
          }else{
              initPool(toHostAndPort(masterAddr)); 
          }
          //正常情况下会阻塞在这里
          j.subscribe(new JedisPubSub() {
            @Override
            public void onMessage(String channel, String message) {
              log.fine("Sentinel " + host + ":" + port + " published: " + message + ".");

              String[] switchMasterMsg = message.split(" ");

              if (switchMasterMsg.length > 3) {

                if (masterName.equals(switchMasterMsg[0])) {
                  initPool(toHostAndPort(Arrays.asList(switchMasterMsg[3], switchMasterMsg[4])));
                } else {
                  log.fine("Ignoring message on +switch-master for master name "
                      + switchMasterMsg[0] + ", our master name is " + masterName);
                }

              } else {
                log.severe("Invalid message received on Sentinel " + host + ":" + port
                    + " on channel +switch-master: " + message);
              }
            }
          }, "+switch-master");

        } catch (JedisException e) {

          if (running.get()) {
            log.log(Level.SEVERE, "Lost connection to Sentinel at " + host + ":" + port
                + ". Sleeping 5000ms and retrying.", e);
            try {
              Thread.sleep(subscribeRetryWaitTimeMillis);
            } catch (InterruptedException e1) {
              log.log(Level.SEVERE, "Sleep interrupted: ", e1);
            }
          } else {
            log.fine("Unsubscribing from Sentinel at " + host + ":" + port);
          }
        } finally {
          j.close();
        }
      }
    }