c++ - 关闭套接字时防止 FIN_WAIT2

Question

我有一个服务器程序通过给定的套接字连接到另一个程序，在某些情况下我需要关闭连接并几乎立即在同一个套接字上重新打开它。总的来说，这是可行的，除了我必须等待整整一分钟才能重置套接字。同时，netstat 表明服务器看到的套接字处于 FIN_WAIT2，而客户端看到的是 CLOSE_WAIT。我已经在使用 SO_REUSEADDR，我认为这会阻止等待，但那并没有起到作用。将 SO_LINGER 设置为零也无济于事。我还能做些什么来解决这个问题？

以下是相关的代码片段:

SetUpSocket()
{
   // Set up the socket and listen for a connection from the exelerate client.
   // Open a TCP/IP socket.
   m_baseSock = socket(PF_INET, SOCK_STREAM, IPPROTO_IP);
   if (m_baseSock < 0)
   {
      return XERROR;
   }

   // Set the socket options to reuse local addresses.
   int flag = 1;
   if (setsockopt(m_baseSock, SOL_SOCKET, SO_REUSEADDR, &flag, sizeof(flag)) == -1)
   {
      return XERROR;
   }

   // Set the socket options to prevent lingering after closing the socket.
   //~ linger li = {1,0};
   //~ if (setsockopt(m_baseSock, SOL_SOCKET, SO_LINGER, &li, sizeof(li)) == -1)
   //~ {
      //~ return XERROR;
   //~ }

   // Bind the socket to the address of the current host and our given port.
   struct sockaddr_in addr;
   memset(&addr, 0, sizeof(addr));
   addr.sin_family = AF_INET;
   addr.sin_addr.s_addr = INADDR_ANY;
   addr.sin_port = htons(m_port);
   if (bind(m_baseSock, (struct sockaddr*)&addr, sizeof(addr)) != 0)
   {
      return XERROR;
   }

   // Tell the socket to listen for a connection from client.
   if (listen(m_baseSock, 4) != 0)
   {
      return XERROR;
   }
   return XSUCCESS;
}

ConnectSocket()
{
   // Add the socket to a file descriptor set.
   fd_set readfds;
   FD_ZERO(&readfds);
   FD_SET(m_baseSock, &readfds);

   // Set timeout to ten seconds. Plenty of time.
   struct timeval timeout;
   timeout.tv_sec = 10;
   timeout.tv_usec = 0;

   // Check to see if the socket is ready for reading.
   int numReady = select(m_baseSock + 1, &readfds, NULL, NULL, &timeout);
   if (numReady > 0)
   {
      int flags = fcntl(m_baseSock, F_GETFL, 0);
      fcntl(m_baseSock, flags | O_NONBLOCK, 1);

      // Wait for a connection attempt from the client. Do not block - we shouldn't
      // need to since we just selected.
      m_connectedSock = accept(m_baseSock, NULL, NULL);
      if (m_connectedSock > 0)
      {
         m_failedSend = false;
         m_logout = false;

         // Spawn a thread to accept commands from client.
         CreateThread(&m_controlThread, ControlThread, (void *)&m_connectedSock);

         return XSUCCESS;
      }
   }
   return XERROR;
}

ControlThread(void *arg)
{
   // Get the socket from the argument.
   socket sock = *((socket*)arg);

   while (true)
   {
      // Add the socket to a file descriptor set.
      fd_set readfds;
      FD_ZERO(&readfds);
      FD_SET(sock, &readfds);

      // Set timeout to ten seconds. Plenty of time.
      struct timeval timeout;
      timeout.tv_sec = 10;
      timeout.tv_usec = 0;

      // Check if there is any readable data on the socket.
      int num_ready = select(sock + 1, &readfds, NULL, NULL, &timeout);
      if (num_ready < 0)
      {
         return NULL;
      }

      // If there is data, read it.
      else if (num_ready > 0)
      {
         // Check the read buffer.
         xuint8 buf[128];
         ssize_t size_read = recv(sock, buf, sizeof(buf));
         if (size_read > 0)
         {
            // Get the message out of the buffer.
            char msg = *buf;
            if (msg == CONNECTED)
            {
               // Do some things...
            }
            // If we get the log-out message, log out.
            else if (msg == LOGOUT)
            {
               return NULL;
            }
         }
      }
   } // while
   return NULL;
}

~Server()
{
   // Close the sockets.
   if (m_baseSock != SOCKET_ERROR)
   {
      close(m_baseSock);
      m_baseSock = SOCKET_ERROR;
   }
   if (m_connectedSock != SOCKET_ERROR)
   {
      close(m_connectedSock);
      m_connectedSock = SOCKET_ERROR;
   }
}

SOCKET_ERROR 等于 -1。服务器对象被销毁，此时连接应该关闭，然后重新创建，此时调用 SetUpSocket() 和 ConnectSocket() 例程。

那么为什么我必须等待一分钟才能清除套接字？任何想法都会受到赞赏。

编辑:按照我的第一张海报的建议，我找到了一种让客户端从其末端关闭套接字的方法。不过还是有些不对劲。现在，netstat 从服务器的角度在 TIME_WAIT 中显示套接字，而从客户端的角度来看没有任何条目。我所拥有的是:

tcp 0 0 localhost.localdomain:19876 localhost.localdomain:54598 TIME_WAIT

反之亦然。服务器和客户端仍然需要一分钟时间来清除 TIME_WAIT 以便能够重新连接。现在出了什么问题 - 在客户端的套接字上使用 close() 是不是不正确？

编辑 2:现在，如果我强制客户端重新连接，它会立即 - 但如果我只是让它做自己的事情，它会等待整整一分钟以清除 TIME_WAIT。我怀疑客户端代码中有问题。我对此无能为力。

Answer 1

服务器正在等待客户端发送一个FIN数据包。这应该通过关闭客户端的套接字(或者可能关闭应用程序)来完成。然后服务器进入TIME_WAIT状态，等待socket超时。 SO_REUSEADDR 使您能够绕过此状态。

(来源 http://upload.wikimedia.org/wikipedia/commons/0/08/TCP_state_diagram.jpg)