我的 epoll 服务器丢失了一些连接。 为什么？

Question

我想做一个 epoll 服务器。 但是我的服务器代码丢失了一些连接。

我的客户端产生 100 个线程，每个线程都发送相同的消息。 然后我的服务器应该接收并打印带有计数的数字。

但是服务器似乎失去了连接，我不知道为什么。

我将EPOLL_SIZE从 50 更改为 200，并将listen()的 backlog 参数从 5 更改为 1000。但是它们没有用。

1.服务器：

#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>
#include <sys/epoll.h>
#include <memory>
#include <array>

#define BUF_SIZE 100
#define EPOLL_SIZE 200
void error_handling(const char *buf);

int main(int argc, char *argv[])
{
   // Step 1. Initialization
   int server_socket, client_socket;
   struct sockaddr_in client_addr;
   socklen_t addr_size;
   int str_len, i;
   char buf[BUF_SIZE];

   int epfd, event_cnt;

   if (argc != 2) {
      printf("Usage : %s <port>\n", argv[0]);
      exit(1);
   }

   // Step 2. Creating a socket
   server_socket = socket(PF_INET, SOCK_STREAM, 0);

   struct sockaddr_in server_addr;
   memset(&server_addr, 0, sizeof(server_addr));
   server_addr.sin_family = AF_INET;
   server_addr.sin_addr.s_addr = htonl(INADDR_ANY);
   server_addr.sin_port = htons(atoi(argv[1]));

   // Step 3. Binding the server address onto the socket created just right before.
   if (bind(server_socket, (struct sockaddr*) &server_addr, sizeof(server_addr)) == -1)
      error_handling("bind() error");

   // Step 4. Start to listen to the socket.
   if (listen(server_socket, 1000) == -1)
      error_handling("listen() error");

   // Step 5. Create an event poll instance.
   epfd = epoll_create(EPOLL_SIZE);
   auto epoll_events = (struct epoll_event*) malloc(sizeof(struct epoll_event) * EPOLL_SIZE);

   struct epoll_event event;
   event.events = EPOLLIN;
   event.data.fd = server_socket;

   // Step 6. Adding the server socket file descriptor to the event poll's control.
   epoll_ctl(epfd, EPOLL_CTL_ADD, server_socket, &event);
   int recv_cnt = 0;

   while(true)
   {
      // Step 7. Wait until some event happens
      event_cnt = epoll_wait(epfd, epoll_events, EPOLL_SIZE, -1);
      if (event_cnt == -1)
      {
         puts("epoll_wait() error");
         break;
      }

      for (i = 0; i < event_cnt; i++)
      {
         if (epoll_events[i].data.fd == server_socket)
         {
            addr_size = sizeof(client_addr);
            client_socket = accept(server_socket, (struct sockaddr*)&client_addr, &addr_size);
            event.events = EPOLLIN;
            event.data.fd = client_socket;
            epoll_ctl(epfd, EPOLL_CTL_ADD, client_socket, &event);
            //printf("Connected client: %d\n", client_socket);
         }
         else  // client socket?
         {
            str_len = read(epoll_events[i].data.fd, buf, BUF_SIZE);
            if (str_len == 0) // close request!
            {
               epoll_ctl(epfd, EPOLL_CTL_DEL, epoll_events[i].data.fd, nullptr);
               close(epoll_events[i].data.fd);
               printf("%d: %s\n", ++recv_cnt,  buf);
               //printf("closed client: %d \n", epoll_events[i].data.fd);
            }
            else
            {
               write(epoll_events[i].data.fd, buf, str_len);   // echo!
            }
         } // end of else()
      } // end of for()
   }  // end of while()

   close(server_socket);
   close(epfd);
   free(epoll_events);

   return EXIT_SUCCESS;
}

void error_handling(const char *buf)
{
   fputs(buf, stderr);
   fputc('\n', stderr);
   exit(EXIT_FAILURE);
}

2.客户端：

#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <string>
#include <unistd.h>
#include <arpa/inet.h>
#include <sys/socket.h>
#include <thread>
#include <vector>
#include <algorithm>
#include <mutex>

#define BUF_SIZE 100
#define EPOLL_SIZE 50

void error_handling(const char *buf);

int main(int argc, char *argv[])
{
   // Step 1. Initialization
   int socketfd;

   if (argc != 3) {
      printf("Usage : %s <ip address> <port>\n", argv[0], argv[1]);
      exit(EXIT_FAILURE);
   }
   std::vector<std::thread> cli_threads;
   std::mutex wlock;

   for (int i = 0; i < 100; i++) {
      cli_threads.push_back(std::thread([&](const char* szIpAddr, const char* szPort) {
         // Step 2. Creating a socket
         socketfd = socket(PF_INET, SOCK_STREAM, 0);

         struct sockaddr_in server_addr;
         memset(&server_addr, 0, sizeof(server_addr));
         server_addr.sin_family = AF_INET;
         server_addr.sin_addr.s_addr = inet_addr(szIpAddr);
         server_addr.sin_port = htons(atoi(szPort));

         // Step 3. Connecting to the server
         if(connect(socketfd, (struct sockaddr*)&server_addr, sizeof(server_addr)) == -1)
            error_handling("connect() error"); 

         // Step 4. Writing message to the server
         std::string msg = "Hey I'm a client!";
         wlock.lock();
         auto str_len = write(socketfd, msg.c_str(), msg.size()+1);
         wlock.unlock();

         close(socketfd); 
      }, argv[1], argv[2]));
   }

   std::for_each(cli_threads.begin(), cli_threads.end(), 
      [](std::thread &t)
      {
         t.join();
      }
   );
   return EXIT_SUCCESS;
}

void error_handling(const char *buf)
{
   fputs(buf, stderr);
   fputc('\n', stderr);
   exit(EXIT_FAILURE);
}

预计像...

1: Hey I'm a client!
...
100: Hey I'm a client!

但是，结果会有所不同，例如...

1: Hey I'm a client!
...
n: Hey I'm a client!

其中n小于 100。

Answer 1

由于通过引用线程传递socketfd ，您有未定义的行为 - std::thread([&](... 。所有线程同时修改套接字描述符的一个实例 - 它导致了问题。每个线程都应该存储自己的描述符.