epoll_wait 之后接收时的 EBADF

Question

我遇到了以下问题：我有一个接收连接的 epoll 代码：

while (1) {
    int nfds = epoll_wait(epollfd, events, 4096, -1);
    if (nfds == -1) {
        if (errno == EINTR)
            continue;
        perror("epoll_wait");
        exit(EXIT_FAILURE);
    }

    for (int i = 0; i < nfds; i++) {
        if (events[i].data.fd == server_sock) {
            client_sock = accept(server_sock,
                         (struct sockaddr *)&client_name,
                         (socklen_t *)(&client_name_len));

        if (client_sock == -1) //server overloaded
            continue;

        ev.events = EPOLLIN | EPOLLERR;

#ifdef CORE_NONBLOCKING_SOCKETS
        Arch::set_nonblocking(client_sock);
        ev.events |= EPOLLET; //input data and connection closing
#endif


#ifdef EPOLLRDHUP
        ev.events |= EPOLLRDHUP ;//
#else
        //for old libraries
        ev.events |= EPOLLHUP;//
#endif

        ev.data.fd = client_sock;

        if (epoll_ctl(epollfd, EPOLL_CTL_ADD, client_sock, &ev) == -1) {
            perror("epoll_ctl: client_socket");
            exit(EXIT_FAILURE);
        }

        accept_request(client_sock);

        } else {

#ifdef EPOLLRDHUP
            if (events[i].events & EPOLLRDHUP) {
                std::cout << "EPOLLRDHUP on " << events[i].data.fd << std::endl;
                listener->disconnectDriver(events[i].data.fd);
            }
#else
            if (events[i].events & EPOLLHUP) {
                std::cout << "EPOLLHUP on " << events[i].data.fd << std::endl;
                listener->disconnectDriver(events[i].data.fd);
            }
#endif
            if (events[i].events & EPOLLIN) {
                std::cout << "debug EPOLLIN on " << events[i].data.fd << std::endl;
                accept_request(events[i].data.fd);
            }

            if (events[i].events & EPOLLERR) {
                std::cout << "debug EPOLLERR on " << events[i].data.fd << std::endl;
                listener->disconnectDriver(events[i].data.fd);
            }


        }
    }

当我收到输入连接时，我尝试读取所有 buff 数据：

void get_all_buf(int sock, std::string & inStr) {
int n = 1;
int total = 0;

char c;
char temp[1024*1024]; 

bzero(temp, sizeof(temp));

do {
#ifdef CORE_NONBLOCKING_SOCKETS
    timespec time_to_wait;
    time_to_wait.tv_nsec = 10000000;
    time_to_wait.tv_sec = 0;
    timespec tm;

    time_t begin = time(NULL);
    do {
#endif

        n = recv(sock, &temp[total], sizeof(temp), 0);

#ifdef CORE_NONBLOCKING_SOCKETS
        nanosleep(&time_to_wait, &tm); 
        time_t end = time(NULL); 
        if ((end - begin) > MAX_CLIENT_TIME) {
            inStr = std::string();
            return;
        }
    } while (n < 0 && errno == EAGAIN); //nonblocking sockets in edge-triggered mode
#endif

    if (n > 0) {
        total += n;
    } else if (n == 0) {
        //TODO: error handling
        //debug
        std::cout << "possibly no one byte was received" << std::endl;
        break;
    } else if (n < 0) {
        //TODO: error handling
        //debug
        std::cout << "error while receiving data" << std::endl;
        if (errno == EBADF) {
            std::cout << "recv returns with EBADF: " << strerror(errno) << std::endl;
        } else if (errno == EFAULT) {
            std::cout << "recv returns with EFAULT: " << strerror(errno) << std::endl;
        } else if (errno == EINTR) {
            std::cout << "recv returns with EINTR: " << strerror(errno) << std::endl;
        } else if (errno == EINVAL) {
            std::cout << "recv returns with EINVAL: " << strerror(errno) << std::endl;
        }
        //end debug
        break;
    }

} while (!strstr(temp, "</packet>")); 
inStr = temp;
};

在 accept_request 函数中。但有时我在调试输出中得到以下信息：

packet type='connect'
size of vector<Driver> in getDriversWithMoney is 1
epoll_wait detected activity of 164 counter i = 0 nfds = 1
EPOLLRDHUP on 164
disconnectDriver (fd = 164)
driver 1 disconnected
debug EPOLLIN on 164
error while receiving data
recv returns with EBADF: Invalid file descriptor

这意味着有人先连接而不是断开连接，当他尝试再次连接时，recv 返回EBADF。我做错了什么？请帮我。

PS on EPOLLRDHUP 我只是关闭文件描述符。 epoll man说没问题，因为epoll自己从epoll_wait队列中删除了关闭的fd。

Answer 1

当远程主机关闭套接字时，epoll() 会报告文件描述符的 HUP 和 EPOLLIN。

首先检查EPOLLRDHUP，然后关闭套接字；然后检查 EPOLLIN，也找到它，然后尝试调用 recv()。由于套接字已关闭，文件描述符不再有效，并且您得到EBADF（已关闭的套接字已从epoll集中删除，因此后续< /em> epoll_wait() 调用不会返回它；但对于已经返回的 epoll_wait() 来说已经太晚了 - EPOLLIN已在您的 events[i] 中等待。

您需要在调用 disconnectDriver() 后停止检查事件（如果它关闭了文件描述符）：

        if (events[i].events & EPOLLRDHUP) {
            std::cout << "EPOLLRDHUP on " << events[i].data.fd << std::endl;
            listener->disconnectDriver(events[i].data.fd);
            continue;
        }