How can I trap a signal (`SIGPIPE`) for a socket that closes?

Question

I've written a server that accepts a socket connection on a secondary port for the purposes of streaming debugging information that normally goes to stderr. This second port --an error serving port-- is only intended to have one connection at a time, which, is convenient, because it allows to me redirect stderr using a dup2(2) call. (See Can I redirect a parent process's stderr to a socket file descriptor on a forked process?).

The following code is nearly satisfactory in every regard. When a client logs into the port, the stderr stream is directed to the socket. When another client logs in, the stream is redirected again, and the first client stops receiving: entirely satisfactory.

Where it falls short in the design is when the client closes the connection, the server crashes because it is trying to write() to a socket that is closed.

I've got a rudimentary signal handler for the normal child processes, but I'm not sure how to handle the specific signal from the parent process when the error socket closes.

How can I trap the signal (in the parent) that the connection on the ERR_PORT_NUM has closed and have the signal handler reopen (or dup) stderr back to /dev/null for the next awaiting error client?

Also, what should I do with an original error client connection when a second connects? Currently the first client is left dangling. Even a non-graceful shut-down of the first connection is acceptable.

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/socket.h>
#include <fcntl.h>
#include <errno.h>
#include <pwd.h>
#include <signal.h>
#include <netinet/in.h>
#include <sys/mman.h>

#define PORT_NUM 12345
#define ERR_PORT_NUM 54321

static void child_handler(int signum)
{
    switch (signum) {
        case SIGALRM:
            exit(EXIT_FAILURE);
            break;
        case SIGUSR1:
            exit(EXIT_SUCCESS);
            break;
        case SIGCHLD:
            exit(EXIT_FAILURE);
            break;
    }
}

static void daemonize(void)
{
    /* Trap signals that we expect to recieve */
    signal(SIGUSR1, child_handler);
    signal(SIGALRM, child_handler);

    signal(SIGCHLD, SIG_IGN);   /* A child process dies */
    signal(SIGTSTP, SIG_IGN);   /* Various TTY signals */
    signal(SIGTTOU, SIG_IGN);
    signal(SIGTTIN, SIG_IGN);
    signal(SIGHUP, SIG_IGN);    /* Ignore hangup signal */
    signal(SIGTERM, SIG_DFL);   /* Die on SIGTERM */

    freopen("/dev/null", "r", stdin);
    freopen("/dev/null", "w", stdout);
    freopen("/dev/null", "w", stderr);
}

static void server_work(void)
{
    int sockfd, err_sockfd;
    socklen_t clilen;
    struct sockaddr_in serv_addr, cli_addr, err_serv_addr, err_cli_addr;
    struct timeval tv = { 0 };
    int new_stderr;

    sockfd = socket(AF_INET, SOCK_STREAM, 0);
    err_sockfd = socket(AF_INET, SOCK_STREAM, 0);
    if (sockfd < 0 || err_sockfd < 0)
        return;

    memset((char *) &serv_addr, '\0', sizeof(serv_addr));
    memset((char *) &err_serv_addr, '\0', sizeof(serv_addr));

    serv_addr.sin_family = AF_INET;
    serv_addr.sin_addr.s_addr = INADDR_ANY;
    serv_addr.sin_port = htons(PORT_NUM);

    err_serv_addr.sin_family = AF_INET;
    err_serv_addr.sin_addr.s_addr = INADDR_ANY;
    err_serv_addr.sin_port = htons(ERR_PORT_NUM);

    if (bind(sockfd, (struct sockaddr *) &serv_addr, sizeof(serv_addr))
        < 0)
        return;
    if (bind
        (err_sockfd, (struct sockaddr *) &err_serv_addr,
         sizeof(err_serv_addr)) < 0)
        return;

    listen(sockfd, 5);
    listen(err_sockfd, 5);

    clilen = sizeof(cli_addr);

    while (1) {
        int maxfd;
        fd_set read_sockets_set;

        FD_ZERO(&read_sockets_set);
        FD_SET(sockfd, &read_sockets_set);
        FD_SET(err_sockfd, &read_sockets_set);

        maxfd = (err_sockfd > sockfd) ? err_sockfd : sockfd;

        if (select(maxfd + 1, &read_sockets_set, NULL, NULL, NULL) < 0) {
            break;
        }
        if (FD_ISSET(sockfd, &read_sockets_set)) {
            /* Typical process fork(2) and such ... not gremaine to the question. */
        }
        if (FD_ISSET(err_sockfd, &read_sockets_set)) {
            new_stderr =
                accept(err_sockfd, (struct sockaddr *) &err_cli_addr,
                       &clilen);
            dup2(new_stderr, STDERR_FILENO);
        }
    }
    close(sockfd);
    close(err_sockfd);
    return;
}

int main(int argc, char *argv[])
{
    daemonize();                /* greatly abbreviated for question */

    server_work();
    return 0;
}

Solution

You could simply ignore SIGPIPE. It's a useless, annoying signal.

signal(SIGPIPE, SIG_IGN);

If you ignore it then your program will instead receive an EPIPE error code from the failed write() call. This lets you handle the I/O error at a sensible place in your code rather than in some global signal handler.

EPIPE

fd is connected to a pipe or socket whose reading end is closed. When this happens the writing process will also receive a SIGPIPE signal. (Thus, the write return value is seen only if the program catches, blocks or ignores this signal.)

Comments

[Sergey Kotyushkin]

hmm ... the failing write() calls are inside the library. Which appear to ignore the return values. I suppose I could do an if (ftell(stderr) < 0) ... just before my dup2() call. Messy ... but it is only a debugging tool.

[sudo]

Where should we put signal(SIGPIPE, SIG_IGN);? Just anywhere before any sockets are created, or is it once per thread?