Pregunta

Environment: a RedHat-like distro, 2.6.39 kernel, glibc 2.12.

I fully expect that if a signal was delivered while accept() was in progress, accept should fail, leaving errno==EINTR. However, mine doesn't do that, and I'm wondering why. Below are the sample program, and strace output.

#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <signal.h>
#include <errno.h>
#include <arpa/inet.h>
#include <string.h>

static void sigh(int);

int main(int argc, char ** argv) {

    int s;
    struct sockaddr_in sin;

    if ((s = socket(AF_INET, SOCK_STREAM, 0))<0) {
        perror("socket");
        return 1;
    }
    memset(&sin, 0, sizeof(struct sockaddr_in));
    sin.sin_family = AF_INET;
    if (bind(s, (struct sockaddr*)&sin, sizeof(struct sockaddr_in))) {
        perror("bind"); 
        return 1;
    }
    if (listen(s, 5)) {
        perror("listen");
    }

    signal(SIGQUIT, sigh);

    while (1) {
        socklen_t sl = sizeof(struct sockaddr_in);
        int rc = accept(s, (struct sockaddr*)&sin, &sl);
        if (rc<0) {
            if (errno == EINTR) {
                printf("accept restarted\n");
                continue;
            }
            perror("accept");
            return 1;
        }
        printf("accepted fd %d\n", rc);
        close(rc);
    }

}

void sigh(int s) {

    signal(s, sigh);

    unsigned char p[100];
    int i = 0;
    while (s) {
        p[i++] = '0'+(s%10);
        s/=10;
    }
    write(1, "sig ", 4);
    for (i--; i>=0; i--) {
        write(1, &p[i], 1);
    }
    write(1, "\n", 1);

}

strace output:

execve("./accept", ["./accept"], [/* 57 vars */]) = 0
<skipped>
socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 3
bind(3, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
listen(3, 5)                            = 0
rt_sigaction(SIGQUIT, {0x4008c4, [QUIT], SA_RESTORER|SA_RESTART, 0x30b7e329a0}, {SIG_DFL, [], 0}, 8) = 0
accept(3, 0x7fffe3e3c500, [16])         = ? ERESTARTSYS (To be restarted)
--- SIGQUIT (Quit) @ 0 (0) ---
rt_sigaction(SIGQUIT, {0x4008c4, [QUIT], SA_RESTORER|SA_RESTART, 0x30b7e329a0}, {0x4008c4, [QUIT], SA_RESTORER|SA_RESTART, 0x30b7e329a0}, 8) = 0
write(1, "sig ", 4sig )                     = 4
write(1, "3", 13)                        = 1
write(1, "\n", 1
)                       = 1
rt_sigreturn(0x1)                       = 43
accept(3, ^C <unfinished ...>
¿Fue útil?

Solución 2

Just when I was about to post this, the SA_RESTART flag in strace output caught my attention. signal(2) man page says that signal() "...calls sigaction(2) using flags that supply BSD semantics..." starting from glibc 2.x.

The SA_RESTART flag "...makes certain system calls restartable across signals...", which hides the process of restarting a call from the user. So, this is not specific to accept(), a number of other system calls are also affected, not that there is a clear list of which ones.

So, if you need to react to a signal from a thread that may be blocked on a system call, you should use sigaction() to set your signal handlers, and not signal(). Below is the modified sample program that does exactly that, for reference.

#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#include <signal.h>
#include <errno.h>
#include <arpa/inet.h>
#include <string.h>

static void sigh(int);

static struct sigaction sa;

int main(int argc, char ** argv) {

    int s;
    struct sockaddr_in sin;

    if ((s = socket(AF_INET, SOCK_STREAM, 0)) < 0) {
        perror("socket");
        return 1;
    }
    memset(&sin, 0, sizeof(struct sockaddr_in));
    sin.sin_family = AF_INET;
    if (bind(s, (struct sockaddr*)&sin, sizeof(struct sockaddr_in))) {
        perror("bind"); 
        return 1;
    }
    if (listen(s, 5)) {
        perror("listen");
    }

    memset(&sa, 0, sizeof(struct sigaction));
    sa.sa_handler = sigh;
    sigemptyset(&sa.sa_mask);
    sigaction(SIGQUIT, &sa, 0);

    while (1) {
        socklen_t sl = sizeof(struct sockaddr_in);
        int rc = accept(s, (struct sockaddr*)&sin, &sl);
        if (rc<0) {
            if (errno == EINTR) {
                printf("accept restarted\n");
                continue;
            }
            perror("accept");
            return 1;
        }
        printf("accepted fd %d\n", rc);
        close(rc);
    }

}

void sigh(int s) {

    sigaction(SIGQUIT, &sa, 0);

    unsigned char p[100];
    int i = 0;
    while (s) {
        p[i++] = '0'+(s%10);
        s/=10;
    }
    write(1, "sig ", 4);
    for (i--; i>=0; i--) {
        write(1, &p[i], 1);
    }
    write(1, "\n", 1);

}

And strace:

execve("./accept", ["./accept"], [/* 57 vars */]) = 0
socket(PF_INET, SOCK_STREAM, IPPROTO_IP) = 3
bind(3, {sa_family=AF_INET, sin_port=htons(0), sin_addr=inet_addr("0.0.0.0")}, 16) = 0
listen(3, 5)                            = 0
rt_sigaction(SIGQUIT, {0x400994, [], SA_RESTORER, 0x30b7e329a0}, NULL, 8) = 0
accept(3, 0x7fffb626be90, [16])         = ? ERESTARTSYS (To be restarted)
--- SIGQUIT (Quit) @ 0 (0) ---
rt_sigaction(SIGQUIT, {0x400994, [], SA_RESTORER, 0x30b7e329a0}, NULL, 8) = 0
write(1, "sig ", 4)                  = 4
write(1, "3", 13)                        = 1
write(1, "\n", 1)                       = 1
rt_sigreturn(0x1)                       = -1 EINTR (Interrupted system call)
write(1, "accept restarted\n", 17)      = 17
accept(3, 

Otros consejos

Within Unix Network Programming book, there is a section which says:

We used the term "slow system call" to describe accept, and we use this term for any system call that can block forever. That is, the system call need never return. Most networking functions fall into this category. For example, there is no guarantee that a server's call to accept will ever return, if there are no clients that will connect to the server. Similarly, our server's call to read in Figure 5.3 will never return if the client never sends a line for the server to echo. Other examples of slow system calls are reads and writes of pipes and terminal devices. A notable exception is disk I/O, which usually returns to the caller (assuming no catastrophic hardware failure).

The basic rule that applies here is that when a process is blocked in a slow system call and the process catches a signal and the signal handler returns, the system call can return an error of EINTR. Some kernels automatically restart some interrupted system calls. For portability, when we write a program that catches signals (most concurrent servers catch SIGCHLD), we must be prepared for slow system calls to return EINTR. Portability problems are caused by the qualifiers "can" and "some," which were used earlier, and the fact that support for the POSIX SA_RESTART flag is optional. Even if an implementation supports the SA_RESTART flag, not all interrupted system calls may automatically be restarted. Most Berkeley-derived implementations, for example, never automatically restart select, and some of these implementations never restart accept or recvfrom.

Licenciado bajo: CC-BY-SA con atribución
No afiliado a StackOverflow
scroll top