跟踪儿童过程的死亡

Question

如何在不让父进程等待直到子进程被杀死的情况下追踪子进程的死亡？

我正在尝试一种客户端 - 服务器方案,其中服务器接受来自客户端的连接,并为它接受的每个连接分叉一个新进程.

我忽略了SIGCHLD信号以防止僵尸创建.

signal(SIGCHLD, SIG_IGN);
while(1)
{
  accept();
  clients++;
  if(fork() ==0)
  {
     childfunction();
     clients--;
  }
  else
  {
  }
}

上述场景中的问题是,如果子进程在childfunction()函数中被杀死,则全局变量clients不会减少.

注意:我正在寻找一种不使用SIGCHLD信号的解决方案......如果可能的话

Answer 1

通常,您编写一个对pid 进行SIGCHLD调用的处理程序.您可以使用其中的返回值来确定pid死亡的原因.例如:waitpid()-1

void my_sigchld_handler(int sig)
{
    pid_t p;
    int status;

    while ((p=waitpid(-1, &status, WNOHANG)) != -1)
    {
       /* Handle the death of pid p */
    }
}

/* It's better to use sigaction() over signal().  You won't run into the
 * issue where BSD signal() acts one way and Linux or SysV acts another. */

struct sigaction sa;

memset(&sa, 0, sizeof(sa));
sa.sa_handler = my_sigchld_handler;

sigaction(SIGCHLD, &sa, NULL);

或者,您可以waitpid(pid, &status, 0)使用指定的子进程ID进行调用,并同步等待它死亡.或者用它WNOHANG来检查其状态而不会阻塞.

Answer 2

到目前为止,没有一个解决方案提供了一种不使用SIGCHLD作为问题请求的方法.以下是本答案中概述的使用轮询的替代方法的实现(这也解释了为什么在这种情况下应避免使用SIGCHLD):

确保您有一个管道往/来自您创建的每个子进程.它可以是他们的stdin/stdout/stderr,也可以只是一个额外的虚拟fd.子进程终止时,管道的末尾将关闭,主事件循环将检测该文件描述符上的活动.从它关闭的事实,你认识到子进程死了,并调用waitpid来收获僵尸.

(注意:为了简洁起见,我省略了一些最佳实践,如错误检查和清理文件描述符)

/**
 * Specifies the maximum number of clients to keep track of.
 */
#define MAX_CLIENT_COUNT 1000

/**
 * Tracks clients by storing their process IDs and pipe file descriptors.
 */
struct process_table {
    pid_t clientpids[MAX_CLIENT_COUNT];
    struct pollfd clientfds[MAX_CLIENT_COUNT];
} PT;

/**
 * Initializes the process table. -1 means the entry in the table is available.
 */
void initialize_table() {
    for (int i = 0; i < MAX_CLIENT_COUNT; i++) {
        PT.clientfds[i].fd = -1;
    }
}

/**
 * Returns the index of the next available entry in the process table.
 */
int get_next_available_entry() {
    for (int i = 0; i < MAX_CLIENT_COUNT; i++) {
        if (PT.clientfds[i].fd == -1) {
            return i;
        }
    }
    return -1;
}

/**
 * Adds information about a new client to the process table.
 */
void add_process_to_table(int i, pid_t pid, int fd) {
    PT.clientpids[i] = pid;
    PT.clientfds[i].fd = fd;
}

/**
 * Removes information about a client from the process table.
 */
void remove_process_from_table(int i) {
    PT.clientfds[i].fd = -1;
}

/**
 * Cleans up any dead child processes from the process table.
 */
void reap_zombie_processes() {
    int p = poll(PT.clientfds, MAX_CLIENT_COUNT, 0);

    if (p > 0) {
        for (int i = 0; i < MAX_CLIENT_COUNT; i++) {
            /* Has the pipe closed? */
            if ((PT.clientfds[i].revents & POLLHUP) != 0) {
                // printf("[%d] done\n", PT.clientpids[i]);
                waitpid(PT.clientpids[i], NULL, 0);
                remove_process_from_table(i);
            }
        }
    }
}

/**
 * Simulates waiting for a new client to connect.
 */
void accept() {
    sleep((rand() % 4) + 1);
}

/**
 * Simulates useful work being done by the child process, then exiting.
 */
void childfunction() {
    sleep((rand() % 10) + 1);
    exit(0);
}

/**
 * Main program
 */
int main() {
    /* Initialize the process table */
    initialize_table();

    while (1) {
        accept();

        /* Create the pipe */
        int p[2];
        pipe(p);

        /* Fork off a child process. */
        pid_t cpid = fork();

        if (cpid == 0) {
            /* Child process */
            close(p[0]);
            childfunction();
        }
        else {
            /* Parent process */
            close(p[1]);
            int i = get_next_available_entry();
            add_process_to_table(i, cpid, p[0]);
            // printf("[%d] started\n", cpid);
            reap_zombie_processes();
        }
    }

    return 0;
}

以下是运行程序的一些示例输出,其中printf语句未注释:

[31066] started
[31067] started
[31068] started
[31069] started
[31066] done
[31070] started
[31067] done
[31068] done
[31071] started
[31069] done
[31072] started
[31070] done
[31073] started
[31074] started
[31072] done
[31075] started
[31071] done
[31074] done
[31081] started
[31075] done