Nginx之监控进程和工作进程

1. 函数调用分析

在开启 master 的情况下，多进程模型的下的入口函数为 ngx_master_process_cycle，如下：

int mian()
{
...
    if (ngx_process == NGX_PROCESS_SINGLE)
    {
        /* 单进程模型下的入口函数 */
        ngx_single_process_cycle(cycle);
    }
    else
    {
        /* 多进程模型下的入口函数 */
        ngx_master_process_cycle(cycle);
    }

    return 0;
}

Nginx 核心进程模型框图

1.1 ngx_master_process_cycle：

static ngx_cycle_t      ngx_exit_cycle;
static ngx_log_t        ngx_exit_log;
static ngx_open_file_t  ngx_exit_log_file;

/*
 * 参数意义：
 * - cycle是当前进程ngx_cycle_t的结构体指针
 *
 * 执行意义：
 * 进入master进程的工作循环
 */
void ngx_master_process_cycle(ngx_cycle_t *cycle)
{
    char              *title;
    u_char            *p;
    size_t             size;
    ngx_int_t          i;
    ngx_uint_t         n, sigio;
    sigset_t           set;
    struct itimerval   itv;
    ngx_uint_t         live;
    ngx_msec_t         delay;
    ngx_listening_t   *ls;
    ngx_core_conf_t   *ccf;

    /* 将下列信号添加到 set 信号集中 */
    sigemptyset(&set);
    sigaddset(&set, SIGCHLD);
    sigaddset(&set, SIGALRM);
    sigaddset(&set, SIGIO);
    sigaddset(&set, SIGINT);
    sigaddset(&set, ngx_signal_value(NGX_RECONFIGURE_SIGNAL));
    sigaddset(&set, ngx_signal_value(NGX_REOPEN_SIGNAL));
    sigaddset(&set, ngx_signal_value(NGX_NOACCEPT_SIGNAL));
    sigaddset(&set, ngx_signal_value(NGX_TERMINATE_SIGNAL));
    sigaddset(&set, ngx_signal_value(NGX_SHUTDOWN_SIGNAL));
    sigaddset(&set, ngx_signal_value(NGX_CHANGEBIN_SIGNAL));

    /*
     * sigprocmask(int how, const sigset_t *set, sigset_t *oldset);
     * 函数既可以修改进程的信号掩码，又可获取现有掩码，或者两者皆可。
     * - SIG_BLOCK：将set指向信号集内的指定信号添加到信号掩码中。换言之，将信号掩码
     *   设置为其当前值和set的并集。
     * - SIG_UNBLOCK：将set指向信号集中的指定信号从信号掩码中移除。即使要接触阻塞的信号当前
     *   并未处于阻塞状态，也不会返回错误。
     * - SIG_SETMASK：将set指向的信号集赋给信号掩码。
     */

    /* 临时阻塞上面所示信号，防止其信号处理器将某些关键代码片段的执行中断，然后下面调用
     * sigsuspend()解除对信号的阻塞，然后暂停执行，直至有信号到达. */
    if (sigprocmask(SIG_BLOCK, &set, NULL) == -1) {
        ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                      "sigprocmask() failed");
    }

    sigemptyset(&set);

    size = sizeof(master_process);

    for (i = 0; i < ngx_argc; i++) {
        size += ngx_strlen(ngx_argv[i]) + 1;
    }

    title = ngx_pnalloc(cycle->pool, size);
    if (title == NULL) {
        /* fatal */
        exit(2);
    }

    p = ngx_cpymem(title, master_process, sizeof(master_process) - 1);
    for (i = 0; i < ngx_argc; i++) {
        *p++ = ' ';
        p = ngx_cpystrn(p, (u_char *) ngx_argv[i], size);
    }

    /* 设置监控进程的名字 */
    ngx_setproctitle(title);

    ccf = (ngx_core_conf_t *) ngx_get_conf(cycle->conf_ctx, ngx_core_module);

    /* 该函数用于fork()产生子进程，该函数的主体是一个无限for( ;; )循环，持续不断地处理
     * 客户端的服务请求，而主进程继续执行ngx_master_process_cycle()函数，也就是作为监控
     * 进程执行主体for(;;)循环，这也是一个无限循环，直到进程终止才退出. */
    ngx_start_worker_processes(cycle, ccf->worker_processes,
                               NGX_PROCESS_RESPAWN);
    ngx_start_cache_manager_processes(cycle, 0);

    ngx_new_binary = 0;
    delay = 0;
    sigio = 0;
    live = 1;

    for ( ;; ) {
        if (delay) {
            if (ngx_sigalrm) {
                sigio = 0;
                delay *= 2;
                ngx_sigalrm = 0;
            }

            ngx_log_debug1(NGX_LOG_DEBUG_EVENT, cycle->log, 0,
                           "termination cycle: %M", delay);

            itv.it_interval.tv_sec = 0;
            itv.it_interval.tv_usec = 0;
            itv.it_value.tv_sec = delay / 1000;
            itv.it_value.tv_usec = (delay % 1000 ) * 1000;

            if (setitimer(ITIMER_REAL, &itv, NULL) == -1) {
                ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                              "setitimer() failed");
            }
        }

        ngx_log_debug0(NGX_LOG_DEBUG_EVENT, cycle->log, 0, "sigsuspend");

        /*
         * sigsuspend(const sigset_t *mask);
         * 该函数将以mask所指向的信号集来替换进程的信号掩码，然后挂起进程的执行，
         * 直到其捕获到信号，并从信号处理器中返回。一旦处理器返回，sigsuspend()
         * 会将进程信号掩码恢复为调用前的值。
         */

        /* 该函数使得监控进程的大部分时间都处于挂起等待状态，直到监控进程接收到信号为止。
         * 当监控进程接收到信号时，信号处理函数ngx_signal_handler()就会被执行。*/
        sigsuspend(&set);

        ngx_time_update();

        ngx_log_debug1(NGX_LOG_DEBUG_EVENT, cycle->log, 0,
                       "wake up, sigio %i", sigio);

        /* 有子进程退出? */
        if (ngx_reap) {
            ngx_reap = 0;
            ngx_log_debug0(NGX_LOG_DEBUG_EVENT, cycle->log, 0, "reap children");

            live = ngx_reap_children(cycle);
        }

        /* 进程要退出或终止? */
        if (!live && (ngx_terminate || ngx_quit)) {
            ngx_master_process_exit(cycle);
        }

        /* 进程要终止?
         * 结束比较粗暴，不过它通过使用SIGKILL信号能保证在一段
         * 时间后必定被结束掉. */
        if (ngx_terminate) {
            if (delay == 0) {
                delay = 50;
            }

            if (sigio) {
                sigio--;
                continue;
            }

            sigio = ccf->worker_processes + 2 /* cache processes */;

            if (delay > 1000) {
                ngx_signal_worker_processes(cycle, SIGKILL);
            } else {
                ngx_signal_worker_processes(cycle,
                                       ngx_signal_value(NGX_TERMINATE_SIGNAL));
            }

            continue;
        }

        /* 进程要退出?
         * 该结束比较优雅，会让Nginx监控进程做一些清理工作且等待
         * 子进程也完全清理并退出之后才终止. */
        if (ngx_quit) {
            ngx_signal_worker_processes(cycle,
                                        ngx_signal_value(NGX_SHUTDOWN_SIGNAL));

            ls = cycle->listening.elts;
            for (n = 0; n < cycle->listening.nelts; n++) {
                if (ngx_close_socket(ls[n].fd) == -1) {
                    ngx_log_error(NGX_LOG_EMERG, cycle->log, ngx_socket_errno,
                                  ngx_close_socket_n " %V failed",
                                  &ls[n].addr_text);
                }
            }
            cycle->listening.nelts = 0;

            continue;
        }

        /* 重新加载配置? */
        if (ngx_reconfigure) {
            ngx_reconfigure = 0;

            if (ngx_new_binary) {
                ngx_start_worker_processes(cycle, ccf->worker_processes,
                                           NGX_PROCESS_RESPAWN);
                ngx_start_cache_manager_processes(cycle, 0);
                ngx_noaccepting = 0;

                continue;
            }

            ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "reconfiguring");

            cycle = ngx_init_cycle(cycle);
            if (cycle == NULL) {
                cycle = (ngx_cycle_t *) ngx_cycle;
                continue;
            }

            ngx_cycle = cycle;
            ccf = (ngx_core_conf_t *) ngx_get_conf(cycle->conf_ctx,
                                                   ngx_core_module);
            ngx_start_worker_processes(cycle, ccf->worker_processes,
                                       NGX_PROCESS_JUST_RESPAWN);
            ngx_start_cache_manager_processes(cycle, 1);

            /* allow new processes to start */
            ngx_msleep(100);

            live = 1;
            ngx_signal_worker_processes(cycle,
                                        ngx_signal_value(NGX_SHUTDOWN_SIGNAL));
        }

        if (ngx_restart) {
            ngx_restart = 0;
            ngx_start_worker_processes(cycle, ccf->worker_processes,
                                       NGX_PROCESS_RESPAWN);
            ngx_start_cache_manager_processes(cycle, 0);
            live = 1;
        }

        if (ngx_reopen) {
            ngx_reopen = 0;
            ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "reopening logs");
            ngx_reopen_files(cycle, ccf->user);
            ngx_signal_worker_processes(cycle,
                                        ngx_signal_value(NGX_REOPEN_SIGNAL));
        }

        if (ngx_change_binary) {
            ngx_change_binary = 0;
            ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "changing binary");
            ngx_new_binary = ngx_exec_new_binary(cycle, ngx_argv);
        }

        if (ngx_noaccept) {
            ngx_noaccept = 0;
            ngx_noaccepting = 1;
            ngx_signal_worker_processes(cycle,
                                        ngx_signal_value(NGX_SHUTDOWN_SIGNAL));
        }
    }
}

1.2 ngx_start_worker_processes

/*
 * 参数含义：
 * - cycle: 是当前进程的ngx_cycle_t结构体指针
 * - n: 是启动子进程的个数
 * - type: 是启动方式，取值范围有以下5个：
 *      - NGX_PROCESS_RESPAWN
 *      - NGX_PROCESS_NORESPAWN
 *      - NGX_PROCESS_JUST_SPAWN
 *      - NGX_PROCESS_JUST_RESPAWN
 *      - NGX_PROCESS_DETACHED
 *   type的值将会影响ngx_process_t结构体的respawn、detached、just_spawn标志位的值.
 *
 * 执行意义：
 * 启动n个worker子进程，并设置好每个子进程与master父进程之间使用socketpair系统调用
 * 建立起来的socket句柄通信机制.
 */
static void ngx_start_worker_processes(ngx_cycle_t *cycle, ngx_int_t n, ngx_int_t type)
{
    ngx_int_t      i;
    ngx_channel_t  ch;

    ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "start worker processes");

    ngx_memzero(&ch, sizeof(ngx_channel_t));

    ch.command = NGX_CMD_OPEN_CHANNEL;

    for (i = 0; i < n; i++) {

        ngx_spawn_process(cycle, ngx_worker_process_cycle,
                          (void *) (intptr_t) i, "worker process", type);

        ch.pid = ngx_processes[ngx_process_slot].pid;       // 子进程的id号
        ch.slot = ngx_process_slot; // 子进程的相关信息在全局数组ngx_processes中的下标
        // 父进程使用的socket描述符
        ch.fd = ngx_processes[ngx_process_slot].channel[0];

        /* 父进程fork()生成一个新子进程后，就会立即调用该函数ngx_pass_open_channel()
         * 把这个子进程的相关信息告知给其前面已生成的子进程. */
        ngx_pass_open_channel(cycle, &ch);
    }
}

1.3 ngx_spawn_process

ngx_pid_t ngx_spawn_process(ngx_cycle_t *cycle, ngx_spawn_proc_pt proc, void *data,
                                char *name, ngx_int_t respawn)
{
    u_long     on;
    ngx_pid_t  pid;
    ngx_int_t  s;

    if (respawn >= 0)
    {
        s = respawn;
    }
    else
    {
        /* 遍历所有存活的子进程，找到一个空闲的下标值 */
        for (s = 0; s < ngx_last_process; s++)
        {
            if (ngx_processes[s].pid == -1)
            {
                break;
            }
        }

        if (s == NGX_MAX_PROCESSES)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, 0,
                          "no more than %d processes can be spawned",
                          NGX_MAX_PROCESSES);
            return NGX_INVALID_PID;
        }
    }

    if (respawn != NGX_PROCESS_DETACHED)
    {
        /* Solaris 9 still has no AF_LOCAL */

        /* 采用socketpair()函数创造一对未命名的UNIX域套接字来进行Linux下具有
         * 亲缘关系的进程之间的双向通信. */

        /*
         * 在fork()之前，先调用了socketpair()创建了一对socket描述符存放在变量
         * ngx_processes[s].channel内(其中s标志在ngx_processes数组内第一个可用
         * 元素的下标，比如最开始产生第一个工作进程时，可用元素的下标s为0)，而
         * 在fork()之后，由于子进程继承了父进程的资源，那么父子进程就都有了这一对
         * socket描述符，而Nginx将channel[0]给父进程使用，channel[1]给子进程使用，
         * 这样分别错开地使用不同socket描述符，即可以实现父子进程之间的双向通信.
         */

        if (socketpair(AF_UNIX, SOCK_STREAM, 0, ngx_processes[s].channel) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          "socketpair() failed while spawning \"%s\"", name);
            return NGX_INVALID_PID;
        }

        ngx_log_debug2(NGX_LOG_DEBUG_CORE, cycle->log, 0,
                       "channel: master socket:%d, worker socket:%d",
                       ngx_processes[s].channel[0],
                       ngx_processes[s].channel[1]);

        if (ngx_nonblocking(ngx_processes[s].channel[0]) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          ngx_nonblocking_n " failed while spawning \"%s\"",
                          name);
            ngx_close_channel(ngx_processes[s].channel, cycle->log);
            return NGX_INVALID_PID;
        }

        if (ngx_nonblocking(ngx_processes[s].channel[1]) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          ngx_nonblocking_n " failed while spawning \"%s\"",
                          name);
            ngx_close_channel(ngx_processes[s].channel, cycle->log);
            return NGX_INVALID_PID;
        }

        on = 1;
        if (ioctl(ngx_processes[s].channel[0], FIOASYNC, &on) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          "ioctl(FIOASYNC) failed while spawning \"%s\"", name);
            ngx_close_channel(ngx_processes[s].channel, cycle->log);
            return NGX_INVALID_PID;
        }

        if (fcntl(ngx_processes[s].channel[0], F_SETOWN, ngx_pid) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          "fcntl(F_SETOWN) failed while spawning \"%s\"", name);
            ngx_close_channel(ngx_processes[s].channel, cycle->log);
            return NGX_INVALID_PID;
        }

        if (fcntl(ngx_processes[s].channel[0], F_SETFD, FD_CLOEXEC) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          "fcntl(FD_CLOEXEC) failed while spawning \"%s\"", name);
            ngx_close_channel(ngx_processes[s].channel, cycle->log);
            return NGX_INVALID_PID;
        }

        if (fcntl(ngx_processes[s].channel[1], F_SETFD, FD_CLOEXEC) == -1)
        {
            ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                          "fcntl(FD_CLOEXEC) failed while spawning \"%s\"", name);
            ngx_close_channel(ngx_processes[s].channel, cycle->log);
            return NGX_INVALID_PID;
        }

        /* 记录子进程使用的socket描述符 */
        ngx_channel = ngx_processes[s].channel[1];
    }
    else
    {
        ngx_processes[s].channel[0] = -1;
        ngx_processes[s].channel[1] = -1;
    }

    /* 记录该子进程的相关信息在全局数组中的下标 */
    ngx_process_slot = s;

    pid = fork();

    switch (pid)
    {
    case -1:
        ngx_log_error(NGX_LOG_ALERT, cycle->log, ngx_errno,
                      "fork() failed while spawning \"%s\"", name);
        ngx_close_channel(ngx_processes[s].channel, cycle->log);
        return NGX_INVALID_PID;

    case 0:
        ngx_pid = ngx_getpid(); // 获取该子进程的进程id号
        proc(cycle, data);
        break;

    default:
        break;
    }

    ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "start child %s pid:%P", name, pid);

    ngx_processes[s].pid = pid;  // 记录子进程的pid
    ngx_processes[s].exited = 0;

    if (respawn >= 0)
    {
        return pid;
    }

    ngx_processes[s].proc = proc;
    ngx_processes[s].data = data;
    ngx_processes[s].name = name;
    ngx_processes[s].exiting = 0;

    switch (respawn)
    {
    case NGX_PROCESS_NORESPAWN:
        ngx_processes[s].respawn = 0;
        ngx_processes[s].just_spawn = 0;
        ngx_processes[s].detached = 0;
        break;

    case NGX_PROCESS_JUST_SPAWN:
        ngx_processes[s].respawn = 0;
        ngx_processes[s].just_spawn = 1;
        ngx_processes[s].detached = 0;
        break;

    case NGX_PROCESS_RESPAWN:
        ngx_processes[s].respawn = 1;
        ngx_processes[s].just_spawn = 0;
        ngx_processes[s].detached = 0;
        break;

    case NGX_PROCESS_JUST_RESPAWN:
        ngx_processes[s].respawn = 1;
        ngx_processes[s].just_spawn = 1;
        ngx_processes[s].detached = 0;
        break;

    case NGX_PROCESS_DETACHED:
        ngx_processes[s].respawn = 0;
        ngx_processes[s].just_spawn = 0;
        ngx_processes[s].detached = 1;
        break;
    }

    if (s == ngx_last_process)
    {
        ngx_last_process++;
    }

    return pid;
}

1.4 ngx_worker_process_cycle

/*
 * 参数意义：
 * - cycle是当前进程的ngx_cycle_t结构体指针，这里还未开始使用data参数，所以data一般为NULL
 *
 * 执行意义：
 * 进入worker进程工作的循环
 */
static void ngx_worker_process_cycle(ngx_cycle_t *cycle, void *data)
{
    ngx_int_t worker = (intptr_t) data;

    ngx_process = NGX_PROCESS_WORKER;
    ngx_worker = worker;

    /* 子进程的启动初始化函数 */
    ngx_worker_process_init(cycle, worker);

    /* 设置子进程的进程名 */
    ngx_setproctitle("worker process");

    for ( ;; ) {

        if (ngx_exiting) {
            if (ngx_event_no_timers_left() == NGX_OK) {
                ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "exiting");
                ngx_worker_process_exit(cycle);
            }
        }

        ngx_log_debug0(NGX_LOG_DEBUG_EVENT, cycle->log, 0, "worker cycle");

        /* 最重要的函数：监听并处理事件 */
        ngx_process_events_and_timers(cycle);

        if (ngx_terminate) {
            ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "exiting");
            ngx_worker_process_exit(cycle);
        }

        if (ngx_quit) {
            ngx_quit = 0;
            ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0,
                          "gracefully shutting down");
            ngx_setproctitle("worker process is shutting down");

            if (!ngx_exiting) {
                ngx_exiting = 1;
                ngx_set_shutdown_timer(cycle);
                ngx_close_listening_sockets(cycle);
                ngx_close_idle_connections(cycle);
            }
        }

        if (ngx_reopen) {
            ngx_reopen = 0;
            ngx_log_error(NGX_LOG_NOTICE, cycle->log, 0, "reopening logs");
            ngx_reopen_files(cycle, -1);
        }
    }
}

1.5 ngx_event_accept

每个监听待连接事件的回调函数都是 ngx_event_accept，一旦监听到客户端发来的连接请求，就会调用该回调方法。

致此，就完成了一个连接的建立.