void signal_handler_init() { 
  // Create a signalling mechanism for SIGCHLD. 
  int s[2]; 
  //socketpair()创造一对未命名的、相互连接的UNIX域套接字 
  if (socketpair(AF_UNIX, SOCK_STREAM | SOCK_NONBLOCK | SOCK_CLOEXEC, 0, s) == -1) { 
    ERROR("socketpair failed: %s\n", strerror(errno)); 
    exit(1); 
  } 
 
  signal_write_fd = s[0]; 
  signal_read_fd = s[1]; 
 
  // Write to signal_write_fd if we catch SIGCHLD. 
  struct sigaction act; 
  memset(&act, 0, sizeof(act)); 
  act.sa_handler = SIGCHLD_handler;//设置信号处理函数句柄,当有信号产生时,会向上面创建的socket写入数据,epoll监控到该socket对中的fd可读时,就会调用注册的函数去处理该事件 
  act.sa_flags = SA_NOCLDSTOP;//设置标志,表示只有当子进程终止时才接受SIGCHID信号 
  sigaction(SIGCHLD, &act, 0);//初始化SIGCHLD信号处理方式 
 
  reap_any_outstanding_children();//处理这之前退出的子进程 
  register_epoll_handler(signal_read_fd, handle_signal); 
} 

static void SIGCHLD_handler(int) { 
  if (TEMP_FAILURE_RETRY(write(signal_write_fd, "1", 1)) == -1) { 
    ERROR("write(signal_write_fd) failed: %s\n", strerror(errno)); 
  } 
}

#define TEMP_FAILURE_RETRY(exp)      \ 
 ({                    \ 
  decltype(exp) _rc;           \ 
  do {                  \ 
   _rc = (exp);             \ 
  } while (_rc == -1 && errno == EINTR); \ 
  _rc;                  \ 
 }) 

static void reap_any_outstanding_children() { 
  while (wait_for_one_process()) { 
  } 
} 

register_epoll_handler(signal_read_fd, handle_signal); 

void register_epoll_handler(int fd, void (*fn)()) { 
  epoll_event ev; 
  ev.events = EPOLLIN;//对文件描述符可读 
  ev.data.ptr = reinterpret_cast<void*>(fn);//保存指定的函数指针,用于后续的事件处理 
  if (epoll_ctl(epoll_fd, EPOLL_CTL_ADD, fd, &ev) == -1) {//向epoll_fd添加要监听的fd,比如property、keychord和signal事件监听 
    ERROR("epoll_ctl failed: %s\n", strerror(errno)); 
  } 
} 

static void handle_signal() { 
  // Clear outstanding requests. 
  char buf[32]; 
  read(signal_read_fd, buf, sizeof(buf)); 
 
  reap_any_outstanding_children(); 
} 

static void reap_any_outstanding_children() { 
  while (wait_for_one_process()) { 
  } 
} 

static bool wait_for_one_process() { 
  int status; 
  pid_t pid = TEMP_FAILURE_RETRY(waitpid(-1, &status, WNOHANG));//等待子进程结束,并获取到它的pid进程号,WNOHANG表明若没有进程结束,则立即返回. 
  if (pid == 0) { 
    return false; 
  } else if (pid == -1) { 
    ERROR("waitpid failed: %s\n", strerror(errno)); 
    return false; 
  } 
 
  service* svc = service_find_by_pid(pid);//根据pid,在链表中找到这个服务信息 
 
  std::string name; 
  if (svc) { 
    name = android::base::StringPrintf("Service '%s' (pid %d)", svc->name, pid); 
  } else { 
    name = android::base::StringPrintf("Untracked pid %d", pid); 
  } 
 
  NOTICE("%s %s\n", name.c_str(), DescribeStatus(status).c_str()); 
 
  if (!svc) { 
    return true; 
  } 
 
  // TODO: all the code from here down should be a member function on service. 
  //如果该服务进程没有设定SVC_ONESHOT标志,或者设置了SVC_RESTART标志,则先杀掉当前的进程,在重新创建新的进程; 
  //以避免后面重启进程时,因当前服务进程已经存在而发生错误. 
  if (!(svc->flags & SVC_ONESHOT) || (svc->flags & SVC_RESTART)) { 
    NOTICE("Service '%s' (pid %d) killing any children in process group\n", svc->name, pid); 
    kill(-pid, SIGKILL); 
  } 
 
  // Remove any sockets we may have created. 
  //如果之前为这个服务进程创建过socket,这时我们需要清除掉该socket 
  for (socketinfo* si = svc->sockets; si; si = si->next) { 
    char tmp[128]; 
    snprintf(tmp, sizeof(tmp), ANDROID_SOCKET_DIR"/%s", si->name); 
    unlink(tmp);//删除这个socket设备文件 
  } 
 
  if (svc->flags & SVC_EXEC) {////服务完全退出,清除掉所有信息,并将该服务从svc-slist中移除 
    INFO("SVC_EXEC pid %d finished...\n", svc->pid); 
    waiting_for_exec = false; 
    list_remove(&svc->slist); 
    free(svc->name); 
    free(svc); 
    return true; 
  } 
 
  svc->pid = 0; 
  svc->flags &= (~SVC_RUNNING); 
 
  // Oneshot processes go into the disabled state on exit, 
  // except when manually restarted. 
  //如果该服务进程带有SVC_ONESHOT标志,且没有SVC_RESTART标志,则表明该服务无需重启 
  if ((svc->flags & SVC_ONESHOT) && !(svc->flags & SVC_RESTART)) { 
    svc->flags |= SVC_DISABLED; 
  } 
 
  // Disabled and reset processes do not get restarted automatically. 
  //如果服务带有SVC_RESET标志,表示服务无需重启 
  if (svc->flags & (SVC_DISABLED | SVC_RESET)) {//从结果看SVC_RESET标志的判断优先级最高 
    svc->NotifyStateChange("stopped"); 
    return true; 
  } 
 
  //到此,我们可以得知一个服务进程在init.rc中只要没有声明SVC_ONESHOT和SVC_RESET标志,当该进程死亡时，就会被重启; 
  //但是,如果一个服务进程带有SVC_CRITICAL标志,且没有SVC_RESTART标志,当它crash、重启的次数超过4此时,系统会自动重启并进入recovery模式 
  time_t now = gettime(); 
  if ((svc->flags & SVC_CRITICAL) && !(svc->flags & SVC_RESTART)) { 
    if (svc->time_crashed + CRITICAL_CRASH_WINDOW >= now) { 
      if (++svc->nr_crashed > CRITICAL_CRASH_THRESHOLD) { 
        ERROR("critical process '%s' exited %d times in %d minutes; " 
           "rebooting into recovery mode\n", svc->name, 
           CRITICAL_CRASH_THRESHOLD, CRITICAL_CRASH_WINDOW / 60); 
        android_reboot(ANDROID_RB_RESTART2, 0, "recovery"); 
        return true; 
      } 
    } else { 
      svc->time_crashed = now; 
      svc->nr_crashed = 1; 
    } 
  } 
 
  svc->flags &= (~SVC_RESTART); 
  svc->flags |= SVC_RESTARTING;//为服务加上重启标志,表明它需要重启;后续工作要以此判断 
 
  // Execute all onrestart commands for this service. 
  struct listnode* node; 
  list_for_each(node, &svc->onrestart.commands) {//如果服务有onrestart选项,则遍历进程重启时需要执行的命令列表,并执行 
    command* cmd = node_to_item(node, struct command, clist); 
    cmd->func(cmd->nargs, cmd->args); 
  } 
  svc->NotifyStateChange("restarting"); 
  return true; 
} 

while (true) { 
   if (!waiting_for_exec) { 
     execute_one_command();//执行命令列表中的命令 
     restart_processes();//启动服务列表中的进程 
   } 
 
   int timeout = -1; 
   if (process_needs_restart) { 
     timeout = (process_needs_restart - gettime()) * 1000; 
     if (timeout < 0) 
       timeout = 0; 
   } 
 
   if (!action_queue_empty() || cur_action) { 
     timeout = 0; 
   } 
 
   bootchart_sample(&timeout);//bootchart是一个用可视化方式对启动过程进行性能分析的工具;需要定时唤醒进程 
 
   epoll_event ev; 
   int nr = TEMP_FAILURE_RETRY(epoll_wait(epoll_fd, &ev, 1, timeout));//开始轮询,epoll_wait()等待事件产生 
   if (nr == -1) { 
     ERROR("epoll_wait failed: %s\n", strerror(errno)); 
   } else if (nr == 1) { 
     ((void (*)()) ev.data.ptr)();//调用epoll_event事件存储的函数指针处理事件 
   } 
 } 

static void restart_processes() 
{ 
  process_needs_restart = 0; 
  service_for_each_flags(SVC_RESTARTING, 
              restart_service_if_needed); 
} 
 
void service_for_each_flags(unsigned matchflags, 
              void (*func)(struct service *svc)) 
{ 
  struct listnode *node; 
  struct service *svc; 
  list_for_each(node, &service_list) { 
    svc = node_to_item(node, struct service, slist); 
    if (svc->flags & matchflags) { 
      func(svc); 
    } 
  } 
}

static void restart_service_if_needed(struct service *svc) 
{ 
  time_t next_start_time = svc->time_started + 5; 
 
  if (next_start_time <= gettime()) { 
    svc->flags &= (~SVC_RESTARTING); 
    service_start(svc, NULL); 
    return; 
  } 
 
  if ((next_start_time < process_needs_restart) || 
    (process_needs_restart == 0)) { 
    process_needs_restart = next_start_time; 
  } 
}