我有两个守护进程,A 正在与 B 通话。B 正在监听一个端口,A 打开到该端口的 tcp 连接。 A 能够打开一个到 B 的套接字,但是当它尝试实际写入所说的套接字时,我得到了一个 SIGPIPE,所以我试图找出 B 可以在哪里关闭打开的套接字。

但是,如果我附加到 gdb 中的两个守护程序,则 SIGPIPE 会在调用任何处理数据的代码之前发生。这种是有道理的,因为初始写入永远不会成功,并且监听器是从接收数据中触发的。我的问题是 - 什么可能导致守护进程 B 在发送任何数据之前关闭套接字?套接字在打开后不到一微秒就关闭了,所以我认为它不可能是超时或任何类似的事情。我很想列出一份可能的 list ,因为我已经研究了几天,而且我几乎没有想法。

根据要求,这里是接受和处理通信的代码:

{
extern char *PAddrToString(pbs_net_t *);

int i;
int n;

time_t now;

fd_set *SelectSet = NULL;
int SelectSetSize = 0;

int MaxNumDescriptors = 0;

char id[] = "wait_request";
char tmpLine[1024];

struct timeval timeout;

long OrigState = 0;

if (SState != NULL)
  OrigState = *SState;

timeout.tv_usec = 0;

timeout.tv_sec  = waittime;

SelectSetSize = sizeof(char) * get_fdset_size();
SelectSet = (fd_set *)calloc(1,SelectSetSize);

pthread_mutex_lock(global_sock_read_mutex);

memcpy(SelectSet,GlobalSocketReadSet,SelectSetSize);

/* selset = readset;*/  /* readset is global */
MaxNumDescriptors = get_max_num_descriptors();

pthread_mutex_unlock(global_sock_read_mutex);
n = select(MaxNumDescriptors, SelectSet, (fd_set *)0, (fd_set *)0, &timeout);

if (n == -1)
  {
  if (errno == EINTR)
    {
    n = 0; /* interrupted, cycle around */
    }
  else
    {
    int i;

    struct stat fbuf;

    /* check all file descriptors to verify they are valid */

    /* NOTE: selset may be modified by failed select() */

    for (i = 0; i < MaxNumDescriptors; i++)
      {
      if (FD_ISSET(i, GlobalSocketReadSet) == 0)
        continue;

      if (fstat(i, &fbuf) == 0)
        continue;

      /* clean up SdList and bad sd... */

      pthread_mutex_lock(global_sock_read_mutex);
      FD_CLR(i, GlobalSocketReadSet);
      pthread_mutex_unlock(global_sock_read_mutex);
      } /* END for each socket in global read set */

    free(SelectSet);

    log_err(errno, id, "Unable to select sockets to read requests");


    return(-1);
    }  /* END else (errno == EINTR) */
  }    /* END if (n == -1) */

for (i = 0; (i < max_connection) && (n != 0); i++)
  {
  pthread_mutex_lock(svr_conn[i].cn_mutex);

  if (FD_ISSET(i, SelectSet))
    {
    /* this socket has data */
    n--;

    svr_conn[i].cn_lasttime = time(NULL);

    if (svr_conn[i].cn_active != Idle)
      {
      void *(*func)(void *) = svr_conn[i].cn_func;

      netcounter_incr();

      pthread_mutex_unlock(svr_conn[i].cn_mutex);

      func((void *)&i);

      /* NOTE:  breakout if state changed (probably received shutdown request) */

      if ((SState != NULL) &&
          (OrigState != *SState))
        break;
      }
    else
      {

      pthread_mutex_lock(global_sock_read_mutex);
      FD_CLR(i, GlobalSocketReadSet);
      pthread_mutex_unlock(global_sock_read_mutex);

      close_conn(i, TRUE);

      pthread_mutex_unlock(svr_conn[i].cn_mutex);
      pthread_mutex_lock(num_connections_mutex);

      sprintf(tmpLine, "closed connections to fd %d - num_connections=%d (select bad socket)",
        i,
        num_connections);

      pthread_mutex_unlock(num_connections_mutex);
      log_err(-1, id, tmpLine);
      }
    }
  else
    pthread_mutex_unlock(svr_conn[i].cn_mutex);
  } /* END for i */

/* NOTE:  break out if shutdown request received */

if ((SState != NULL) && (OrigState != *SState))
  return(0);

/* have any connections timed out ?? */
now = time((time_t *)0);

for (i = 0;i < max_connection;i++)
  {
  struct connection *cp;

  pthread_mutex_lock(svr_conn[i].cn_mutex);

  cp = &svr_conn[i];

  if (cp->cn_active != FromClientDIS)
    {
    pthread_mutex_unlock(svr_conn[i].cn_mutex);

    continue;
    }

  if ((now - cp->cn_lasttime) <= PBS_NET_MAXCONNECTIDLE)
    {
    pthread_mutex_unlock(svr_conn[i].cn_mutex);

    continue;
    }

  if (cp->cn_authen & PBS_NET_CONN_NOTIMEOUT)
    {
    pthread_mutex_unlock(svr_conn[i].cn_mutex);

    continue; /* do not time-out this connection */
    }

  /* NOTE:  add info about node associated with connection - NYI */

  snprintf(tmpLine, sizeof(tmpLine), "connection %d to host %s has timed out after %d seconds - closing stale connection\n",
    i,
    PAddrToString(&cp->cn_addr),
    PBS_NET_MAXCONNECTIDLE);

  log_err(-1, "wait_request", tmpLine);

  /* locate node associated with interface, mark node as down until node responds */
  /* NYI */
  close_conn(i, TRUE);

  pthread_mutex_unlock(svr_conn[i].cn_mutex);
  }  /* END for (i) */

return(0);
}

注意:我没有写这段代码。

最佳答案

有没有可能你搞砸了,在程序的其他地方你试图关闭同一个句柄两次?

那可以很容易地对你做到这一点。

提示:systrace 可以确定这是否正在发生。

关于c - 带运行程序的 SIGPIPE,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/8040945/

10-12 20:07