Nginx-ru mailing list archive (nginx-ru@sysoev.ru)
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: Software caused connection abort
On Tue, Jul 19, 2005 at 10:51:25PM +0400, Igor Sysoev wrote:
> On Tue, 19 Jul 2005, Konstantin N. Bezruchenko wrote:
>
> >On Fri, Jul 08, 2005 at 03:59:45PM +0400, Igor Sysoev wrote:
> >Скорее всего не клиент.
> >Сейчас возникла интересная ситуация. В логе постоянно вижу
> >
> >2005/07/19 18:04:18 [crit] 34462#0: accept() on 192.168.1.1:80 failed (53:
> >Software caused connection abort)
[skip]
> >Трафик упал в двое (было 60 мегабит, стало 30)
> >Поробовал перезапустить Nginx - результат 0
> >
> >5.4-STABLE FreeBSD 5.4-STABLE #0: Wed Jul 13 02:16:38 CEST 2005
>
> А что показывают
> ps ax -o pid,ppid,%cpu,vsz,wchan,command|egrep '(nginx|PID)'
> и
> netstat -m ?
Скорее всего надо задирать mbufs, что-то нереально много в current :-Возможна ли была ситуация с Software caused connection abort если mbufs
мало?
# netstat -m
346113 mbufs in use
46988/32768 mbuf clusters in use (current/max)
4209/4838/32768 sfbufs in use (current/peak/max)
180504 KBytes allocated to network
0 requests for sfbufs denied
0 requests for sfbufs delayed
29617 requests for I/O initiated by sendfile
0 calls to protocol drain routines
# ps ax -o pid,ppid,%cpu,vsz,wchan,command|egrep '(nginx|PID)'
PID PPID %CPU VSZ WCHAN COMMAND
453 1 0.0 1692 pause nginx: master process /usr/local/nginx/sbin/nginx
456 453 0.0 2544 kqread nginx: worker process (nginx)
457 453 0.0 2520 kqread nginx: worker process (nginx)
458 453 0.0 2648 kqread nginx: worker process (nginx)
459 453 0.0 2632 kqread nginx: worker process (nginx)
460 453 0.0 2484 kqread nginx: worker process (nginx)
462 453 0.0 2612 kqread nginx: worker process (nginx)
463 453 0.0 2680 kqread nginx: worker process (nginx)
464 453 0.0 2604 kqread nginx: worker process (nginx)
2814 601 0.0 1416 - egrep (nginx|PID)
--
Konstantin N. Bezruchenko, BK5536-RIPE
|
