[FUG-BR] Problema com rede (no buffer space)

[Fabiano Carlos Heringer]

Pessoal, to com um problema que tá me tirando o sono,

de uma hora pra outra, meu gateway um FreeBSD8.0-RELEASE começa a ficar 
com os pings nas alturas, para qualquer estacao da rede...

PING 10.0.0.29 (10.0.0.29): 56 data bytes
64 bytes from 10.0.0.29: icmp_seq=0 ttl=128 time=60.318 ms
64 bytes from 10.0.0.29: icmp_seq=1 ttl=128 time=285.742 ms
64 bytes from 10.0.0.29: icmp_seq=2 ttl=128 time=316.280 ms
64 bytes from 10.0.0.29: icmp_seq=3 ttl=128 time=297.772 ms
64 bytes from 10.0.0.29: icmp_seq=4 ttl=128 time=252.032 ms
64 bytes from 10.0.0.29: icmp_seq=5 ttl=128 time=198.022 ms
64 bytes from 10.0.0.29: icmp_seq=6 ttl=128 time=300.550 ms
64 bytes from 10.0.0.29: icmp_seq=7 ttl=128 time=362.574 ms
64 bytes from 10.0.0.29: icmp_seq=8 ttl=128 time=306.901 ms
64 bytes from 10.0.0.29: icmp_seq=9 ttl=128 time=351.775 ms
64 bytes from 10.0.0.29: icmp_seq=10 ttl=128 time=426.242 ms
64 bytes from 10.0.0.29: icmp_seq=11 ttl=128 time=387.190 ms
64 bytes from 10.0.0.29: icmp_seq=12 ttl=128 time=208.324 ms
64 bytes from 10.0.0.29: icmp_seq=13 ttl=128 time=220.007 ms
64 bytes from 10.0.0.29: icmp_seq=14 ttl=128 time=190.634 ms
64 bytes from 10.0.0.29: icmp_seq=15 ttl=128 time=302.118 ms
64 bytes from 10.0.0.29: icmp_seq=16 ttl=128 time=181.868 ms
64 bytes from 10.0.0.29: icmp_seq=17 ttl=128 time=280.190 ms
64 bytes from 10.0.0.29: icmp_seq=19 ttl=128 time=288.460 ms
64 bytes from 10.0.0.29: icmp_seq=20 ttl=128 time=191.378 ms
ping: sendto: No buffer space available
64 bytes from 10.0.0.29: icmp_seq=21 ttl=128 time=459.408 ms
64 bytes from 10.0.0.29: icmp_seq=22 ttl=128 time=354.824 ms
64 bytes from 10.0.0.29: icmp_seq=23 ttl=128 time=227.251 ms
64 bytes from 10.0.0.29: icmp_seq=24 ttl=128 time=243.110 ms
64 bytes from 10.0.0.29: icmp_seq=25 ttl=128 time=399.936 ms

se eu pingar entre estacoes fica tudo normal, sinal que o problema é com 
gateway, sem regras de controle, sem PF ativado.

meus buffers:

400/920/1320 mbufs in use (current/cache/total)
398/718/1116/32768 mbuf clusters in use (current/cache/total/max)
397/245 mbuf+clusters out of packet secondary zone in use (current/cache)
0/239/239/16384 4k (page size) jumbo clusters in use 
(current/cache/total/max)
0/0/0/8192 9k jumbo clusters in use (current/cache/total/max)
0/0/0/4096 16k jumbo clusters in use (current/cache/total/max)
896K/2622K/3518K bytes allocated to network (current/cache/total)
0/0/0 requests for mbufs denied (mbufs/clusters/mbuf+clusters)
0/0/0 requests for jumbo clusters denied (4k/9k/16k)
0/7/6656 sfbufs in use (current/peak/max)
0 requests for sfbufs denied
0 requests for sfbufs delayed
0 requests for I/O initiated by sendfile
0 calls to protocol drain routines


Minha interface é uma 3com 3c509.

Alguma sugestao?

Obrigado