Unstable ARP responses times

[Jeremy Chadwick]

On Fri, May 13, 2011 at 02:48:01PM +0200, Bartosz Woronicz wrote:
> Since I moved from 7.3-stable to 8.2-stable I go strange long
> responses of arp, with arping.
> I.e.
> root at Korbotron82|pts/3|13:35:35|/home/mastier # arping -i vlan92
> 79.110.194.140
> ARPING 79.110.194.140
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=0 time=1.579 msec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=1 time=653.326 msec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=2 time=7.153 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=3 time=6.199 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=4 time=6.199 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=5 time=5.960 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=6 time=7.153 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=7 time=5.960 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=8 time=6.199 usec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=9 time=280.132 msec
> 60 bytes from 00:15:17:a2:ea:38 (79.110.194.140): index=10
> time=120.429 msec
> ^C
> --- 79.110.194.140 statistics ---
> 18 packets transmitted, 11 packets received,  39% unanswered (0 extra)
> root at Korbotron82|pts/3|13:36:06|/home/mastier # ping 79.110.194.140
> PING 79.110.194.140 (79.110.194.140): 56 data bytes
> 64 bytes from 79.110.194.140: icmp_seq=0 ttl=64 time=0.348 ms
> 64 bytes from 79.110.194.140: icmp_seq=1 ttl=64 time=0.204 ms
> 64 bytes from 79.110.194.140: icmp_seq=2 ttl=64 time=0.171 ms
> 64 bytes from 79.110.194.140: icmp_seq=3 ttl=64 time=0.223 ms
> 64 bytes from 79.110.194.140: icmp_seq=4 ttl=64 time=0.283 ms
> 64 bytes from 79.110.194.140: icmp_seq=5 ttl=64 time=0.322 ms
> 64 bytes from 79.110.194.140: icmp_seq=6 ttl=64 time=0.250 ms
> ^C
> --- 79.110.194.140 ping statistics ---
> 7 packets transmitted, 7 packets received, 0.0% packet loss
> round-trip min/avg/max/stddev = 0.171/0.257/0.348/0.059 ms
> 
> Any Idea what does mean ?

Can you try turning off flowtable to see if that makes any difference?
This is a sysctl and can be adjusted in real-time.

net.inet.flowtable.enable=0

Thanks.

-- 
| Jeremy Chadwick                                   jdc at parodius.com |
| Parodius Networking                       http://www.parodius.com/ |
| UNIX Systems Administrator                  Mountain View, CA, USA |
| Making life hard for others since 1977.               PGP 4BD6C0CB |