Unstable ARP responses times

[Bartosz Woronicz]

W dniu 13.05.2011 20:10, Jeremy Chadwick pisze:
> 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.
>
It is already turned off

# sysctl net.inet.flowtable.enable
net.inet.flowtable.enable: 0

Also trurning it on doesn't make much difference
# sysctl net.inet.flowtable.enable=1
net.inet.flowtable.enable: 0 -> 1


# arping -i vlan50 10.6.56.160
ARPING 10.6.56.160
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=0 time=2.147 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=1 time=174.050 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=2 time=221.634 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=3 time=283.422 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=4 time=525.137 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=5 time=663.274 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=6 time=213.200 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=7 time=660.249 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=8 time=589.227 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=9 time=378.279 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=10 time=624.204 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=11 time=158.019 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=12 time=6.169 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=13 time=4.587 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=14 time=2.722 msec
60 bytes from 00:08:a1:9b:47:af (10.6.56.160): index=15 time=82.936 msec



-- 
Pozdrawiam,
Bartosz Woronicz, System Adminstrator,
Korbank S.A.
ul. Nabycińska 19
53-677 Wrocław
NIP: 894-26-41-602
tel. 071-723-43-23
fax. 071-723-43-29