On Sat, Aug 28, 2004 at 12:03:37AM +0200, roberto wrote:
> On NETBSD20 without VPN
> # ping 10.1.1.10
> PING 10.1.1.10 (10.1.1.10): 56 data bytes
> 64 bytes from 10.1.1.10: icmp_seq=0 ttl=128 time=8.989 ms
> ...
> ----10.1.1.10 PING Statistics----
> 11 packets transmitted, 11 packets received, 0.0% packet loss
> round-trip min/avg/max/stddev = 0.406/1.276/8.989/2.561 ms
> 
> On NETBSD20 WITH VPN
> # ping 172.1.1.9
> PING 172.1.1.9 (172.1.1.9): 56 data bytes
> 64 bytes from 172.1.1.9: icmp_seq=0 ttl=128 time=8.308 ms
> ...
> ----172.1.1.9 PING Statistics----
> 13 packets transmitted, 13 packets received, 0.0% packet loss
> round-trip min/avg/max/stddev = 0.942/1.782/8.308/1.967 ms

OK, it's not a RTT problem then. I don't have more idea, sorry

> 
> On NetBSD162 WITHOUT VPN
> batuffolo:/root> ping 10.1.1.1
> PING 10.1.1.1 (10.1.1.1): 56 data bytes
> 64 bytes from 10.1.1.1: icmp_seq=0 ttl=255 time=0.063 ms
> ...
> ----10.1.1.1 PING Statistics----
> 21 packets transmitted, 21 packets received, 0.0% packet loss
> round-trip min/avg/max/stddev = 0.063/0.109/0.168/0.028 ms
> batuffolo:/root>
> 
> On NetBSD162 WITH VPN (I leave the full output cause some strange negative
> time value)
> batuffolo:/root> ping 172.1.1.3
> PING 172.1.1.3 (172.1.1.3): 56 data bytes
> 64 bytes from 172.1.1.3: icmp_seq=0 ttl=128 time=7.843 ms
> 64 bytes from 172.1.1.3: icmp_seq=1 ttl=128 time=1.238 ms
> 64 bytes from 172.1.1.3: icmp_seq=2 ttl=128 time=0.921 ms
> 64 bytes from 172.1.1.3: icmp_seq=3 ttl=128 time=1.379 ms
> 64 bytes from 172.1.1.3: icmp_seq=4 ttl=128 time=0.948 ms
> 64 bytes from 172.1.1.3: icmp_seq=5 ttl=128 time=-9.008 ms
> 64 bytes from 172.1.1.3: icmp_seq=6 ttl=128 time=0.980 ms
> 64 bytes from 172.1.1.3: icmp_seq=7 ttl=128 time=1.072 ms
> 64 bytes from 172.1.1.3: icmp_seq=8 ttl=128 time=1.114 ms
> 64 bytes from 172.1.1.3: icmp_seq=9 ttl=128 time=0.928 ms
> 64 bytes from 172.1.1.3: icmp_seq=10 ttl=128 time=-9.114 ms
> 64 bytes from 172.1.1.3: icmp_seq=11 ttl=128 time=1.071 ms
> 64 bytes from 172.1.1.3: icmp_seq=12 ttl=128 time=1.109 ms
> 64 bytes from 172.1.1.3: icmp_seq=13 ttl=128 time=1.213 ms
> 64 bytes from 172.1.1.3: icmp_seq=14 ttl=128 time=1.020 ms
> 64 bytes from 172.1.1.3: icmp_seq=15 ttl=128 time=0.932 ms
> 64 bytes from 172.1.1.3: icmp_seq=16 ttl=128 time=0.946 ms
> 64 bytes from 172.1.1.3: icmp_seq=17 ttl=128 time=1.012 ms
> 64 bytes from 172.1.1.3: icmp_seq=18 ttl=128 time=-9.080 ms
> 64 bytes from 172.1.1.3: icmp_seq=19 ttl=128 time=1.067 ms
> 64 bytes from 172.1.1.3: icmp_seq=20 ttl=128 time=1.311 ms
> ^C
> ----172.1.1.3 PING Statistics----
> 21 packets transmitted, 21 packets received, 0.0% packet loss
> round-trip min/avg/max/stddev = -9.114/-0.052/7.843/4.050 ms
> batuffolo:/root>
> 
> N.B.: the previous tests were made on the same (my home) PC with 2 Netbsd
> on VMWare cause I'm not in office. As the transfer rate on the VMWare is
> the same I suppose the RTT similar to real PC to PC;

Was the last one (with negative values) done on wmware too ?
Maybe wmware could explain the negative values ...

-- 
Manuel Bouyer <bouyer@antioche.eu.org>
     NetBSD: 26 ans d'experience feront toujours la difference
--