Crazy idea, but have you tried changing the Ethernet cable? A dodgy cable can cause L1 issues.
Lloyd Kirill A. Korinsky wrote: > On Sun, 08 Jun 2025 19:33:51 +0200, > "H. Hartzer" h...@hartzer.sh wrote: > > > Jarod Watkins wrote: > > > > > Hi Jon, > > > Great questions and something I should have included in my original post. > > > The Linux firewall is still in place (it is VYOS, and running on similar > > > hardware). It is connected to a Brocade ICX-6450 switch trunked with > > > various VLANs. In order to do a “hot swap” I wanted to initially > > > configure OpenBSD and then switch them out. So my Internet interface > > > (em0) on OpenBSD is connected to one VLAN (172.31.1.0/24 subnet) and what > > > will become my transit VLAN is on em1 (I’m moving all my inter vlan > > > routing to the switch). All connections are wired, copper, and gigabit. > > > > > > Whether I ping the switch virtual interface (10.255.255.2) or another > > > wired client in VLAN 10 from OpenBSD, I see varying ping times. I also > > > see the same results going in the other direction (pinging OpenBSD from > > > the switch or other wired clients). If I ping any other wired host on my > > > VLAN 10 network from the router or any other host, I do not see this > > > issue. My pings are routinely sub millisecond. That is why this through > > > me off guard. I was not expecting to see this kind of variability on my > > > local network with this kind of hardware. > > > > > > Here is an example ping from a wired Linux box on my networking pinging > > > the router: > > > > > > $ ping 172.31.1.1 > > > PING 172.31.1.1 (172.31.1.1) 56(84) bytes of data. > > > 64 bytes from 172.31.1.1: icmp_seq=1 ttl=64 time=0.219 ms > > > 64 bytes from 172.31.1.1: icmp_seq=2 ttl=64 time=0.213 ms > > > 64 bytes from 172.31.1.1: icmp_seq=3 ttl=64 time=0.168 ms > > > 64 bytes from 172.31.1.1: icmp_seq=4 ttl=64 time=0.228 ms > > > 64 bytes from 172.31.1.1: icmp_seq=5 ttl=64 time=0.216 ms > > > 64 bytes from 172.31.1.1: icmp_seq=6 ttl=64 time=0.292 ms > > > 64 bytes from 172.31.1.1: icmp_seq=7 ttl=64 time=0.217 ms > > > 64 bytes from 172.31.1.1: icmp_seq=8 ttl=64 time=0.227 ms > > > 64 bytes from 172.31.1.1: icmp_seq=9 ttl=64 time=0.222 ms > > > ^C > > > --- 172.31.1.1 ping statistics --- > > > 9 packets transmitted, 9 received, 0% packet loss, time 8179ms > > > rtt min/avg/max/mdev = 0.168/0.222/0.292/0.029 ms > > > > > > And the same ping from OpenBSD: > > > > > > bsd# ping 172.31.1.1 > > > PING 172.31.1.1 (172.31.1.1): 56 data bytes > > > 64 bytes from 172.31.1.1: icmp_seq=0 ttl=64 time=3.744 ms > > > 64 bytes from 172.31.1.1: icmp_seq=1 ttl=64 time=3.585 ms > > > 64 bytes from 172.31.1.1: icmp_seq=2 ttl=64 time=4.743 ms > > > 64 bytes from 172.31.1.1: icmp_seq=3 ttl=64 time=0.978 ms > > > 64 bytes from 172.31.1.1: icmp_seq=4 ttl=64 time=4.548 ms > > > > > > Thanks, > > > Jarod > > > > Hi Jarod, > > > > I agree that this is off. I've pretty much universally seen sub-ms pings > > on ethernet, at least gigabit ethernet, for a very long time. > > > > I have been wanting to setup an OpenBSD router for a while. I hope to > > report back on my findings, but I'm not sure when I'll have the time to > > do this. > > > For what it worh here a ping from: > > hw.machine=octeon > hw.model=Cavium OCTEON (rev 0.1) @ 500 MHz > > both machines is connected via 1G Ethernet on the same switch. > > octeon$ ping -c 10 172.31.2.1 > PING 172.31.2.1 (172.31.2.1): 56 data bytes > 64 bytes from 172.31.2.1: icmp_seq=0 ttl=255 time=1.046 ms > 64 bytes from 172.31.2.1: icmp_seq=1 ttl=255 time=0.999 ms > 64 bytes from 172.31.2.1: icmp_seq=2 ttl=255 time=10.170 ms > 64 bytes from 172.31.2.1: icmp_seq=3 ttl=255 time=0.907 ms > 64 bytes from 172.31.2.1: icmp_seq=4 ttl=255 time=0.808 ms > 64 bytes from 172.31.2.1: icmp_seq=5 ttl=255 time=7.992 ms > 64 bytes from 172.31.2.1: icmp_seq=6 ttl=255 time=0.809 ms > 64 bytes from 172.31.2.1: icmp_seq=7 ttl=255 time=0.818 ms > 64 bytes from 172.31.2.1: icmp_seq=8 ttl=255 time=10.170 ms > 64 bytes from 172.31.2.1: icmp_seq=9 ttl=255 time=0.803 ms > > --- 172.31.2.1 ping statistics --- > 10 packets transmitted, 10 packets received, 0.0% packet loss > round-trip min/avg/max/std-dev = 0.803/3.452/10.170/3.963 ms > octeon$ > > -- > wbr, Kirill
