igb + lagg + vlan + bridge broken in -CURRENT?

I have a -CURRENT system where the networking is kind of convoluted. The native networking on the machine itself is across 4 cxl(4) interfaces + lagg(4) + if_bridge(4). The host itself and the few bhyve VMs on that bridge are still working fine. There is also a 2 igb(4) interfaces + lagg(4) + vlan

Re: Wireguard, MTUs, and jumbo packets

On Tue, Apr 5, 2022 at 9:46 AM wrote: > > Interesting. That 60 byte overhead (which I understand is intended > to make the protocol connectionless) is concerning, because to send > a 1500 byte packet one needs to have enabled jumbo packets along > the entire path. Otherwise, there will be a lot of

Re: Weirdness with same-host IPv6 packets

22150 IP6 (flowlabel 0x9b06b, hlim 64, next-header TCP (6) payload length: 32) 2001:470:bc52:4::101.55029 > 2001:470:bc52:4::101.: Flags [.], cksum 0xc3b7 (incorrect -> 0x4577), ack 2, win 4, options [nop,nop,TS val 194211436 ecr 2005091770], length 0 Any ideas on how to further troublesho

Weirdness with same-host IPv6 packets

I'm seeing a weird issue with -CURRENT that I don't recall seeing before. It started at least a couple of weeks back and a new build from yesterday still shows it. UDP packets inside a host using the host's non-loopback address seems to get dropped. TCP does work, however there's a delay, almost li

Re: 10 Gbps NIC - advice needed

I second the recommendation for Chelsio. I had brand new retail Intel 40GE NICs (4 x 10GE) and I got so frustrated with the bugs that I sold them used on eBay just to recoup some of the cost. -Dustin On Thu, Aug 29, 2019 at 6:41 AM Robert Heron wrote: > > Hi, > > I need to use a 10 Gbps, 2 port

Re: Chelsio TOE not working in CURRENT

That worked! Thanks for the fast fix! -Dustin On Fri, Mar 29, 2019 at 11:44 AM Navdeep Parhar wrote: > > Fixed in r345701. > > > On 2019-03-28 22:59, Dustin Marquess wrote: > > On a brand new CURRENT Chelsio (cxl) TOE doesn't work, as loading the > > dependent

Chelsio TOE not working in CURRENT

On a brand new CURRENT Chelsio (cxl) TOE doesn't work, as loading the dependent t4_tom module fails: If VIMAGE is enabled: link_elf_obj: symbol vnet_entry_tcp_autorcvbuf_inc undefined linker_load_file: /boot/kernel/t4_tom.ko - unsupported file type If VIMAGE isn't enabled: link_elf_obj: symbol

Re: lagg interface doesn't work

On Wed, Oct 4, 2017 at 3:25 PM, Rainer Duffner wrote: > Hi, > > I’m trying to get a lagg(4) setup going. > > This has previously been a linux host, which had to be replace on short > notice. > > I’ve rarely used lagg(4). > > > Basically, we have two trunk-ports with a bunch of clans that needs to

Re: Changing MTU on cxgbe

Okay, so ya, I'm stupid. The MTU won't change w/ ifconfig on the command line because of the lagg/bridge. The real issue seems to be ifconfig ordering, eg: ifconfig_cxgbe0="mtu 9000 toe4 toe6 up" Works ifconfig_cxgbe0="toe4 toe6 mtu 9000 up" Does NOT. So that's what was biting me in the butt

Re: Changing MTU on cxgbe

I tried setting it via ifconfig_cxgbe0 in rc.conf, but that didn't seem to work either. -Dustin On Thu, May 26, 2016 at 9:57 PM -0700, "Garrett Wollman" wrote: In article you write: ># ifconfig -m cxgbe0 >cxgbe0: flags=8943 ># ifconfig cxgbe0 mtu 9000 >ifconfig: ioctl SIOCSIFMT

Changing MTU on cxgbe

After my many issues with ixgbe & ixv, I ended up removing the Intel X520s with Chelsio T420-CR and the Intel X710s with Chelsio T520-CR. So far so good, except I can't seem to change the MTU away from 1500. In fact, ifconfig can't seem to change the mtu at all. On -CURRENT as of yesterday: # ifc

Re: Issues with ixl(4)

stin On Thu, Apr 21, 2016 at 4:52 PM, K. Macy wrote: > > > On Wednesday, April 20, 2016, Dustin Marquess wrote: >> >> I tried backing out that change and everything worked for a few minutes >> and then started acting up again. Then I notice Sean Bruno's "TCP

Re: Issues with ixl(4)

I tried backing out that change and everything worked for a few minutes and then started acting up again. Then I notice Sean Bruno's "TCP Packets Drop!!!" email about LACP. I disabled LACP on the switch side and then changed the lagg config from "lacp" to "roundrobin", and so far so good. On the

Re: aliases & netmasks, WAS: Issues with ixl(4)

me after this change. I have a bad feeling that changing the network mask on the alias is causing other issues. Was there some recent change in -CURRENT that would have caused this? Thanks! -Dustin On Mon, Apr 18, 2016 at 11:06 PM, Dustin Marquess wrote: > I'm having some strange issues

Issues with ixl(4)

I'm having some strange issues with ixl(4) and a X710-DA4 card in a new-ish Intel-based server. I'm pretty much replicating an existing setup from an older AMD machine that used 2 x X520-DA2 cards and ixgbe(4). This is all on -CURRENT. It's meant to be a bhyve server, so the 4x10GE ports are put