Thanks for your input. In the interim, I have actually implemented your second (harder) option and it appears to be working quite well. I am still testing but it does look promising.
Kim > On Sep 26, 2022, at 10:05 AM, Vincenzo Maffione <vmaffi...@freebsd.org> wrote: > > I think you could avoid any modifications to lb(8) and take advantage of the > "multiple pipe groups" feature. > You open two groups, > # lb -i netmap:em0/R -p mon:$N -p fwd:$M [...] > Each group receives all the packets arriving on the RX (NIC) rings of em0. > (I'm pretty sure) this happens without packet copies, i.e. by swapping netmap > slots. > > The first group (mon) is for your existing monitor process. The second one > (fwd) would be used for a separate process that handles the host stack: > - It reads from fwd:$M pipes, selecting only the RX packets that should be > forwarded to the host stack. Selected packets will be forwarded to > netmap:em0^/T. All the other packets are just dropped. > - it forwards all traffic from netmap:em0^/R to netmap:em0/T (e.g. from the > em0 host RX ring to the em0 TX rings). Keep in mind that lb does not touch > em0 TX rings, so there would not be conflicts. In any case, it is good > practice to have lb only open RX rings (netmap:em0/R). > This second process can probably be a modified version of the netmap bridge, > although you have asymmetric three-party forwarding here (fwd/R --> > netmap:em0^T, netmap:em0^/R --> netmap:em0/T). > > The alternative (harder) option would be to actually modify lb(8). You should > probably: > - open netmap:em0^/R and netmap:em0*/T with separate nmport_open() calls > - parse the packet before pkt_hdr_hash() to select the RX packets that you > need to forward to the host TX ring, and modify the forwarding logic to > perform this task. > - modify the logic of the lb poll() loop so that it also performs the > forwarding from host RX rings to NIC TX rings > I'm not sure that you would have any advantages by choosing this path. > > Cheers, > Vincenzo >
