state of packet forwarding in FreeBSD?

[Vincenzo Maffione]

Some comments inline:

2017-06-16 14:13 GMT+02:00 Jordan Caraballo <jordancaraballo87 at gmail.com>:

> Hi guys,
>
> We tried multiple attempts to implement netmap vale-ctl and bridge in
> chelsio vcxl* interfaces. The most interesting attempts, are mentioned
> below.
>
> First Attempt: Ran "./bridge vcxl0 vcxl1"; but it would complain about
> having a 0 burst size. Added "-b 1024" to the command as recommended by
> the log from the script, but the issue was still present.
>

If

# ./bridge ifname1 ifname2

doesn't work it means there is some problem with the driver the interfaces
are using. Default burst size used by "bridge" is already 1024.
You may try to repeat this experiment after setting "sysctl
dev.netmap.admode=2", to use the emulated mode, that is the legacy driver
(of course performance would be limited, but at least you check
functionality).
Check netmap(4) for more info.


>
> Second Attempt: Tried to combine vale-ctl and bridge by:
> # ./vale -h vale0:vcxl0
> # ./vale -h vale0:vcxl1
> # ./bridge vale0:1 vale0:3


> There was no error, however, traffic did not flow at the time of
> shooting packets to the interfaces.
>

What did you mean to do here? This setup creates a forwarding loop
involving the VALE switch "vale0" and the userspace hub implemented by
"bridge".
I'm not surprised that you see nothing..


>
> Third Attempt: By following this email
> threadhttps://lists.openinfosecfoundation.org/pipermail/oisf-users/2015-
> October/005310.html;
> we ran:
> # ./vale-ctl -n b0
> # ./vale-ctl -n b1
> # ./vale-ctl -a vale0:b0
> # ./vale-ctl -a vale0:vcxl0
> # ./vale-ctl -a vale1:b1
> # ./vale-ctl -a vale1:vcxl1
> # ./bridge -i netmap:vcxl0 -i netmap:vcxl1
>
> Same result as before, no errors, yet no traffic in the interfaces.
>
>
This should throw errors, as you are first attaching vcxl0 to a VALE
switch, and then opening vclx0 in netmap mode with the bridge program:
netmap forbids you to do that, because when an interface is attached to a
VALE switch it is "busy", and cannot be opened again from another netmap
application (like bridge).
Same reasoning for vcxl1.

Have you tried with the basic TX/RX tests first, without involving VALE?

# pkt-gen -i netmap:vcxl0 -f tx
# pkt-gen -i netmap:vcxl0 -f rx


Regards,
  Vincenzo


> Any feedback or advice on why traffic is not flowing?
>
> We would like to note that throwing packets to the vcxl interfaces
> without any netmap aware application ranges from 1.1M to 1.2M pps.
>
> Is this supposed to happen? (We consider that still, the number is quite
> low)
>
> - Jordan
>
>
> 2017-06-15 17:15 GMT-04:00 Navdeep Parhar <nparhar at gmail.com>:
>
> > On 06/14/2017 10:42, Olivier Cochard-Labbé wrote:
> >
> >> On Wed, Jun 14, 2017 at 7:36 PM, Navdeep Parhar <nparhar at gmail.com
> >> <mailto:nparhar at gmail.com>> wrote:
> >>
> >>
> >>     I think I fixed this a long time back.  Have you tried recently?  We
> >>     moved the netmap functionality to the vcxl interfaces and it should
> >>     just work.
> >>
> >> ​
> >> It stills panic with an -head build today.
> >>
> >>
> > Fixed in r319986.
> >
> >
> > _______________________________________________
> > freebsd-net at freebsd.org mailing list
> > https://lists.freebsd.org/mailman/listinfo/freebsd-net
> > To unsubscribe, send any mail to "freebsd-net-unsubscribe at freebsd.org"
> >
>
>
>
> --
> Jordan
> _______________________________________________
> freebsd-net at freebsd.org mailing list
> https://lists.freebsd.org/mailman/listinfo/freebsd-net
> To unsubscribe, send any mail to "freebsd-net-unsubscribe at freebsd.org"
>



-- 
Vincenzo Maffione