netmap-ipfw on em0 em1

[Evandro Nunes]

On Tue, Nov 4, 2014 at 8:12 PM, Luigi Rizzo <rizzo at iet.unipi.it> wrote:

> On Tue, Nov 04, 2014 at 05:44:43PM -0200, Evandro Nunes wrote:
> > On Tue, Nov 4, 2014 at 5:26 PM, Luigi Rizzo <rizzo at iet.unipi.it> wrote:
> ...
> > >> i gues I am missing a piece of the architecture...
> > >>
> > >
> > > ???probably yes :)
> > >
> > > kipfw em1 em2 connects the two interfaces to each other, keeping the
> > > rest ???
> > >
> > > ???of the host stack completely out of the game.
> > >
> >
> > got it
>
> uhmmm... probably not, see below:
>
> > however it's still not counting any packets coming in or out of the
> > interfaces
> >
> >
> > > ???I am not sure where you are running pkt-gen (is it on a separate
> > > machine ?) and what the 'em1' used in ???
> > > ???
> > > ???pkt-gen is connected to.
> > >
> >
> >
> > I am running one pkt-gen in TX mode on the same machine, and another one
> in
> > RX mode in a separate machine, but this is just for reference, to make
> sure
> > packets are actually getting transmitted, and it is...
>
> you cannot run two netmap clients on the same NIC at the same time
> (unless you know how to do that, and avoid they stomp on each other).
>
> In this particular case it means that you should test things as follows
>
>   machine A:  pkt-gen -i em1 -f tx ...
>
>   machine B   kipfw em1 em2
>
>   machine C   pkt-gen -i em3 -f rx
>
> And the connection between the ports is the following
>
>   [A em1] <-->  [em1 B  em2] <--> [em3 C]
>
> cheers
> luigi
>

ok this scenario will take a bit more time to create, Ill do it today
so there is no way to filter a traffic generated by the same box, at least
not right now, correct?

one more thing, in this scenario you draw, should netmap-ipfw also filter
host traffic? I mean, machine A pinging machine C instead of generating
netmap-away traffic should be just like the same, right?

thank you very much again