On Wed, May 07, 2008 at 08:40:56AM +0100, Bruce M. Simpson wrote:
> Julian Elischer wrote:
> >actually the divert sockets should really not be in PF_INET
> >they could deliver both inet and inet6 packets.
> >the sockaddr that they return (and which needs to be read for divert
> >to make sense) coul
On Wed, May 14, 2008 at 12:37:58AM +1000, Edwin Groothuis wrote:
> It contains links to patches for FreeBSD 6.3 and the nat6to4d.c.
Needless to say that the code of nat6to4d.c is a proof-of-concept
and is missing essential features like garbage-collection and
configurationability.
Edwin
--
Edwi
Good Day,
I see that the new igb driver has a tunable for multiple rx/tx queues.
Is that for future use or already working when using a 82575 NIC?
Currently the processing of packets is limited to one CPU per NIC.
Can we now have multiple taskq processes for one NIC in parallel?
Best Regards,
Ma
This would be awesome, like the Yandex driver for fbsd 6..
I wish there was some way of doing this for 7.0 :) maybe this is it..
So this is the question now...
Markus Oestreicher wrote:
Good Day,
I see that the new igb driver has a tunable for multiple rx/tx queues.
Is that for future us
0n Mon, May 12, 2008 at 01:19:58PM +0200, Marius Strobl wrote:
>If the system is running the simplest thing in order to identifiy
>the PHYs is to check the oui= and model= output of `devinfo -v`.
>Otherwise boot verbose and check the OUI and model output of
>ukphy(4).
Curiou
