Interesting, +1 Garret.

%m

On Thu, Apr 30, 2009 at 9:23 PM, Garrett D'Amore <[email protected]> wrote:
> Earlier this week I got yet another request for qfe support for x86
> systems.  I get these requests fairly periodically.  I guess there are a
> lot of 4-port qfe cards still out there.
>
> This last one finally gave me the impetus to do the work to do the
> port.  What I want to do is poll the community on this, because I'm
> going to need help:
>
>   1) testing -- my last SPARC system with onboard hme died a while back
>   2) testing -- I have no sbus hme ports -- a Sun Ultra 2 or some
> other system with sbus qfe or sunswift would be helpful here.
>   3) review -- as part of this effort I've removed all the legacy dvma
> and on-demand DMA resource allocation, and replaced it with a very
> simple "preallocated" DMA region/bcopy -- this is typical for most
> simple 1G and slower ethernet NICs today.  (This eliminated about 1000
> lines from the driver.)
>   4) perf. testing -- the above changes "potentially" have performance
> impact.  I think on any supported CPU that these cards run on, the
> simplifications will greatly outweigh the savings formerly afforded by
> the "private" dvma interface this driver used to use
>
> Now, the good news is that the entire effort here has only taken me a
> few hours.  But I figure if I can help out some of these folks with
> those older qfe cards, its probably worth it.  And the simplification in
> the code, and getting one closer to elimination of the "private" dvma
> interface is IMO a worthy goal.
>
> I'd also like to convert this driver (and also eri and dmfe) to support
> Brussels.  If some enterprising community member wants to help out, let
> me know.
>
>   -- Garrett
>
>
>
> _______________________________________________
> driver-discuss mailing list
> [email protected]
> http://mail.opensolaris.org/mailman/listinfo/driver-discuss
>
_______________________________________________
driver-discuss mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/driver-discuss

Reply via email to