[snip]
> Interesting driver, it contains code that has been through a C
> pre-processor. I wouldn't want to be the person who had try making it
> run on non x86 hardware, they didn't even try to make it
> portable. References PCI device registers directly not using the
> readl/writel macros as one should, no memory barriers and it expects
> operations like ptr->foo++ to be atomic - yummy, lotsa fun.
>
> Oh and is the hardware really so bad that it requires spin locks to
> protect the tx queue? (hint, where are the public docs? ;-)
>
> Would be interesting to see how it performs against the Alteon and
> Packet Engines cards, despite the broken license.
Well their (intel) site claimes this card has only a 64KB buffer.
(http://www.intel.com/network/tech_specs/pro1000giga.htm)
Furthermore, it sells for almost $600 US street price (while the netgear
sells for around $300)!
I'd be seriously supprised to see a reason to buy this over a netgear
card.
> Jes
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/