[rescue] Re: Fast Ethernet vs. SS2
nimitz at speakeasy.net
Mon Nov 11 23:33:01 CST 2002
Greg A. Woods wrote:
> I don't know about that -- it would depend a great deal on the driver.
True. Software overhead does play a more than significant part.
> It also doesn't quite make sense. Most drivers already send packets
> to the ethernet interface at bus speeds -- the IF then buffers them
> out tothe wire.
Exactly why having a faster output on the wire allows the card to not
tie up so many cycles. The faster the output - unless the whole amount
of data fits in the IF buffer - the faster the data moves off of the
bus. Reduced bus-time means reduced CPU cycles handling those actions.
> I don't think even NetBSD offloads CPU work to the hme yet, does it?
> I don't see anything in the CVS logs. I do see that some direct DMA
> changes going in and then being backed out again.... (it does DMA,
> but not direct to/from MBUFs I think).
You're most likely right again - I'm not a developer by any sense of the
(I just kinda understand some things without really needing to learn all
about them. It's odd _and_ annoying at times. As if you were looking
at one of the "Matrix" screensavers and suddenly understanding it.)
Still, if it's not being done then why couldn't it? By my understanding
it makes more sense to off-load as much as you can to other components
that can take the load so that the overall load is evened out over the
whole system. Something in me is wondering if I'm not leaning a little
towards asychronous computing here but then I don't know enough about
More information about the rescue