On 12 Jul 2000, Jes Sorensen wrote:
> >>>>> "Alan" == Alan Cox <alan@lxorguk.ukuu.org.uk> writes:
>
> Richard> It might not be a 2.0.36 driver that is needed. It may be the
> Richard> 2.0.36 reliability!
> >> 2.0.36 reliawhat?? If you are looking for GigE performance you are
> >> likely to want SMP and SMP in 2.0.36 is absolutely not realiable.
>
> Alan> Actually by 2.0.36 its very reliable. It still gives sucky
> Alan> performance.
>
> Depends on what you do with it, at CERN we had soo many problems with
> it on SMP machines. 2.2.x was an order of magnitude better.
I think alot of it comes down to hardware choice. There
seemed to be many more driver vs SMP issues with 2.0.3x, and some SMP
support that 2.2.x did better when dealing with interesting SMP setups
(some compaqs, ALR/Unisys/DataGeneral PProx4 and PProx6 units/etc).
Pick known clean running MBs, and cards and you did well,
catalog engineer the system without researching what was stable with
SMP and get bitten hard.
---
As folks might have suspected, not much survives except roaches,
and they don't carry large enough packets fast enough...
--About the Internet and nuclear war.
-
: send the line "unsubscribe linux-net" in
the body of a message to majordomo@vger.rutgers.edu
