On Mon, Oct 30, 2000 at 12:01:08PM +0100, Ingo Molnar wrote:
>
> On Mon, 30 Oct 2000, Jeff V. Merkey wrote:
>
> > > And please check your numbers, 857 million
> > > context switches per second means that on a 1 GHZ CPU you do one context
> > > switch per 1.16 clock cycles. Wow!
> >
> > Excuse me, 857,000,000 instructions executed and 460,000,000 context switches
> > a second -- on a PII system at 350 Mhz. [...]
>
> so it does 1.3 context switches per clock cycle? Wow! And i can type
> 100000000000000000000 characters a second, just measured it. Really!
Go download it and try it, then come back with that smirk wiped off your face.
I'll enjoy it.....
:-)
>
> > Your Tux web server will also run on it, at significantly increased
> > performance.
>
> as i told you in the previous mails, TUX does not depend on schedule()
> performance. schedule() cost does not even show up in the top 20 entries
> of the profiler.
And as I told, you, your code has nothing to do with it, it's the fact it
goes on at all. Ingo, go get a copy of NetWare 3.12 (I'll even send you
one -- I've got extra licensed copies), install it, put a load of 5000
connections on it, with 4 adapters. Dual boot Linux on it, and attempt
the same with SAMBA or MARS-NWE, and watch it oink.
Go do it. What's your address to I can ship you the CD's for 3.12. Then come
back and tell me how TUX is going to solve the File and Print performance
issues in Linux.
:-)
Jeff
>
> Ingo
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
Please read the FAQ at http://www.tux.org/lkml/
This archive was generated by hypermail 2b29 : Tue Oct 31 2000 - 21:00:26 EST