RE: SMP scalability: 8 -> 32 CPUs

Rik van Riel (H.H.vanRiel@phys.uu.nl)
Tue, 1 Dec 1998 00:17:10 +0100 (CET)


On Mon, 30 Nov 1998, The Galaxy Ranger wrote:
> On Mon, 30 Nov 1998, Rik van Riel wrote:
> > On Fri, 27 Nov 1998, Dave Wreski wrote:
> > > On 28-Nov-98 Eloy A. Paris wrote:
> > >
> > > 1. Because there aren't many PCs with 8 or more CPUs around to do
> > > testing on.
> > > 2. Because of #1, our efforts are better spent working on more
> > > real-life problems.
> >
> > Number 2 is the most important reason. Just look at the
> > Linux-MM site (on my home page) to get an impression on
> > the average TODO list each subsystem has.
>
> I'll grant you that the majority of installations are done
> on PC's. But if reason #2 above is really an issue, then
> why even bother doing things like a Sparc port, or an
> Alpha port, or a PPC port, or a 68K port. The number of
> people running Linux on an Alpha has to be small compared
> to the number of people using Linux on x86. So why do
> it at all?

Because there are people who own those machines and hate
to have them idling around. If you had a $2000 machine
idling around that you'd wish to run Linux on, you'd be
motivated to port the kernel.

Most of the stuff that's in the kernel now has been put
there by a hacker who really wanted to see that feature
/himself/. What other people want is somewhat important
too (for some stuff), but drivers and ports are mainly
done because someone has a machine he wants to run Linux
on.

Rik -- now completely used to dvorak kbd layout...
+-------------------------------------------------------------------+
| Linux memory management tour guide. H.H.vanRiel@phys.uu.nl |
| Scouting Vries cubscout leader. http://www.phys.uu.nl/~riel/ |
+-------------------------------------------------------------------+

-
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/