Re: Kernel Threads: Dr. Russinovich's response

Matthias Andree (mandree@sx1.HRZ.Uni-Dortmund.DE)
Wed, 13 Jan 1999 21:48:00 +0100


On Tue, Jan 12, 1999 at 03:00:38PM -0500, Benjamin Scherrey wrote:
> I haven't had a lot of experience with SMP under Linux yet but that's about
> to change. I pretty much have stayed with Solaris for this as it seems to scale
> pretty well. NT had never approached linear increases in performance for my
> applications in SMP. OS/2 did surprisingly well but was unfortunately not made

[...]

> Solaris. Are my expectations too high and are the criticisms brought up by Dr.
> Russ potentially going to impact me in this area?

You can expect linear scalement ONLY in very limited special cases -
and that is something you learn pretty early in lectures about parallel
machines. Although application and OS implementation, of course, also
have impact on the scalabilty. It can be supported or spoiled.

Hiding latencies that come from locks, however, is always important, UP
or SMP.

-- 
Matthias Andree

- 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/