Date: Wed, 31 May 2000 11:29:32 -0700 From: "Marty Fouts" <marty@dotcast.com> To: <arch@FreeBSD.ORG> Subject: RE: Preemptive kernel on older X86 hardware Message-ID: <NDBBIAOKGLCDCFEJFOOAMEJECAAA.marty@dotcast.com> In-Reply-To: <20000531172432.A7547@sophos.com>
next in thread | previous in thread | raw e-mail | index | archive | help
It depends a great deal on how you want to use the NUMA system and what it's internal architecture supports. I spent a number of years at HP Labs investigating a similar proposition for a different Un*x, and the amount of work varies dramatically with the requirements. Loosely coupled "cluster" applications mostly require adding some shared namespace features, which is a lot of work. Tightly coupled highly available systems pretty much require a significant rewrite, or, lacking that, a collection of bubble gum and bailing wire sufficient to stretch from here to the moon and back. Marty -----Original Message----- From: owner-freebsd-arch@FreeBSD.ORG [mailto:owner-freebsd-arch@FreeBSD.ORG]On Behalf Of Mark Blackman Sent: Wednesday, May 31, 2000 9:25 AM To: Chuck Paterson Cc: Luoqi Chen; arch@FreeBSD.ORG Subject: Re: Preemptive kernel on older X86 hardware On a nearly unrelated note, anybody care to venture how tough would it be to modify *BSD* to run on a NUMA system instead of an SMP solution. This, obviously, is very high-end tiny niche area, but interesting to contemplate, especially if you're not doing the development. :) -- Mark Blackman,Internet Systems Administrator,Sophos Anti-Virus e-mail: tmb@sophos.com http://www.sophos.com US Support: +1 888 SOPHOS 9 UK Support: +44 1235 559933 To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-arch" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-arch" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?NDBBIAOKGLCDCFEJFOOAMEJECAAA.marty>