From owner-freebsd-current Thu Dec 4 01:04:33 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id BAA04853 for current-outgoing; Thu, 4 Dec 1997 01:04:33 -0800 (PST) (envelope-from owner-freebsd-current) Received: from mail.san.rr.com (ns.san.rr.com [204.210.0.1]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id BAA04845 for ; Thu, 4 Dec 1997 01:04:29 -0800 (PST) (envelope-from Studded@dal.net) Received: from dt051n19.san.rr.com (dt051n19.san.rr.com [204.210.32.25]) by mail.san.rr.com (8.8.7/8.8.7) with SMTP id BAA02517; Thu, 4 Dec 1997 01:01:55 -0800 (PST) Message-Id: <199712040901.BAA02517@mail.san.rr.com> From: "Studded" To: "dg@root.com" Cc: "FreeBSD-current@FreeBSD.ORG" Date: Thu, 04 Dec 97 01:00:40 -0800 Reply-To: "Studded" Priority: Normal X-Mailer: PMMail 1.95a For OS/2 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Subject: Re: 3.0 -release ? Sender: owner-freebsd-current@FreeBSD.ORG X-Loop: FreeBSD.org Precedence: bulk On Thu, 04 Dec 1997 00:01:22 -0800, David Greenman wrote: > What we have now is pretty bad for just about everything and might >actually be slower on a two CPU machine for things that spend their >time mostly in the kernel (like Internet servers). There are two things >that need to be done: locks need to be pushed down so that we have at >least per-subsystem locking (networking, filesystems, VM system, etc), >and we need to rewrite the scheduler for process affinity. With those >two things working reliably, I would consider the SMP implementation not >finished, but releasable as a first cut. During the 2.2.5-Beta cycle some ideas like this were kicked around, but discussion was put on hold. Is it possible to put this on a more formal schedule? I think we would gain a lot by coming out with a "practice release" of -Current that has known bugs/conflicts ironed out, and SMP code that at least wasn't likely to make things worse. :) I know several adventurous people that would put SMP code on production machines if they had a reasonable assurance that it would be (at least mostly) stable. We could use the feedback from people who are using the thing in a production environment, and garner some good pre-publicity. I'm sure I'm not saying anything new, my point is simply that this would be a well-received project. :) I think we can all see the SMP writing on the wall, it would be nice to be ahead of the curve. Doug *** Proud operator, designer and maintainer of the world's largest *** Internet Relay Chat server. 4,168 clients and still growing. :-) *** Try spider.dal.net on ports 6662-4 (Powered by FreeBSD) *** Part of the DALnet IRC network ***