From owner-freebsd-hackers Sun Apr 11 21:39:36 1999 Delivered-To: freebsd-hackers@freebsd.org Received: from Ilsa.StevesCafe.com (Ilsa.StevesCafe.com [205.168.119.129]) by hub.freebsd.org (Postfix) with ESMTP id C8B7814E21 for ; Sun, 11 Apr 1999 21:39:33 -0700 (PDT) (envelope-from fbsd@Ilsa.StevesCafe.com) Received: from Ilsa.StevesCafe.com (localhost.StevesCafe.com [127.0.0.1]) by Ilsa.StevesCafe.com (8.8.8/8.8.5) with ESMTP id WAA01409 for ; Sun, 11 Apr 1999 22:41:35 -0600 (MDT) Message-Id: <199904120441.WAA01409@Ilsa.StevesCafe.com> X-Mailer: exmh version 2.0.2 2/24/98 From: Steve Passe To: hackers@FreeBSD.ORG Subject: Re: Some ideas on the evolution of -CURRENT In-reply-to: Your message of "12 Apr 1999 01:48:45 +0200." Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Date: Sun, 11 Apr 1999 22:41:35 -0600 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Hi, > - Smaller-grained locks in the SMP code. Perhaps someone will prove me wrong, but I don't think there's a lot of milage to be had pursuing the "small-grained SMP lock" grail. It could be done to some extent, but would be costly in programming effort and would be a never ending battle... Up to now the SMP effort has been evolutionary, to go much further it needs to be revolutionary. The current kernel model just doesn't fit. To create a true SMP system we need: mutex model as oppossed to spl(). kernel threads (and thread-based ISRs). (preferably) pre-emptible processes. -- Steve Passe | powered by smp@csn.net | Symmetric MultiProcessor FreeBSD To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message