Date: Sun, 11 Apr 1999 22:41:35 -0600 From: Steve Passe <smp@csn.net> To: hackers@FreeBSD.ORG Subject: Re: Some ideas on the evolution of -CURRENT Message-ID: <199904120441.WAA01409@Ilsa.StevesCafe.com> In-Reply-To: Your message of "12 Apr 1999 01:48:45 %2B0200." <xzpzp4evhuq.fsf@flood.ping.uio.no>
next in thread | previous in thread | raw e-mail | index | archive | help
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
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199904120441.WAA01409>