Date: Fri, 25 Jun 1999 19:48:21 -0500 From: Alan Cox <alc@cs.rice.edu> To: Julian Elischer <julian@whistle.com> Cc: Luoqi Chen <luoqi@watermarkgroup.com>, dyson@iquest.net, smp@freebsd.org Subject: Re: Call to arms..-SMP Message-ID: <19990625194821.H2974@nonpc.cs.rice.edu> In-Reply-To: <Pine.BSF.3.95.990625132540.4244B-100000@current1.whistle.com>; from Julian Elischer on Fri, Jun 25, 1999 at 01:27:49PM -0700 References: <19990625135341.H2331@cs.rice.edu> <Pine.BSF.3.95.990625132540.4244B-100000@current1.whistle.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, Jun 25, 1999 at 01:27:49PM -0700, Julian Elischer wrote: > > So I don't really understand the _cpl stuff. > in regards to _cml > > I guess that theoretically, the BSDI method (lazy treading) > makes all that go away doesn't it?. > Umm. In general, and not specifically in regard to this problem, the BSDI method is a good idea, but it's not a silver bullet. spl's only exist around data that are shared between the top half of the kernel and (roughly speaking) device-level (bottom-half) code. When you have multiple processors running around the top-half of the kernel, there will be critical sections between those processors that aren't spl'ized. Alan To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-smp" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?19990625194821.H2974>