From owner-freebsd-hackers Thu Sep 26 19:22:56 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.5/8.7.3) id TAA16111 for hackers-outgoing; Thu, 26 Sep 1996 19:22:56 -0700 (PDT) Received: from rocky.mt.sri.com (rocky.mt.sri.com [206.127.76.100]) by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id TAA16055 for ; Thu, 26 Sep 1996 19:22:46 -0700 (PDT) Received: (from nate@localhost) by rocky.mt.sri.com (8.7.5/8.7.3) id UAA18954; Thu, 26 Sep 1996 20:21:12 -0600 (MDT) Date: Thu, 26 Sep 1996 20:21:12 -0600 (MDT) Message-Id: <199609270221.UAA18954@rocky.mt.sri.com> From: Nate Williams To: Michael Smith Cc: durian@plutotech.com (Mike Durian), freebsd-hackers@freebsd.org Subject: Re: Special Cycles on the PCI bus In-Reply-To: <199609270131.LAA17240@genesis.atrad.adelaide.edu.au> References: <199609262306.RAA12457@pluto.plutotech.com> <199609270131.LAA17240@genesis.atrad.adelaide.edu.au> Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > > Now that I've located the problem, does anyone have any suggestions > > on what I can do to avoid using the "hlt" command. Is there something > > else the idle_loop can do while waiting for interrupts? > > Er. If your system has an APM BIOS, you could enable APM and use the > "Idle CPU" function, but it wouldn't surprise me if that used "hlt" > as well. It might, but then again it might not. In any case, we call 'hlt' if the APM bios isnt' enabled but the APM code is used. > I don't know if there's any way other than using "hlt" to > wait until the next interrupt - you could perhaps spin waiting on the > interrupt statistics counter(s)... You could ignore 'hlt', but it uses up more power. A machine that doesn't use 'hlt' gets significantly hotter than a machine that does. It's not really necessary though. Nate