From owner-freebsd-hackers Fri Apr 5 10:10:25 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id KAA29894 for hackers-outgoing; Fri, 5 Apr 1996 10:10:25 -0800 (PST) Received: from rocky.sri.MT.net (rocky.sri.MT.net [204.182.243.10]) by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id KAA29889 for ; Fri, 5 Apr 1996 10:10:22 -0800 (PST) Received: (from nate@localhost) by rocky.sri.MT.net (8.6.12/8.6.12) id LAA19904; Fri, 5 Apr 1996 11:09:59 -0700 Date: Fri, 5 Apr 1996 11:09:59 -0700 From: Nate Williams Message-Id: <199604051809.LAA19904@rocky.sri.MT.net> To: Warner Losh Cc: hackers@freebsd.org Subject: Re: interrupts and such In-Reply-To: <199604051725.KAA16272@rover.village.org> References: <199604051725.KAA16272@rover.village.org> Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Warner Losh writes: > I just did a vmstat -i on my 2.1R I notice that I get 100/s for clk0 > (which is what I'd expect) and 128/s for rtc0 on irq8. This seems > excessive to me to have both. Also, I notice on an older 1.1.5.1R > system that the rtc0 device isn't listed in vmstat's output. > > So what is rtc0 and why is it acting like a clock interrupt? Because it is a clock interrupt. rtc0 is 'sufficiently' faster than clk0 so that statistics gathering is significantly better and more accurate. This helps scheduling and accounting immensely, and is now depended on by many parts of the system. Unfortunately, on my laptop if rtc0 is enabled APM suspend/resume fails, so I have to disable it on my box. However, parts of the library now depend on this behavior for correct values, so I haven't figured out a clean way to disable it for the GENERIC kernels but enable it for machines who break with it enabled. However, in your case it's a 'good thing'. Nate