Date: Fri, 5 Apr 1996 11:09:59 -0700 From: Nate Williams <nate@sri.MT.net> To: Warner Losh <imp@village.org> Cc: hackers@freebsd.org Subject: Re: interrupts and such Message-ID: <199604051809.LAA19904@rocky.sri.MT.net> In-Reply-To: <199604051725.KAA16272@rover.village.org> References: <199604051725.KAA16272@rover.village.org>
next in thread | previous in thread | raw e-mail | index | archive | help
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
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199604051809.LAA19904>