Date: Thu, 19 Apr 2001 22:02:48 +0200 From: Poul-Henning Kamp <phk@critter.freebsd.dk> To: Warner Losh <imp@harmony.village.org> Cc: David Miller <dmiller@sparks.net>, freebsd-hackers@FreeBSD.ORG Subject: Re: [OT] parallel port for IO? Message-ID: <60866.987710568@critter> In-Reply-To: Your message of "Thu, 19 Apr 2001 13:52:21 MDT." <200104191952.f3JJqL806575@harmony.village.org>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <200104191952.f3JJqL806575@harmony.village.org>, Warner Losh writes: >In message <60546.987709317@critter> Poul-Henning Kamp writes: >: Use the pps driver and you get microsecond jitter with nanosecond >: resolution. > >While I usually see microsecond jitter, I have seen it as high as a >few milliseconds when the interrupt load on the machine was high and >the cpu was slow. > >I setup a system for a user here for pps (pulse per second signal), >and he was quite upset to see the occasional spike in his data. Fast >interrupts reduced the occurance of spikes from a few an hour to one a >day. The BIOS misuse of SMM mode can give you jitter in the 1msec range and there is not much you can do about it. I found out when I clocked a motherboard with a 14.318 derived from a Rb, and timed 1Hz pulses derived from a Cs. Every 400 seconds I ran into the SMM interrupt for about 10 seconds, and all my measurements were late by 800-900 microseconds :-( Intel doesn't care much for precision timing... -- Poul-Henning Kamp | UNIX since Zilog Zeus 3.20 phk@FreeBSD.ORG | TCP/IP since RFC 956 FreeBSD committer | BSD since 4.3-tahoe Never attribute to malice what can adequately be explained by incompetence. 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?60866.987710568>