From owner-freebsd-current Sun Feb 11 05:35:11 1996 Return-Path: owner-current Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id FAA06824 for current-outgoing; Sun, 11 Feb 1996 05:35:11 -0800 (PST) Received: from tfs.com (tfs.com [140.145.250.1]) by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id FAA06817 for ; Sun, 11 Feb 1996 05:35:08 -0800 (PST) Received: from critter.tfs.com by tfs.com (smail3.1.28.1) with SMTP id m0tlbvl-0003wSC; Sun, 11 Feb 96 05:35 PST Received: from localhost.tfs.com (localhost.tfs.com [127.0.0.1]) by critter.tfs.com (8.6.12/8.6.12) with SMTP id OAA06364; Sun, 11 Feb 1996 14:20:42 +0100 X-Authentication-Warning: critter.tfs.com: Host localhost.tfs.com didn't use HELO protocol To: Bruce Evans cc: current@freebsd.org Subject: Re: calibrating clocks In-reply-to: Your message of "Sun, 11 Feb 1996 21:04:46 +1100." <199602111004.VAA04514@godzilla.zeta.org.au> Date: Sun, 11 Feb 1996 14:20:42 +0100 Message-ID: <6362.824044842@critter.tfs.com> From: Poul-Henning Kamp Sender: owner-current@freebsd.org Precedence: bulk > >Did you see the email about the "almost correct sub-tic" stunt ? > > I don't think it's OK. It would be too inaccurate to use in mi_switch(), > which seems to be the only place where its overhead is noticeable. OK. > The i586 clock is good enough for the sub-tick count. Even if it varies, > it can be rescaled often. The i8254 clock probably needs to be read on > i586's every clock tick to determine the latency of hardclock(). The > cost of this is < 5usec * 100 Hz = 500 usec/sec = 0.05%. You know about the counter in the APIC too ? It runs at the "bus frequency" but that may vary as well :-( -- Poul-Henning Kamp | phk@FreeBSD.ORG FreeBSD Core-team. http://www.freebsd.org/~phk | phk@login.dknet.dk Private mailbox. whois: [PHK] | phk@ref.tfs.com TRW Financial Systems, Inc. Future will arrive by its own means, progress not so.