From owner-freebsd-arch Fri Nov 17 11:59:19 2000 Delivered-To: freebsd-arch@freebsd.org Received: from critter.freebsd.dk (flutter.freebsd.dk [212.242.40.147]) by hub.freebsd.org (Postfix) with ESMTP id 8691137B479; Fri, 17 Nov 2000 11:59:16 -0800 (PST) Received: from critter (localhost [127.0.0.1]) by critter.freebsd.dk (8.11.1/8.11.1) with ESMTP id eAHKLd726146; Fri, 17 Nov 2000 21:21:39 +0100 (CET) (envelope-from phk@critter.freebsd.dk) To: John Baldwin Cc: arch@FreeBSD.org, mark@grondar.za, John Hay Subject: Re: new monotime() call for all architectures. In-Reply-To: Your message of "Fri, 17 Nov 2000 11:53:50 PST." Date: Fri, 17 Nov 2000 21:21:39 +0100 Message-ID: <26144.974492499@critter> From: Poul-Henning Kamp Sender: owner-freebsd-arch@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG In message , John Baldwin writes: > >On 17-Nov-00 Poul-Henning Kamp wrote: >> >>>> Ok, I just thought the "mono" in his function name is for monotonic. If >>>> you are staying on one processor it will work, but if the timestamps >>>> have scheduling inbetween the timestamps and you land on a different >>>> processor it won't be monotonic anymore. >>> >>>It's close enough. :) >> >> If it isn't dealing properly with async PCC/TSC counters on SMP machines >> it shouldn't be called "monoanyting". >> >> I guess I totally object to the name now :-) > >It will be increasing at least. :) (except for occasional cases when you get >events close together on 2 CPU's that are within the drift between teh CPU's >and in the right order to result in the later event coming "earlier"). It will flicker forth and back, because there may be a finite, but potentially large and pretty constant offset between the counters. Unless this function returns a monotonic increasing (modules the inevietable wraparound) integer of some width, it should not be called "mono*". Unless it returns true units of time it should not be called "*time". -- 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-arch" in the body of the message