Date: Sun, 22 Feb 1998 18:55:35 +0100 From: Poul-Henning Kamp <phk@critter.freebsd.dk> To: "Jordan K. Hubbard" <jkh@time.cdrom.com> Cc: John Hay <jhay@mikom.csir.co.za>, freebsd-current@FreeBSD.ORG Subject: Re: clock code working properly in -current? Message-ID: <11816.888170135@critter.freebsd.dk> In-Reply-To: Your message of "Sun, 22 Feb 1998 09:16:00 PST." <27159.888167760@time.cdrom.com>
next in thread | previous in thread | raw e-mail | index | archive | help
In message <27159.888167760@time.cdrom.com>, "Jordan K. Hubbard" writes: >> With kernels build today, both my 90MHz Pentium UP machine and my 266MHz >> PII SMP machine gain a lot of time. The Pentium gain about 2 seconds per >> minute and the SMP machine about 1 second per minute. Needless to say >> xntpd can't cope with a frequency error that big. Previously xntpd and >> ntp-4 reported a 24ppm error on the Pentium and a -297ppm error on the >> SMP machine. > >That's pretty interesting since I know of a dual PII box at a friend's >place of work that's been doing *exactly* this ever since SMP entered >-current; it's never worked properly. You know how hard it is to >benchmark a machine who's clock runs twice as fast, too? :-) > >I wonder if this is a bug which has been latent since the beginning >but only bites some people. We asked Steve Passe if he wanted to >borrow the box in question but he was too busy. :( Please boot -v and send me the dmesg & sysctl -a outputs, then add to the kernel config CLK_USE_I8254_CALIBRATION and CLK_USE_TSC_CALIBRATION and send the dmesg & sysctl -a for those too. -- Poul-Henning Kamp FreeBSD coreteam member phk@FreeBSD.ORG "Real hackers run -current on their laptop." "Drink MONO-tonic, it goes down but it will NEVER come back up!" To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-current" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?11816.888170135>