From owner-freebsd-current  Sat Nov 25 13:25:46 1995
Return-Path: owner-current
Received: (from root@localhost)
          by freefall.freebsd.org (8.6.12/8.6.6) id NAA17211
          for current-outgoing; Sat, 25 Nov 1995 13:25:46 -0800
Received: from localhost.cdrom.com (localhost.cdrom.com [127.0.0.1])
          by freefall.freebsd.org (8.6.12/8.6.6) with SMTP id NAA17204
          for <current@freebsd.org>; Sat, 25 Nov 1995 13:25:42 -0800
X-Authentication-Warning: freefall.freebsd.org: Host localhost.cdrom.com didn't use HELO protocol
To: current@freebsd.org
Subject: pentiums, clocks and xntpd: a smoking gun...
MIME-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <17201.817334741.1@freefall.freebsd.org>
Date: Sat, 25 Nov 1995 13:25:41 -0800
Message-ID: <17202.817334741@freefall.freebsd.org>
From: Poul-Henning Kamp <phk@freefall.freebsd.org>
Sender: owner-current@freebsd.org
Precedence: bulk

I remember a thread a little while back about the suitability of
the pentiums clock for timekeeping, in particular when we have
no way of knowing the actual frequency.

I hooked a DCF77 receiver up to my Pentium/133 and here is my findings:

My microtime() drifts at a rate of:

	(7.679466-5.081014)/(76710.567-75815.162) = .002901

this is ten and a half second per hour :-(

It is surprisingly close to the ratio of:

	(133.333333-133)/133 = .002506

If this was the case, then my residual drift would be .000395,
or one and a half second per hour.

Poul-Henning