Date: Sun, 27 Apr 1997 10:44:53 -0400 (EDT) From: Garrett Wollman <wollman@khavrinen.lcs.mit.edu> To: Peter Wemm <peter@spinner.dialix.com> Cc: current@freebsd.org Subject: Re: cvs commit: src/etc rc rc.network Message-ID: <199704271444.KAA08965@khavrinen.lcs.mit.edu> In-Reply-To: <199704271347.VAA07550@spinner.DIALix.COM> References: <199704271230.WAA07923@godzilla.zeta.org.au> <199704271347.VAA07550@spinner.DIALix.COM>
next in thread | previous in thread | raw e-mail | index | archive | help
<<On Sun, 27 Apr 1997 21:47:34 +0800, Peter Wemm <peter@spinner.dialix.com> said: > Apr 27 10:39:07 pasteur xntpd[171]: time reset (step) -0.418709 s > Apr 27 10:45:01 pasteur xntpd[171]: time reset (step) 0.561284 s > remote local st poll reach delay offset disp > ======================================================================= > *tictoc.dap.CSIR 203.12.3.8 1 256 377 0.05458 -0.061465 0.03783 You don't really give enough information here... There are two possibilities: 1) If that is your only server, then it's clear, you have substantial jitter on the link to it which is causing NTP to step all over the place. This is a flaw in xntpd, but it can't be fixed without having either a super-stable local clock, or at least a model of how the local oscillator behaves. If I were at work, I've give you the title of a Ph.D. thesis which explores these issues. 2) If you have multiple servers (as my ntpq seems to suggest), then the problem is also clear: you have different jitter on the links to those different servers, and the difference is enough, and varies enough, to cause xntpd to clock-hop. (You should be able to confirm this theory by examining which servers are considered synchronization sources before and after a step.) If I were at work, I'd give you the title of a Ph.D. thesis which explores these issues. > It seems to go through wild oscillations quite regularly. What worrys me > is that xntpd seems to call adjtime() very frequently, about every second > or so.. Does it have it's own PLL inside xntpd? Yes, it does. > Does having a PLL driving > a PLL work? The kernel PLL doesn't ever come into play, since xntpd doesn't think the time is stable enough to start using it. It would be calling adjtimex() if it were. -GAWollman -- Garrett A. Wollman | O Siem / We are all family / O Siem / We're all the same wollman@lcs.mit.edu | O Siem / The fires of freedom Opinions not those of| Dance in the burning flame MIT, LCS, CRS, or NSA| - Susan Aglukark and Chad Irschick
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199704271444.KAA08965>