[time-nuts] PPS jitter - Oncore VP w/NTP

Jim Miller timenuts at jcmco.com
Wed Jun 22 14:58:52 EDT 2005


Thanks for the quick replies, everybody!  My comments below:

On Jun 22, 2005, at 2:39 PM, Poul-Henning Kamp wrote:

>>> pll offset:           1.106e-06 s
>>> pll frequency:        80.865 ppm
> This is not indicative of good hardware.

OK. What sort of numbers would I look for on a good system?  An order  
of magnitude difference from these?

> What does
>     sysctl kern.timecounter
> say ?

% sysctl kern.timecounter
kern.timecounter.stepwarnings: 0
kern.timecounter.nbinuptime: 61716868
kern.timecounter.nnanouptime: 0
kern.timecounter.nmicrouptime: 9157
kern.timecounter.nbintime: 6824690
kern.timecounter.nnanotime: 6715023
kern.timecounter.nmicrotime: 109663
kern.timecounter.ngetbinuptime: 0
kern.timecounter.ngetnanouptime: 9147
kern.timecounter.ngetmicrouptime: 15113666
kern.timecounter.ngetbintime: 0
kern.timecounter.ngetnanotime: 0
kern.timecounter.ngetmicrotime: 4
kern.timecounter.nsetclock: 4
kern.timecounter.hardware: TSC
kern.timecounter.choice: TSC(800) i8254(0) dummy(-1000000)
kern.timecounter.tick: 1
%

> The jitter warning thing is very likely if you load on the
> machine which might disable interrupts for any amount of time.

It is a 200Mhz Pentium dedicated to the NTP role and doing nothing  
other than ntpd and my login shells.

I will try some other motherboard/cpu combinations and compare the  
results. Should I look at other platforms (Sun, etc) for better  
interrupt service?

Do you have some ntptime or kerninfo output from a "good" piece of  
hardware that I can use as a goal?  I'm mostly guessing at this point  
what is good performance and what is bad but increasing error  
counters most always seem bad. :-)

Thanks,

Jim





More information about the time-nuts mailing list