Re: strange behaviour of ntp peerstats entries.

"David L. Mills" <mills@xxxxxxxx> writes:

Root,

You could have saved a lot of time sweating the code if you looked at
the briefings. See especially the before and after time series and note
the 10 dB improvement in S/N.

I am sorry, but looking at the code is far simpler than trying to find
something in the documentation. Code I can use grep on, your documents I
cannot.


You might not have noticed a couple of crucial issues in the clock
filter code.

I did notice them all. Thus my caveate. However throwing away 80% of the
precious data you have seems excessive.



1. The basic principle is to select the samples that have not been
delayed in queues, leaving hopefully the ones delayed only by
propagation. It's better to discard the others that can only result in
less accurate measurements.

2. The filter samples are correlated only if the total span of the
filter is less than the Allan intercept, generally assumed in the order
of 2000 s. For poll intervals above that, the samples become
uncorrelated, so fewer samples are used.

3. Never use an old sample, only new onese. It often happens that the
last used minimum delay sample is older than the most recent sample. The
result is that the filter can toss out up to seven samples before
finding a new candidate. The clock discipline loop is specifically
designed to deal with that, which is one reason the time constant is
larger than you might like.

Dave

root wrote:

OK, having looked at the code, I see what it is doing. It essentially
takes the measurement with the shortest delay in the past 8 measurements.
If that measurement happens to be the current one, it is actually used
in the clock loop. (Yes, I know this characterisation of the clock filter is cruder
than reality).


This makes the smaller variance of chrony even more impressive, since in my
tests, evey single measurement of offset was used to calculate the variance
in the case of chrony, while
for ntp, only those "smallest" values as reported in peerstats were used. This also
explains why the roundtrip variance in ntp was so much better than chrony's.

snip





.

Relevant Pages

  • Re: strange behaviour of ntp peerstats entries.
    ... You might not have noticed a couple of crucial issues in the clock filter code. ... The filter samples are correlated only if the total span of the filter is less than the Allan intercept, generally assumed in the order of 2000 s. ... If that measurement happens to be the current one, it is actually used in the clock loop. ... This makes the smaller variance of chrony even more impressive, ...
    (comp.protocols.time.ntp)
  • Re: how to compute distance metrics with multi dimensional data
    ... > time series in the units of measurement is important. ... > trying to get the distances you might have something in mind where ...
    (sci.nonlinear)
  • Measurement error estimation
    ... It seems that there should be no way to partition total variance into ... population variability and measurement error unless one has more than ... sdM <- sd) ...
    (sci.stat.math)
  • Re: MFJ-269 Antenna/SWR/RF Analyzer
    ... >> bandpass filter for the lower frequencies. ... > If you do want to measure antenna impedance with something like the MFJ ... > measurement too much. ... This filter will cause little impedance disturbance at 7 ...
    (rec.radio.amateur.antenna)
  • Re: how to compute distance metrics with multi dimensional data
    ... does not matter what it is, but the measurement units are different for ... paper on computing multi dimensional distances... ... suppose you have a time series with 3d ... vectors ie with 3d embedded time series? ...
    (sci.nonlinear)