[ntp:questions] NTP server with Garmin GPS 18 LVC

unruh unruh at invalid.ca
Wed Dec 18 23:16:18 UTC 2013

On 2013-12-18, Adrian P <ntp at pascalau.ro> wrote:
>> It is hard to say, but it could be that the interrupt for the PPS is
>> delayed because of, say, disk activity which ties up the interrupts for
>> 50us. The next one will of course occur on time ( ie 50us early with
>> respect to the previous interrupt). That may be what you are seeing. Are
>> you looking at the raw graphs of offset every second? The median filter
>> should remove those spikes. (it basically throws away about 40% of the
>> measurements that are furthest from the median in order to eliminate
>> "popcorn" events) so they should not affect your timing.
>> Looking at your graph, the events are extremely regular. Unfortunately I
>> have no idea what the lower axis is. You claim seconds, but there are no
>> tick marks. Does that span represent a day, a year, a microsecond?
>> If it is say minutes or hours, then the decay suggests that the computer
>> say a huge spike for a relatively long time ( many seconds) responded by
>> changing the clock rate, and then that anomaly disappeared and it
>> relaxed back to its proper rate.
> That graph (http://goo.gl/JpSyeO) is based on the entries in the
> peerstats file, and the lower axis is the time past midnight in
> seconds. The peerstats file is rotated every day, so the graph shows
> the clock offset and the RMS jitter for a 24h period, as the graph
> title tells. I have configured the NMEA driver using minpoll 4 maxpoll
> 4, so I have an entry in the peerstats file every 16 secconds or so.
> To be more precise, I recreated the graph for the first negative /
> positive spike only, see this URL: http://goo.gl/pBrI4C. I displayed
> the ticks for the lower axis as well. As can be seen from this newer
> graph, the negative spikes takes around 9 minutes, while the positive
> spike takes somewhere around 24 minutes.
> So, what do you think?

So it repeats approx every 1.5  hours, quite regularly (slightly longer
period at night than during the day). Are you doing
something on the machine every two hours? 9 minutes is a long time (
over 30 time periods) so disk activity or other interrupt delays does
not seem a reasonable explanation. I really do not have any idea why
there would be this extremely regular long term delay
> Best regards,
> Adrian

More information about the questions mailing list