Achim, thank you for your graph and for the link to Dan Drown blog and your suggestions. I am going to collect data and replicate his research. I doubt I'll discover anything new, but it's interesting nevertheless to look into these time series data.
-- Fio Cattaneo Universal AC, can Entropy be reversed? -- "THERE IS AS YET INSUFFICIENT DATA FOR A MEANINGFUL ANSWER." On Mon, Oct 21, 2019 at 12:06 PM Achim Gratz <[email protected]> wrote: > > Fiorenzo Cattaneo writes: > > I have been quite puzzled about the asymmetric nature of my home Cable > > Modem connection to the Internet in regard with the offset discrepancy > > I observe. The "last mile" asymmetric nature of Cable Modem (Comcast > > in my case) is not very high compared the delta I see between my > > stratum-1 servers at home and the nearest public stratum-1 NTP server. > > The upload/download discrepancy would be much less than 100 > > microseconds - as you point out in your calculation the worst is 33 > > microseconds for an upload speed of 12 Mbps, which is a drop in the > > bucket compared to other potential sources of jitter, switch queueing > > delays or asymmetric routing. The latter is not an issue in my case. > > The asymmetry from different bandwifth up-/downstream is only a small > part of the effective up-/downstream difference. Dan Drown has measured > that: > > https://blog.dan.drown.org/tag/asymmetric-latency/ > > I would think the jitter distributions are skewed as well, so some of > that gets finally interpreted as an offset. If you can trust the clocks > on either end of the connection to be accurate, then you can set the > offset to zero and solve for the asymmetry instead of the usual > assumption of zero asymmetry to solve for the offset. > > Plotting the offset against the RTT like Dan does is instructive, but > you won't always get such nice graphs. I've attached a plot of how one > of my stratum-1 has seen the three PTB servers through my DSL connection > during the last three months. > > > So while the connection is stable you can sort of remove the extra > offset that comes from a changing RTT, but at any one time you might > jump to one other set of correlation lines and get that "correction" > wrong. > > > Regards, > Achim. > -- > +<[Q+ Matrix-12 WAVE#46+305 Neuron microQkb Andromeda XTk Blofeld]>+ > > Factory and User Sound Singles for Waldorf Blofeld: > http://Synth.Stromeko.net/Downloads.html#WaldorfSounds > _______________________________________________ > time-nuts mailing list -- [email protected] > To unsubscribe, go to > http://lists.febo.com/mailman/listinfo/time-nuts_lists.febo.com > and follow the instructions there. _______________________________________________ time-nuts mailing list -- [email protected] To unsubscribe, go to http://lists.febo.com/mailman/listinfo/time-nuts_lists.febo.com and follow the instructions there.
