[ntp:questions] Re: Strange scattergram

Karel Sandler sandler at ujf.cas.cz
Wed May 17 22:23:32 UTC 2006


thank you for your explanation - a significant temporary frequency error at 
the server or client. Hope the server - other peers have small or nearly 
none asymmetry and almost all of their delays are not far from their blunt 
noses - a mirrors of my own offset scatter. The second plot was only 
enlarged part of the first one. Yes, I will try the huffpuff filter to see 
how it works.

<user at domain.invalid> wrote:
> Karel,
> Your first scattergram shows a tail extending downward to the left. That 
> happens when there is a significant freqency error at the server or client 
> and generally damps out once the critters have stabilized. In the first 
> and second scattergrams there is evidence of a 30-ms delay in both 
> directions at least some of the time. The darker upper limb of both grams 
> show a highly unsymmetric traffic. Fix that with the huffpuff option. The 
> blunt nose in both grams is due to jitter.
> Dave
> Karel Sandler wrote:
>> Hello,
>> to better know the network quality between my S2 and its peers, the wedge 
>> scattergrams were used. That strange one has the upper limb prolonged 
>> down to the left side of the head. Only few samples (status 9314) are 
>> located there but their existence is beyond all my understanding.
>> Hope my S2 works well, only one plot (one peer from seven) shows up that 
>> feature - lx.ujf.cas.cz/ntp-lx/antitail.png .
>> --
>> K. Sandler

More information about the questions mailing list