[ntp:questions] Re: Known asymmetry (DSL) compensation
jpp at cloudview.com
Mon Feb 14 19:58:37 UTC 2005
David J Taylor wrote:
> John Pettitt wrote:
>>I know it's not possible to know or compensate for all asymmetry in
>>the packets between two machines. However where there is a fixed,
>>known, asymmetry - like on a DSL line shouldn't it be possible to
>>calculate a fudge factor?
> Isn't there a "fudge" command you can apply to a server exactly to provide
> a fixed offset? I belive the radio-clock people need to do this to
> compensate for receiver bandwidth and propagation delays.
The time1 fudge provides a offset to correct for some systemic error in
my ref clock - my ref clock isn't in error, the GPS 18 is spec says +/-
1us for the PPS signal, so I don't want to fudge my ref time. I think
what I need to do is fudge the network time calculation to account for
the known asymmetry.
More information about the questions