[ntp:questions] 500ppm - is it too small?
Unruh
unruh-spam at physics.ubc.ca
Sat Aug 15 17:50:43 UTC 2009
John Hasler <john at dhh.gt.org> writes:
>Bill Unruh writes:
>> Surely being way out on the time is far worse than slewing rapidly. It
>> is after all the time that they are supposed to deliver (as recognized
>> by the willingness to step the time).
>Slewing too rapidly could be worse for network stability than being way
>out for a long time.
Why?
Stability implies feedback, and one of the things a network of ntp
systems does not have is feedback-- that is why the tree structure.
>We need to induce a grad student to do a stability analysis of a network
>of Chrony servers. Should be good for a published paper, if not a
>thesis subject. For extra credit follow up with an analysis of a
>network with both Ntpd and Chrony servers.
Agreed. I am still confused by what you mean by stability.
>--
>John Hasler
>john at dhh.gt.org
>Dancing Horse Hill
>Elmwood, WI USA
More information about the questions
mailing list