[ntp:questions] Ntpd accuracy

Brad Knowles brad at stop.mail-abuse.org
Wed Jun 8 08:15:01 UTC 2005

At 2:41 PM +0800 2005-06-08, Eric Liu wrote:

>  We can see that the offset varys in a very large range. How can I make the
>  offset much more regualr?

	There are a lot of variables involved.  One is letting the system 
run long enough to gather enough statistical information regarding 
clock variability so that ntpd can make better guesses as to what 
kinds of changes it should make when it detects that the internal 
clock is divergent from the correct time.

>                             After our hard work, can I have 1ms accuracy?

	Maybe, but you'd need to have your own Stratum-1 time sources, 
and they'd have to be good quality Stratum-1 time sources.  And that 
can get expensive.

>                                                                            If
>  there are many clients(in fact, there will), 1ms accuracy means among all
>  clients, relative to each other.

	To achieve that, you'd probably need good quality Stratum-1 time 
sources directly attached to each and every client.  That would be 
much more expensive.

Brad Knowles, <brad at stop.mail-abuse.org>

"Those who would give up essential Liberty, to purchase a little
temporary Safety, deserve neither Liberty nor Safety."

     -- Benjamin Franklin (1706-1790), reply of the Pennsylvania
     Assembly to the Governor, November 11, 1755

   SAGE member since 1995.  See <http://www.sage.org/> for more info.

More information about the questions mailing list