[ntp:questions] Can NTP sync within 1ms

Joe Gwinn joegwinn at comcast.net
Sun Apr 27 15:42:28 UTC 2014

In article <ljf8q0$mt2$3 at dont-email.me>, William Unruh
<unruh at invalid.ca> wrote:

> On 2014-04-26, Joe Gwinn <joegwinn at comcast.net> wrote:
> > In article
> ><8188BA2B01FB534A99C03D79C62CE1D80982FB4C at UUSNWE3A.global.utcmail.com>,
> > Montgomery, Peter         BIS <Peter.Montgomery at fs.utc.com> wrote:
> >
> >> I am new to NTP. But I have a quick question that I need to answer soon.
> >> 
> >> I would like to know whether NTP can sync between a client and a server
> >> within 1ms if the client and server are Linux applications on a simple
> >> local
> >> network ( less than 10 nodes).
> >
> > Not reliably, for a million reasons.  A better rule is 10 milliseconds,
> > and even that requires work and care.  
> Well, since I have 8 machines that reliably sync from one GPS PPS driven
> machine (all using chrony) and they get time reliability of about
> 10microseconds, your experience seems a bit different than mine. 
> And how did you determine that you were only getting 10ms. As I said,
> you cannot conclude that by looking at the offsets reported by ntpd.

I've managed 7 microseconds rms in a sterile lab setup, but I would
hardly tell people that they will achieve anything like that in an
unconstrained and complex network.

We know next to nothing about the OP's network et al, so I quoted a
worst case.  With added data, we may be able to tighten the estimate. 
Or, widen it if there turns out to be something unfortunate in the

> > The most reliable approach is an IRIG network.
> Or put a gps pps receiver onto each  machine. 

Yes, but IRIG is simpler and cheaper, and the OP asked for synchronized
time, and did not mention any need for accurate time.  

For all we know, the OP has no access to the sky.

> > But you need to describe your problem and constraints before people can
> > give better answers.
> Agreed.

And this is the key.

Joe Gwinn

More information about the questions mailing list