Re: Installing more stable oscillator?

On Jul 13, 7:43 pm, Pete Stephenson <pete+use...@xxxxxxxxxxx> wrote:

Surely many of the stratum 1 servers (say, time.nist.gov) that get and
distribute time directly from atomic clocks aren't just off-the-shelf
servers with cheap, unstabilized system clocks, right? I know that many
of the public stratum 1 servers deployed by individuals and
organizations get their time from GPS, and are probably ordinary
computers, but I have this (again, perhaps incorrect) assumption that
the servers that supply the time /to/ the GPS system are not ordinary
computers.

time.nist.gov (and all of the other NIST time servers) use
standard
servers. The older systems are built using Tru64 Unix and the newer
ones are built using FreeBSD. The systems are synchronized using a
telephone connection to the NIST ACTS time service.
I have modified both the kernel and the serial port driver to reduce
the
jitter and latency, but the systems are basically off-the-shelf in
terms of
hardware.
Some of the systems have external rubidium atomic frequency standards.
These devices improve the short-term stability and the reliability
("Holdover
performance") of the system, but do not improve the accuracy very
much,
since the external clock must be set on time using some external
means.
The servers are synchronized using a separate process that is
independent
of NTP. It is an adaptive frequency-lock loop that adjusts itself for
the statistics
of each individual server The details are a bit complicated and have
been
published in the literature.
Once it has been characterized, a cheap computer clock can probably
provide
timing accuracy of about 50 milliseconds for 1 day with no external
calibration.
Cheap no-name hardware is typically worse, but your mileage may vary.
An
external quartz crystal oscillator might improve this to about 10
milliseconds
per day (characterized but free-running), but it is hard to do better
than that
without more expensive hardware and/or semi-heroic measures.

Judah Levine
Time and Frequency Division
NIST Boulder

.

Relevant Pages

  • Kernel clock issue "Clocksource tsc unstable"
    ... I have a wierd problem effecting two different 8.04LTS servers (fully ... Their clocks stop updating. ...
    (Ubuntu)
  • Re: kerberos and time zone
    ... issue lies in the fact that the servers are in different time-zone, ... machine (including the NTP service) is configured correctly. ... I neglected to mention this in my previous message, but the Kerberos ... national labs that have time standard setups have atomic clocks that ...
    (comp.protocols.kerberos)
  • Re: How do you change the system time of your whole domain?
    ... > decrements you ... > The servers don't set their clocks, apart from each other, ... > which is probably why the clocks are out of sync. ... > that document says that the time service synchronises ...
    (microsoft.public.win2000.active_directory)
  • Re: NTP architecture recommendation
    ... the offset between ALL servers needs to be < 3 ms; ... clocks in the datacenters; ... Meinberg Lantime M300 GPS with OCX LQ or even MQ in the office (ie. ... Many of the stratum 1 internet servers have local atomic ...
    (comp.protocols.time.ntp)
  • Re: Install Silverlight?
    ... probably be horrified to hear we never use Xeon processors for servers. ... I buy "cheap" quad core and dual core units and thus get twice as much bang for my buck. ... Well, perhaps you can argue with Western Digital over whether they are "cheap" and what that implies but we generally have good 320GB units that spin at 10,000 rpm. ... Most gamers spec their PCs better than most servers. ...
    (microsoft.public.windows.server.sbs)