-----BEGIN PGP SIGNED MESSAGE----- Hash: RIPEMD160 Val Schmidt wrote: > Thanks Danny. > > So let me see if I can summarize what I think everyone has said in > these past few posts and you all can grade how well I was paying > attention. > >
[really good summary snipped] > Follow up Question: > > 1) From the discussion above, it is not at all clear how one measures > offsets less than about 10ms. How are measurements taken between a GPS > reference with 1PPS signal and the local system clock when people > report accuracies in the micro-seconds or even nano- seconds? Do I > understand correctly that the local system time typically can't be > reliably determined to better than 10's of milliseconds? > > -Val > > To get a time better than the resolution obtainable from the system clock tick frequency most modern OS's read the processor instruction counter. This is how I can tell you that my system time is good to +/- 20 microseconds relative to the PPS signal from my GPS. I don't agree with Brad that 10ms is as good as it gets, looking at the logs from my NTP box I see one excursion greater than 200us in the last month and that was when I rebuilt the OS (this on a soekris 4801 running FreeBSD 5.4) On my home server system (Celeron 2.9Ghz) I see a typical offset in the 10us range with fairly regular 200us and occasional 500us events. I hasn't been more than 1ms off since I hooked up the GPS. I suspect these events are due to rapid temperature changes caused by system load. John -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.1 (MingW32) iD8DBQFDPBwiaVyA7PElsKkRA8/wAJ9mJJV6GLS83YkKoOqHwWcedgzQ5ACfVHIJ kPzZ9HDk5zcjYgzh8FbJ448= =Or5r -----END PGP SIGNATURE----- _______________________________________________ questions mailing list [email protected] https://lists.ntp.isc.org/mailman/listinfo/questions
