[ntp:questions] TSC, default precision, FreeBSD
mills at udel.edu
Sun Sep 6 03:53:23 UTC 2009
No, what you suggest is properly called resolution, not precision. Do
your homework; -21 is just fine for a Sun faster than mine, where the
precision is -20. Confirm that the jitter.c program, included in the NTP
distribution for just that purpose, shows the gettimeofday() routine
takes on average 500 ns per call.
Richard B. Gilbert wrote:
>Garrett Wollman wrote:
>>In article <9fa237cd-eaf8-4303-8720-3e290547fa90 at g1g2000pra.googlegroups.com>,
>>Dave Hart <davehart at gmail.com> wrote:
>>>I hope this help you understand NTP precision. I also hope you will
>>>cease attempting to conflate it with any other definitions of
>>>"precision" or related terms.
>>It's a pity that the authors of the NTP specification chose to
>>Humpty-Dumpty an existing word with a well-defined meaning.
>At least it's stated what meaning it was "Humpty-Dumpty'd" to.
>Precision is the smallest possible difference between two consecutive
>readings of the system clock. It's normally expressed as a negative
>power of two. I once wrote a tiny program to read the clock twice in
>succession and do the arithmetic and ran it on a Sun Ultra 10
>workstation with a 440 MHz CPU. IIRC the result was 2^-21.
>It has nothing whatever to do with accuracy, it simply specifies how
>finely you can slice the time.
>questions mailing list
>questions at lists.ntp.org
More information about the questions