[ntp:questions] best gps receiver for time synchronization

Unruh unruh-spam at physics.ubc.ca
Wed May 13 20:19:04 UTC 2009


"David J Taylor" <david-taylor at blueyonder.not-this-part.nor-this.co.uk.invalid> writes:

>Unruh wrote:
>[]
>> Since the same machine can run Linux or BSD whose resolution is usec
>> or
>> nsec, yes, the hardware can do better. The question is how good is the
>> software in the kernel. If I do a timestamp on an event, how accurate
>> is
>> that timestamp?
>> Is it msec? Is it 15msec?

>The precision with which a standard Windows system call returns the 
>current time will be 1 millisecond.  The value reported by that call may 
>step in 1, 10 or 15ms steps depending on the version of Windows you use, 
>and whether you turn on the "fast" timer (the multi-media timer).

>I am running ntp on windows and it is reporting offsets of a fraction of a 
>millisecond, so does that mean that the milliseconds reported are within a 
>millisecond of UTC?

Thanks. That was waht I wanted to know. 

>It's not a matter of "how good" is the kernel, it's what the design 
>specifications are, if I understand it correctly, and the design specs for 
>different versions of Windows are different.

Well, I call "good" to include the design. If a car is designed so that
the wheels fall off every 100 miles, no matter how closely the car meets
the design, it is a bad car.






More information about the questions mailing list