[ntp:questions] 500ppm - is it too small?

Unruh unruh-spam at physics.ubc.ca
Fri May 8 03:23:27 UTC 2009


"Richard B. Gilbert" <rgilbert88 at comcast.net> writes:

>David J Taylor wrote:
>> Richard B. Gilbert wrote:
>> []
>>> An error greater than 500 PPM suggests seriously broken hardware! 
>>> There might be some way to "kludge" the software to compensate for
>>> this brokenness but I think it would be easier and cheaper to fix or
>>> replace the broken hardware.
>> 
>> I was trying to see what errors might be expected in the typical PC 
>> clock crystals, but my gut instinct is to agree with you.  However, 
>> suggesting that someone replace their pride and joy just because it 
>> doesn't run ntp is unlikely to elicit a favourable response!

>I'm not here to make people feel good!

>I've checked the hardware available to me and none is worse than 50 PPM.
>That's two PC's running Windows XP, three Sun Ultra 10 Workstations 
>running Solaris 8, 9, and 10, two DEC Alpha workstations running VMS.

>The specifications for NTPD say that it will correct errors less than or 
>equal to 500 PPM.

And that was a random figure chosen for no good reason, from what I can see. There is no 
reason why that figure could not be different.

>I beleive that hardware outside of this limit can properly be described 
>as broken!  Would *you* tolerate a clock, computer or wall, that gained 
>or lost more then 43 seconds per day?  Our forefathers, limited to 
>springs, gears and pendulums could do better than that.

I could define hardware outside of 1PPM as broken. the whole purpose of 
ntp is to take broken hardware and make it deliver the time accurately.
After using ntp, the computer will NOT deliver time that gains or looses more than 43 sec per day.




More information about the questions mailing list