[ntpwg] Testing NTP performance

[TS Glassey]

----- Original Message ----- 
From: "Danny Mayer" <mayer at ntp.isc.org>
To: "Rob Seaman" <seaman at noao.edu>
Cc: <ntpwg at lists.ntp.org>
Sent: Saturday, May 03, 2008 3:54 PM
Subject: Re: [ntpwg] Testing NTP performance


> Rob Seaman wrote:
>> Not to get too philosophical, but isn't this a description of the
>> precise problem that NTP itself is designed to solve?
>>
>> Rob Seaman
>> NOAO
>
> I think that the real questions that needs to be answered are:
> 1) How accurate is the estimated offset that the server is using at any
> point in time;

yes

> 2) What is the error in the calculated frequency that the server has
> estimated;

yes

> 3) What is the error of the jitter that the server has calculated?

yes

But there is a minimum availability and loading overhaed model needed to 
manage the latency/overhead added by the underlying platform activity.


>
> There are two possibilities here:
> 1) The server itself calculates these values so it will have an estimate
> of the error;

yes - but the question of whether the main-thread of the server is handling 
this or there is some form of alternative or co-processor handling the 
overhead for the quantum non-deterministic values of the underlying platform 
dynamics.

The other possibility is to create a MACH or other uKernal type 
implementation to run the core NTP application suite on and rate performance 
relative to it as the reference system.

Todd
> 2) An external estimate of these errors introduces you to quantum
> physics issues, the measurement affects the values being measured.
>
> Does this restate the question better?
>
> Danny
> _______________________________________________
> ntpwg mailing list
> ntpwg at lists.ntp.org
> https://lists.ntp.org/mailman/listinfo/ntpwg