How much do we care about high-load scenarios?

Eric S. Raymond esr at
Tue Sep 13 09:20:04 UTC 2016

Gary E. Miller <gem at>:
> > I'd prefer to bias towards architectural simplicity unless and until
> > field reports force us to optimize for the high-load case.
> If NTPsec is to seriously challenge NTP Classic, it must outperform
> NTPsec at the bleeding edge.  In the NTP case that is high load
> factor and high performance.

Me, I would have thought that since we chose to brand ourselves
"NTPsec", security is the relevant dimension of performance, and not
having more holes than a shotgunned colander would be sufficient to
get past Classic.

We can actually point to one other dimension of better performance right
now. We step at a theoretical 10e3 higher accuracy - less than that in
practice but only because nothing shy of a cesium-fountain clock can
slice time that fine.

Given these, I'm really curious why you choose high-load performance as a
hill to die on.
		<a href="">Eric S. Raymond</a>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 811 bytes
Desc: not available
URL: <>

More information about the devel mailing list