Heres some stats for you...
Both these servers are Stratum 2 on VPS's and look at my own Statum 1 PPS
Server in Spain. Data is whats currently reported to me from munin.
neon.trippett.org NL - Xen
Cur Min Avg Max
UDP Connections 3.5k 3.0k 9.92k 31.6k
Packets Per Second 110 90 255 807
NTP Delay 9.3m 8.4m 9.04m 26m
NTP Offset -1.2m -4.29m 889u 4.52m
NTP Jitter 195u 58u 889u 4.52m
argon.trippett.org DE - Xen
Cur Min Avg Max
UDP Connections 6.09k 2.22k 6.25k 15.52k
Packets Per Second 563 457 560 884
NTP Delay 2.9m 1.9m 5.3m 11m
NTP Offset -202u -1.6m -59u 1.5m
NTP Jitter 289u 46u 505u 2.11m
On Thu, Jan 07, 2016 at 10:57:57AM +0100, Kiss Gábor wrote:
> On 5th of October, 2015 Dan Geist wrote:
>
> > I've been challenged to show some evidence that ntpd running on a VM (as a
> > stratum 2 server in a company-internal pool) really does perform differently
> > than on bare metal.
> > Can anyone point me to any non-anecdotal scenarios or
> > tests that might help demonstrate the performance/accuracy differences? One
>
> Now I set up a (non public) NTP server on a VM.
> Number of planned clients is about 5500. (They are various Cisco routers.)
> I measure offset, dispersion, jitter in every 5 minutes.
> I'll inform you, guys, if as soon as I have some experiences.
>
> Gabor
> _______________________________________________
> pool mailing list
> [email protected]
> http://lists.ntp.org/listinfo/pool
_______________________________________________
pool mailing list
[email protected]
http://lists.ntp.org/listinfo/pool
