On 2015-10-05T14:06:22-0400, Dan Geist <[email protected]> wrote:
> Greetings, all. 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 thought I had
> was to make a small cluster of several VM servers and several bare
> metal ones and add all of them to some clients and simply observe
> deltas in ntpq stats. Does anyone know of other good ways to get
> some "apples-to-apples" comparison data?

Just anecdotal evidence, but with a properly configured VM, I think
you might have a hard time showing any difference. I see no difference
between my high-traffic Linode KVM NTP pool server and my bare metal
NTP servers.

http://www.pool.ntp.org/user/kenyon
http://kenyonralph.com/munin/time-day.html

NTP performance depends a lot more on network conditions than whether
it's a VM.

-- 
Kenyon Ralph

Attachment: signature.asc
Description: Digital signature

_______________________________________________
pool mailing list
[email protected]
http://lists.ntp.org/listinfo/pool

Reply via email to