I had this problem for a while but I traced it back to the way the Munin
NTP plugins work.

Basically the plugins are very simple counters tracking the stats from
ntpdc/ntpq, what was happening in my case was that whenever I restarted
NTPD (or the server) these stats got reset to zero when Munin wasn't
expecting it.

In short; all of my spikes coincided with NTPD restarts.

Regards,

Oliver Jones

On 10 October 2012 13:23, Anssi Johansson <[email protected]> wrote:

> Simon Fondrie-Teitler kirjoitti:
>
>  I've got a server in the ntp pool with the connection speed set to
>> 1000Mbit. Munin is showing me spikes of up to 500k queries per
>> second. Is this a reasonably possible number, or is there likely
>> something wrong with either munin or ntp?
>>
>
> I'd venture to guess that those figures are erroneous. The highest spikes
> I've seen (averaged over five minutes) are around 26k queries per second.
> That server has two IP addresses, each configured for 1000Mbit.
>
> When in doubt, run tcpdump and capture the packets to your UDP port 123.
>
> ______________________________**_________________
> pool mailing list
> [email protected]
> http://lists.ntp.org/listinfo/**pool <http://lists.ntp.org/listinfo/pool>
>
_______________________________________________
pool mailing list
[email protected]
http://lists.ntp.org/listinfo/pool

Reply via email to