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
