[collectd] load average peaks periodically on unloaded host

Vincent McIntyre vincent.mcintyre at gmail.com
Thu Mar 31 00:20:25 CEST 2011


I am running collectd 4.10 backported to debian lenny (official
backport), amd64.

I have a new host that is doing something odd - every 100 minutes or
so the load average
peaks at about 1.0-1.5. It rises over a period of a minute or so, bobs
around for a minute
or two and then declines steadily back to 0.0 after about 5 minutes.

I started turning things off and found that collectd seems to be the
culprit - the peaks go away entirely if I turn it off. If I turn off
say half of the plugins, the load peak still occurs but with half the
amplitude. I have a cron job printing the process table when the peak
is occurring but
nothing obvious shows up; the only process with %CPU larger than 0.0
is collectd. Neither does anything in the various plots (we use
collection3), related to collectd or the other processes that are
showing any activity (see Processes config below).

Has anyone seen this before? Any debugging tips?

Current collectd.conf:

FQDNLookup true
LoadPlugin syslog
<Plugin syslog>
        LogLevel info
Include "/etc/collectd/filters.conf"
Include "/etc/collectd/thresholds.conf"
LoadPlugin cpu
LoadPlugin disk
LoadPlugin interface
LoadPlugin load
LoadPlugin memory
LoadPlugin processes
LoadPlugin rrdtool
LoadPlugin network
<Plugin network>
LoadPlugin ntpd
<Plugin "ntpd">
  Host "localhost"
  Port "123"
  ReverseLookups false
<Plugin processes>
       Process "collectd"
       Process "ntpd"
       ProcessMatch "atop" "atop"
       ProcessMatch "exim4" "exim4"

More information about the collectd mailing list