summaryrefslogtreecommitdiffstats
path: root/conf.d
diff options
context:
space:
mode:
authorChris <github.account@chrigel.net>2018-07-03 21:01:51 +0200
committerChris <github.account@chrigel.net>2018-07-03 21:01:51 +0200
commit75eb439103e93f567ac47f5ee63f5c8586ba09b4 (patch)
tree2f69b9de3fc2df864d3c3dd47ad8bbdd3a00dba7 /conf.d
parent80e2409248fcc7754148d46861c76037ac5ba7bd (diff)
Add basic apcupsd alarm templates
Diffstat (limited to 'conf.d')
-rw-r--r--conf.d/Makefile.am1
-rw-r--r--conf.d/health.d/apcupsd.conf38
2 files changed, 39 insertions, 0 deletions
diff --git a/conf.d/Makefile.am b/conf.d/Makefile.am
index 72807b6804..7bd3622f65 100644
--- a/conf.d/Makefile.am
+++ b/conf.d/Makefile.am
@@ -88,6 +88,7 @@ healthconfigdir=$(configdir)/health.d
dist_healthconfig_DATA = \
health.d/apache.conf \
+ health.d/apcupsd.conf \
health.d/backend.conf \
health.d/bcache.conf \
health.d/beanstalkd.conf \
diff --git a/conf.d/health.d/apcupsd.conf b/conf.d/health.d/apcupsd.conf
new file mode 100644
index 0000000000..bfacaede50
--- /dev/null
+++ b/conf.d/health.d/apcupsd.conf
@@ -0,0 +1,38 @@
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+template: 10min_ups_load
+ on: apcupsd.load
+ os: *
+ hosts: *
+ lookup: average -10m unaligned of percentage
+ units: %
+ every: 1m
+ warn: $this > (($status >= $WARNING) ? (70) : (80))
+ crit: $this > (($status == $CRITICAL) ? (85) : (95))
+ delay: down 10m multiplier 1.5 max 1h
+ info: average UPS load for the last 10 minutes
+ to: sitemgr
+
+template: ups_charge
+ on: apcupsd.charge
+ os: *
+ hosts: *
+ lookup: average -60s unaligned of charge
+ units: %
+ every: 60s
+ warn: $this < (($status >= $WARNING) ? (90) : (95))
+ crit: $this < (($status == $CRITICAL) ? (20) : (15))
+ delay: down 10m multiplier 1.5 max 1h
+ info: current UPS charge, averaged over the last 60 seconds to reduce measurement errors
+ to: sitemgr
+
+template: apcupsd_last_collected_secs
+ on: apcupsd.load
+ calc: $now - $last_collected_t
+ every: 10s
+ units: seconds ago
+ warn: $this > (($status >= $WARNING) ? ($update_every) : ( 2 * $update_every))
+ crit: $this > (($status == $CRITICAL) ? ($update_every) : (10 * $update_every))
+ delay: down 5m multiplier 1.5 max 1h
+ info: number of seconds since the last successful data collection
+ to: sitemgr