summaryrefslogtreecommitdiffstats
path: root/health/health.d/load.conf
diff options
context:
space:
mode:
Diffstat (limited to 'health/health.d/load.conf')
-rw-r--r--health/health.d/load.conf20
1 files changed, 9 insertions, 11 deletions
diff --git a/health/health.d/load.conf b/health/health.d/load.conf
index ee0c54b8..ffaea172 100644
--- a/health/health.d/load.conf
+++ b/health/health.d/load.conf
@@ -4,18 +4,19 @@
# Calculate the base trigger point for the load average alarms.
# This is the maximum number of CPU's in the system over the past 1
# minute, with a special case for a single CPU of setting the trigger at 2.
- alarm: load_trigger
+ alarm: load_cpu_number
on: system.load
os: linux
hosts: *
calc: ($active_processors == nan or $active_processors == inf or $active_processors < 2) ? ( 2 ) : ( $active_processors )
units: cpus
every: 1m
- info: trigger point for load average alarms
+ info: number of active CPU cores in the system
# Send alarms if the load average is unusually high.
# These intentionally _do not_ calculate the average over the sampled
# time period because the values being checked already are averages.
+
alarm: load_average_15
on: system.load
os: linux
@@ -23,10 +24,9 @@
lookup: max -1m unaligned of load15
units: load
every: 1m
- warn: $this > (($status >= $WARNING) ? (1.75 * $load_trigger) : (2 * $load_trigger))
- crit: $this > (($status == $CRITICAL) ? (3.5 * $load_trigger) : (4 * $load_trigger))
+ warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 175 : 200)
delay: down 15m multiplier 1.5 max 1h
- info: fifteen-minute load average
+ info: system fifteen-minute load average
to: sysadmin
alarm: load_average_5
@@ -36,10 +36,9 @@
lookup: max -1m unaligned of load5
units: load
every: 1m
- warn: $this > (($status >= $WARNING) ? (3.5 * $load_trigger) : (4 * $load_trigger))
- crit: $this > (($status == $CRITICAL) ? (7 * $load_trigger) : (8 * $load_trigger))
+ warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 350 : 400)
delay: down 15m multiplier 1.5 max 1h
- info: five-minute load average
+ info: system five-minute load average
to: sysadmin
alarm: load_average_1
@@ -49,8 +48,7 @@
lookup: max -1m unaligned of load1
units: load
every: 1m
- warn: $this > (($status >= $WARNING) ? (7 * $load_trigger) : (8 * $load_trigger))
- crit: $this > (($status == $CRITICAL) ? (14 * $load_trigger) : (16 * $load_trigger))
+ warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 700 : 800)
delay: down 15m multiplier 1.5 max 1h
- info: one-minute load average
+ info: system one-minute load average
to: sysadmin