1 files changed, 72 insertions, 0 deletions
diff --git a/health/health.d/load.conf b/health/health.d/load.conf
new file mode 100644
index 00000000..fd8bf939
--- /dev/null
+++ b/health/health.d/load.conf
@@ -0,0 +1,72 @@
+
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+# 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_cpu_number
+       on: system.load
+    class: Utilization
+     type: System
+component: Load
+       os: linux
+    hosts: *
+     calc: ($active_processors == nan or $active_processors == 0) ? (nan) : ( ($active_processors < 2) ? ( 2 ) : ( $active_processors ) )
+    units: cpus
+    every: 1m
+     info: Number of active CPU cores in the system
+
+# Send alarms if the load average is unusually high.
+# These intentionally _do not_ calculate the average over the sampled
+# time period because the values being checked already are averages.
+
+    alarm: load_average_15
+       on: system.load
+    class: Utilization
+     type: System
+component: Load
+       os: linux
+    hosts: *
+   lookup: max -1m unaligned of load15
+     calc: ($load_cpu_number == nan) ? (nan) : ($this)
+    units: load
+    every: 1m
+     warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 175 : 200)
+    delay: down 15m multiplier 1.5 max 1h
+  summary: Host load average (15 minutes)
+     info: System load average for the past 15 minutes
+       to: silent
+
+    alarm: load_average_5
+       on: system.load
+    class: Utilization
+     type: System
+component: Load
+       os: linux
+    hosts: *
+   lookup: max -1m unaligned of load5
+     calc: ($load_cpu_number == nan) ? (nan) : ($this)
+    units: load
+    every: 1m
+     warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 350 : 400)
+    delay: down 15m multiplier 1.5 max 1h
+  summary: System load average (5 minutes)
+     info: System load average for the past 5 minutes
+       to: silent
+
+    alarm: load_average_1
+       on: system.load
+    class: Utilization
+     type: System
+component: Load
+       os: linux
+    hosts: *
+   lookup: max -1m unaligned of load1
+     calc: ($load_cpu_number == nan) ? (nan) : ($this)
+    units: load
+    every: 1m
+     warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 700 : 800)
+    delay: down 15m multiplier 1.5 max 1h
+  summary: System load average (1 minute)
+     info: System load average for the past 1 minute
+       to: silent