From 8020f71afd34d7696d7933659df2d763ab05542f Mon Sep 17 00:00:00 2001 From: Daniel Baumann Date: Sat, 4 May 2024 16:31:17 +0200 Subject: Adding upstream version 1.37.1. Signed-off-by: Daniel Baumann --- health/health.d/load.conf | 66 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 66 insertions(+) create mode 100644 health/health.d/load.conf (limited to 'health/health.d/load.conf') diff --git a/health/health.d/load.conf b/health/health.d/load.conf new file mode 100644 index 0000000..0bd872f --- /dev/null +++ b/health/health.d/load.conf @@ -0,0 +1,66 @@ + +# 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 == inf or $active_processors < 2) ? ( 2 ) : ( $active_processors ) + units: cpus + every: 1m + info: number of active CPU cores in the system + +# Send alarms if the load average is unusually high. +# These intentionally _do not_ calculate the average over the sampled +# time period because the values being checked already are averages. + + alarm: load_average_15 + on: system.load + class: Utilization + type: System +component: Load + os: linux + hosts: * + lookup: max -1m unaligned of load15 + units: load + every: 1m + warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 175 : 200) + delay: down 15m multiplier 1.5 max 1h + info: system fifteen-minute load average + to: sysadmin + + alarm: load_average_5 + on: system.load + class: Utilization + type: System +component: Load + os: linux + hosts: * + lookup: max -1m unaligned of load5 + units: load + every: 1m + warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 350 : 400) + delay: down 15m multiplier 1.5 max 1h + info: system five-minute load average + to: sysadmin + + alarm: load_average_1 + on: system.load + class: Utilization + type: System +component: Load + os: linux + hosts: * + lookup: max -1m unaligned of load1 + units: load + every: 1m + warn: ($this * 100 / $load_cpu_number) > (($status >= $WARNING) ? 700 : 800) + delay: down 15m multiplier 1.5 max 1h + info: system one-minute load average + to: sysadmin -- cgit v1.2.3