summaryrefslogtreecommitdiffstats
path: root/src/health/health.d/cgroups.conf
diff options
context:
space:
mode:
Diffstat (limited to 'src/health/health.d/cgroups.conf')
-rw-r--r--src/health/health.d/cgroups.conf67
1 files changed, 67 insertions, 0 deletions
diff --git a/src/health/health.d/cgroups.conf b/src/health/health.d/cgroups.conf
new file mode 100644
index 000000000..52ca02624
--- /dev/null
+++ b/src/health/health.d/cgroups.conf
@@ -0,0 +1,67 @@
+# you can disable an alarm notification by setting the 'to' line to: silent
+
+ template: cgroup_10min_cpu_usage
+ on: cgroup.cpu_limit
+ class: Utilization
+ type: Cgroups
+ component: CPU
+host labels: _os=linux
+ lookup: average -10m unaligned
+ units: %
+ every: 1m
+ warn: $this > (($status == $CRITICAL) ? (85) : (95))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Cgroup ${label:cgroup_name} CPU utilization
+ info: Cgroup ${label:cgroup_name} average CPU utilization over the last 10 minutes
+ to: silent
+
+ template: cgroup_ram_in_use
+ on: cgroup.mem_usage
+ class: Utilization
+ type: Cgroups
+ component: Memory
+host labels: _os=linux
+ calc: ($ram) * 100 / $memory_limit
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Cgroup ${label:cgroup_name} memory utilization
+ info: Cgroup ${label:cgroup_name} memory utilization
+ to: silent
+
+# ---------------------------------K8s containers--------------------------------------------
+
+ template: k8s_cgroup_10min_cpu_usage
+ on: k8s.cgroup.cpu_limit
+ class: Utilization
+ type: Cgroups
+ component: CPU
+host labels: _os=linux
+ lookup: average -10m unaligned
+ units: %
+ every: 1m
+ warn: $this > (($status >= $WARNING) ? (75) : (85))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} CPU utilization
+ info: Container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
+ average CPU utilization over the last 10 minutes
+ to: silent
+
+ template: k8s_cgroup_ram_in_use
+ on: k8s.cgroup.mem_usage
+ class: Utilization
+ type: Cgroups
+ component: Memory
+host labels: _os=linux
+ calc: ($ram) * 100 / $memory_limit
+ units: %
+ every: 10s
+ warn: $this > (($status >= $WARNING) ? (80) : (90))
+ crit: $this > (($status == $CRITICAL) ? (90) : (98))
+ delay: down 15m multiplier 1.5 max 1h
+ summary: Container ${label:k8s_container_name} pod ${label:k8s_pod_name} memory utilization
+ info: container ${label:k8s_container_name} of pod ${label:k8s_pod_name} of namespace ${label:k8s_namespace}, \
+ memory utilization
+ to: silent