martinhaus

- alert: DisableKubeDev
  override: ["K8S.*"]
  enabled: false
  expr: '{kubernetes_cluster="kube-dev"}'

martinhaus

# The result after pre-processing.

- alert: K8SNodeCPUUtilization
  expr: K8SNodeCPUUtilization{kubernetes_cluster!="kube-dev"} > 90
  for: 5m
  labels:
    severity: high
  annotations:
    identifier: '{{ $labels.kubernetes_cluster }}/{{ $labels.instance_name }}'
    msg: Node CPU ultilization by containers has been over 90% for more than 5m.

martinhaus

# The generic rule

- alert: K8SNodeCPUUtilization
  expr: K8SNodeCPUUtilization > 90
  for: 5m
  labels:
    severity: high
  annotations:
    identifier: '{{ $labels.kubernetes_cluster }}/{{ $labels.instance_name }}'
    msg: Node CPU ultilization by containers has been over 90% for more than 5m.

martinhaus

- alert: K8SNodeCPUUtilizationDev
  override: ["K8SNodeCPUUtilization"]
  enabled: true
  expr: K8SNodeCPUUtilization{kubernetes_cluster="kube-dev"}
  for: 1h
  labels:
    severity: warning
  annotations:
    identifier: '{{ $labels.kubernetes_cluster }}/{{ $labels.instance_name }}'
    msg: Node CPU ultilization by containers has been over 90% for more than 5m.

martinhaus

alert: K8SNodeCPUUtilization
Expr: node:node_container_cpu_usage_seconds:irate1m{kubernetes_cluster!="kube-dev"} / node:node_allocatable_cpu_cores:sum{kubernetes_cluster!="kube-dev"}) * 100 > 90
for: 5m
labels:
  group: system
  severity: high
annotations:
  identifier: '{{ $labels.kubernetes_cluster }}/{{ $labels.instance_name }}'
  msg: Node CPU ultilization by containers has been over 90% for more than 5m.
  reason: Node CPU ultilization by containers is high. Recalculate CPU request and

martinhaus

alert: K8SNodeCPUUtilizationDev
Expr: node:node_container_cpu_usage_seconds:irate1m{kubernetes_cluster=”kube-dev”} / node:node_allocatable_cpu_cores:sum{kubernetes_cluster=”kube-dev”}) * 100 > 90
for: 1h
labels:
  group: system
  severity: warning
annotations:
  identifier: '{{ $labels.kubernetes_cluster }}/{{ $labels.instance_name }}'
  msg: Node CPU ultilization by containers has been over 90% for more than 1h.
  reason: Node CPU ultilization by containers is high. Recalculate CPU request and

martinhaus

alert: K8SNodeCPUUtilization
Expr: node:node_container_cpu_usage_seconds:irate1m / node:node_allocatable_cpu_cores:sum) * 100 > 90
for: 5m
labels:
  group: system
  severity: high
annotations:
  identifier: '{{ $labels.kubernetes_cluster }}/{{ $labels.instance_name }}'
  msg: Node CPU ultilization by containers has been over 90% for more than 5m.
  reason: Node CPU ultilization by containers is high. Recalculate CPU request and