28 lines
1.3 KiB
YAML
28 lines
1.3 KiB
YAML
groups:
|
|
- name: container
|
|
interval: 15s
|
|
rules:
|
|
- alert: ContainerKilled
|
|
expr: time() - container_last_seen > 60
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Container killed (instance {{ $labels.instance }})
|
|
description: "A container has disappeared\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: ContainerHighCpuUtilization
|
|
expr: (sum(rate(container_cpu_usage_seconds_total{container!=""}[5m])) by (pod, container) / sum(container_spec_cpu_quota{container!=""}/container_spec_cpu_period{container!=""}) by (pod, container) * 100) > 80
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Container High CPU utilization (instance {{ $labels.instance }})
|
|
description: "Container CPU utilization is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: ContainerHighMemoryUsage
|
|
expr: (sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) > 80
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Container High Memory usage (instance {{ $labels.instance }})
|
|
description: "Container Memory usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" |