monitoring/conf/prometheus/alerts/google-cadvisor.yml
nyyu f7d73a0df5
All checks were successful
ci/woodpecker/push/woodpecker Pipeline was successful
feat: alerts
2025-01-06 08:45:05 +01:00

77 lines
3.6 KiB
YAML

groups:
- name: GoogleCadvisor
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: ContainerAbsent
expr: 'absent(container_last_seen)'
for: 5m
labels:
severity: warning
annotations:
summary: Container absent (instance {{ $labels.instance }})
description: "A container is absent for 5 min\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 }}"
- alert: ContainerVolumeUsage
expr: '(1 - (sum(container_fs_inodes_free{name!=""}) BY (instance) / sum(container_fs_inodes_total) BY (instance))) * 100 > 80'
for: 2m
labels:
severity: warning
annotations:
summary: Container Volume usage (instance {{ $labels.instance }})
description: "Container Volume usage is above 80%\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ContainerHighThrottleRate
expr: 'sum(increase(container_cpu_cfs_throttled_periods_total{container!=""}[5m])) by (container, pod, namespace) / sum(increase(container_cpu_cfs_periods_total[5m])) by (container, pod, namespace) > ( 25 / 100 )'
for: 5m
labels:
severity: warning
annotations:
summary: Container high throttle rate (instance {{ $labels.instance }})
description: "Container is being throttled\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ContainerLowCpuUtilization
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) < 20'
for: 7d
labels:
severity: info
annotations:
summary: Container Low CPU utilization (instance {{ $labels.instance }})
description: "Container CPU utilization is under 20% for 1 week. Consider reducing the allocated CPU.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: ContainerLowMemoryUsage
expr: '(sum(container_memory_working_set_bytes{name!=""}) BY (instance, name) / sum(container_spec_memory_limit_bytes > 0) BY (instance, name) * 100) < 20'
for: 7d
labels:
severity: info
annotations:
summary: Container Low Memory usage (instance {{ $labels.instance }})
description: "Container Memory usage is under 20% for 1 week. Consider reducing the allocated memory.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"