- 中央:config/(prometheus,alertmanager,grafana)、apps/(tile-cache,topology-editor) - 边缘:config/(vmagent,blackbox,targets)、apps/(onvif-exporter) - env: TRAEFIK_PROVIDER、prometheus/env.example 详细说明 - 文档:README/doc 重构,EDGE_CACHE 合并到 EDGE_AGENT_CONFIG - targets.csv 更新流程说明,ARCHITECTURE 图收窄 Made-with: Cursor
50 lines
1.4 KiB
YAML
50 lines
1.4 KiB
YAML
groups:
|
|
- name: onvif_alerts
|
|
rules:
|
|
- alert: ONVIFDeviceDown
|
|
expr: up{job="onvif-devices"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "ONVIF设备离线"
|
|
description: "ONVIF设备 {{ $labels.instance }} 已离线超过1分钟"
|
|
|
|
- alert: ONVIFDeviceHighTemperature
|
|
expr: onvif_device_temperature > 70
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "ONVIF设备温度过高"
|
|
description: "设备 {{ $labels.instance }} 温度达到 {{ $value }}°C"
|
|
|
|
- alert: ONVIFDeviceLowStorage
|
|
expr: onvif_storage_usage_percent > 90
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "ONVIF设备存储空间不足"
|
|
description: "设备 {{ $labels.instance }} 存储使用率达到 {{ $value }}%"
|
|
|
|
- name: network_alerts
|
|
rules:
|
|
- alert: NetworkDeviceDown
|
|
expr: probe_success{job="network-ping"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "网络设备离线"
|
|
description: "网络设备 {{ $labels.instance }} 无法ping通"
|
|
|
|
- alert: HighNetworkLatency
|
|
expr: probe_duration_seconds{job="network-ping"} > 1
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "网络延迟过高"
|
|
description: "设备 {{ $labels.instance }} 延迟达到 {{ $value }}秒"
|