qpismont
ede28f6d12
Add hostmetrics receiver and OTel Collector telemetry, and move Alertmanager and Blackbox scraping to the collector. Raise collector memory limits, restrict Blackbox to HTTP 200, and add collector and Caddy down alerts with inhibition. Update portfolio title and copy.
28 lines
918 B
YAML
28 lines
918 B
YAML
groups:
|
|
- name: uptime_alerts
|
|
rules:
|
|
- alert: ServiceDown
|
|
expr: probe_success{job="blackbox_http"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "{{ $labels.instance }} est down"
|
|
description: "Le service {{ $labels.instance }} ne répond plus depuis plus d'1 minute."
|
|
- alert: OtelCollectorDown
|
|
expr: up{job="otel-collector"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "OTel Collector est down"
|
|
description: "L'OTel Collector ne répond plus depuis plus d'1 minute."
|
|
- alert: CaddyDown
|
|
expr: up{job="reverse_caddy"} == 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Caddy est down"
|
|
description: "Le reverse proxy Caddy ne répond plus depuis plus d'1 minute."
|