plasmagoat/homelab
1
0
Fork 0
Code Issues Pull requests 1 Projects Releases Packages Wiki Activity Actions

colmena initial implementation for sandbox and monitor
All checks were successful
Hello World / test (push) Successful in 4s
Details

Browse source
This commit is contained in:
plasmagoat 2025-07-06 21:25:57 +02:00
parent a90630ecb6
commit 5feb74d56d
40 changed files with 27629 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

21
machines/monitor/provisioning/alerts/promtail-alerts.yml Normal file
View file

@ -0,0 +1,21 @@
groups:
- name: Promtail
rules:
- alert: PromtailRequestErrors
expr: '100 * sum(rate(promtail_request_duration_seconds_count{status_code=~"5..|failed"}[1m])) by (namespace, job, route, instance) / sum(rate(promtail_request_duration_seconds_count[1m])) by (namespace, job, route, instance) > 10'
for: 5m
labels:
severity: critical
annotations:
summary: Promtail request errors (instance {{ $labels.instance }})
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: PromtailRequestLatency
expr: "histogram_quantile(0.99, sum(rate(promtail_request_duration_seconds_bucket[5m])) by (le)) > 1"
for: 5m
labels:
severity: critical
annotations:
summary: Promtail request latency (instance {{ $labels.instance }})
description: "The {{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"