torjus/nixos-servers
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects 1 Releases Wiki Activity

monitoring: exclude step-ca serving cert from general expiry alert #17

Merged
torjus merged 1 commits from monitoring-cleanup into master 2026-02-05 00:22:16 +00:00
Conversation 0 Commits 1 Files Changed 1 +9 -1
1 changed files with 9 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 3a9a47f1ad - Show all commits

10
services/monitoring/rules.yml
View File

@@ -307,13 +307,21 @@ groups:
- name: certificate_rules - name: certificate_rules
rules: rules:
- alert: certificate_expiring_soon - alert: certificate_expiring_soon
expr: labmon_tlsconmon_certificate_seconds_left < 86400 expr: labmon_tlsconmon_certificate_seconds_left{address!="ca.home.2rjus.net:443"} < 86400
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: "TLS certificate expiring soon for {{ $labels.instance }}" summary: "TLS certificate expiring soon for {{ $labels.instance }}"
description: "TLS certificate for {{ $labels.address }} is expiring within 24 hours." description: "TLS certificate for {{ $labels.address }} is expiring within 24 hours."
- alert: step_ca_serving_cert_expiring
expr: labmon_tlsconmon_certificate_seconds_left{address="ca.home.2rjus.net:443"} < 3600
for: 5m
labels:
severity: critical
annotations:
summary: "Step-CA serving certificate expiring"
description: "The step-ca serving certificate (24h auto-renewed) has less than 1 hour of validity left. Renewal may have failed."
- alert: certificate_check_error - alert: certificate_check_error
expr: labmon_tlsconmon_certificate_check_error == 1 expr: labmon_tlsconmon_certificate_check_error == 1
for: 5m for: 5m