acme: migrate from step-ca to OpenBao PKI
Switch all ACME certificate issuance from step-ca (ca.home.2rjus.net) to OpenBao PKI (vault.home.2rjus.net:8200/v1/pki_int/acme/directory). - Update default ACME server in system/acme.nix - Update Caddy acme_ca in http-proxy and nix-cache services - Remove labmon service from monitoring01 (step-ca monitoring) - Remove labmon scrape target and certificate_rules alerts - Remove alloy.nix (only used for labmon profiling) - Add docs/plans/cert-monitoring.md for future cert monitoring needs Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
@@ -338,40 +338,6 @@ groups:
|
||||
annotations:
|
||||
summary: "Pyroscope service not running on {{ $labels.instance }}"
|
||||
description: "Pyroscope service not running on {{ $labels.instance }}"
|
||||
- name: certificate_rules
|
||||
rules:
|
||||
- alert: certificate_expiring_soon
|
||||
expr: labmon_tlsconmon_certificate_seconds_left{address!="ca.home.2rjus.net:443"} < 86400
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "TLS certificate expiring soon for {{ $labels.instance }}"
|
||||
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
|
||||
expr: labmon_tlsconmon_certificate_check_error == 1
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Error checking certificate for {{ $labels.address }}"
|
||||
description: "Certificate check is failing for {{ $labels.address }} on {{ $labels.instance }}."
|
||||
- alert: step_ca_certificate_expiring
|
||||
expr: labmon_stepmon_certificate_seconds_left < 3600
|
||||
for: 5m
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Step-CA certificate expiring for {{ $labels.instance }}"
|
||||
description: "Step-CA certificate is expiring within 1 hour on {{ $labels.instance }}."
|
||||
- name: proxmox_rules
|
||||
rules:
|
||||
- alert: pve_node_down
|
||||
|
||||
Reference in New Issue
Block a user