ced4568
4e8fa1d413
Self-hosted, no paid SaaS. Host/container/Postgres metrics, uptime probes against the new /healthz endpoints, alert rules split critical (pages) vs warning (informational), one starter Grafana dashboard. Deliberately separate from the application's instructor learning analytics (Phase 3B) - different audience, different data. Validated: promtool check config (valid), promtool check rules (11 rules, valid), amtool check-config (1 inhibit rule, 2 receivers, valid).
40 lines
1.3 KiB
Django/Jinja
40 lines
1.3 KiB
Django/Jinja
# Alertmanager config — routes CRITICAL alerts and WARNING alerts to the same webhook by
|
|
# default (Uptime Kuma's push-monitor webhook, or ntfy, or another already-available target —
|
|
# not a new paid service; the user's stated preference for Uptime Kuma is honored here without
|
|
# forcing it if a cleaner existing target turns out to be available at deploy time, per the
|
|
# Phase 4 instruction). Swap the receiver's url for whatever's actually wired up.
|
|
|
|
global:
|
|
resolve_timeout: 5m
|
|
|
|
route:
|
|
receiver: rootnode-default
|
|
group_by: ["alertname", "host"]
|
|
group_wait: 30s
|
|
group_interval: 5m
|
|
repeat_interval: 4h
|
|
routes:
|
|
- match:
|
|
severity: critical
|
|
receiver: rootnode-critical
|
|
repeat_interval: 30m
|
|
|
|
receivers:
|
|
- name: rootnode-default
|
|
webhook_configs:
|
|
- url: "{{ vault_alertmanager_webhook_url | default('http://example.invalid/webhook') }}"
|
|
send_resolved: true
|
|
|
|
- name: rootnode-critical
|
|
webhook_configs:
|
|
- url: "{{ vault_alertmanager_webhook_url | default('http://example.invalid/webhook') }}"
|
|
send_resolved: true
|
|
|
|
inhibit_rules:
|
|
# If the whole Lab Host is down, don't also page separately for every dependent warning.
|
|
- source_match:
|
|
alertname: LabHostDown
|
|
target_match:
|
|
severity: warning
|
|
equal: ["host"]
|