- Prometheus alert rules (files/alerting-rules.yml): SiteDown,
CertificateExpiringSoon, ScrapeTargetDown, GpuOverheating (>= 85 C),
HostOverheating and HostRebooted. Disk and RAM are already covered by
Grafana rules. Templates use Helm's {{` `}} escaping because the chart
runs alertingRules through tpl.
- Alertmanager routes everything to the grafana-matrix-forwarder (same
Matrix room as Grafana alerts), resolved notifications on, repeat 24h.
- Blackbox exporter (prom/blackbox-exporter) probing every public site,
plus a scrape job for the NVIDIA DCGM exporter (T4 temperature, clocks).
- forum-digest CronJob (9:00 ET): posts unanswered member topics on
discourse.eom.dev to Matrix through the same forwarder, and nothing when
there are none. Standard-library Python, public Discourse JSON only.
These replace the LocalAI SRE and community agents, which were too slow
and unreliable on the throttled T4.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
35 lines
1.2 KiB
YAML
35 lines
1.2 KiB
YAML
#SPDX-License-Identifier: MIT-0
|
|
---
|
|
# defaults file for ansible-role-prometheus
|
|
prometheus_blackbox_exporter_tag: v0.27.0
|
|
# Grafana-matrix-forwarder endpoint; the room is the existing Grafana alerts room.
|
|
prometheus_matrix_forwarder_url: "http://matrix-forwarder.grafana-matrix-forwarder.svc.cluster.local/api/v1/unified?roomId=!HOBNfTFECIjTOhxwDe:eom.dev"
|
|
prometheus_alert_repeat_interval: 24h
|
|
prometheus_blackbox_targets:
|
|
- https://www.eom.dev
|
|
- https://eom.dev
|
|
- https://discourse.eom.dev
|
|
- https://gitea.eom.dev
|
|
- https://nextcloud.eom.dev
|
|
- https://element.eom.dev
|
|
- https://synapse.eom.dev
|
|
- https://mas.eom.dev
|
|
- https://dex.eom.dev
|
|
- https://peertube.eom.dev
|
|
- https://owncast.eom.dev
|
|
- https://mastodon.eom.dev
|
|
- https://listmonk.eom.dev
|
|
- https://mailman.eom.dev
|
|
- https://grafana.eom.dev
|
|
- https://localai.eom.dev
|
|
- https://wanderer.eom.dev
|
|
- https://wikideck.eom.dev
|
|
- https://button.eom.dev
|
|
- https://collabora.eom.dev
|
|
- https://fediprofile.eom.dev
|
|
- https://minio.eom.dev
|
|
- https://shkeeper.eom.dev
|
|
# Daily digest of unanswered forum topics (9:00 US Eastern).
|
|
prometheus_forum_digest_schedule: "0 9 * * *"
|
|
prometheus_forum_digest_exclude: [eric, claude]
|