Deployed prometheus/grafana

ansible/playbooks/roles/monitoring/templates/alertmanager.yml.j2

@@ -0,0 +1,13 @@
+# ------------------------------------------------------------------------------
+# FILE: roles/monitoring/templates/alertmanager.yml.j2
+# DESCRIPTION: Alertmanager configuration — routing deferred (P.XX)
+# ------------------------------------------------------------------------------
+
+route:
+  receiver: blackhole
+  group_wait: 30s
+  group_interval: 5m
+  repeat_interval: 4h
+
+receivers:
+  - name: blackhole

ansible/playbooks/roles/monitoring/templates/env.j2

@@ -0,0 +1,11 @@
+# ------------------------------------------------------------------------------
+# FILE: roles/monitoring/templates/env.j2
+# DESCRIPTION: Environment file for monitoring compose stack
+# Deployed to {{ monitoring_base_dir }}/.env
+# ------------------------------------------------------------------------------
+
+GRAFANA_ADMIN_USER={{ grafana_admin_user }}
+GRAFANA_ADMIN_PASSWORD={{ grafana_admin_password }}
+PROMETHEUS_RETENTION_TIME={{ prometheus_retention_time }}
+PROMETHEUS_RETENTION_SIZE={{ prometheus_retention_size }}
+TRUSTED_PROXIES={{ trusted_proxy_ip }}

ansible/playbooks/roles/monitoring/templates/grafana-datasource.yml.j2

@@ -0,0 +1,14 @@
+# ------------------------------------------------------------------------------
+# FILE: roles/monitoring/templates/grafana-datasource.yml.j2
+# DESCRIPTION: Auto-provisions Prometheus as Grafana default datasource
+# ------------------------------------------------------------------------------
+
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: false

ansible/playbooks/roles/monitoring/templates/prometheus.yaml.j2

@@ -0,0 +1,50 @@
+# ------------------------------------------------------------------------------
+# FILE: roles/monitoring/templates/prometheus.yml.j2
+# DESCRIPTION: Prometheus scrape configuration
+# ------------------------------------------------------------------------------
+
+global:
+  scrape_interval: {{ prometheus_scrape_interval }}
+  evaluation_interval: {{ prometheus_scrape_interval }}
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+            - alertmanager:9093
+
+rule_files: []
+
+scrape_configs:
+
+  # Prometheus self-monitoring
+  - job_name: prometheus
+    static_configs:
+      - targets:
+          - localhost:9090
+
+  # cinderella-castle node exporter (this host)
+  - job_name: node-cinderella-castle
+    static_configs:
+      - targets:
+          - cinderella-castle:9100
+        labels:
+          hostname: cinderella-castle
+
+  # Proxmox nodes
+  - job_name: proxmox-nodes
+    static_configs:
+      - targets:
+          - 10.1.71.11:9100
+          - 10.1.71.12:9100
+          - 10.1.71.13:9100
+        labels:
+          job: proxmox
+
+  # Traefik metrics
+  - job_name: traefik
+    static_configs:
+      - targets:
+          - 10.1.71.35:8080
+        labels:
+          hostname: lightning-lane