added 'monitoring' path - ask devs why it's there

monitoring/cast04/prometheus.yml

@@ -0,0 +1,105 @@
+# Prometheus main config — cast04 (10.7.16.239)
+# Track A monitoring SPEC: ac-docs/specs/20260626_cluster_monitoring.md
+# Generated: 2026-06-26
+
+global:
+  scrape_interval:     15s
+  evaluation_interval: 15s
+  external_labels:
+    cluster: 'ac-cluster0'
+    monitor: 'cast04'
+
+rule_files:
+  - "/etc/prometheus/rules/*.yml"
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ['localhost:9093']
+
+scrape_configs:
+
+  # ── node_exporter on all cluster nodes ──────────────────────────────────────
+  - job_name: 'node'
+    static_configs:
+      - targets:
+          - '10.7.16.236:9100'   # cast01
+          - '10.7.16.237:9100'   # cast02
+          - '10.7.16.238:9100'   # cast03
+          - '10.7.16.239:9100'   # cast04 (self)
+          - '10.7.16.128:9100'   # artc0 (BE/MariaDB)
+        labels:
+          env: 'production'
+    relabel_configs:
+      - source_labels: [__address__]
+        regex: '(10\.7\.16\.236):.*'
+        target_label: instance
+        replacement: 'cast01'
+      - source_labels: [__address__]
+        regex: '(10\.7\.16\.237):.*'
+        target_label: instance
+        replacement: 'cast02'
+      - source_labels: [__address__]
+        regex: '(10\.7\.16\.238):.*'
+        target_label: instance
+        replacement: 'cast03'
+      - source_labels: [__address__]
+        regex: '(10\.7\.16\.239):.*'
+        target_label: instance
+        replacement: 'cast04'
+      - source_labels: [__address__]
+        regex: '(10\.7\.16\.128):.*'
+        target_label: instance
+        replacement: 'artc0'
+
+  # ── blackbox_exporter — HTTP probes (internal BE; FE port 443 unreachable from cluster) ─
+  # External HTTPS availability → UptimeRobot (SaaS external probe)
+  - job_name: 'blackbox_http'
+    metrics_path: /probe
+    params:
+      module: [http_2xx]
+    static_configs:
+      - targets:
+          - 'http://10.7.16.128/app/androidcast_project/'          # BE main app
+          - 'http://10.7.16.128/app/androidcast_project/issues/'   # crash reporter
+          - 'http://10.7.16.239:3000/api/health'                   # Grafana health
+        labels:
+          env: 'production'
+    relabel_configs:
+      - source_labels: [__address__]
+        target_label: __param_target
+      - source_labels: [__param_target]
+        target_label: instance
+      - target_label: __address__
+        replacement: 'localhost:9115'
+
+  # TCP probes removed: MariaDB uses skip-networking (socket only), PostgreSQL binds loopback only.
+  # Database health is covered by mysqld_exporter (job: mysqld) and postgres_exporter (job: postgres).
+
+  # ── MariaDB exporter (artc0) ─────────────────────────────────────────────────
+  - job_name: 'mysqld'
+    static_configs:
+      - targets: ['10.7.16.128:9104']
+        labels:
+          instance: 'artc0-mariadb'
+
+  # ── PostgreSQL exporter (cast01) ─────────────────────────────────────────────
+  - job_name: 'postgres'
+    static_configs:
+      - targets: ['10.7.16.236:9187']
+        labels:
+          instance: 'cast01-postgres'
+
+  # ── prometheus self-scrape ───────────────────────────────────────────────────
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+        labels:
+          instance: 'cast04-prometheus'
+
+  # ── alertmanager self-scrape ─────────────────────────────────────────────────
+  - job_name: 'alertmanager'
+    static_configs:
+      - targets: ['localhost:9093']
+        labels:
+          instance: 'cast04-alertmanager'