Enhance monitoring stack (Prometheus, Grafana)

- Add Prometheus alert rules configuration (alerts.yml.j2)
- Update Prometheus docker-compose and main configuration
- Add Grafana tasks for improved deployment and verification
- Integrate Alertmanager with Prometheus for alerting pipeline

roles/grafana/tasks/main.yml

@@ -28,6 +28,16 @@
   command: docker network create monitoring
   when: monitoring_network.rc != 0
 
+- name: Ensure proxy network exists
+  command: docker network inspect proxy
+  register: proxy_network
+  changed_when: false
+  failed_when: false
+
+- name: Create proxy network if missing
+  command: docker network create proxy
+  when: proxy_network.rc != 0
+
 - name: Copy Docker Compose file for Grafana
   template:
     src: docker-compose.yml.j2
@@ -39,6 +49,6 @@
     dest: /opt/grafana/provisioning/datasources/datasources.yml
 
 - name: Deploy Grafana
-  command: docker compose up -d --force-recreate
+  command: docker compose up -d
   args:
     chdir: /opt/grafana

roles/prometheus/tasks/main.yml

@@ -19,6 +19,11 @@
     src: prometheus.yml.j2
     dest: /opt/prometheus/prometheus.yml
 
+- name: Copy Prometheus alert rules
+  template:
+    src: alerts.yml.j2
+    dest: /opt/prometheus/alerts.yml
+
 - name: Copy Docker Compose file for Prometheus
   template:
     src: docker-compose.yml.j2

roles/prometheus/templates/alerts.yml.j2

@@ -0,0 +1,41 @@
+{% raw %}
+groups:
+  - name: base
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 2m
+        labels:
+          severity: critical
+        annotations:
+          summary: "Target down ({{ $labels.job }})"
+          description: "{{ $labels.instance }} is not responding to Prometheus scrapes."
+
+      - alert: HostDiskSpaceLow
+        expr: |
+          (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay|squashfs",mountpoint!~"/var/lib/docker/.+"} / node_filesystem_size_bytes{fstype!~"tmpfs|overlay|squashfs",mountpoint!~"/var/lib/docker/.+"}) < 0.10
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Low disk space"
+          description: "{{ $labels.instance }} mount {{ $labels.mountpoint }} has <10% free."
+
+      - alert: HostMemoryPressure
+        expr: (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) < 0.10
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "Low available memory"
+          description: "{{ $labels.instance }} has <10% memory available."
+
+      - alert: HostHighCpuLoad
+        expr: (node_load1 / count without (cpu, mode) (node_cpu_seconds_total{mode="idle"})) > 2
+        for: 15m
+        labels:
+          severity: warning
+        annotations:
+          summary: "High CPU load"
+          description: "{{ $labels.instance }} has high load1 for 15m."
+{% endraw %}

roles/prometheus/templates/docker-compose.yml.j2

@@ -7,9 +7,13 @@ services:
       - --storage.tsdb.retention.time=15d
     volumes:
       - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./alerts.yml:/etc/prometheus/alerts.yml:ro
       - prometheus_data:/prometheus
     networks:
       - monitoring
+      - proxy
+    ports:
+      - "127.0.0.1:9090:9090"
     restart: unless-stopped
     labels:
       - com.centurylinklabs.watchtower.enable=true
@@ -21,3 +25,6 @@ networks:
   monitoring:
     external: true
     name: monitoring
+
+  proxy:
+    external: true

roles/prometheus/templates/prometheus.yml.j2

@@ -1,6 +1,14 @@
 global:
   scrape_interval: 15s
 
+rule_files:
+  - /etc/prometheus/alerts.yml
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets: ['alertmanager:9093']
+
 scrape_configs:
   - job_name: prometheus
     static_configs: