add: lab08 solution and report

Author: Ge-os

ansible/playbooks/deploy-monitoring.yml

@@ -1,8 +1,8 @@
 ---
 # Deploy Loki Monitoring Stack
-# This playbook deploys the complete logging stack with Loki, Promtail, and Grafana
+# This playbook deploys the complete observability stack with Prometheus, Loki, Promtail, and Grafana
 
-- name: Deploy Loki Monitoring Stack
+- name: Deploy Observability Monitoring Stack
   hosts: all
   become: true
 
@@ -38,6 +38,7 @@
           
           Services:
           - Grafana: http://{{ ansible_default_ipv4.address | default('localhost') }}:{{ grafana_port }}
+          - Prometheus: http://{{ ansible_default_ipv4.address | default('localhost') }}:{{ prometheus_port }}
           - Loki API: http://{{ ansible_default_ipv4.address | default('localhost') }}:{{ loki_port }}
           - Promtail: http://{{ ansible_default_ipv4.address | default('localhost') }}:{{ promtail_port }}
           {% if python_app_enabled %}
@@ -49,16 +50,18 @@
           - Password: (check {{ monitoring_dir }}/.env on target host)
           
           Configuration:
+          - Prometheus Version: {{ prometheus_version }}
+          - Prometheus Retention: {{ prometheus_retention_days }}d / {{ prometheus_retention_size }}
           - Log Retention: {{ loki_retention_period }}
           - Loki Version: {{ loki_version }}
           - Grafana Version: {{ grafana_version }}
           
           Next Steps:
-          1. Access Grafana web UI
-          2. Verify Loki datasource is configured
-          3. Navigate to Explore and run: {job="docker"}
-          4. Create dashboards based on Lab 7 requirements
-          5. Take screenshots for documentation
+          1. Open Prometheus targets page and verify all jobs are UP
+          2. Access Grafana web UI and verify Loki + Prometheus datasources
+          3. Open pre-provisioned logs and metrics dashboards
+          4. Generate app traffic and validate live metrics/log streams
+          5. Take screenshots for Lab 8 documentation
           
           Useful Commands:
           - View logs: docker compose -f {{ monitoring_dir }}/docker-compose.yml logs -f

ansible/roles/monitoring/README.md

@@ -1,6 +1,6 @@
 # Monitoring Ansible Role
 
-This Ansible role deploys the Grafana Loki monitoring stack including Loki 3.0, Promtail 3.0, and Grafana 11.3.1.
+This Ansible role deploys the full observability stack including Prometheus 3.9, Loki 3.0, Promtail 3.0, and Grafana 12.3 with pre-provisioned datasources and dashboards.
 
 ## Requirements
 
@@ -18,16 +18,23 @@ See `defaults/main.yml` for all available variables. Key variables:
 # Service versions
 loki_version: "3.0.0"
 promtail_version: "3.0.0"
-grafana_version: "11.3.1"
+grafana_version: "12.3.0"
+prometheus_version: "3.9.0"
 
 # Service ports
+prometheus_port: 9090
 loki_port: 3100
 grafana_port: 3000
 promtail_port: 9080
 
 # Loki configuration
 loki_retention_period: "168h"  # 7 days
 
+# Prometheus configuration
+prometheus_retention_days: 15
+prometheus_retention_size: "10GB"
+prometheus_scrape_interval: "15s"
+
 # Grafana security
 grafana_admin_user: "admin"
 grafana_admin_password: "{{ vault_grafana_password }}"
@@ -96,7 +103,8 @@ ansible-playbook -i inventory/hosts.ini playbooks/deploy-monitoring.yml --limit
 - **Idempotent**: Safe to run multiple times
 - **Templated Configs**: Easy to customize via variables
 - **Health Checks**: Automatic service health verification
-- **Grafana Provisioning**: Auto-configured Loki datasource
+- **Grafana Provisioning**: Auto-configured Loki + Prometheus datasources
+- **Dashboard Provisioning**: Auto-imported logs + metrics dashboards
 - **Security**: Secrets managed via Ansible Vault
 - **Resource Limits**: Configurable resource constraints
 - **Multi-Environment**: Support for dev/staging/prod
@@ -105,10 +113,11 @@ ansible-playbook -i inventory/hosts.ini playbooks/deploy-monitoring.yml --limit
 
 The role deploys:
 
-1. **Loki**: Log aggregation with TSDB storage
-2. **Promtail**: Docker log collector with service discovery
-3. **Grafana**: Visualization with pre-configured Loki datasource
-4. **Python App** (optional): Application with JSON logging
+1. **Prometheus**: Metrics collection and TSDB storage
+2. **Loki**: Log aggregation with TSDB storage
+3. **Promtail**: Docker log collector with service discovery
+4. **Grafana**: Visualization with pre-configured Loki + Prometheus datasources
+5. **Python App** (optional): Application with JSON logging and `/metrics`
 
 All services run in Docker containers managed by Docker Compose.
 
@@ -125,7 +134,11 @@ monitoring/
 │   ├── docker-compose.yml.j2  # Docker Compose template
 │   ├── loki-config.yml.j2     # Loki configuration
 │   ├── promtail-config.yml.j2 # Promtail configuration
+│   ├── prometheus.yml.j2      # Prometheus scrape configuration
 │   └── env.j2                 # Environment variables
+├── files/
+│   ├── grafana-app-dashboard.json
+│   └── grafana-logs-dashboard.json
 ├── handlers/main.yml      # Service restart handlers
 └── meta/main.yml          # Role metadata
 ```
@@ -135,6 +148,7 @@ monitoring/
 After deployment, the stack is available at:
 
 - **Grafana**: http://localhost:3000
+- **Prometheus**: http://localhost:9090
 - **Loki API**: http://localhost:3100
 - **Promtail**: http://localhost:9080
 

ansible/roles/monitoring/defaults/main.yml

@@ -4,19 +4,39 @@
 # Service versions
 loki_version: "3.0.0"
 promtail_version: "3.0.0"
-grafana_version: "11.3.1"
+grafana_version: "12.3.0"
+prometheus_version: "3.9.0"
 
 # Service ports
 loki_port: 3100
 grafana_port: 3000
 promtail_port: 9080
+prometheus_port: 9090
 
 # Loki configuration
 loki_retention_period: "168h"  # 7 days
 loki_schema_version: "v13"
 loki_compaction_interval: "10m"
 loki_retention_delete_delay: "2h"
 
+# Prometheus configuration
+prometheus_retention_days: 15
+prometheus_retention_size: "10GB"
+prometheus_scrape_interval: "15s"
+
+prometheus_targets:
+  - job: "prometheus"
+    targets: ["localhost:9090"]
+  - job: "loki"
+    targets: ["loki:3100"]
+    path: "/metrics"
+  - job: "grafana"
+    targets: ["grafana:3000"]
+    path: "/metrics"
+  - job: "app"
+    targets: ["app-python:5000"]
+    path: "/metrics"
+
 # Resource limits
 loki_memory_limit: "1G"
 loki_cpu_limit: "1.0"
@@ -25,8 +45,13 @@ loki_cpu_reservation: "0.5"
 
 grafana_memory_limit: "1G"
 grafana_cpu_limit: "1.0"
-grafana_memory_reservation: "512M"
-grafana_cpu_reservation: "0.5"
+grafana_memory_reservation: "256M"
+grafana_cpu_reservation: "0.25"
+
+prometheus_memory_limit: "1G"
+prometheus_cpu_limit: "1.0"
+prometheus_memory_reservation: "512M"
+prometheus_cpu_reservation: "0.5"
 
 promtail_memory_limit: "512M"
 promtail_cpu_limit: "0.5"
@@ -49,6 +74,10 @@ python_app_port: 8000
 python_app_internal_port: 5000
 python_app_log_level: "INFO"
 python_app_context: "../app_python"
+python_app_memory_limit: "256M"
+python_app_cpu_limit: "0.5"
+python_app_memory_reservation: "128M"
+python_app_cpu_reservation: "0.25"
 
 # Docker configuration
 docker_network_name: "logging-network"