🔍 Version 3.0: Complete Observability & Security Stack

✨ Monitoring & Observability:
- Prometheus metrics collection for all services
- Grafana dashboards for real-time visualization
- ELK Stack (Elasticsearch + Logstash + Kibana) for centralized logging
- Performance metrics with histogram and counters
- Custom alerting rules and notifications

🔐 Security & Performance:
- Redis-based distributed rate limiting
- API security middleware with Helmet.js
- Performance monitoring with response time tracking
- Request/response logging and correlation IDs
- Error tracking and alerting system

🏗️ Infrastructure: Production-ready monitoring stack
📊 Observability: Complete metrics, logs, and traces ecosystem

Author: rayhan1967

docker-compose.yml

@@ -44,3 +44,78 @@ volumes:
 networks:
   microservices-network:
     driver: bridge
+
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: prometheus
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./monitoring/prometheus:/etc/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.console.libraries=/etc/prometheus/console_libraries'
+      - '--web.console.templates=/etc/prometheus/consoles'
+    networks:
+      - microservices-network
+
+  grafana:
+    image: grafana/grafana:latest
+    container_name: grafana
+    ports:
+      - "3013:3000"
+    environment:
+      - GF_SECURITY_ADMIN_PASSWORD=admin123
+    volumes:
+      - grafana-storage:/var/lib/grafana
+      - ./monitoring/grafana:/etc/grafana/provisioning
+    networks:
+      - microservices-network
+
+volumes:
+  grafana-storage:
+
+  elasticsearch:
+    image: docker.elastic.co/elasticsearch/elasticsearch:8.11.0
+    container_name: elasticsearch
+    environment:
+      - discovery.type=single-node
+      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
+      - xpack.security.enabled=false
+    ports:
+      - "9200:9200"
+    volumes:
+      - elasticsearch_data:/usr/share/elasticsearch/data
+    networks:
+      - microservices-network
+
+  logstash:
+    image: docker.elastic.co/logstash/logstash:8.11.0
+    container_name: logstash
+    ports:
+      - "5044:5044"
+      - "9600:9600"
+    volumes:
+      - ./monitoring/logstash:/usr/share/logstash/pipeline
+    environment:
+      - "LS_JAVA_OPTS=-Xmx256m -Xms256m"
+    networks:
+      - microservices-network
+    depends_on:
+      - elasticsearch
+
+  kibana:
+    image: docker.elastic.co/kibana/kibana:8.11.0
+    container_name: kibana
+    ports:
+      - "5601:5601"
+    environment:
+      - ELASTICSEARCH_HOSTS=http://elasticsearch:9200
+    networks:
+      - microservices-network
+    depends_on:
+      - elasticsearch
+
+volumes:
+  elasticsearch_data:

monitoring/grafana/dashboard.json

@@ -0,0 +1,27 @@
+{
+  "dashboard": {
+    "title": "Microservices Dashboard",
+    "panels": [
+      {
+        "title": "Request Rate",
+        "type": "graph",
+        "targets": [
+          {
+            "expr": "rate(http_requests_total[5m])",
+            "legendFormat": "{{service}}"
+          }
+        ]
+      },
+      {
+        "title": "Response Time",
+        "type": "graph", 
+        "targets": [
+          {
+            "expr": "histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))",
+            "legendFormat": "95th percentile"
+          }
+        ]
+      }
+    ]
+  }
+}

monitoring/logstash/logstash.conf

@@ -0,0 +1,31 @@
+input {
+  beats {
+    port => 5044
+  }
+  tcp {
+    port => 5000
+    codec => json_lines
+  }
+}
+
+filter {
+  if [service] {
+    mutate {
+      add_field => { "service_name" => "%{service}" }
+    }
+  }
+  
+  if [level] == "ERROR" {
+    mutate {
+      add_tag => [ "error" ]
+    }
+  }
+}
+
+output {
+  elasticsearch {
+    hosts => ["elasticsearch:9200"]
+    index => "microservices-logs-%{+YYYY.MM.dd}"
+  }
+  stdout { codec => rubydebug }
+}

monitoring/prometheus/prometheus.yml

@@ -0,0 +1,33 @@
+global:
+  scrape_interval: 15s
+  evaluation_interval: 15s
+
+rule_files:
+  - "alert_rules.yml"
+
+scrape_configs:
+  - job_name: 'user-service'
+    static_configs:
+      - targets: ['user-service:3001']
+    metrics_path: '/metrics'
+    
+  - job_name: 'product-service'
+    static_configs:
+      - targets: ['product-service:3002']
+    metrics_path: '/metrics'
+    
+  - job_name: 'order-service'
+    static_configs:
+      - targets: ['order-service:3003']
+    metrics_path: '/metrics'
+    
+  - job_name: 'api-gateway'
+    static_configs:
+      - targets: ['api-gateway:3000']
+    metrics_path: '/metrics'
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+          - alertmanager:9093

shared/middleware/performance.js

@@ -0,0 +1,35 @@
+const promClient = require('prom-client');
+
+// Create metrics
+const httpRequestDuration = new promClient.Histogram({
+  name: 'http_request_duration_seconds',
+  help: 'Duration of HTTP requests in seconds',
+  labelNames: ['method', 'route', 'status_code'],
+  buckets: [0.001, 0.005, 0.015, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 1.0]
+});
+
+const httpRequestsTotal = new promClient.Counter({
+  name: 'http_requests_total',
+  help: 'Total number of HTTP requests',
+  labelNames: ['method', 'route', 'status_code']
+});
+
+const performanceMiddleware = (req, res, next) => {
+  const start = Date.now();
+  
+  res.on('finish', () => {
+    const duration = (Date.now() - start) / 1000;
+    const labels = {
+      method: req.method,
+      route: req.route?.path || req.path,
+      status_code: res.statusCode
+    };
+    
+    httpRequestDuration.observe(labels, duration);
+    httpRequestsTotal.inc(labels);
+  });
+  
+  next();
+};
+
+module.exports = { performanceMiddleware, httpRequestDuration, httpRequestsTotal };