Implement Node.js application monitoring with Prometheus metrics and Grafana dashboards

Install Prometheus server

Start by installing Prometheus to collect and store metrics from your Node.js applications.

sudo apt update
sudo apt install -y prometheus prometheus-node-exporter
sudo systemctl enable --now prometheus
sudo systemctl enable --now prometheus-node-exporter

sudo dnf install -y epel-release
sudo dnf install -y prometheus2 node_exporter
sudo systemctl enable --now prometheus
sudo systemctl enable --now node_exporter

Configure Prometheus scraping

Configure Prometheus to scrape metrics from your Node.js application endpoints.

global:
  scrape_interval: 15s
  evaluation_interval: 15s

rule_files:
  - "/etc/prometheus/nodejs_alerts.yml"

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - localhost:9093

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

  - job_name: 'node-exporter'
    static_configs:
      - targets: ['localhost:9100']

  - job_name: 'nodejs-app'
    static_configs:
      - targets: ['localhost:3000']
    metrics_path: '/metrics'
    scrape_interval: 10s

  - job_name: 'nodejs-app-custom'
    static_configs:
      - targets: ['localhost:3001', 'localhost:3002']
    metrics_path: '/metrics'
    scrape_interval: 10s

Install Grafana for visualization

Install Grafana to create dashboards and alerts for your Node.js metrics.

wget -q -O - https://packages.grafana.com/gpg.key | sudo apt-key add -
echo "deb https://packages.grafana.com/oss/deb stable main" | sudo tee /etc/apt/sources.list.d/grafana.list
sudo apt update
sudo apt install -y grafana
sudo systemctl enable --now grafana-server

sudo dnf install -y https://dl.grafana.com/oss/release/grafana-10.2.0-1.x86_64.rpm
sudo systemctl enable --now grafana-server

Create Node.js application with metrics

Set up a sample Node.js application with comprehensive Prometheus metrics collection.

mkdir ~/nodejs-monitoring && cd ~/nodejs-monitoring
npm init -y
npm install express prom-client response-time

const express = require('express');
const client = require('prom-client');
const responseTime = require('response-time');

const app = express();
const port = process.env.PORT || 3000;

// Enable collection of default metrics
client.collectDefaultMetrics({
  timeout: 5000,
  gcDurationBuckets: [0.001, 0.01, 0.1, 1, 2, 5]
});

// Custom metrics
const httpRequestDuration = new client.Histogram({
  name: 'http_request_duration_ms',
  help: 'Duration of HTTP requests in ms',
  labelNames: ['method', 'route', 'status_code'],
  buckets: [0.1, 5, 15, 50, 100, 500, 1000]
});

const httpRequestsTotal = new client.Counter({
  name: 'http_requests_total',
  help: 'Total number of HTTP requests',
  labelNames: ['method', 'route', 'status_code']
});

const activeConnections = new client.Gauge({
  name: 'nodejs_active_connections',
  help: 'Number of active connections',
});

const businessMetric = new client.Gauge({
  name: 'business_orders_processed',
  help: 'Number of orders processed',
});

const errorRate = new client.Counter({
  name: 'nodejs_errors_total',
  help: 'Total number of errors',
  labelNames: ['type', 'endpoint']
});

// Middleware to collect HTTP metrics
app.use(responseTime((req, res, time) => {
  const route = req.route ? req.route.path : req.path;
  const labels = {
    method: req.method,
    route: route,
    status_code: res.statusCode
  };
  
  httpRequestDuration.observe(labels, time);
  httpRequestsTotal.inc(labels);
}));

// Middleware to track active connections
app.use((req, res, next) => {
  activeConnections.inc();
  res.on('finish', () => {
    activeConnections.dec();
  });
  next();
});

// Sample routes
app.get('/', (req, res) => {
  res.json({ message: 'Node.js monitoring demo', timestamp: new Date().toISOString() });
});

app.get('/api/users', (req, res) => {
  // Simulate processing time
  setTimeout(() => {
    res.json({ users: ['alice', 'bob', 'charlie'], count: 3 });
  }, Math.random() * 100);
});

app.get('/api/orders', (req, res) => {
  // Simulate business metric
  businessMetric.inc(Math.floor(Math.random() * 5) + 1);
  res.json({ orders: ['order1', 'order2'], processed: true });
});

app.get('/api/error', (req, res) => {
  // Simulate error for testing
  errorRate.inc({ type: 'validation', endpoint: '/api/error' });
  res.status(500).json({ error: 'Simulated error for testing' });
});

app.get('/health', (req, res) => {
  res.status(200).json({
    status: 'healthy',
    uptime: process.uptime(),
    memory: process.memoryUsage(),
    timestamp: new Date().toISOString()
  });
});

// Metrics endpoint for Prometheus
app.get('/metrics', async (req, res) => {
  try {
    res.set('Content-Type', client.register.contentType);
    const metrics = await client.register.metrics();
    res.send(metrics);
  } catch (error) {
    res.status(500).send(error.message);
  }
});

// Graceful shutdown
process.on('SIGTERM', () => {
  console.log('SIGTERM received, shutting down gracefully');
  server.close(() => {
    console.log('Process terminated');
    process.exit(0);
  });
});

const server = app.listen(port, () => {
  console.log(`Node.js monitoring app listening on port ${port}`);
  console.log(`Metrics available at http://localhost:${port}/metrics`);
  console.log(`Health check at http://localhost:${port}/health`);
});

module.exports = app;

Create production-ready package.json

Configure proper Node.js application scripts and dependencies for production deployment.

{
  "name": "nodejs-prometheus-monitoring",
  "version": "1.0.0",
  "description": "Node.js application with Prometheus metrics",
  "main": "app.js",
  "scripts": {
    "start": "node app.js",
    "dev": "nodemon app.js",
    "test": "jest",
    "healthcheck": "curl -f http://localhost:3000/health || exit 1"
  },
  "dependencies": {
    "express": "^4.18.2",
    "prom-client": "^14.2.0",
    "response-time": "^2.3.2"
  },
  "devDependencies": {
    "nodemon": "^3.0.1",
    "jest": "^29.0.0"
  },
  "keywords": ["nodejs", "prometheus", "monitoring", "metrics"],
  "author": "DevOps Team",
  "license": "MIT"
}

Create systemd service for Node.js app

Set up a systemd service to run your Node.js application with proper monitoring and restart policies.

[Unit]
Description=Node.js Monitoring Application
After=network.target
Requires=network.target

[Service]
Type=simple
User=nodejs
Group=nodejs
WorkingDirectory=/home/nodejs/nodejs-monitoring
ExecStart=/usr/bin/node app.js
Restart=always
RestartSec=5
Environment=NODE_ENV=production
Environment=PORT=3000
StandardOutput=journal
StandardError=journal
SyslogIdentifier=nodejs-monitoring

# Resource limits
LimitNOFILE=65536
MemoryMax=512M

# Security settings
NoNewPrivileges=true
ProtectSystem=strict
ProtectHome=true
ReadWritePaths=/home/nodejs/nodejs-monitoring/logs

[Install]
WantedBy=multi-user.target

sudo useradd -r -s /bin/false nodejs
sudo mkdir -p /home/nodejs
sudo cp -r ~/nodejs-monitoring /home/nodejs/
sudo chown -R nodejs:nodejs /home/nodejs/nodejs-monitoring
sudo systemctl daemon-reload
sudo systemctl enable --now nodejs-monitoring

Configure Prometheus alerting rules

Create alerting rules for Node.js application monitoring with threshold-based notifications.

groups:
- name: nodejs_alerts
  rules:
  - alert: NodejsHighResponseTime
    expr: histogram_quantile(0.95, rate(http_request_duration_ms_bucket[5m])) > 500
    for: 2m
    labels:
      severity: warning
      service: nodejs
    annotations:
      summary: "High response time detected"
      description: "95th percentile response time is {{ $value }}ms for {{ $labels.instance }}"

  - alert: NodejsHighErrorRate
    expr: rate(http_requests_total{status_code=~"5.."}[5m]) / rate(http_requests_total[5m]) > 0.05
    for: 5m
    labels:
      severity: critical
      service: nodejs
    annotations:
      summary: "High error rate detected"
      description: "Error rate is {{ $value | humanizePercentage }} for {{ $labels.instance }}"

  - alert: NodejsHighMemoryUsage
    expr: nodejs_memory_heap_used_bytes / nodejs_memory_heap_total_bytes > 0.85
    for: 5m
    labels:
      severity: warning
      service: nodejs
    annotations:
      summary: "High memory usage"
      description: "Memory usage is {{ $value | humanizePercentage }} for {{ $labels.instance }}"

  - alert: NodejsApplicationDown
    expr: up{job="nodejs-app"} == 0
    for: 1m
    labels:
      severity: critical
      service: nodejs
    annotations:
      summary: "Node.js application is down"
      description: "Node.js application on {{ $labels.instance }} is not responding"

  - alert: NodejsHighActiveConnections
    expr: nodejs_active_connections > 100
    for: 5m
    labels:
      severity: warning
      service: nodejs
    annotations:
      summary: "High number of active connections"
      description: "{{ $value }} active connections on {{ $labels.instance }}"

  - alert: NodejsEventLoopLag
    expr: nodejs_eventloop_lag_seconds > 0.1
    for: 3m
    labels:
      severity: warning
      service: nodejs
    annotations:
      summary: "Event loop lag detected"
      description: "Event loop lag is {{ $value }}s on {{ $labels.instance }}"

  - alert: NodejsGCDuration
    expr: rate(nodejs_gc_duration_seconds_sum[5m]) > 0.1
    for: 5m
    labels:
      severity: warning
      service: nodejs
    annotations:
      summary: "High garbage collection time"
      description: "GC duration is {{ $value }}s/sec on {{ $labels.instance }}"

Install and configure Alertmanager

Set up Alertmanager to handle notifications from Prometheus alerts.

sudo apt install -y prometheus-alertmanager

sudo dnf install -y alertmanager

global:
  smtp_smarthost: 'localhost:587'
  smtp_from: 'alerts@example.com'

route:
  group_by: ['alertname', 'cluster', 'service']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver: 'nodejs-alerts'
  routes:
  - match:
      severity: critical
    receiver: 'critical-alerts'
    continue: true

receivers:
- name: 'nodejs-alerts'
  email_configs:
  - to: 'devops@example.com'
    subject: 'Node.js Alert: {{ .GroupLabels.alertname }}'
    body: |
      {{ range .Alerts }}
      Alert: {{ .Annotations.summary }}
      Description: {{ .Annotations.description }}
      Instance: {{ .Labels.instance }}
      Severity: {{ .Labels.severity }}
      {{ end }}

- name: 'critical-alerts'
  email_configs:
  - to: 'oncall@example.com'
    subject: 'CRITICAL: {{ .GroupLabels.alertname }}'
    body: |
      CRITICAL ALERT TRIGGERED
      {{ range .Alerts }}
      Alert: {{ .Annotations.summary }}
      Description: {{ .Annotations.description }}
      Instance: {{ .Labels.instance }}
      Time: {{ .StartsAt }}
      {{ end }}

sudo systemctl enable --now alertmanager
sudo systemctl restart prometheus

Create comprehensive Grafana dashboards

Import and configure detailed Grafana dashboards for Node.js application monitoring.

curl -X POST http://admin:admin@localhost:3000/api/datasources \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Prometheus",
    "type": "prometheus",
    "url": "http://localhost:9090",
    "access": "proxy",
    "isDefault": true
  }'

{
  "dashboard": {
    "id": null,
    "title": "Node.js Application Monitoring",
    "tags": ["nodejs", "prometheus", "monitoring"],
    "timezone": "browser",
    "panels": [
      {
        "id": 1,
        "title": "HTTP Request Rate",
        "type": "stat",
        "targets": [
          {
            "expr": "rate(http_requests_total[5m])",
            "legendFormat": "Requests/sec"
          }
        ],
        "gridPos": {"h": 8, "w": 12, "x": 0, "y": 0}
      },
      {
        "id": 2,
        "title": "Response Time Percentiles",
        "type": "graph",
        "targets": [
          {
            "expr": "histogram_quantile(0.50, rate(http_request_duration_ms_bucket[5m]))",
            "legendFormat": "50th percentile"
          },
          {
            "expr": "histogram_quantile(0.95, rate(http_request_duration_ms_bucket[5m]))",
            "legendFormat": "95th percentile"
          },
          {
            "expr": "histogram_quantile(0.99, rate(http_request_duration_ms_bucket[5m]))",
            "legendFormat": "99th percentile"
          }
        ],
        "gridPos": {"h": 8, "w": 12, "x": 12, "y": 0}
      },
      {
        "id": 3,
        "title": "Memory Usage",
        "type": "graph",
        "targets": [
          {
            "expr": "nodejs_memory_heap_used_bytes",
            "legendFormat": "Heap Used"
          },
          {
            "expr": "nodejs_memory_heap_total_bytes",
            "legendFormat": "Heap Total"
          },
          {
            "expr": "nodejs_memory_external_bytes",
            "legendFormat": "External"
          }
        ],
        "gridPos": {"h": 8, "w": 12, "x": 0, "y": 8}
      },
      {
        "id": 4,
        "title": "Error Rate by Endpoint",
        "type": "graph",
        "targets": [
          {
            "expr": "rate(http_requests_total{status_code=~\"5..\"}[5m]) by (route)",
            "legendFormat": "{{route}}"
          }
        ],
        "gridPos": {"h": 8, "w": 12, "x": 12, "y": 8}
      },
      {
        "id": 5,
        "title": "Active Connections",
        "type": "singlestat",
        "targets": [
          {
            "expr": "nodejs_active_connections",
            "legendFormat": "Active Connections"
          }
        ],
        "gridPos": {"h": 4, "w": 6, "x": 0, "y": 16}
      },
      {
        "id": 6,
        "title": "Event Loop Lag",
        "type": "singlestat",
        "targets": [
          {
            "expr": "nodejs_eventloop_lag_seconds",
            "legendFormat": "Event Loop Lag (s)"
          }
        ],
        "gridPos": {"h": 4, "w": 6, "x": 6, "y": 16}
      },
      {
        "id": 7,
        "title": "GC Duration",
        "type": "graph",
        "targets": [
          {
            "expr": "rate(nodejs_gc_duration_seconds_sum[5m]) by (kind)",
            "legendFormat": "{{kind}}"
          }
        ],
        "gridPos": {"h": 8, "w": 12, "x": 12, "y": 16}
      }
    ],
    "time": {
      "from": "now-1h",
      "to": "now"
    },
    "refresh": "10s"
  }
}

curl -X POST http://admin:admin@localhost:3000/api/dashboards/db \
  -H "Content-Type: application/json" \
  -d @nodejs_dashboard.json

Set up advanced custom metrics

Add business-specific metrics and advanced monitoring patterns to your Node.js application.

const client = require('prom-client');

// Business metrics
const userRegistrations = new client.Counter({
  name: 'user_registrations_total',
  help: 'Total number of user registrations',
  labelNames: ['source', 'country']
});

const orderValue = new client.Histogram({
  name: 'order_value_dollars',
  help: 'Order value in dollars',
  labelNames: ['category', 'payment_method'],
  buckets: [10, 25, 50, 100, 250, 500, 1000, 2500]
});

const activeUsers = new client.Gauge({
  name: 'active_users_current',
  help: 'Current number of active users',
  labelNames: ['session_type']
});

const databaseConnections = new client.Gauge({
  name: 'database_connections_active',
  help: 'Active database connections',
  labelNam