Monitoring & Observability

import express from 'express';
import promClient from 'prom-client';

const app = express();

// Default metrics (CPU, Memory, etc.)
promClient.collectDefaultMetrics();

// Custom metrics
const httpRequestDuration = new promClient.Histogram({
  name: 'http_request_duration_seconds',
  help: 'Duration of HTTP requests in seconds',
  labelNames: ['method', 'route', 'status_code']
});

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

// Middleware to track requests
app.use((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);
    httpRequestTotal.inc(labels);
  });

  next();
});

// Metrics endpoint
app.get('/metrics', async (req, res) => {
  res.set('Content-Type', promClient.register.contentType);
  res.end(await promClient.register.metrics());
});

app.listen(3000);

global:
  scrape_interval: 15s
  evaluation_interval: 15s

scrape_configs:
  - job_name: 'my-app'
    static_configs:
      - targets: ['localhost:3000']
    metrics_path: '/metrics'

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

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['localhost:9093']

rule_files:
  - 'alert_rules.yml'

groups:
  - name: application_alerts
    interval: 30s
    rules:
      # High error rate
      - alert: HighErrorRate
        expr: |
          (
            sum(rate(http_requests_total{status_code=~"5.."}[5m]))
            /
            sum(rate(http_requests_total[5m]))
          ) > 0.05
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "High error rate detected"
          description: "Error rate is {{ $value }}% (threshold: 5%)"

      # Slow response time
      - alert: SlowResponseTime
        expr: |
          histogram_quantile(0.95,
            sum(rate(http_request_duration_seconds_bucket[5m])) by (le)
          ) > 1
        for: 10m
        labels:
          severity: warning
        annotations:
          summary: "Slow response time"
          description: "95th percentile is {{ $value }}s"

      # Pod down
      - alert: PodDown
        expr: up{job="my-app"} == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Pod is down"
          description: "{{ $labels.instance }} has been down for more than 2 minutes"

      # High memory usage
      - alert: HighMemoryUsage
        expr: |
          (
            node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes
          ) / node_memory_MemTotal_bytes > 0.90
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage"
          description: "Memory usage is {{ $value }}%"

import winston from 'winston';

const logger = winston.createLogger({
  level: process.env.LOG_LEVEL || 'info',
  format: winston.format.combine(
    winston.format.timestamp(),
    winston.format.errors({ stack: true }),
    winston.format.json()
  ),
  defaultMeta: {
    service: 'my-app',
    environment: process.env.NODE_ENV
  },
  transports: [
    new winston.transports.Console({
      format: winston.format.combine(
        winston.format.colorize(),
        winston.format.simple()
      )
    }),
    new winston.transports.File({
      filename: 'logs/error.log',
      level: 'error'
    }),
    new winston.transports.File({
      filename: 'logs/combined.log'
    })
  ]
});

// Usage
logger.info('User logged in', { userId: '123', ip: '1.2.3.4' });
logger.error('Database connection failed', { error: err.message, stack: err.stack });

// Express middleware
app.use((req, res, next) => {
  logger.info('HTTP Request', {
    method: req.method,
    path: req.path,
    ip: req.ip,
    userAgent: req.get('user-agent')
  });
  next();
});

{
  "dashboard": {
    "title": "Application Metrics",
    "panels": [
      {
        "title": "Request Rate",
        "type": "graph",
        "targets": [
          {
            "expr": "rate(http_requests_total[5m])",
            "legendFormat": "{{method}} {{route}}"
          }
        ]
      },
      {
        "title": "Error Rate",
        "type": "graph",
        "targets": [
          {
            "expr": "rate(http_requests_total{status_code=~\"5..\"}[5m])",
            "legendFormat": "Errors"
          }
        ]
      },
      {
        "title": "Response Time (p95)",
        "type": "graph",
        "targets": [
          {
            "expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))"
          }
        ]
      },
      {
        "title": "CPU Usage",
        "type": "gauge",
        "targets": [
          {
            "expr": "rate(process_cpu_seconds_total[5m]) * 100"
          }
        ]
      }
    ]
  }
}

interface HealthStatus {
  status: 'healthy' | 'degraded' | 'unhealthy';
  timestamp: string;
  uptime: number;
  checks: {
    database: { status: string; latency?: number; error?: string };
    redis: { status: string; latency?: number };
    externalApi: { status: string; latency?: number };
  };
}

app.get('/health', async (req, res) => {
  const startTime = Date.now();
  const health: HealthStatus = {
    status: 'healthy',
    timestamp: new Date().toISOString(),
    uptime: process.uptime(),
    checks: {
      database: { status: 'unknown' },
      redis: { status: 'unknown' },
      externalApi: { status: 'unknown' }
    }
  };

  // Database check
  try {
    const dbStart = Date.now();
    await db.raw('SELECT 1');
    health.checks.database = {
      status: 'healthy',
      latency: Date.now() - dbStart
    };
  } catch (error) {
    health.status = 'unhealthy';
    health.checks.database = {
      status: 'unhealthy',
      error: error.message
    };
  }

  // Redis check
  try {
    const redisStart = Date.now();
    await redis.ping();
    health.checks.redis = {
      status: 'healthy',
      latency: Date.now() - redisStart
    };
  } catch (error) {
    health.status = 'degraded';
    health.checks.redis = { status: 'unhealthy' };
  }

  const statusCode = health.status === 'healthy' ? 200 : health.status === 'degraded' ? 200 : 503;
  res.status(statusCode).json(health);
});

Golden Signals:
1. Latency (Response Time)
   - P50, P95, P99 percentiles
   - Per API endpoint

2. Traffic (Request Volume)
   - Requests per second
   - Per endpoint, per status code

3. Errors (Error Rate)
   - 5xx error rate
   - 4xx error rate
   - Per error type

4. Saturation (Resource Utilization)
   - CPU usage
   - Memory usage
   - Disk I/O
   - Network bandwidth