Advanced Monitoring with Prometheus and AlertManager

Introduction

Prometheus and AlertManager provide comprehensive monitoring and alerting for distributed systems. This guide covers metrics collection, alerting rules, and notification routing.

Prerequisites

• Kubernetes cluster or Docker environment
• Basic understanding of monitoring concepts

Step 1: Prometheus Configuration

Create prometheus.yml:

global:
  scrape_interval: 15s
  evaluation_interval: 15s
  external_labels:
    cluster: 'production'
    region: 'us-east-1'

rule_files:
  - "alert_rules.yml"
  - "recording_rules.yml"

alerting:
  alertmanagers:
    - static_configs:
        - targets:
          - alertmanager:9093

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

  # Node Exporter
  - job_name: 'node'
    static_configs:
      - targets: 
        - 'node-exporter:9100'
    scrape_interval: 30s
    metrics_path: /metrics

  # Application metrics
  - job_name: 'app'
    kubernetes_sd_configs:
      - role: pod
    relabel_configs:
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
        action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_pod_name]
        action: replace
        target_label: kubernetes_pod_name

  # Kafka metrics
  - job_name: 'kafka'
    static_configs:
      - targets: ['kafka-exporter:9308']
    scrape_interval: 30s

  # PostgreSQL metrics
  - job_name: 'postgres'
    static_configs:
      - targets: ['postgres-exporter:9187']
    scrape_interval: 30s

  # Redis metrics
  - job_name: 'redis'
    static_configs:
      - targets: ['redis-exporter:9121']
    scrape_interval: 30s

Step 2: Recording Rules

Create recording_rules.yml:

groups:
  - name: application_rules
    interval: 30s
    rules:
      # HTTP request rate
      - record: http_requests_per_second
        expr: sum(rate(http_requests_total[5m])) by (job, instance, method, status)
      
      # HTTP error rate
      - record: http_error_rate
        expr: |
          sum(rate(http_requests_total{status=~"5.."}[5m])) by (job, instance) 
          / 
          sum(rate(http_requests_total[5m])) by (job, instance)
      
      # HTTP request latency percentiles
      - record: http_request_duration_p95
        expr: histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (job, instance, le))
      
      - record: http_request_duration_p99
        expr: histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (job, instance, le))

  - name: infrastructure_rules
    interval: 30s
    rules:
      # CPU utilization
      - record: cpu_utilization
        expr: 100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)
      
      # Memory utilization
      - record: memory_utilization
        expr: |
          (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100
      
      # Disk utilization
      - record: disk_utilization
        expr: |
          100 - ((node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"}) * 100)
      
      # Network throughput
      - record: network_throughput_rx
        expr: sum(rate(node_network_receive_bytes_total[5m])) by (instance)
      
      - record: network_throughput_tx
        expr: sum(rate(node_network_transmit_bytes_total[5m])) by (instance)

  - name: business_rules
    interval: 60s
    rules:
      # Order processing rate
      - record: orders_per_minute
        expr: sum(rate(orders_total[1m])) * 60
      
      # Revenue per hour
      - record: revenue_per_hour
        expr: sum(rate(revenue_total[1h])) * 3600
      
      # Active users
      - record: active_users_5m
        expr: count(increase(user_activity_total[5m]) > 0)

Step 3: Alert Rules

Create alert_rules.yml:

groups:
  - name: system_alerts
    rules:
      - alert: HighCPUUsage
        expr: cpu_utilization > 80
        for: 5m
        labels:
          severity: warning
          service: infrastructure
        annotations:
          summary: "High CPU usage detected"
          description: "CPU usage is {{ $value }}% on {{ $labels.instance }}"
          runbook_url: "https://wiki.company.com/runbooks/high-cpu"

      - alert: HighMemoryUsage
        expr: memory_utilization > 90
        for: 3m
        labels:
          severity: critical
          service: infrastructure
        annotations:
          summary: "High memory usage detected"
          description: "Memory usage is {{ $value }}% on {{ $labels.instance }}"

      - alert: DiskSpaceLow
        expr: disk_utilization > 85
        for: 1m
        labels:
          severity: warning
          service: infrastructure
        annotations:
          summary: "Disk space is running low"
          description: "Disk usage is {{ $value }}% on {{ $labels.instance }}"

      - alert: NodeDown
        expr: up{job="node"} == 0
        for: 1m
        labels:
          severity: critical
          service: infrastructure
        annotations:
          summary: "Node is down"
          description: "Node {{ $labels.instance }} has been down for more than 1 minute"

  - name: application_alerts
    rules:
      - alert: HighErrorRate
        expr: http_error_rate > 0.05
        for: 5m
        labels:
          severity: critical
          service: application
        annotations:
          summary: "High HTTP error rate"
          description: "Error rate is {{ $value | humanizePercentage }} for {{ $labels.job }}"

      - alert: HighLatency
        expr: http_request_duration_p95 > 2
        for: 5m
        labels:
          severity: warning
          service: application
        annotations:
          summary: "High response latency"
          description: "95th percentile latency is {{ $value }}s for {{ $labels.job }}"

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

  - name: database_alerts
    rules:
      - alert: PostgreSQLDown
        expr: up{job="postgres"} == 0
        for: 1m
        labels:
          severity: critical
          service: database
        annotations:
          summary: "PostgreSQL is down"
          description: "PostgreSQL instance {{ $labels.instance }} is down"

      - alert: HighDatabaseConnections
        expr: pg_stat_database_numbackends / pg_settings_max_connections > 0.8
        for: 5m
        labels:
          severity: warning
          service: database
        annotations:
          summary: "High database connection usage"
          description: "Database connections are {{ $value | humanizePercentage }} of maximum"

  - name: business_alerts
    rules:
      - alert: LowOrderVolume
        expr: orders_per_minute < 10
        for: 10m
        labels:
          severity: warning
          service: business
        annotations:
          summary: "Low order processing volume"
          description: "Only {{ $value }} orders per minute (expected > 10)"

      - alert: PaymentFailures
        expr: increase(payment_failures_total[5m]) > 5
        for: 2m
        labels:
          severity: critical
          service: business
        annotations:
          summary: "High payment failure rate"
          description: "{{ $value }} payment failures in the last 5 minutes"

Step 4: AlertManager Configuration

Create alertmanager.yml:

global:
  smtp_smarthost: 'mail.company.com:587'
  smtp_from: 'alerts@company.com'
  smtp_auth_username: 'alerts@company.com'
  smtp_auth_password: 'password'

# Inhibition rules to reduce noise
inhibit_rules:
  - source_match:
      severity: 'critical'
    target_match:
      severity: 'warning'
    equal: ['instance', 'service']

# Route configuration
route:
  group_by: ['alertname', 'service']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver: 'default'
  
  routes:
    # Critical alerts go to on-call
    - match:
        severity: critical
      receiver: 'critical-alerts'
      group_wait: 0s
      repeat_interval: 5m
    
    # Infrastructure alerts
    - match:
        service: infrastructure
      receiver: 'infrastructure-team'
      
    # Application alerts
    - match:
        service: application
      receiver: 'development-team'
      
    # Database alerts
    - match:
        service: database
      receiver: 'dba-team'
      
    # Business alerts
    - match:
        service: business
      receiver: 'business-team'

# Receiver configurations
receivers:
  - name: 'default'
    email_configs:
      - to: 'team@company.com'
        subject: 'Alert: {{ .GroupLabels.alertname }}'
        html: |
          <!DOCTYPE html>
          <html>
          <body>
            <h2>Alert Summary</h2>
            <p><strong>Alert:</strong> {{ .GroupLabels.alertname }}</p>
            <p><strong>Service:</strong> {{ .GroupLabels.service }}</p>
            <h3>Firing Alerts</h3>
            <ul>
            {{ range .Alerts.Firing }}
              <li>{{ .Annotations.summary }} ({{ .Labels.instance }})</li>
            {{ end }}
            </ul>
          </body>
          </html>

  - name: 'critical-alerts'
    email_configs:
      - to: 'oncall@company.com'
        subject: 'CRITICAL: {{ .GroupLabels.alertname }}'
        html: |
          <h1 style="color: red;">CRITICAL ALERT</h1>
          <p><strong>Alert:</strong> {{ .GroupLabels.alertname }}</p>
          {{ range .Alerts.Firing }}
          <p><strong>Description:</strong> {{ .Annotations.description }}</p>
          <p><strong>Instance:</strong> {{ .Labels.instance }}</p>
          {{ end }}
    
    slack_configs:
      - api_url: 'https://hooks.slack.com/services/YOUR/SLACK/WEBHOOK'
        channel: '#alerts'
        title: 'Critical Alert: {{ .GroupLabels.alertname }}'
        text: |
          {{ range .Alerts.Firing }}
          *Instance:* {{ .Labels.instance }}
          *Description:* {{ .Annotations.description }}
          {{ end }}
        color: 'danger'

  - name: 'infrastructure-team'
    email_configs:
      - to: 'infrastructure@company.com'
        subject: 'Infrastructure Alert: {{ .GroupLabels.alertname }}'

  - name: 'development-team'
    slack_configs:
      - api_url: 'https://hooks.slack.com/services/YOUR/DEV/WEBHOOK'
        channel: '#development'
        title: 'App Alert: {{ .GroupLabels.alertname }}'
        
  - name: 'dba-team'
    email_configs:
      - to: 'dba@company.com'
        subject: 'Database Alert: {{ .GroupLabels.alertname }}'

  - name: 'business-team'
    email_configs:
      - to: 'business@company.com'
        subject: 'Business Metric Alert: {{ .GroupLabels.alertname }}'

Step 5: Docker Compose Setup

Create docker-compose.yml:

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:v2.47.0
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
      - ./alert_rules.yml:/etc/prometheus/alert_rules.yml
      - ./recording_rules.yml:/etc/prometheus/recording_rules.yml
      - prometheus_data:/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'
      - '--storage.tsdb.retention.time=200h'
      - '--web.enable-lifecycle'

  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: alertmanager
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'

  grafana:
    image: grafana/grafana:10.1.0
    container_name: grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning

  node-exporter:
    image: prom/node-exporter:v1.6.0
    container_name: node-exporter
    ports:
      - "9100:9100"
    command:
      - '--path.rootfs=/host'
    volumes:
      - '/:/host:ro,rslave'

volumes:
  prometheus_data:
  alertmanager_data:
  grafana_data:

Step 6: Custom Application Metrics

Instrument Node.js app with Prometheus metrics:

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

// Create a Registry
const register = new client.Registry();

// Add default metrics
client.collectDefaultMetrics({ register });

// Custom metrics
const httpRequestDuration = new client.Histogram({
  name: 'http_request_duration_seconds',
  help: 'Duration of HTTP requests in seconds',
  labelNames: ['method', 'route', 'status'],
  buckets: [0.1, 0.5, 1, 2, 5, 10],
  registers: [register],
});

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

const activeConnections = new client.Gauge({
  name: 'active_connections',
  help: 'Number of active connections',
  registers: [register],
});

// Business metrics
const ordersTotal = new client.Counter({
  name: 'orders_total',
  help: 'Total number of orders processed',
  labelNames: ['status'],
  registers: [register],
});

const revenueTotal = new client.Counter({
  name: 'revenue_total',
  help: 'Total revenue generated',
  registers: [register],
});

// Middleware for HTTP metrics
function metricsMiddleware(req, res, next) {
  const start = Date.now();
  
  res.on('finish', () => {
    const duration = (Date.now() - start) / 1000;
    const route = req.route?.path || req.path;
    
    httpRequestDuration
      .labels(req.method, route, res.statusCode)
      .observe(duration);
      
    httpRequestTotal
      .labels(req.method, route, res.statusCode)
      .inc();
  });
  
  next();
}

module.exports = {
  register,
  metricsMiddleware,
  httpRequestDuration,
  httpRequestTotal,
  activeConnections,
  ordersTotal,
  revenueTotal,
};

Summary

Prometheus and AlertManager provide comprehensive monitoring and intelligent alerting for production systems. Use recording rules for performance, alert rules for notifications, and proper routing for team-specific alerts to maintain system reliability.