cicd-chaos/docker-compose.yml

# CI/CD Chaos Engine - Over-engineered Docker Compose Configuration
# This configuration demonstrates professional multi-container orchestration with satirical complexity

version: '3.8'

services:
  # Main chaos engine application
  chaos-engine:
    build:
      context: .
      dockerfile: docker/Dockerfile
      args:
        CHAOS_LEVEL: 8
        ROAST_INTENSITY: 9
        BUILD_DATE: ${BUILD_DATE:-$(date -u +'%Y-%m-%dT%H:%M:%SZ')}
        GIT_COMMIT: ${GIT_COMMIT:-$(git rev-parse --short HEAD 2>/dev/null || echo 'unknown')}
        GIT_BRANCH: ${GIT_BRANCH:-$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo 'unknown')}
    container_name: cicd-chaos-engine
    restart: unless-stopped
    environment:
      - CHAOS_LEVEL=8
      - ROAST_INTENSITY=9
      - CELEBRATION_MODE=full
      - DEVELOPER_CHALLENGE=true
      - LOG_LEVEL=INFO
      - PYTHONUNBUFFERED=1
      - PYTHONDONTWRITEBYTECODE=1
    volumes:
      - ./scripts:/app/scripts:ro
      - ./config:/app/config:ro
      - ./logs:/app/logs
      - ./artifacts:/app/artifacts
      - ./reports:/app/reports
    ports:
      - "8080:8080"
      - "9090:9090"
    healthcheck:
      test: ["CMD", "/app/healthcheck.sh"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s
    networks:
      - chaos-network
    depends_on:
      - redis
      - postgres
      - grafana
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.chaos-engine.rule=Host(`chaos.local`)"
      - "traefik.http.routers.chaos-engine.entrypoints=web"
      - "traefik.http.services.chaos-engine.loadbalancer.server.port=8080"

  # Redis cache (overkill for this application)
  redis:
    image: redis:7-alpine
    container_name: cicd-chaos-redis
    restart: unless-stopped
    command: redis-server --appendonly yes --maxmemory 256mb --maxmemory-policy allkeys-lru
    volumes:
      - redis_data:/data
      - ./config/redis.conf:/etc/redis/redis.conf:ro
    ports:
      - "6379:6379"
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 3
    networks:
      - chaos-network
    labels:
      - "traefik.enable=false"

  # PostgreSQL database (excessive for this demo)
  postgres:
    image: postgres:15-alpine
    container_name: cicd-chaos-postgres
    restart: unless-stopped
    environment:
      POSTGRES_DB: chaos_db
      POSTGRES_USER: chaos_user
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:-chaos_password}
      PGDATA: /var/lib/postgresql/data/pgdata
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./config/postgres/init.sql:/docker-entrypoint-initdb.d/init.sql:ro
      - postgres_logs:/var/log/postgresql
    ports:
      - "5432:5432"
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U chaos_user -d chaos_db"]
      interval: 10s
      timeout: 5s
      retries: 5
    networks:
      - chaos-network
    labels:
      - "traefik.enable=false"

  # Grafana for monitoring (overkill)
  grafana:
    image: grafana/grafana:10.0.0
    container_name: cicd-chaos-grafana
    restart: unless-stopped
    environment:
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_PASSWORD:-admin}
      GF_USERS_ALLOW_SIGN_UP: "false"
      GF_INSTALL_PLUGINS: "grafana-clock-panel,grafana-simple-json-datasource"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./config/grafana/provisioning:/etc/grafana/provisioning:ro
      - ./config/grafana/dashboards:/var/lib/grafana/dashboards:ro
    ports:
      - "3000:3000"
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    depends_on:
      - postgres
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.grafana.rule=Host(`grafana.chaos.local`)"
      - "traefik.http.routers.grafana.entrypoints=web"
      - "traefik.http.services.grafana.loadbalancer.server.port=3000"

  # Prometheus for metrics collection (excessive)
  prometheus:
    image: prom/prometheus:v2.45.0
    container_name: cicd-chaos-prometheus
    restart: unless-stopped
    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'
      - '--web.enable-admin-api'
    volumes:
      - prometheus_data:/prometheus
      - ./config/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./config/prometheus/rules:/etc/prometheus/rules:ro
    ports:
      - "9091:9090"
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.prometheus.rule=Host(`prometheus.chaos.local`)"
      - "traefik.http.routers.prometheus.entrypoints=web"
      - "traefik.http.services.prometheus.loadbalancer.server.port=9090"

  # Nginx reverse proxy (overkill)
  nginx:
    image: nginx:alpine
    container_name: cicd-chaos-nginx
    restart: unless-stopped
    volumes:
      - ./config/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./config/nginx/conf.d:/etc/nginx/conf.d:ro
      - nginx_logs:/var/log/nginx
      - nginx_cache:/var/cache/nginx
    ports:
      - "80:80"
      - "443:443"
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    depends_on:
      - chaos-engine
    labels:
      - "traefik.enable=false"

  # Traefik reverse proxy (even more overkill)
  traefik:
    image: traefik:v2.10
    container_name: cicd-chaos-traefik
    restart: unless-stopped
    command:
      - "--api.insecure=true"
      - "--providers.docker=true"
      - "--providers.docker.exposedbydefault=false"
      - "--entrypoints.web.address=:80"
      - "--entrypoints.websecure.address=:443"
      - "--entrypoints.web.http.redirections.entryPoint.to=websecure"
      - "--certificatesresolvers.myresolver.acme.tlschallenge=true"
      - "--certificatesresolvers.myresolver.acme.email=chaos@example.com"
      - "--certificatesresolvers.myresolver.acme.storage=/letsencrypt/acme.json"
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - traefik_letsencrypt:/letsencrypt
    ports:
      - "8081:8080"  # Traefik dashboard
      - "80:80"
      - "443:443"
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8080/ping"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.traefik.rule=Host(`traefik.chaos.local`)"
      - "traefik.http.routers.traefik.entrypoints=web"
      - "traefik.http.routers.traefik.service=api@internal"

  # Fluentd for log aggregation (excessive)
  fluentd:
    build:
      context: .
      dockerfile: docker/fluentd.Dockerfile
    container_name: cicd-chaos-fluentd
    restart: unless-stopped
    volumes:
      - ./config/fluentd/conf:/fluentd/etc
      - ./logs:/logs
      - fluentd_data:/fluentd/log
    ports:
      - "24224:24224"
      - "24224:24224/udp"
    networks:
      - chaos-network
    depends_on:
      - elasticsearch
    labels:
      - "traefik.enable=false"

  # Elasticsearch for log storage (way overkill)
  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:8.9.0
    container_name: cicd-chaos-elasticsearch
    restart: unless-stopped
    environment:
      - discovery.type=single-node
      - "ES_JAVA_OPTS=-Xms512m -Xmx512m"
      - xpack.security.enabled=false
    volumes:
      - elasticsearch_data:/usr/share/elasticsearch/data
    ports:
      - "9200:9200"
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:9200/_cluster/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    labels:
      - "traefik.enable=false"

  # Kibana for log visualization (excessive)
  kibana:
    image: docker.elastic.co/kibana/kibana:8.9.0
    container_name: cicd-chaos-kibana
    restart: unless-stopped
    environment:
      - ELASTICSEARCH_HOSTS=http://elasticsearch:9200
    volumes:
      - kibana_data:/usr/share/kibana/data
    ports:
      - "5601:5601"
    healthcheck:
      test: ["CMD-SHELL", "curl -f http://localhost:5601/api/status || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    depends_on:
      - elasticsearch
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.kibana.rule=Host(`kibana.chaos.local`)"
      - "traefik.http.routers.kibana.entrypoints=web"
      - "traefik.http.services.kibana.loadbalancer.server.port=5601"

  # Jaeger for distributed tracing (absolutely overkill)
  jaeger:
    image: jaegertracing/all-in-one:latest
    container_name: cicd-chaos-jaeger
    restart: unless-stopped
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    ports:
      - "16686:16686"  # UI
      - "14268:14268"  # HTTP collector
      - "14250:14250"  # gRPC collector
      - "4317:4317"    # OTLP gRPC
      - "4318:4318"    # OTLP HTTP
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:16686"]
      interval: 30s
      timeout: 10s
      retries: 3
    networks:
      - chaos-network
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.jaeger.rule=Host(`jaeger.chaos.local`)"
      - "traefik.http.routers.jaeger.entrypoints=web"
      - "traefik.http.services.jaeger.loadbalancer.server.port=16686"

  # Jenkins for CI/CD (completely overkill for this demo)
  jenkins:
    image: jenkins/jenkins:lts-jdk17
    container_name: cicd-chaos-jenkins
    restart: unless-stopped
    environment:
      - JAVA_OPTS=-Xmx2048m
      - JENKINS_OPTS=--httpPort=8081 --httpsPort=-1
    volumes:
      - jenkins_home:/var/jenkins_home
      - /var/run/docker.sock:/var/run/docker.sock:ro
    ports:
      - "8082:8081"
      - "50000:50000"
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8081/login"]
      interval: 60s
      timeout: 10s
      retries: 5
    networks:
      - chaos-network
    labels:
      - "traefik.enable=true"
      - "traefik.http.routers.jenkins.rule=Host(`jenkins.chaos.local`)"
      - "traefik.http.routers.jenkins.entrypoints=web"
      - "traefik.http.services.jenkins.loadbalancer.server.port=8081"

volumes:
  redis_data:
    driver: local
  postgres_data:
    driver: local
  postgres_logs:
    driver: local
  grafana_data:
    driver: local
  prometheus_data:
    driver: local
  nginx_logs:
    driver: local
  nginx_cache:
    driver: local
  traefik_letsencrypt:
    driver: local
  fluentd_data:
    driver: local
  elasticsearch_data:
    driver: local
  kibana_data:
    driver: local
  jenkins_home:
    driver: local

networks:
  chaos-network:
    driver: bridge
    ipam:
      config:
        - subnet: 172.20.0.0/16