metabuilder/frontends/emailclient/deployment/monitoring/docker-compose.monitoring.yml

# Docker Compose - Monitoring Stack for Phase 8 Email Client
# Complete ELK stack, Prometheus, Grafana, and distributed tracing infrastructure
# Last Updated: 2026-01-24

version: '3.9'

services:
  # ============================================================================
  # Prometheus - Metrics Collection & Alerting
  # ============================================================================
  prometheus:
    image: prom/prometheus:latest
    container_name: emailclient-prometheus
    hostname: prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
    ports:
      - '9090:9090'
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
      - ./prometheus/alert_rules.yml:/etc/prometheus/rules/alert_rules.yml
      - prometheus-data:/prometheus
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.metabuilder.service=prometheus"
      - "com.metabuilder.component=metrics"

  # ============================================================================
  # Alertmanager - Alert Management & Notification
  # ============================================================================
  alertmanager:
    image: prom/alertmanager:latest
    container_name: emailclient-alertmanager
    hostname: alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://alertmanager:9093'
    ports:
      - '9093:9093'
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml
      - alertmanager-data:/alertmanager
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.metabuilder.service=alertmanager"
      - "com.metabuilder.component=alerting"

  # ============================================================================
  # Grafana - Visualization & Dashboarding
  # ============================================================================
  grafana:
    image: grafana/grafana:latest
    container_name: emailclient-grafana
    hostname: grafana
    environment:
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_PASSWORD:-admin}
      GF_SECURITY_ADMIN_USER: ${GRAFANA_USER:-admin}
      GF_INSTALL_PLUGINS: 'grafana-piechart-panel,grafana-worldmap-panel,grafana-status-panel'
      GF_SERVER_ROOT_URL: http://grafana:3000
      GF_DATABASE_TYPE: sqlite3
      GF_PATHS_PROVISIONING: /etc/grafana/provisioning
      GF_USERS_ALLOW_SIGN_UP: false
    ports:
      - '3000:3000'
    volumes:
      - ./grafana/provisioning:/etc/grafana/provisioning
      - ./grafana/dashboards:/etc/grafana/provisioning/dashboards
      - grafana-data:/var/lib/grafana
    depends_on:
      - prometheus
      - elasticsearch
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.metabuilder.service=grafana"
      - "com.metabuilder.component=visualization"

  # ============================================================================
  # Elasticsearch - Log Storage & Search
  # ============================================================================
  elasticsearch:
    image: docker.elastic.co/elasticsearch/elasticsearch:8.10.0
    container_name: emailclient-elasticsearch
    hostname: elasticsearch
    environment:
      discovery.type: single-node
      ELASTIC_PASSWORD: ${ELASTICSEARCH_PASSWORD:-changeme}
      xpack.security.enabled: true
      xpack.security.enrollment.enabled: true
      xpack.ml.enabled: true
      xpack.watcher.enabled: true
      ES_JAVA_OPTS: '-Xms512m -Xmx512m'
      logger.level: info
    ports:
      - '9200:9200'
      - '9300:9300'
    volumes:
      - elasticsearch-data:/usr/share/elasticsearch/data
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "curl -s http://elasticsearch:9200 | grep -q cluster_name || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    labels:
      - "com.metabuilder.service=elasticsearch"
      - "com.metabuilder.component=search-engine"

  # ============================================================================
  # Kibana - Log Visualization
  # ============================================================================
  kibana:
    image: docker.elastic.co/kibana/kibana:8.10.0
    container_name: emailclient-kibana
    hostname: kibana
    environment:
      ELASTICSEARCH_HOSTS: http://elasticsearch:9200
      ELASTICSEARCH_USERNAME: elastic
      ELASTICSEARCH_PASSWORD: ${ELASTICSEARCH_PASSWORD:-changeme}
      KIBANA_DEFAULTAPPID: discover
      xpack.security.enabled: true
      xpack.reporting.enabled: true
    ports:
      - '5601:5601'
    depends_on:
      - elasticsearch
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:5601/api/status"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
    labels:
      - "com.metabuilder.service=kibana"
      - "com.metabuilder.component=logging-ui"

  # ============================================================================
  # Logstash - Log Processing & Forwarding
  # ============================================================================
  logstash:
    image: docker.elastic.co/logstash/logstash:8.10.0
    container_name: emailclient-logstash
    hostname: logstash
    environment:
      ELASTICSEARCH_PASSWORD: ${ELASTICSEARCH_PASSWORD:-changeme}
      LS_JAVA_OPTS: '-Xmx256m -Xms256m'
    ports:
      - '5000:5000/tcp'
      - '5000:5000/udp'
      - '9600:9600'
      - '514:514/tcp'
      - '514:514/udp'
      - '8080:8080'
    volumes:
      - ./logstash/logstash.conf:/usr/share/logstash/pipeline/logstash.conf
      - ./logstash/email-service-template.json:/etc/logstash/templates/email-service-template.json
      - /var/log/emailclient:/var/log/emailclient:ro
      - /var/log/postgresql:/var/log/postgresql:ro
      - /var/log/postfix:/var/log/postfix:ro
      - /var/log/dovecot:/var/log/dovecot:ro
      - logstash-data:/usr/share/logstash/data
    depends_on:
      - elasticsearch
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:9600"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.metabuilder.service=logstash"
      - "com.metabuilder.component=log-processing"

  # ============================================================================
  # Loki - Lightweight Log Aggregation (Optional)
  # ============================================================================
  loki:
    image: grafana/loki:latest
    container_name: emailclient-loki
    hostname: loki
    ports:
      - '3100:3100'
    volumes:
      - ./loki/loki-config.yml:/etc/loki/local-config.yml
      - loki-data:/loki
    command: -config.file=/etc/loki/local-config.yml
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:3100/ready"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.metabuilder.service=loki"
      - "com.metabuilder.component=log-aggregation"

  # ============================================================================
  # OpenTelemetry Collector - Distributed Tracing & Metrics
  # ============================================================================
  otel-collector:
    image: otel/opentelemetry-collector-k8s:latest
    container_name: emailclient-otel-collector
    hostname: otel-collector
    command: ["--config=/etc/otel-collector-config.yml"]
    ports:
      - '4317:4317'    # OTLP gRPC
      - '4318:4318'    # OTLP HTTP
      - '8888:8888'    # Metrics endpoint
      - '13133:13133'  # Health check
      - '14250:14250'  # Jaeger gRPC
      - '14268:14268'  # Jaeger Thrift HTTP
      - '6831:6831/udp'  # Jaeger Thrift Compact
      - '9411:9411'    # Zipkin
      - '55679:55679'  # zPages
    volumes:
      - ./opentelemetry/otel-collector-config.yml:/etc/otel-collector-config.yml
    depends_on:
      - prometheus
      - jaeger
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=otel-collector"
      - "com.metabuilder.component=tracing"

  # ============================================================================
  # Jaeger - Distributed Tracing Backend
  # ============================================================================
  jaeger:
    image: jaegertracing/all-in-one:latest
    container_name: emailclient-jaeger
    hostname: jaeger
    environment:
      COLLECTOR_ZIPKIN_HTTP_PORT: 9411
      MEMORY_MAX_TRACES: 10000
    ports:
      - '6831:6831/udp'   # Jaeger Thrift Compact
      - '16686:16686'     # Jaeger UI
      - '14268:14268'     # Jaeger Thrift HTTP Collector
      - '14250:14250'     # Jaeger gRPC
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:16686"]
      interval: 30s
      timeout: 10s
      retries: 3
    labels:
      - "com.metabuilder.service=jaeger"
      - "com.metabuilder.component=distributed-tracing"

  # ============================================================================
  # Prometheus Exporters
  # ============================================================================

  # cAdvisor - Docker Container Metrics
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: emailclient-cadvisor
    hostname: cadvisor
    ports:
      - '8080:8080'
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
    privileged: true
    networks:
      - monitoring
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=cadvisor"
      - "com.metabuilder.component=container-metrics"

  # Node Exporter - System Metrics
  node-exporter:
    image: prom/node-exporter:latest
    container_name: emailclient-node-exporter
    hostname: node-exporter
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    ports:
      - '9100:9100'
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    networks:
      - monitoring
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=node-exporter"
      - "com.metabuilder.component=system-metrics"

  # PostgreSQL Exporter
  postgres-exporter:
    image: prometheuscommunity/postgres-exporter:latest
    container_name: emailclient-postgres-exporter
    hostname: postgres-exporter
    environment:
      DATA_SOURCE_NAME: postgresql://${DB_USER:-emailclient}:${DB_PASSWORD:-secure_password}@postgres:5432/${DB_NAME:-emailclient_db}?sslmode=disable
    ports:
      - '9187:9187'
    depends_on:
      - postgres
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=postgres-exporter"
      - "com.metabuilder.component=database-metrics"

  # Redis Exporter
  redis-exporter:
    image: oliver006/redis_exporter:latest
    container_name: emailclient-redis-exporter
    hostname: redis-exporter
    environment:
      REDIS_ADDR: redis:6379
    ports:
      - '9121:9121'
    depends_on:
      - redis
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=redis-exporter"
      - "com.metabuilder.component=cache-metrics"

  # Postfix Exporter
  postfix-exporter:
    image: boynux/postfix-exporter:latest
    container_name: emailclient-postfix-exporter
    hostname: postfix-exporter
    ports:
      - '9307:9307'
    volumes:
      - /var/spool/postfix:/var/spool/postfix:ro
      - /var/log/postfix:/var/log/postfix:ro
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=postfix-exporter"
      - "com.metabuilder.component=smtp-metrics"

  # Dovecot Exporter
  dovecot-exporter:
    image: custom/dovecot-exporter:latest
    container_name: emailclient-dovecot-exporter
    hostname: dovecot-exporter
    ports:
      - '9998:9998'
    environment:
      DOVECOT_SOCKET: dovecot:/var/run/dovecot/stats
    volumes:
      - /var/run/dovecot:/var/run/dovecot:ro
    networks:
      - monitoring
      - emailclient-net
    restart: unless-stopped
    labels:
      - "com.metabuilder.service=dovecot-exporter"
      - "com.metabuilder.component=imap-pop3-metrics"

# ============================================================================
# Volumes
# ============================================================================
volumes:
  prometheus-data:
    driver: local
  alertmanager-data:
    driver: local
  grafana-data:
    driver: local
  elasticsearch-data:
    driver: local
  logstash-data:
    driver: local
  loki-data:
    driver: local

# ============================================================================
# Networks
# ============================================================================
networks:
  monitoring:
    driver: bridge
    ipam:
      config:
        - subnet: 172.26.0.0/16
  emailclient-net:
    external: true