1. Instrument Everything

name: boxoffice

# lab 8: OpenTelemetry settings shared by every Java service (merged into each "environment")
x-otel: &otel
  JAVA_TOOL_OPTIONS: -javaagent:/otel/opentelemetry-javaagent.jar
  OTEL_JAVAAGENT_ENABLED: ${OTEL_ON:-true}          # false = same image, agent off
  OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-lgtm:4318
  OTEL_METRIC_EXPORT_INTERVAL: "10000"              # 10 s instead of 60 s
  OTEL_RESOURCE_ATTRIBUTES: service.namespace=boxoffice,deployment.environment.name=local
  OTEL_TRACES_SAMPLER: ${OTEL_TRACES_SAMPLER:-parentbased_always_on}
  OTEL_TRACES_SAMPLER_ARG: ${OTEL_TRACES_SAMPLER_ARG:-1.0}
  LOGGING_PATTERN_CORRELATION: "[%X{trace_id:-},%X{span_id:-}] "   # trace id in console logs

# settings shared by the three catalog replicas (a YAML anchor)
x-catalog: &catalog
  build: ./services/catalog
  image: boxoffice-catalog
  volumes:
    - ./infra/otel:/otel:ro          # lab 8: the Java agent
  environment:
    <<: *otel
    OTEL_SERVICE_NAME: catalog       # three replicas, ONE service
    DB_HOST: db
    DB_PORT: 5432
    DB_NAME: ${DB_NAME:-boxoffice}
    DB_USER: ${DB_USER:-boxoffice}
    DB_PASSWORD: ${DB_PASSWORD:-boxoffice}
    DB_POOL_SIZE: ${DB_POOL_SIZE:-10}
    REDIS_HOST: redis
    REDIS_PORT: 6379
    CACHE_ENABLED: ${CACHE_ENABLED:-true}
    CACHE_TTL_EVENT: ${CACHE_TTL_EVENT:-60s}
    CACHE_TTL_LIST: ${CACHE_TTL_LIST:-10s}
    CACHE_STAMPEDE_PROTECTION: ${CACHE_STAMPEDE_PROTECTION:-false}
  depends_on:
    db:
      condition: service_healthy
    redis:
      condition: service_healthy
  deploy:
    resources:
      limits:
        cpus: "1.0"
        memory: 768M
  healthcheck:
    test: ["CMD-SHELL", "wget -qO- http://localhost:8082/actuator/health/readiness || exit 1"]
    interval: 10s
    timeout: 3s
    start_period: 120s       # lab 8: with the agent, JVMs starting together need up to ~90 s
    retries: 3

services:

  db:
    image: postgres:17
    command: ["postgres", "-c", "max_connections=${DB_MAX_CONNECTIONS:-100}"]
    environment:
      POSTGRES_DB: ${DB_NAME:-boxoffice}
      POSTGRES_USER: ${DB_USER:-boxoffice}
      POSTGRES_PASSWORD: ${DB_PASSWORD:-boxoffice}
      REPLICATION_PASSWORD: ${REPLICATION_PASSWORD:-replicator}
    ports:
      - "5432:5432"
    volumes:
      - db-data:/var/lib/postgresql/data
      # runs only when the volume is new: creates the "replicator" user
      - ./infra/postgres/10-replication.sh:/docker-entrypoint-initdb.d/10-replication.sh:ro
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U $${POSTGRES_USER} -d $${POSTGRES_DB}"]
      interval: 5s
      timeout: 3s
      retries: 10

  # read-only streaming replica of db (hot standby)
  db-replica:
    image: postgres:17
    user: postgres
    entrypoint: ["/usr/local/bin/replica-entrypoint.sh"]
    environment:
      PGPASSWORD: ${REPLICATION_PASSWORD:-replicator}     # used by pg_basebackup
      REPLICA_DELAY: ${REPLICA_DELAY:-0}                   # e.g. 2s: artificial lag
    ports:
      - "5433:5432"
    volumes:
      - replica-data:/var/lib/postgresql/data
      - ./infra/postgres/replica-entrypoint.sh:/usr/local/bin/replica-entrypoint.sh:ro
    depends_on:
      db:
        condition: service_healthy
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U boxoffice -d boxoffice"]
      interval: 5s
      timeout: 3s
      retries: 20

  pgbouncer:
    image: edoburu/pgbouncer:v1.26.0-p0
    ports:
      - "6432:6432"
    volumes:
      - ./infra/pgbouncer/pgbouncer.ini:/etc/pgbouncer/pgbouncer.ini:ro
      - ./infra/pgbouncer/userlist.txt:/etc/pgbouncer/userlist.txt:ro
    depends_on:
      db:
        condition: service_healthy

  redis:
    image: redis:8-alpine
    # a pure cache: bounded memory, evict least-recently-used keys, no persistence
    command: ["redis-server", "--maxmemory", "256mb", "--maxmemory-policy", "allkeys-lru",
              "--save", "", "--appendonly", "no"]
    ports:
      - "6379:6379"
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 10

  # three identical replicas; no "ports:" — only the edge is reachable from outside
  catalog-1:
    <<: *catalog
    hostname: catalog-1
  catalog-2:
    <<: *catalog
    hostname: catalog-2
  catalog-3:
    <<: *catalog
    hostname: catalog-3

  inventory:
    build: ./services/inventory
    volumes:
      - ./infra/otel:/otel:ro
    environment:
      <<: *otel
      OTEL_SERVICE_NAME: inventory
      DB_HOST: ${INVENTORY_DB_HOST:-pgbouncer}      # writes go through PgBouncer...
      DB_PORT: ${INVENTORY_DB_PORT:-6432}
      DB_MIGRATION_HOST: db                         # ...migrations straight to the primary
      DB_REPLICA_HOST: ${DB_REPLICA_HOST:-db-replica}
      DB_REPLICA_PORT: 5432
      DB_NAME: ${DB_NAME:-boxoffice}
      DB_USER: ${DB_USER:-boxoffice}
      DB_PASSWORD: ${DB_PASSWORD:-boxoffice}
      DB_POOL_SIZE: ${INVENTORY_POOL_SIZE:-20}
      INVENTORY_LOCKING: ${INVENTORY_LOCKING:-pessimistic}
      INVENTORY_HOLD_TTL: ${INVENTORY_HOLD_TTL:-PT10M}
    ports:
      - "8083:8083"            # published for experiments; clients go through the edge
    depends_on:
      db:
        condition: service_healthy
      db-replica:
        condition: service_healthy
      pgbouncer:
        condition: service_started
    deploy:
      resources:
        limits:
          cpus: "1.0"
          memory: 768M
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8083/actuator/health/readiness || exit 1"]
      interval: 10s
      timeout: 3s
      start_period: 120s
      retries: 3

  auth:
    build: ./services/auth
    volumes:
      - ./infra/otel:/otel:ro
    environment:
      <<: *otel
      OTEL_SERVICE_NAME: auth
      DB_HOST: db
      DB_PORT: 5432
      DB_NAME: ${DB_NAME:-boxoffice}
      DB_USER: ${DB_USER:-boxoffice}
      DB_PASSWORD: ${DB_PASSWORD:-boxoffice}
      JWT_ISSUER: ${JWT_ISSUER:-boxoffice-auth}
      JWT_TTL: ${JWT_TTL:-PT1H}
      ADMIN_EMAIL: ${ADMIN_EMAIL:-admin@boxoffice.dev}
      ADMIN_PASSWORD: ${ADMIN_PASSWORD:-boxoffice-admin}
    depends_on:
      db:
        condition: service_healthy
    deploy:
      resources:
        limits:
          cpus: "1.0"
          memory: 768M
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8081/actuator/health/readiness || exit 1"]
      interval: 10s
      timeout: 3s
      start_period: 120s
      retries: 3

  gateway:
    build: ./services/gateway
    volumes:
      - ./infra/otel:/otel:ro
    environment:
      <<: *otel
      OTEL_SERVICE_NAME: gateway
      AUTH_URL: http://auth:8081
      INVENTORY_URL: http://inventory:8083
      AUTH_JWKS_URI: http://auth:8081/auth/.well-known/jwks.json
      JWT_ISSUER: ${JWT_ISSUER:-boxoffice-auth}
    ports:
      - "8080:8080"          # published for experiments; clients use the edge (port 80)
    depends_on:
      - auth
      - inventory
      - catalog-1
      - catalog-2
      - catalog-3
    deploy:
      resources:
        limits:
          cpus: "1.0"
          memory: 768M
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8080/actuator/health/readiness || exit 1"]
      interval: 10s
      timeout: 3s
      start_period: 120s
      retries: 3

  edge:
    image: nginx:1.30-alpine
    ports:
      - "80:80"
    volumes:
      - ./infra/nginx/nginx.conf:/etc/nginx/nginx.conf:ro
    depends_on:
      - gateway

  # ---- lab 7: Kafka (KRaft), Kafka UI, Mailpit, order and notification ----

  kafka:
    image: apache/kafka:4.3.1
    hostname: kafka
    ports:
      - "9094:9094"
    environment:
      KAFKA_NODE_ID: 1
      KAFKA_PROCESS_ROLES: broker,controller
      KAFKA_CONTROLLER_QUORUM_VOTERS: 1@kafka:9093
      KAFKA_LISTENERS: PLAINTEXT://:9092,CONTROLLER://:9093,EXTERNAL://:9094
      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:9092,EXTERNAL://localhost:9094
      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,CONTROLLER:PLAINTEXT,EXTERNAL:PLAINTEXT
      KAFKA_CONTROLLER_LISTENER_NAMES: CONTROLLER
      KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: 1
      KAFKA_TRANSACTION_STATE_LOG_REPLICATION_FACTOR: 1
      KAFKA_TRANSACTION_STATE_LOG_MIN_ISR: 1
      KAFKA_GROUP_INITIAL_REBALANCE_DELAY_MS: 0
      KAFKA_AUTO_CREATE_TOPICS_ENABLE: "false"
    healthcheck:
      test: ["CMD-SHELL", "/opt/kafka/bin/kafka-broker-api-versions.sh --bootstrap-server localhost:9092 > /dev/null 2>&1"]
      interval: 10s
      timeout: 10s
      start_period: 60s      # a busy laptop can take a minute to start the broker
      retries: 20

  kafka-init:
    image: apache/kafka:4.3.1
    depends_on:
      kafka:
        condition: service_healthy
    entrypoint: ["/bin/sh", "-c"]
    command:
      - |
        /opt/kafka/bin/kafka-topics.sh --bootstrap-server kafka:9092 --create --if-not-exists \
          --topic order-events --partitions 6 --replication-factor 1 &&
        /opt/kafka/bin/kafka-topics.sh --bootstrap-server kafka:9092 --create --if-not-exists \
          --topic order-events-dlt --partitions 6 --replication-factor 1
    restart: "no"

  kafka-ui:
    image: kafbat/kafka-ui:v1.5.0
    depends_on:
      kafka:
        condition: service_healthy
    ports:
      - "8089:8080"
    environment:
      KAFKA_CLUSTERS_0_NAME: boxoffice
      KAFKA_CLUSTERS_0_BOOTSTRAPSERVERS: kafka:9092

  mailpit:
    image: axllent/mailpit:v1.31
    ports:
      - "8025:8025"
      - "1025:1025"

  order:
    build: ./services/order
    volumes:
      - ./infra/otel:/otel:ro
    environment:
      <<: *otel
      OTEL_SERVICE_NAME: order
      DB_HOST: db
      DB_PORT: 5432
      DB_NAME: ${DB_NAME:-boxoffice}
      DB_USER: ${DB_USER:-boxoffice}
      DB_PASSWORD: ${DB_PASSWORD:-boxoffice}
      REDIS_HOST: redis
      KAFKA_BOOTSTRAP_SERVERS: kafka:9092
      NOTIFICATION_URL: http://notification:8086
      NOTIFY_MODE: ${NOTIFY_MODE:-outbox}            # outbox (after) | sync (before)
      ADMIT_PER_SECOND: ${ADMIT_PER_SECOND:-20}      # waiting-room admission rate
    ports:
      - "8084:8084"
    depends_on:
      db:
        condition: service_healthy
      redis:
        condition: service_healthy
      kafka-init:
        condition: service_completed_successfully
    deploy:
      resources:
        limits:
          cpus: "1.0"
          memory: 768M
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8084/actuator/health/readiness || exit 1"]
      interval: 10s
      timeout: 3s
      start_period: 120s
      retries: 3

  notification:
    build: ./services/notification
    volumes:
      - ./infra/otel:/otel:ro
    environment:
      <<: *otel
      OTEL_SERVICE_NAME: notification
      DB_HOST: db
      DB_PORT: 5432
      DB_NAME: ${DB_NAME:-boxoffice}
      DB_USER: ${DB_USER:-boxoffice}
      DB_PASSWORD: ${DB_PASSWORD:-boxoffice}
      KAFKA_BOOTSTRAP_SERVERS: kafka:9092
      MAIL_HOST: mailpit
      NOTIFY_CONCURRENCY: ${NOTIFY_CONCURRENCY:-3}   # consumer threads (max useful: 6 partitions)
      EMAIL_LATENCY: ${EMAIL_LATENCY:-50ms}          # simulated e-mail provider latency
      NOTIFY_IDEMPOTENT: ${NOTIFY_IDEMPOTENT:-true}  # false = no dedupe (to see duplicates)
    ports:
      - "8086:8086"
    depends_on:
      db:
        condition: service_healthy
      mailpit:
        condition: service_started
      kafka-init:
        condition: service_completed_successfully
    deploy:
      resources:
        limits:
          cpus: "1.0"
          memory: 768M
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://localhost:8086/actuator/health/readiness || exit 1"]
      interval: 10s
      timeout: 3s
      start_period: 120s
      retries: 3

  # ---- lab 8: observability backend (Grafana, Prometheus, Tempo, Loki, OTel Collector) ----

  otel-lgtm:
    image: grafana/otel-lgtm:0.37.0
    ports:
      - "3000:3000"   # Grafana (no login)
      - "4317:4317"   # OTLP gRPC
      - "4318:4318"   # OTLP HTTP
    volumes:
      - ./infra/grafana/dashboards.yaml:/otel-lgtm/grafana/conf/provisioning/dashboards/boxoffice.yaml:ro
      - ./infra/grafana/dashboards:/otel-lgtm/boxoffice-dashboards:ro
      - ./infra/grafana/alerting:/otel-lgtm/grafana/conf/provisioning/alerting:ro

volumes:
  db-data:
  replica-data: