docker-compose-observability.yml

version: "3.9"
x-default-logging: &logging
#  driver: "json-file"
#  options:
#    max-size: "5m"
#    max-file: "2"
# x-loki-logging: &loki-logging
#   driver: loki
#   options:
#     loki-url: 'http://loki:3100/api/prom/push'
  driver: loki
  options:
    max-size: "5m"
    max-file: "2"
    loki-url: 'http://localhost:3100/api/prom/push'
    loki-pipeline-stages: |
      - multiline:
          firstline: '^\d{4}-\d{2}-\d{2} \d{1,2}:\d{2}:\d{2}' 
          max_wait_time: 3s
      - regex:
          expression: '^(?P<time>\d{4}-\d{2}-\d{2} \d{1,2}:\d{2}:\d{2},\d{3}) (?P<message>(?s:.*))$$'

services:
  backend:
    image: blubin/knowledge-v1-backend:latest
    container_name: backend
    ports:
      - "8000:8000"
    depends_on:
      - loki
    environment:
      APP_NAME: "backend"
    logging: *logging
    networks:
      - monitoring_network

  # ********************
  # Telemetry Components
  # ********************
  # OpenTelemetry Collector
  collector:
    image: otel/opentelemetry-collector-contrib:0.105.0
    container_name: collector
    hostname: ${OTEL_COLLECTOR_HOST}
    depends_on:
      tempo:
        condition: service_healthy
      prometheus:
        condition: service_healthy
    deploy:
      resources:
        limits:
          memory: 125M
    restart: unless-stopped
    command: [ "--config=/etc/otelcol-config.yml","--feature-gates=pkg.translator.prometheus.NormalizeName"]
    volumes:
      - ./docker/otel-collector/otelcol-config.yml:/etc/otelcol-config.yml
      - collector_data:/var/lib/otelcol
    ports:
      - "5555:5555"     # OTLP over gRPC receiver
      - "6666:6666"     # OTLP over HTTP receiver
    logging: *logging
    networks:
      - monitoring_network

  prometheus:
    image: prom/prometheus:v2.42.0
    hostname: ${PROMETHEUS_SERVICE_HOST}
    container_name: prometheus
    command:
      - --web.console.templates=/etc/prometheus/consoles
      - --web.console.libraries=/etc/prometheus/console_libraries
      - --web.enable-remote-write-receiver
      - --storage.tsdb.retention.time=1h
      - --config.file=/etc/prometheus/prometheus.yml
      - --storage.tsdb.path=/prometheus
      - --web.enable-lifecycle
      - --web.route-prefix=/
      - --enable-feature=exemplar-storage
    volumes:
      - ./docker/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
    ports:
      - "${PROMETHEUS_SERVICE_PORT}:${PROMETHEUS_SERVICE_PORT}"
    depends_on:
      - backend
    healthcheck:
      interval: 5s
      retries: 10
      test: wget --no-verbose --tries=1 --spider http://localhost:9090/status || exit 1
    logging: *logging
    networks:
      - monitoring_network

  grafana:
    image: grafana/grafana:10.4.2
    container_name: grafana
    extra_hosts: [ 'host.docker.internal:host-gateway' ]
    volumes:
      - ./docker/grafana/provisioning/datasources:/etc/grafana/provisioning/datasources:ro
      - ./docker/grafana/provisioning/dashboards:/etc/grafana/provisioning/dashboards:ro
#    environment:
#      - GF_AUTH_ANONYMOUS_ENABLED=true
#      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
#      - GF_AUTH_DISABLE_LOGIN_FORM=true
      - grafana_data:/var/lib/grafana
    ports:
      - "3000:3000"
    healthcheck:
      interval: 5s
      retries: 10
      test: wget --no-verbose --tries=1 --spider http://localhost:3000 || exit 1
    logging: *logging
    networks:
      - monitoring_network

  loki:
    image: grafana/loki:3.1.0
    container_name: loki
    ports:
      - "3100:3100"
    command: -config.file=/etc/loki/local-config.yaml
    volumes:
      - loki_data:/loki
    logging: *logging
    networks:
      - monitoring_network

  tempo:
    image: grafana/tempo:1.5.0
    container_name: tempo
    command: [ "-config.file=/etc/tempo.yaml", "-search.enabled=true"]
    volumes:
      - ./docker/tempo/tempo-local.yaml:/etc/tempo.yaml:ro
      - ./tempo-data:/tmp/tempo
    ports:
      - "3200:3200"
      # - "14268:14268"  # jaeger ingest
      # - "9411:9411" # zipkin
#      - "4317:4317" # otlp grpc ingest
      #  - "4318:4318" # otlp http ingest
    healthcheck:
      interval: 5s
      retries: 10
      test: wget --no-verbose --tries=1 --spider http://localhost:3200/status || exit 1
    logging: *logging
    networks:
      - monitoring_network


volumes:
  prometheus_data:
    driver: local
  grafana_data:
    driver: local
  tempo_data:
    driver: local
  loki_data:
    driver: local
  collector_data:
    driver: local

networks:
  monitoring_network:
    driver: bridge
    name: monitoring_network