Lotty/deploy/compose/compose.observability.yaml

services:
  grafana:
    image: docker.io/grafana/grafana-oss:12.3.2
    entrypoint:
      - /etc/grafana/scripts/entrypoint.sh
    env_file:
      - path: ./infrastructure/configs/grafana/.env.template
        required: true
      - path: ./infrastructure/configs/grafana/.env
        required: false
    healthcheck:
      test: ["CMD", "wget", "-O", "-", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 5s
      start_period: 5s
      start_interval: 2s
      retries: 5
    # ports:
    #   - name: web
    #     target: 3000
    #     published: ${GRAFANA_PORT}
    #     host_ip: 127.0.0.1
    #     protocol: tcp
    #     app_protocol: http
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb
    volumes:
      - type: bind
        source: ./infrastructure/configs/grafana/provisioning
        target: /etc/grafana/provisioning
        read_only: true
      - type: bind
        source: ./infrastructure/configs/grafana/scripts
        target: /etc/grafana/scripts
        read_only: true

  otel-collector:
    image: docker.io/otel/opentelemetry-collector-contrib:latest
    command:
      - --config=/etc/otelcol-contrib/config.yaml
    configs:
      - source: otel_collector_config
        target: /etc/otelcol-contrib/config.yaml
    # ports:
    #   - name: otlp-grpc
    #     target: 4317
    #     published: ${OTEL_GRPC_PORT}
    #     host_ip: 127.0.0.1
    #     protocol: tcp
    #   - name: otlp-http
    #     target: 4318
    #     published: ${OTEL_HTTP_PORT}
    #     host_ip: 127.0.0.1
    #     protocol: tcp
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  grafana-loki:
    image: docker.io/grafana/loki:3.6.5
    command:
      - --config.file=/etc/loki/local-config.yaml
      - --config.expand-env=true
    depends_on:
      s3:
        restart: false
        condition: service_healthy
        required: true
    configs:
      - source: grafana_loki_config
        target: /etc/loki/local-config.yaml
    env_file:
      - path: ./infrastructure/configs/s3/.env.template
        required: true
      - path: ./infrastructure/configs/s3/.env
        required: false
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  grafana-tempo:
    image: docker.io/grafana/tempo:2.10.0
    command:
      - --config.file=/etc/tempo/tempo-config.yaml
      - --config.expand-env=true
    depends_on:
      s3:
        restart: false
        condition: service_healthy
        required: true
    configs:
      - source: grafana_tempo_config
        target: /etc/tempo/tempo-config.yaml
    env_file:
      - path: ./infrastructure/configs/s3/.env.template
        required: true
      - path: ./infrastructure/configs/s3/.env
        required: false
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  grafana-pyroscope:
    image: docker.io/grafana/pyroscope:1.18.0
    command:
      - -config.file=/etc/pyroscope/config.yaml
      - -config.expand-env=true
    depends_on:
      s3:
        restart: false
        condition: service_healthy
        required: true
    configs:
      - source: grafana_pyroscope_config
        target: /etc/pyroscope/config.yaml
    env_file:
      - path: ./infrastructure/configs/s3/.env.template
        required: true
      - path: ./infrastructure/configs/s3/.env
        required: false
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  vmagent:
    image: docker.io/victoriametrics/vmagent:v1.135.0
    command:
      - -promscrape.config=/etc/vmagent/scrape.yaml
      - -remoteWrite.url=http://victoriametrics:8428/api/v1/write
    configs:
      - source: vmagent_config
        target: /etc/vmagent/scrape.yaml
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  victoriametrics:
    image: docker.io/victoriametrics/victoria-metrics:v1.134.0
    command:
      - -storageDataPath=/var/lib/victoriametrics
      - -retentionPeriod=30d
      - -httpListenAddr=:8428
    healthcheck:
      test: ["CMD", "wget", "-qO-", "http://127.0.0.1:8428/-/healthy"]
      interval: 30s
      timeout: 5s
      start_period: 5s
      start_interval: 2s
      retries: 5
    # ports:
    #   - name: web
    #     target: 8428
    #     published: ${VICTORIAMETRICS_PORT}
    #     host_ip: 127.0.0.1
    #     protocol: tcp
    #     app_protocol: http
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb
    volumes:
      - type: volume
        source: victoriametrics_data
        target: /var/lib/victoriametrics
        read_only: false

  redis-exporter:
    image: docker.io/oliver006/redis_exporter:v1.80.2-alpine
    depends_on:
      valkey:
        restart: false
        condition: service_healthy
        required: true
    env_file:
      - path: ./infrastructure/configs/redis-exporter/.env.template
        required: true
      - path: ./infrastructure/configs/redis-exporter/.env
        required: false
    healthcheck:
      test: ["CMD", "wget", "-O", "-", "http://localhost:9121/metrics"]
      interval: 30s
      timeout: 5s
      start_period: 5s
      start_interval: 2s
      retries: 5
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  postgres-exporter:
    image: quay.io/prometheuscommunity/postgres-exporter:latest
    depends_on:
      postgresql:
        restart: false
        condition: service_healthy
        required: true
    env_file:
      - path: ./infrastructure/configs/postgres-exporter/.env.template
        required: true
      - path: ./infrastructure/configs/postgres-exporter/.env
        required: false
    healthcheck:
      test: ["CMD", "wget", "-O", "-", "http://localhost:9187/metrics"]
      interval: 30s
      timeout: 5s
      start_period: 5s
      start_interval: 2s
      retries: 5
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb

  pgadmin:
    image: docker.io/dpage/pgadmin4:9
    configs:
      - source: pgadmin_servers_config
        target: /pgadmin4/servers.json
    depends_on:
      postgresql:
        restart: false
        condition: service_healthy
        required: true
    env_file:
      - path: ./infrastructure/configs/pgadmin/.env.template
        required: true
      - path: ./infrastructure/configs/pgadmin/.env
        required: false
    healthcheck:
      test: ["CMD", "wget", "-O", "-", "http://localhost:80/misc/ping"]
      interval: 30s
      timeout: 5s
      start_period: 5s
      start_interval: 2s
      retries: 5
    # ports:
    #   - name: web
    #     target: 80
    #     published: ${PGADMIN_PORT}
    #     host_ip: 127.0.0.1
    #     protocol: tcp
    #     app_protocol: http
    networks:
      - default
    profiles:
      - observability
    restart: unless-stopped
    shm_size: 4mb
    volumes:
      - type: volume
        source: pgadmin_data
        target: /var/lib/pgadmin
        read_only: false

volumes:
  victoriametrics_data:
  pgadmin_data:

configs:
  otel_collector_config:
    file: ./infrastructure/configs/otel-collector/config.yaml
  grafana_loki_config:
    file: ./infrastructure/configs/grafana-loki/loki.yaml
  grafana_tempo_config:
    file: ./infrastructure/configs/grafana-tempo/tempo.yaml
  grafana_pyroscope_config:
    file: ./infrastructure/configs/grafana-pyroscope/config.yaml
  vmagent_config:
    file: ./infrastructure/configs/victoriametrics/vmagent.yaml
  pgadmin_servers_config:
    file: ./infrastructure/configs/pgadmin/servers.json