services: postgres: image: postgres:16.10-bookworm environment: POSTGRES_DB: ${POSTGRES_DB:-messenger} POSTGRES_USER: ${POSTGRES_USER:-lab} POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env} volumes: ["postgres_data:/var/lib/postgresql/data"] healthcheck: test: ["CMD-SHELL", "pg_isready -U $$POSTGRES_USER -d $$POSTGRES_DB"] interval: 2s timeout: 2s retries: 30 mem_limit: 512m cpus: 1.0 restart: unless-stopped networks: [storage] redis: image: redis:7.4.5-alpine command: ["redis-server", "--appendonly", "yes", "--appendfsync", "always", "--save", "60", "1"] volumes: ["redis_data:/data"] healthcheck: test: ["CMD", "redis-cli", "ping"] interval: 2s timeout: 2s retries: 30 mem_limit: 256m cpus: 0.5 restart: unless-stopped networks: [storage] broker: image: rabbitmq:4.1.8-management-alpine hostname: lab6-broker environment: RABBITMQ_DEFAULT_USER: ${BROKER_USER:-labworker} RABBITMQ_DEFAULT_PASS: ${BROKER_PASSWORD:?Set BROKER_PASSWORD in .env} volumes: ["rabbitmq_data:/var/lib/rabbitmq"] healthcheck: test: ["CMD", "rabbitmq-diagnostics", "-q", "ping"] interval: 5s timeout: 5s retries: 25 start_period: 15s mem_limit: 512m cpus: 0.75 restart: unless-stopped networks: [storage] s3-policy: build: . user: "0:0" command: ["python", "-m", "app.s3_policy"] environment: S3_BUCKET: ${S3_BUCKET:-messenger-attachments} S3_ADMIN_ACCESS_KEY: ${S3_ADMIN_ACCESS_KEY:?Set S3_ADMIN_ACCESS_KEY} S3_ADMIN_SECRET_KEY: ${S3_ADMIN_SECRET_KEY:?Set S3_ADMIN_SECRET_KEY} S3_ACCESS_KEY: ${S3_ACCESS_KEY:?Set S3_ACCESS_KEY} S3_SECRET_KEY: ${S3_SECRET_KEY:?Set S3_SECRET_KEY} volumes: ["s3_config:/s3-config"] restart: "no" networks: [storage] s3: image: chrislusf/seaweedfs:4.53 command: ["server", "-dir=/data", "-ip=s3", "-ip.bind=0.0.0.0", "-s3", "-s3.port=8333", "-s3.iam=false", "-s3.config=/s3-config/config.json"] volumes: - s3_data:/data - s3_config:/s3-config:ro - ./infra/filer.toml:/etc/seaweedfs/filer.toml:ro depends_on: s3-policy: condition: service_completed_successfully expose: ["8333"] mem_limit: 640m cpus: 1.0 restart: unless-stopped networks: [storage] s3-bootstrap: build: . command: ["python", "-m", "app.s3_bootstrap"] environment: S3_ENDPOINT: http://s3:8333 S3_BUCKET: ${S3_BUCKET:-messenger-attachments} S3_ADMIN_ACCESS_KEY: ${S3_ADMIN_ACCESS_KEY:?Set S3_ADMIN_ACCESS_KEY} S3_ADMIN_SECRET_KEY: ${S3_ADMIN_SECRET_KEY:?Set S3_ADMIN_SECRET_KEY} depends_on: s3: condition: service_started restart: "no" networks: [storage] migrate: build: . command: ["python", "-m", "app.migrate"] environment: DATABASE_URL: postgresql://${POSTGRES_USER:-lab}:${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env}@postgres:5432/${POSTGRES_DB:-messenger} depends_on: postgres: condition: service_healthy restart: "no" networks: [storage] reconcile: profiles: [maintenance] build: . command: ["python", "-m", "app.reconcile"] environment: DATABASE_URL: postgresql://${POSTGRES_USER:-lab}:${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env}@postgres:5432/${POSTGRES_DB:-messenger} S3_ENDPOINT: http://s3:8333 S3_BUCKET: ${S3_BUCKET:-messenger-attachments} S3_ACCESS_KEY: ${S3_ACCESS_KEY:?Set S3_ACCESS_KEY} S3_SECRET_KEY: ${S3_SECRET_KEY:?Set S3_SECRET_KEY} depends_on: postgres: condition: service_healthy s3-bootstrap: condition: service_completed_successfully migrate: condition: service_completed_successfully restart: "no" networks: [storage] dispatcher: build: . command: ["python", "-m", "app.jobs", "dispatch"] environment: &job_env OTEL_ENABLED: ${OTEL_ENABLED:-yes} OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318 DATABASE_URL: postgresql://${POSTGRES_USER:-lab}:${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env}@postgres:5432/${POSTGRES_DB:-messenger} BROKER_HOST: broker BROKER_USER: ${BROKER_USER:-labworker} BROKER_PASSWORD: ${BROKER_PASSWORD:?Set BROKER_PASSWORD in .env} S3_ENDPOINT: http://s3:8333 S3_BUCKET: ${S3_BUCKET:-messenger-attachments} S3_ACCESS_KEY: ${S3_ACCESS_KEY:?Set S3_ACCESS_KEY} S3_SECRET_KEY: ${S3_SECRET_KEY:?Set S3_SECRET_KEY} JOB_TIMEOUT_SECONDS: ${JOB_TIMEOUT_SECONDS:-60} JOB_MAX_ATTEMPTS: ${JOB_MAX_ATTEMPTS:-5} depends_on: broker: condition: service_healthy migrate: condition: service_completed_successfully s3-bootstrap: condition: service_completed_successfully mem_limit: 192m cpus: 0.5 restart: unless-stopped networks: [storage, telemetry] worker: build: . command: ["python", "-m", "app.jobs", "worker"] environment: <<: *job_env LAB6_FAULT_RETRY_ONCE: ${LAB6_FAULT_RETRY_ONCE:-off} WORKER_PREFETCH: ${WORKER_PREFETCH:-1} LAB5_FAULT_AFTER_S3: ${LAB5_FAULT_AFTER_S3:-off} depends_on: broker: condition: service_healthy migrate: condition: service_completed_successfully s3-bootstrap: condition: service_completed_successfully mem_limit: 768m cpus: 1.0 stop_grace_period: 75s restart: unless-stopped networks: [storage, telemetry] api1: build: . environment: &api_env OTEL_ENABLED: ${OTEL_ENABLED:-yes} OTEL_EXPORTER_OTLP_ENDPOINT: http://otel-collector:4318 APP_PORT: "8080" API_INSTANCE_ID: api1 DATABASE_URL: postgresql://${POSTGRES_USER:-lab}:${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env}@postgres:5432/${POSTGRES_DB:-messenger} REDIS_URL: redis://redis:6379/0 SESSION_TTL_SECONDS: ${SESSION_TTL_SECONDS:-3600} IDEMPOTENCY_TTL_SECONDS: ${IDEMPOTENCY_TTL_SECONDS:-86400} DB_POOL_MAX: ${DB_POOL_MAX:-8} JOB_BACKLOG_LIMIT: ${JOB_BACKLOG_LIMIT:-1000} S3_ENDPOINT: http://s3:8333 S3_BUCKET: ${S3_BUCKET:-messenger-attachments} S3_ACCESS_KEY: ${S3_ACCESS_KEY:?Set S3_ACCESS_KEY} S3_SECRET_KEY: ${S3_SECRET_KEY:?Set S3_SECRET_KEY} depends_on: &api_depends postgres: condition: service_healthy redis: condition: service_healthy migrate: condition: service_completed_successfully s3-bootstrap: condition: service_completed_successfully expose: ["8080"] healthcheck: &api_health test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8080/health/ready', timeout=2)"] interval: 2s timeout: 3s retries: 15 start_period: 10s mem_limit: 384m cpus: 0.75 stop_grace_period: 12s restart: unless-stopped networks: [frontend, storage, telemetry] api2: build: . environment: <<: *api_env API_INSTANCE_ID: api2 depends_on: *api_depends expose: ["8080"] healthcheck: *api_health mem_limit: 384m cpus: 0.75 stop_grace_period: 12s restart: unless-stopped networks: [frontend, storage, telemetry] lb: image: haproxy:3.1.7-alpine volumes: ["./infra/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro"] ports: ["127.0.0.1:8080:8080"] depends_on: api1: condition: service_healthy api2: condition: service_healthy healthcheck: test: ["CMD", "haproxy", "-c", "-f", "/usr/local/etc/haproxy/haproxy.cfg"] interval: 10s timeout: 3s retries: 3 mem_limit: 128m cpus: 0.5 restart: unless-stopped networks: [frontend] telemetry-init: image: busybox:1.37.0 user: "0:0" command: ["sh", "-ec", "chown 10001:10001 /tempo /loki; chown 65534:65534 /prometheus; chown 472:472 /grafana"] volumes: - tempo_data:/tempo - loki_data:/loki - prometheus_data:/prometheus - grafana_data:/grafana network_mode: none restart: "no" otel-collector: image: otel/opentelemetry-collector-contrib:0.123.0 command: ["--config=/etc/otelcol/config.yaml"] volumes: ["./infra/otel/collector.yaml:/etc/otelcol/config.yaml:ro"] environment: GOMEMLIMIT: 180MiB mem_limit: 256m cpus: 0.75 restart: unless-stopped networks: [telemetry] prometheus: depends_on: telemetry-init: condition: service_completed_successfully image: prom/prometheus:v3.2.1 command: ["--config.file=/etc/prometheus/prometheus.yml", "--storage.tsdb.path=/prometheus", "--storage.tsdb.retention.time=72h", "--storage.tsdb.retention.size=512MB"] volumes: - ./infra/otel/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro - ./infra/otel/prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro - prometheus_data:/prometheus ports: ["127.0.0.1:9090:9090"] mem_limit: 384m restart: unless-stopped networks: [telemetry] loki: depends_on: telemetry-init: condition: service_completed_successfully image: grafana/loki:3.4.2 command: ["-config.file=/etc/loki/local-config.yaml"] volumes: - ./infra/otel/loki.yaml:/etc/loki/local-config.yaml:ro - loki_data:/loki ports: ["127.0.0.1:3100:3100"] mem_limit: 512m restart: unless-stopped networks: [telemetry] tempo: depends_on: telemetry-init: condition: service_completed_successfully image: grafana/tempo:2.7.2 command: ["-config.file=/etc/tempo.yaml"] volumes: - ./infra/otel/tempo.yaml:/etc/tempo.yaml:ro - tempo_data:/var/tempo ports: ["127.0.0.1:3200:3200"] mem_limit: 512m restart: unless-stopped networks: [telemetry] grafana: depends_on: telemetry-init: condition: service_completed_successfully image: grafana/grafana:11.6.0 environment: GF_SECURITY_ADMIN_USER: admin GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:?Set GRAFANA_ADMIN_PASSWORD in .env} GF_USERS_ALLOW_SIGN_UP: "false" GF_AUTH_ANONYMOUS_ENABLED: "false" GF_ANALYTICS_REPORTING_ENABLED: "false" volumes: - grafana_data:/var/lib/grafana - ./infra/otel/grafana/provisioning:/etc/grafana/provisioning:ro - ./infra/otel/grafana/dashboards:/var/lib/grafana/dashboards:ro ports: ["127.0.0.1:3000:3000"] mem_limit: 384m restart: unless-stopped networks: [telemetry] networks: telemetry: frontend: storage: internal: true volumes: postgres_data: redis_data: s3_data: s3_config: rabbitmq_data: prometheus_data: loki_data: tempo_data: grafana_data: