services: lb: image: haproxy:2.9-alpine ports: - "127.0.0.1:8080:8080" volumes: - ./infra/haproxy.cfg:/usr/local/etc/haproxy/haproxy.cfg:ro depends_on: api: condition: service_healthy healthcheck: test: ["CMD", "haproxy", "-c", "-f", "/usr/local/etc/haproxy/haproxy.cfg"] interval: 10s timeout: 3s retries: 3 deploy: resources: limits: cpus: "0.25" memory: 64M restart: unless-stopped api: build: . expose: - "8080" environment: PORT: "8080" DATABASE_URL: postgres://${PG_USER}:${PG_PASSWORD}@postgres:5432/${PG_DB}?sslmode=disable&timezone=UTC REDIS_URL: redis://redis:6379/0 BROKER_URL: redis://broker:6379/1 SESSION_TTL_SECONDS: "${SESSION_TTL_SECONDS:-3600}" IDEMPOTENCY_TTL_SECONDS: "${IDEMPOTENCY_TTL_SECONDS:-86400}" S3_ENDPOINT: "${S3_ENDPOINT:-http://s3:9000}" S3_REGION: "${S3_REGION:-us-east-1}" S3_BUCKET: "${S3_BUCKET:-messenger-attachments}" S3_ACCESS_KEY_ID: "${S3_ACCESS_KEY_ID}" S3_SECRET_ACCESS_KEY: "${S3_SECRET_ACCESS_KEY}" S3_USE_SSL: "${S3_USE_SSL:-false}" MAX_UPLOAD_BYTES: "${MAX_UPLOAD_BYTES:-10485760}" MAX_IMAGE_PIXELS: "${MAX_IMAGE_PIXELS:-40000000}" ATTACHMENT_GRACE_SECONDS: "${ATTACHMENT_GRACE_SECONDS:-600}" JOB_MAX_ATTEMPTS: "${JOB_MAX_ATTEMPTS:-5}" # Observability (Lab 6) OTEL_SERVICE_NAME: "messenger-api" OTEL_EXPORTER_OTLP_ENDPOINT: "http://otelcol:4317" OTEL_TRACES_EXPORTER: "otlp" OTEL_METRICS_EXPORTER: "otlp" OTEL_LOGS_EXPORTER: "otlp" OTEL_RESOURCE_ATTRIBUTES: "service.name=messenger-api,service.version=lab6,deployment.environment=dev" depends_on: postgres: condition: service_healthy redis: condition: service_healthy broker: condition: service_healthy s3: condition: service_started healthcheck: test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8080/health/ready"] interval: 5s timeout: 3s start_period: 15s retries: 5 deploy: replicas: 2 resources: limits: cpus: "0.50" memory: 512M restart: unless-stopped worker: build: . command: ["./worker"] environment: DATABASE_URL: postgres://${PG_USER}:${PG_PASSWORD}@postgres:5432/${PG_DB}?sslmode=disable&timezone=UTC REDIS_URL: redis://broker:6379/1 S3_ENDPOINT: "${S3_ENDPOINT:-http://s3:9000}" S3_REGION: "${S3_REGION:-us-east-1}" S3_BUCKET: "${S3_BUCKET:-messenger-attachments}" S3_ACCESS_KEY_ID: "${S3_ACCESS_KEY_ID}" S3_SECRET_ACCESS_KEY: "${S3_SECRET_ACCESS_KEY}" S3_USE_SSL: "${S3_USE_SSL:-false}" MAX_UPLOAD_BYTES: "${MAX_UPLOAD_BYTES:-10485760}" MAX_IMAGE_PIXELS: "${MAX_IMAGE_PIXELS:-40000000}" JOB_MAX_ATTEMPTS: "${JOB_MAX_ATTEMPTS:-5}" JOB_CONCURRENCY: "${JOB_CONCURRENCY:-2}" JOB_LEASE_SECONDS: "${JOB_LEASE_SECONDS:-90}" JOB_TIMEOUT_SECONDS: "${JOB_TIMEOUT_SECONDS:-60}" JOB_POLL_SECONDS: "${JOB_POLL_SECONDS:-5}" JOB_RECLAIM_IDLE_SECONDS: "${JOB_RECLAIM_IDLE_SECONDS:-15}" STAGING_RETENTION_SECONDS: "${STAGING_RETENTION_SECONDS:-300}" FAULT_EXIT_AT: "${FAULT_EXIT_AT:-}" FAULT_FAIL_MODE: "${FAULT_FAIL_MODE:-}" FAULT_FAIL_TIMES: "${FAULT_FAIL_TIMES:-1000000}" # Observability (Lab 6) OTEL_SERVICE_NAME: "messenger-worker" OTEL_EXPORTER_OTLP_ENDPOINT: "http://otelcol:4317" OTEL_TRACES_EXPORTER: "otlp" OTEL_METRICS_EXPORTER: "otlp" OTEL_LOGS_EXPORTER: "otlp" OTEL_RESOURCE_ATTRIBUTES: "service.name=messenger-worker,service.version=lab6,deployment.environment=dev" depends_on: postgres: condition: service_healthy broker: condition: service_healthy s3: condition: service_started healthcheck: disable: true deploy: replicas: 1 resources: limits: cpus: "1.0" memory: 512M restart: unless-stopped postgres: image: postgres:16-alpine environment: POSTGRES_USER: ${PG_USER} POSTGRES_PASSWORD: ${PG_PASSWORD} POSTGRES_DB: ${PG_DB} volumes: - postgres_data:/var/lib/postgresql/data healthcheck: test: ["CMD-SHELL", "pg_isready -U ${PG_USER} -d ${PG_DB}"] interval: 5s timeout: 5s retries: 5 deploy: resources: limits: cpus: "0.50" memory: 256M restart: unless-stopped redis: image: redis:7-alpine command: > redis-server --appendonly yes --appendfsync everysec --auto-aof-rewrite-percentage 100 --auto-aof-rewrite-min-size 64mb --maxmemory 128mb --maxmemory-policy noeviction volumes: - redis_data:/data healthcheck: test: ["CMD", "redis-cli", "ping"] interval: 5s timeout: 3s retries: 5 deploy: resources: limits: cpus: "0.25" memory: 192M restart: unless-stopped broker: image: redis:7-alpine command: > redis-server --appendonly yes --appendfsync everysec --maxmemory 256mb --maxmemory-policy noeviction volumes: - broker_data:/data healthcheck: test: ["CMD", "redis-cli", "ping"] interval: 5s timeout: 3s retries: 5 deploy: resources: limits: cpus: "0.50" memory: 256M restart: unless-stopped s3: image: rustfs/rustfs@sha256:ed9210d6411d77ffceb70d94b964a3cb7d225983368bc25bebe01e995293dcc2 command: ["server", "--address", ":9000"] environment: RUSTFS_ADDRESS: ":9000" RUSTFS_VOLUMES: "/data" RUSTFS_REGION: "${S3_REGION:-us-east-1}" RUSTFS_ROOT_USER: "${S3_ROOT_USER:-minioadmin}" RUSTFS_ROOT_PASSWORD: "${S3_ROOT_PASSWORD:-minioadmin-change-me-123}" RUSTFS_CONSOLE_ENABLE: "false" RUSTFS_OBS_LOGGER_LEVEL: "warn" volumes: - s3_data:/data deploy: resources: limits: cpus: "0.50" memory: 256M restart: unless-stopped prometheus: image: prom/prometheus:v2.55.0 command: - --config.file=/etc/prometheus/prometheus.yml - --storage.tsdb.path=/prometheus - --storage.tsdb.retention.time=2h - --web.enable-lifecycle volumes: - ./infra/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro - ./infra/prometheus/rules.yml:/etc/prometheus/rules.yml:ro - prometheus_data:/prometheus ports: - "127.0.0.1:9090:9090" healthcheck: test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:9090/-/healthy || exit 1"] interval: 5s timeout: 3s retries: 5 deploy: resources: limits: cpus: "0.50" memory: 256M restart: unless-stopped loki: image: grafana/loki:3.2.0 command: -config.file=/etc/loki/local-config.yaml volumes: - ./infra/loki/loki-config.yaml:/etc/loki/local-config.yaml:ro - loki_data:/loki ports: - "127.0.0.1:3100:3100" healthcheck: test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3100/ready || exit 1"] interval: 10s timeout: 5s retries: 10 start_period: 30s deploy: resources: limits: cpus: "0.50" memory: 384M restart: unless-stopped tempo: image: grafana/tempo:2.6.0 user: "10001:10001" command: -config.file=/etc/tempo.yaml volumes: - ./infra/tempo/tempo.yaml:/etc/tempo.yaml:ro ports: - "127.0.0.1:3200:3200" healthcheck: test: [ "CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3200/ready || exit 1" ] interval: 10s timeout: 5s retries: 10 start_period: 30s deploy: resources: limits: cpus: "0.50" memory: 384M restart: unless-stopped otelcol: image: otel/opentelemetry-collector-contrib:0.112.0 command: ["--config=/etc/otelcol/config.yaml"] volumes: - ./infra/otelcol/config.yaml:/etc/otelcol/config.yaml:ro ports: - "127.0.0.1:4317:4317" - "127.0.0.1:4318:4318" - "127.0.0.1:8888:8888" - "127.0.0.1:8889:8889" - "127.0.0.1:13133:13133" healthcheck: test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:8889/health || exit 1"] interval: 5s timeout: 3s retries: 10 start_period: 20s disable: true deploy: resources: limits: cpus: "0.50" memory: 256M restart: unless-stopped grafana: image: grafana/grafana:11.2.0 environment: GF_SECURITY_ADMIN_USER: admin GF_SECURITY_ADMIN_PASSWORD: admin GF_USERS_ALLOW_SIGN_UP: "false" GF_AUTH_ANONYMOUS_ENABLED: "true" GF_AUTH_ANONYMOUS_ORG_ROLE: Viewer volumes: - ./infra/grafana/provisioning:/etc/grafana/provisioning:ro - ./infra/grafana/dashboards:/var/lib/grafana/dashboards:ro - grafana_data:/var/lib/grafana ports: - "127.0.0.1:3000:3000" healthcheck: test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1"] interval: 5s timeout: 3s retries: 10 start_period: 20s deploy: resources: limits: cpus: "0.50" memory: 256M restart: unless-stopped volumes: postgres_data: redis_data: s3_data: broker_data: prometheus_data: loki_data: grafana_data: