webmail-client/docker/docker-compose.prod.yml

# Production stack for a single box (Synology / QNAP / any Docker host).
#
#   Data lives in bind mounts under ${DATA_ROOT} — NOT in named volumes — so it
#   survives `docker compose down`, image updates, project deletion in the NAS
#   UI, and a full reinstall, and so the NAS backup tools (Hyper Backup,
#   Snapshot Replication, HBS3) can actually see it.
#
#   Nothing is published except ${WEB_PORT}. Postgres, Redis, Meilisearch and the
#   API are reachable only on the internal `webmail` network.
#
#   Start:  ./deploy/webmail.sh up
#   Manual: docker compose --env-file docker/.env.prod -f docker/docker-compose.prod.yml up -d

# Deliberately NOT "webmail": docker/docker-compose.yml (the dev service stack)
# uses that project name, and two compose files sharing one project name fight
# over each other's containers — running `make up` would stop production.
name: webmail-prod

x-logging: &logging
  # A shared NAS must never have its volume filled by container logs.
  driver: json-file
  options: { max-size: "10m", max-file: "3" }

x-backend-image: &backend-image
  image: ${REGISTRY_PREFIX:-webmail}/backend:${IMAGE_TAG:-local}
  build:
    context: ..
    dockerfile: docker/Dockerfile.backend
    args:
      APP_VERSION: ${IMAGE_TAG:-local}
      GIT_SHA: ${GIT_SHA:-unknown}

x-backend-env: &backend-env
  APP_DOMAIN: ${APP_DOMAIN}
  DATABASE_URL: postgresql+asyncpg://${POSTGRES_USER:-webmail}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-webmail}
  REDIS_URL: redis://redis:6379/0
  MASTER_KEY: ${MASTER_KEY}
  BLOB_ROOT: /data/blobs
  SEARCH_BACKEND: ${SEARCH_BACKEND:-pg}
  MEILI_URL: ${MEILI_URL:-http://meilisearch:7700}
  MEILI_KEY: ${MEILI_MASTER_KEY:-}
  LOG_LEVEL: ${LOG_LEVEL:-INFO}
  UNDO_SECONDS: ${UNDO_SECONDS:-10}
  SESSION_TTL_DAYS: ${SESSION_TTL_DAYS:-30}
  MAX_ATTACHMENT_MB: ${MAX_ATTACHMENT_MB:-25}
  TRASH_RETENTION_DAYS: ${TRASH_RETENTION_DAYS:-30}
  SENDER_AVATARS_ENABLED: ${SENDER_AVATARS_ENABLED:-true}
  GOOGLE_OAUTH_ENABLED: ${GOOGLE_OAUTH_ENABLED:-false}
  OAUTH_GOOGLE_CLIENT_ID: ${OAUTH_GOOGLE_CLIENT_ID:-}
  OAUTH_GOOGLE_CLIENT_SECRET: ${OAUTH_GOOGLE_CLIENT_SECRET:-}
  OAUTH_MS_CLIENT_ID: ${OAUTH_MS_CLIENT_ID:-}
  OAUTH_MS_CLIENT_SECRET: ${OAUTH_MS_CLIENT_SECRET:-}
  # Worker sizing — see docker/.env.prod.example for what these cost in RAM.
  INTERACTIVE_CONCURRENCY: ${INTERACTIVE_CONCURRENCY:-8}
  BULK_CONCURRENCY: ${BULK_CONCURRENCY:-1}
  PARSE_CONCURRENCY: ${PARSE_CONCURRENCY:-2}
  STREAM_PARSE_MB: ${STREAM_PARSE_MB:-8}
  PER_HOST_CONN_CAP: ${PER_HOST_CONN_CAP:-10}
  MAX_ACCOUNTS_PER_WORKER: ${MAX_ACCOUNTS_PER_WORKER:-400}
  HOT_BUDGET_PER_WORKER: ${HOT_BUDGET_PER_WORKER:-50}
  APP_VERSION: ${IMAGE_TAG:-local}
  TZ: ${TZ:-UTC}

services:
  # One-shot: make the bind-mounted host folders writable by the unprivileged
  # container users before anything tries to use them. Runs as root by design.
  init:
    image: alpine:3.20
    user: root
    command:
      - sh
      - -c
      - |
        set -e
        mkdir -p /mnt/blobs /mnt/backups /mnt/redis /mnt/meili
        chown -R 10001:10001 /mnt/blobs          # backend runs as uid 10001
        chown -R 999:999     /mnt/backups        # pg_dump runs as postgres (999)
        chown -R 999:999     /mnt/redis          # redis runs as uid 999
        chmod 700 /mnt/backups
        echo "[init] data directories ready"
    volumes:
      - ${DATA_ROOT}/blobs:/mnt/blobs
      - ${DATA_ROOT}/backups:/mnt/backups
      - ${DATA_ROOT}/redis:/mnt/redis
      - ${DATA_ROOT}/meili:/mnt/meili
    restart: "no"
    logging: *logging

  postgres:
    image: postgres:16
    environment:
      POSTGRES_USER: ${POSTGRES_USER:-webmail}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD}
      POSTGRES_DB: ${POSTGRES_DB:-webmail}
      # Keeps the data directory one level down, so the bind mount can hold lost+found
      # and NAS metadata files without initdb refusing to start.
      PGDATA: /var/lib/postgresql/data/pgdata
      TZ: ${TZ:-UTC}
    command:
      - postgres
      - -c
      - shared_buffers=${PG_SHARED_BUFFERS:-256MB}
      - -c
      - max_connections=${PG_MAX_CONNECTIONS:-100}
      - -c
      - work_mem=${PG_WORK_MEM:-8MB}
      - -c
      - maintenance_work_mem=${PG_MAINTENANCE_WORK_MEM:-128MB}
      - -c
      - effective_cache_size=${PG_EFFECTIVE_CACHE_SIZE:-768MB}
      # Full page writes stay ON: NAS filesystems (btrfs/ext4) are not 8k-atomic.
    volumes:
      - ${DATA_ROOT}/postgres:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-webmail} -d ${POSTGRES_DB:-webmail}"]
      interval: 10s
      timeout: 5s
      retries: 12
      start_period: 30s
    restart: unless-stopped
    mem_limit: ${PG_MEM_LIMIT:-768m}
    stop_grace_period: 60s
    logging: *logging

  redis:
    image: redis:7-alpine
    # Leases and the arq queues live here. AOF everysec means a NAS power cut
    # costs at most a second of queue state instead of the whole queue.
    command:
      - redis-server
      - --appendonly
      - "yes"
      - --appendfsync
      - everysec
      - --maxmemory
      - ${REDIS_MAXMEMORY:-96mb}
      - --maxmemory-policy
      - noeviction
    volumes:
      - ${DATA_ROOT}/redis:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 3s
      retries: 10
    depends_on:
      init: { condition: service_completed_successfully }
    restart: unless-stopped
    mem_limit: ${REDIS_MEM_LIMIT:-160m}
    logging: *logging

  # Opt-in: `./deploy/webmail.sh up --meili` (or COMPOSE_PROFILES=meili).
  # Costs ~700MB-1GB RSS; with SEARCH_BACKEND=pg the stack runs without it.
  meilisearch:
    image: getmeili/meilisearch:v1.8
    profiles: ["meili"]
    environment:
      MEILI_MASTER_KEY: ${MEILI_MASTER_KEY:-}
      MEILI_ENV: production
      MEILI_NO_ANALYTICS: "true"
      TZ: ${TZ:-UTC}
    volumes:
      - ${DATA_ROOT}/meili:/meili_data
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://127.0.0.1:7700/health | grep -q available"]
      interval: 10s
      timeout: 5s
      retries: 12
      start_period: 20s
    depends_on:
      init: { condition: service_completed_successfully }
    restart: unless-stopped
    mem_limit: ${MEILI_MEM_LIMIT:-1g}
    logging: *logging

  # One-shot schema upgrade: core Alembic head + every plugin's own branch.
  # Everything else waits for this to exit 0, so a failed migration stops the
  # roll instead of starting code against an old schema.
  migrate:
    <<: *backend-image
    command: ["migrate"]
    environment:
      <<: *backend-env
      ENABLED_PLUGINS: ${ENABLED_PLUGINS:-calendar contacts labels filters}
    volumes:
      - ${DATA_ROOT}/blobs:/data/blobs
    depends_on:
      postgres: { condition: service_healthy }
      init: { condition: service_completed_successfully }
    restart: "no"
    logging: *logging

  api:
    <<: *backend-image
    command: ["api"]
    environment: *backend-env
    volumes:
      - ${DATA_ROOT}/blobs:/data/blobs
    healthcheck:
      test: ["CMD-SHELL", "python -c \"import urllib.request,sys; sys.exit(0 if urllib.request.urlopen('http://127.0.0.1:8000/api/healthz', timeout=5).status==200 else 1)\""]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    depends_on:
      postgres: { condition: service_healthy }
      redis: { condition: service_healthy }
      migrate: { condition: service_completed_successfully }
    restart: unless-stopped
    mem_limit: ${API_MEM_LIMIT:-512m}
    cpus: ${API_CPUS:-1.0}
    logging: *logging

  worker-sync:
    <<: *backend-image
    command: ["worker-sync"]
    environment: *backend-env
    volumes:
      - ${DATA_ROOT}/blobs:/data/blobs
    # Persistent IMAP IDLE connections; the default 1024 is fine for a personal
    # install but this costs nothing and matches the sync-engine v2 sizing.
    ulimits:
      nofile: { soft: 8192, hard: 8192 }
    depends_on:
      postgres: { condition: service_healthy }
      redis: { condition: service_healthy }
      migrate: { condition: service_completed_successfully }
    restart: unless-stopped
    mem_limit: ${WORKER_SYNC_MEM_LIMIT:-512m}
    cpus: ${WORKER_CPUS:-1.5}
    # Leases are released on SIGTERM (workers/run.py targets <10 s); give it room.
    stop_grace_period: 30s
    logging: *logging

  worker-jobs:
    <<: *backend-image
    command: ["worker-jobs"]
    environment: *backend-env
    volumes:
      - ${DATA_ROOT}/blobs:/data/blobs
    ulimits:
      nofile: { soft: 8192, hard: 8192 }
    depends_on:
      postgres: { condition: service_healthy }
      redis: { condition: service_healthy }
      migrate: { condition: service_completed_successfully }
    restart: unless-stopped
    mem_limit: ${WORKER_JOBS_MEM_LIMIT:-640m}
    cpus: ${WORKER_CPUS:-1.5}
    stop_grace_period: 30s
    logging: *logging

  web:
    image: ${REGISTRY_PREFIX:-webmail}/web:${IMAGE_TAG:-local}
    build:
      context: ..
      dockerfile: docker/Dockerfile.frontend
      args:
        APP_VERSION: ${IMAGE_TAG:-local}
        GIT_SHA: ${GIT_SHA:-unknown}
    environment:
      TZ: ${TZ:-UTC}
    ports:
      # The ONLY published port. Bind to a specific NAS interface by setting
      # WEB_BIND (e.g. 192.168.1.185) to keep it off other networks.
      - "${WEB_BIND:-0.0.0.0}:${WEB_PORT:-8088}:80"
    healthcheck:
      test: ["CMD-SHELL", "wget -qO- http://127.0.0.1/healthz | grep -q ok"]
      interval: 30s
      timeout: 5s
      retries: 5
    depends_on:
      api: { condition: service_started }
    restart: unless-stopped
    mem_limit: ${WEB_MEM_LIMIT:-96m}
    logging: *logging

  # Nightly logical backup of Postgres into ${DATA_ROOT}/backups, pruned to
  # BACKUP_KEEP_DAYS. Point Hyper Backup / HBS3 at ${DATA_ROOT} and this plus the
  # blob store is the whole recoverable state (the other half is MASTER_KEY —
  # see docs/nas-install.md §"The three things that matter").
  backup:
    image: postgres:16
    user: "999:999"
    entrypoint: ["/bin/bash", "/usr/local/bin/backup.sh"]
    environment:
      PGHOST: postgres
      PGUSER: ${POSTGRES_USER:-webmail}
      PGPASSWORD: ${POSTGRES_PASSWORD}
      PGDATABASE: ${POSTGRES_DB:-webmail}
      BACKUP_DIR: /backups
      BACKUP_AT: ${BACKUP_AT:-03:30}
      BACKUP_KEEP_DAYS: ${BACKUP_KEEP_DAYS:-14}
      TZ: ${TZ:-UTC}
    volumes:
      - ${DATA_ROOT}/backups:/backups
      - ./backup.sh:/usr/local/bin/backup.sh:ro
    depends_on:
      postgres: { condition: service_healthy }
      init: { condition: service_completed_successfully }
    restart: unless-stopped
    mem_limit: ${BACKUP_MEM_LIMIT:-256m}
    logging: *logging

networks:
  default:
    name: webmail-prod