windmill/docker-compose.yml

version: "3.7"

x-logging: &default-logging
  driver: "json-file"
  options:
    max-size: "${LOG_MAX_SIZE:-20m}"
    max-file: "${LOG_MAX_FILE:-10}"
    compress: "true"

services:
  ## UPGRADING AN EXISTING STACK: a db_data volume written by postgres:16 holds a
  ## cluster that 18 cannot read. The container exits with an explanatory error
  ## instead of coming up blank, so nothing is lost before you migrate. Postgres 16
  ## is supported upstream until Nov 2028, so staying on `image: postgres:16` with
  ## the old `db_data:/var/lib/postgresql/data` mount remains a valid option.
  ##
  ## Migrating means moving the WHOLE CLUSTER, not the windmill database. Windmill
  ## creates instance datatable, DuckLake and wm_fork_* databases alongside it, and
  ## grants its row-level security policies to cluster-level roles; a single-database
  ## pg_dump carries neither, and the volume is gone before anyone notices. Dump
  ## while the 16 container is still the one running (git checkout the previous
  ## docker-compose.yml if you already replaced it):
  ##   docker compose down && docker compose up --wait db
  ##   docker compose exec -T db pg_dumpall -U postgres > cluster.sql
  ## Check cluster.sql lists every database, then switch to this file:
  ##   docker compose down
  ##   docker volume ls | grep db_data     # then remove the one this project owns
  ##   docker volume rm <that_volume>
  ##   docker compose up --wait db
  ##   docker compose exec -T db psql -U postgres -d postgres -c 'DROP DATABASE windmill'
  ##   docker compose exec -T db psql -U postgres -d postgres < cluster.sql > restore.log 2>&1
  ##   grep -i '^ERROR' restore.log      # only `role "postgres" already exists`
  ##   docker compose exec -T db vacuumdb -U postgres --all --analyze-in-stages
  ##   docker compose up -d
  ## `up --wait` because psql would otherwise race initdb on a fresh volume. The
  ## DROP is what lets the dump's own `CREATE DATABASE windmill` run: POSTGRES_DB
  ## has already made an empty one, and loading into it would keep the new cluster's
  ## encoding and collation instead of the dumped ones, for that database only.
  ## psql does not stop on error and the old volume is already gone by then, so grep
  ## the log rather than trust its exit code; the fresh cluster bootstraps `postgres`
  ## itself, so that role is the one error left. vacuumdb spans every restored
  ## database, which a plain ANALYZE would not: each comes back with no planner
  ## statistics, and a fork database is where the stall shows. Postgres triggers
  ## reading a database in this cluster come back disabled with "replication slot
  ## ... no longer exists", since slots are never dumped; re-saving the trigger
  ## recreates the slot, then re-enable it.
  db:
    deploy:
      # To use an external database, set replicas to 0 and set DATABASE_URL to the external database url in the .env file
      replicas: 1
    image: postgres:18
    shm_size: 1g
    restart: unless-stopped
    volumes:
      # From 18 on the official image keeps the cluster in a major-version
      # subdirectory (/var/lib/postgresql/18/docker), so the mount has to be the
      # parent directory: that is what lets pg_upgrade see an old and a new
      # cluster inside a single mount point. Mounting the pre-18 .../data path
      # instead makes the image exit rather than start, which is what turns a
      # stale 16 cluster into a loud failure instead of an empty instance.
      - db_data:/var/lib/postgresql
    expose:
      - 5432
    environment:
      POSTGRES_PASSWORD: changeme
      POSTGRES_DB: windmill
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U postgres"]
      interval: 10s
      timeout: 5s
      retries: 5
    logging: *default-logging

  windmill_server:
    image: ${WM_IMAGE}
    pull_policy: always
    deploy:
      replicas: 1
    restart: unless-stopped
    expose:
      - 8000
      - 2525
    environment:
      - DATABASE_URL=${DATABASE_URL}
      - MODE=server
    depends_on:
      db:
        condition: service_healthy
    volumes:
      - worker_logs:/tmp/windmill/logs

    logging: *default-logging

  windmill_worker:
    image: ${WM_IMAGE}
    pull_policy: always
    deploy:
      replicas: 3
      resources:
        limits:
          memory: 2048M
          # for GB, use syntax '2Gi'
    restart: unless-stopped
    # Uncomment to enable PID namespace isolation (recommended for security)
    # Requires privileged mode for --mount-proc flag
    # See: https://www.windmill.dev/docs/advanced/security_isolation
    privileged: true
    environment:
      - DATABASE_URL=${DATABASE_URL}
      - MODE=worker
      - WORKER_GROUP=default
      # If running with non-root/non-windmill UID (e.g., user: "1001:1001"),
      # add: - HOME=/tmp
      - FAVOR_UNSHARE_PID=true
    depends_on:
      db:
        condition: service_healthy
    # to mount the worker folder to debug, KEEP_JOB_DIR=true and mount /tmp/windmill
    volumes:
      - worker_dependency_cache:/tmp/windmill/cache
      - worker_logs:/tmp/windmill/logs
      ## Sandboxed containers (`# sandbox <image>`) run daemonless via crane + nsjail
      ## inside the worker itself — no Docker socket or dind sidecar required.
      ## For the legacy full-compat docker (a bare `# docker`, trusted users only),
      ## mount the host Docker socket by uncommenting the line below. WARNING: this
      ## grants user scripts full access to the host Docker daemon (host filesystem
      ## access and privilege escalation) — only use it if you fully trust all users.
      # - /var/run/docker.sock:/var/run/docker.sock

    logging: *default-logging

  ## This worker is specialized for "native" jobs. Native jobs run in-process and thus are much more lightweight than other jobs
  windmill_worker_native:
    # Use ghcr.io/windmill-labs/windmill-ee:main for the ee
    image: ${WM_IMAGE}
    pull_policy: always
    deploy:
      replicas: 1
      resources:
        limits:
          memory: 2048M
          # for GB, use syntax '2Gi'
    restart: unless-stopped
    # Uncomment to enable PID namespace isolation (recommended for security)
    # Requires privileged mode for --mount-proc flag
    # See: https://www.windmill.dev/docs/advanced/security_isolation
    environment:
      - DATABASE_URL=${DATABASE_URL}
      - MODE=worker
      - WORKER_GROUP=native
      - NATIVE_MODE=true
      - SLEEP_QUEUE=200
    depends_on:
      db:
        condition: service_healthy
    volumes:
      - worker_logs:/tmp/windmill/logs
    logging: *default-logging
  # This worker is specialized for reports or scraping jobs. It is assigned the "reports" worker group which has an init script that installs chromium and can be targeted by using the "chromium" worker tag.
  # windmill_worker_reports:
  #   image: ${WM_IMAGE}
  #   pull_policy: always
  #   deploy:
  #     replicas: 1
  #     resources:
  #       limits:
  #         memory: 2048M
  #         # for GB, use syntax '2Gi'
  #   restart: unless-stopped
  #   # Uncomment to enable PID namespace isolation (recommended for security)
  #   # Requires privileged mode for --mount-proc flag
  #   # See: https://www.windmill.dev/docs/advanced/security_isolation
  #   privileged: true
  #   environment:
  #     - DATABASE_URL=${DATABASE_URL}
  #     - MODE=worker
  #     - WORKER_GROUP=reports
  #     - FAVOR_UNSHARE_PID=true
  #   depends_on:
  #     db:
  #       condition: service_healthy
  #   # to mount the worker folder to debug, KEEP_JOB_DIR=true and mount /tmp/windmill
  #   volumes:
  #     - worker_dependency_cache:/tmp/windmill/cache
  #     - worker_logs:/tmp/windmill/logs

  # The indexer powers full-text job and log search, an EE feature.
  windmill_indexer:
    image: ${WM_IMAGE}
    pull_policy: always
    deploy:
      replicas: 0 # set to 1 to enable full-text job and log search
    restart: unless-stopped
    expose:
      - 8002
    environment:
      - PORT=8002
      - DATABASE_URL=${DATABASE_URL}
      - MODE=indexer
    depends_on:
      db:
        condition: service_healthy
    volumes:
      - windmill_index:/tmp/windmill/search
      - worker_logs:/tmp/windmill/logs
    logging: *default-logging

  # Combined extra services: LSP, Multiplayer, and Debugger
  # Each service can be enabled/disabled via environment variables:
  #   - ENABLE_LSP=true (default) - Language Server Protocol for code intelligence
  #   - ENABLE_MULTIPLAYER=false - Real-time collaboration (Enterprise Edition)
  #   - ENABLE_DEBUGGER=false - Interactive debugging via DAP WebSocket
  windmill_extra:
    image: ghcr.io/windmill-labs/windmill-extra:latest
    pull_policy: always
    restart: unless-stopped
    expose:
      - 3001 # LSP
      - 3002 # Multiplayer
      - 3003 # Debugger
    environment:
      - ENABLE_LSP=true
      - ENABLE_MULTIPLAYER=false # Set to true to enable multiplayer (Enterprise Edition)
      - ENABLE_DEBUGGER=true # Set to true to enable debugger
      - DEBUGGER_PORT=3003 # Debugger service port
      - ENABLE_NSJAIL=false # Set to true for nsjail sandboxing (requires privileged: true)
      - REQUIRE_SIGNED_DEBUG_REQUESTS=true # Require backend-signed JWT tokens for debug sessions. Do NOT set to false on any internet-reachable deployment: it exposes an unauthenticated code-execution debugger.
      - WINDMILL_BASE_URL=http://windmill_server:8000
      # - DEBUG_ALLOWED_ORIGINS=https://your-windmill-host # Optional CSWSH hardening: comma-separated allowlist of browser Origins permitted to open debug WebSockets
    volumes:
      - lsp_cache:/pyls/.cache
      # Behind a TLS-intercepting proxy, mount its CA here (as .crt) and it is registered in the
      # system trust store before any service starts. That alone does not cover dependency
      # installation — see debugger/README.md for the variables it also needs
      # - ./corp-ca.crt:/usr/local/share/ca-certificates/corp-ca.crt:ro
    logging: *default-logging

  caddy:
    # Pinned: this image and the ./Caddyfile next to it are version-coupled, so
    # they have to move together. Bump docker/caddy-l4.version in the same
    # commit as any Caddyfile change.
    image: ghcr.io/windmill-labs/caddy-l4:2.11.4-1
    restart: unless-stopped
    # Configure the mounted Caddyfile and the exposed ports or use another reverse proxy if needed
    volumes:
      - ./Caddyfile:/etc/caddy/Caddyfile
      - caddy_data:/data
      # - ./certs:/certs # Provide custom certificate files like cert.pem and key.pem to enable HTTPS - See the corresponding section in the Caddyfile
    ports:
      # To change the exposed port, simply change 80:80 to <desired_port>:80. No other changes needed
      - 80:80
      - 25:25
      # - 443:443 # Uncomment to enable HTTPS handling by Caddy
    environment:
      - BASE_URL=":80"
      # - BASE_URL=":443" # uncomment and comment line above to enable HTTPS via custom certificate and key files
      # - BASE_URL=mydomain.com # Uncomment and comment line above to enable HTTPS handling by Caddy
    logging: *default-logging

volumes:
  db_data: null
  worker_dependency_cache: null
  worker_logs: null
  worker_memory: null
  windmill_index: null
  lsp_cache: null
  caddy_data: null