Bump version for 0.12.1

Allow customizing audit broadcast with env

.github/workflows/ci.yml

@@ -1,5 +1,9 @@
 name: CI
-on: [push, pull_request]
+on: 
+  push:
+    branches:
+      - main
+  pull_request:
 jobs:
   tests:
     strategy:
@@ -8,12 +12,15 @@ jobs:
           - "2.7"
           - "3.1"
           - "3.2"
+        gemfile:
+          - Gemfile
+          - gemfiles/rails_edge.gemfile
         continue-on-error: [false]
-
     name: ${{ format('Tests (Ruby {0})', matrix.ruby-version) }}
     runs-on: ubuntu-latest
     continue-on-error: ${{ matrix.continue-on-error }}
-
+    env:
+      BUNDLE_GEMFILE: ${{ github.workspace }}/${{ matrix.gemfile }}
     steps:
       - uses: actions/checkout@v2
 

.github/workflows/docker-publish.yml

@@ -16,10 +16,6 @@ jobs:
       -
         name: Checkout
         uses: actions/checkout@v3
-      -
-        name: Extract Version Number
-        id: extract_version
-        run: echo "::set-output name=version::${{ github.ref | replace('refs/tags/', '') }}"
       -
         name: Set up QEMU
         uses: docker/setup-qemu-action@v2
@@ -42,4 +38,4 @@ jobs:
           push: true
           tags: |
             ghcr.io/mrsked/mrsk:latest
-            ghcr.io/mrsked/mrsk:${{ steps.extract_version.outputs.version }}
+            ghcr.io/mrsked/mrsk:${{ github.ref_name }}

.gitignore

@@ -1,4 +1,5 @@
 .byebug_history
 *.gem
 coverage/*
-.DS_Store
+.DS_Store
+gemfiles/*.lock

Dockerfile

@@ -1,6 +1,9 @@
 # Use the official Ruby 3.2.0 Alpine image as the base image
 FROM ruby:3.2.0-alpine
 
+# Install  docker/buildx-bin
+COPY --from=docker/buildx-bin /buildx /usr/libexec/docker/cli-plugins/docker-buildx
+
 # Set the working directory to /mrsk
 WORKDIR /mrsk
 
@@ -11,7 +14,7 @@ COPY Gemfile Gemfile.lock mrsk.gemspec ./
 COPY lib/mrsk/version.rb /mrsk/lib/mrsk/version.rb
 
 # Install system dependencies
-RUN apk add --no-cache --update build-base git docker openrc \
+RUN apk add --no-cache --update build-base git docker openrc openssh-client-default \
     && rc-update add docker boot \
     && gem install bundler --version=2.4.3 \
     && bundle install
@@ -28,6 +31,10 @@ RUN gem build mrsk.gemspec && \
 # Set the working directory to /workdir
 WORKDIR /workdir
 
+# Tell git it's safe to access /workdir/.git even if
+# the directory is owned by a different user
+RUN git config --global --add safe.directory /workdir
+
 # Set the entrypoint to run the installed binary in /workdir
 # Example:  docker run -it -v "$PWD:/workdir" mrsk init
 ENTRYPOINT ["mrsk"]

Gemfile

@@ -2,7 +2,3 @@ source 'https://rubygems.org'
 git_source(:github) { |repo| "https://github.com/#{repo}.git" }
 
 gemspec
-
-gem "debug"
-gem "mocha"
-gem "railties"

Gemfile.lock

@@ -1,11 +1,12 @@
 PATH
   remote: .
   specs:
-    mrsk (0.9.1)
+    mrsk (0.12.1)
       activesupport (>= 7.0)
       bcrypt_pbkdf (~> 1.0)
       dotenv (~> 2.8)
       ed25519 (~> 1.2)
+      net-ssh (~> 7.0)
       sshkit (~> 1.21)
       thor (~> 1.2)
       zeitwerk (~> 2.5)
@@ -13,29 +14,29 @@ PATH
 GEM
   remote: https://rubygems.org/
   specs:
-    actionpack (7.0.4)
-      actionview (= 7.0.4)
-      activesupport (= 7.0.4)
+    actionpack (7.0.4.3)
+      actionview (= 7.0.4.3)
+      activesupport (= 7.0.4.3)
       rack (~> 2.0, >= 2.2.0)
       rack-test (>= 0.6.3)
       rails-dom-testing (~> 2.0)
       rails-html-sanitizer (~> 1.0, >= 1.2.0)
-    actionview (7.0.4)
-      activesupport (= 7.0.4)
+    actionview (7.0.4.3)
+      activesupport (= 7.0.4.3)
       builder (~> 3.1)
       erubi (~> 1.4)
       rails-dom-testing (~> 2.0)
       rails-html-sanitizer (~> 1.1, >= 1.2.0)
-    activesupport (7.0.4)
+    activesupport (7.0.4.3)
       concurrent-ruby (~> 1.0, >= 1.0.2)
       i18n (>= 1.6, < 2)
       minitest (>= 5.1)
       tzinfo (~> 2.0)
     bcrypt_pbkdf (1.1.0)
     builder (3.2.4)
-    concurrent-ruby (1.1.10)
+    concurrent-ruby (1.2.2)
     crass (1.0.6)
-    debug (1.7.1)
+    debug (1.7.2)
       irb (>= 1.5.0)
       reline (>= 0.3.1)
     dotenv (2.8.1)
@@ -44,59 +45,55 @@ GEM
     i18n (1.12.0)
       concurrent-ruby (~> 1.0)
     io-console (0.6.0)
-    irb (1.6.2)
+    irb (1.6.3)
       reline (>= 0.3.0)
-    loofah (2.19.1)
+    loofah (2.20.0)
       crass (~> 1.0.2)
       nokogiri (>= 1.5.9)
     method_source (1.0.0)
-    minitest (5.17.0)
+    minitest (5.18.0)
     mocha (2.0.2)
       ruby2_keywords (>= 0.0.5)
     net-scp (4.0.0)
       net-ssh (>= 2.6.5, < 8.0.0)
-    net-ssh (7.0.1)
-    nokogiri (1.14.0-arm64-darwin)
+    net-ssh (7.1.0)
+    nokogiri (1.14.2-arm64-darwin)
       racc (~> 1.4)
-    nokogiri (1.14.0-x86_64-darwin)
+    nokogiri (1.14.2-x86_64-darwin)
       racc (~> 1.4)
-    nokogiri (1.14.0-x86_64-linux)
+    nokogiri (1.14.2-x86_64-linux)
       racc (~> 1.4)
     racc (1.6.2)
-    rack (2.2.5)
-    rack-test (2.0.2)
+    rack (2.2.6.4)
+    rack-test (2.1.0)
       rack (>= 1.3)
     rails-dom-testing (2.0.3)
       activesupport (>= 4.2.0)
       nokogiri (>= 1.6)
-    rails-html-sanitizer (1.4.4)
+    rails-html-sanitizer (1.5.0)
       loofah (~> 2.19, >= 2.19.1)
-    railties (7.0.4)
-      actionpack (= 7.0.4)
-      activesupport (= 7.0.4)
+    railties (7.0.4.3)
+      actionpack (= 7.0.4.3)
+      activesupport (= 7.0.4.3)
       method_source
       rake (>= 12.2)
       thor (~> 1.0)
       zeitwerk (~> 2.5)
     rake (13.0.6)
-    reline (0.3.2)
+    reline (0.3.3)
       io-console (~> 0.5)
     ruby2_keywords (0.0.5)
-    sshkit (1.21.3)
+    sshkit (1.21.4)
       net-scp (>= 1.1.2)
       net-ssh (>= 2.8.0)
     thor (1.2.1)
-    tzinfo (2.0.5)
+    tzinfo (2.0.6)
       concurrent-ruby (~> 1.0)
-    zeitwerk (2.6.6)
+    zeitwerk (2.6.7)
 
 PLATFORMS
-  arm64-darwin-20
-  arm64-darwin-21
-  arm64-darwin-22
-  x86_64-darwin-20
-  x86_64-darwin-21
-  x86_64-darwin-22
+  arm64-darwin
+  x86_64-darwin
   x86_64-linux
 
 DEPENDENCIES

README.md

@@ -4,9 +4,25 @@ MRSK deploys web apps anywhere from bare metal to cloud VMs using Docker with ze
 
 Watch the screencast: https://www.youtube.com/watch?v=LL1cV2FXZ5I
 
+Join us on Discord: https://discord.gg/YgHVT7GCXS
+
+Ask questions: https://github.com/mrsked/mrsk/discussions
+
 ## Installation
 
-Install MRSK globally with `gem install mrsk`. Then, inside your app directory, run `mrsk init` (or `mrsk init --bundle` within Rails apps where you want a bin/mrsk binstub). Now edit the new file `config/deploy.yml`. It could look as simple as this:
+If you have a Ruby environment available, you can install MRSK globally with:
+
+```sh
+gem install mrsk
+```
+
+...otherwise, you can run a dockerized version via an alias (add this to your .bashrc or similar to simplify re-use):
+
+```sh
+alias mrsk='docker run --rm -it -v $HOME/.ssh:/root/.ssh -v /var/run/docker.sock:/var/run/docker.sock -v ${PWD}/:/workdir  ghcr.io/mrsked/mrsk'
+```
+
+Then, inside your app directory, run `mrsk init` (or `mrsk init --bundle` within Rails 7+ apps where you want a bin/mrsk binstub). Now edit the new file `config/deploy.yml`. It could look as simple as this:
 
 ```yaml
 service: hey
@@ -23,7 +39,7 @@ env:
     - RAILS_MASTER_KEY
 ```
 
-Then edit your `.env` file to add your registry password as `MRSK_REGISTRY_PASSWORD` (and your `RAILS_MASTER_KEY` for production with a Rails app). 
+Then edit your `.env` file to add your registry password as `MRSK_REGISTRY_PASSWORD` (and your `RAILS_MASTER_KEY` for production with a Rails app).
 
 Now you're ready to deploy to the servers:
 
@@ -34,7 +50,7 @@ mrsk deploy
 This will:
 
 1. Connect to the servers over SSH (using root by default, authenticated by your ssh key)
-2. Install Docker on any server that might be missing it (using apt-get)
+2. Install Docker on any server that might be missing it (using apt-get): root access is needed via ssh for this.
 3. Log into the registry both locally and remotely
 4. Build the image using the standard Dockerfile in the root of the application.
 5. Push the image to the registry.
@@ -67,6 +83,16 @@ Docker Swarm is much simpler than Kubernetes, but it's still built on the same d
 
 Ultimately, there are a myriad of ways to deploy web apps, but this is the toolkit we're using at [37signals](https://37signals.com) to bring [HEY](https://www.hey.com) [home from the cloud](https://world.hey.com/dhh/why-we-re-leaving-the-cloud-654b47e0) without losing the advantages of modern containerization tooling.
 
+## Running MRSK from Docker
+
+MRSK is packaged up in a Docker container similarly to [rails/docked](https://github.com/rails/docked). This will allow you to run MRSK (from your application directory) without having to install any dependencies other than Docker. Add the following alias to your profile configuration to make working with the container more convenient:
+
+```bash
+alias mrsk="docker run -it --rm -v '${PWD}:/workdir' -v '${SSH_AUTH_SOCK}:/ssh-agent' -v /var/run/docker.sock:/var/run/docker.sock -e 'SSH_AUTH_SOCK=/ssh-agent' ghcr.io/mrsked/mrsk:latest"
+```
+
+Since MRSK uses SSH to establish a remote connection, it will need access to your SSH agent. The above command uses a volume mount to make it available inside the container and configures the SSH agent inside the container to make use of it.
+
 ## Configuration
 
 ### Using .env file to load required environment variables
@@ -99,9 +125,9 @@ If you need separate env variables for different destinations, you can set them
 
 #### Bitwarden as a secret store
 
-If you are using open source secret store like bitwarden, you can create `.env.erb` as a template which looks up the secrets. 
+If you are using open source secret store like bitwarden, you can create `.env.erb` as a template which looks up the secrets.
 
-You can store `SOME_SECRET` in a secure note in bitwarden vault. 
+You can store `SOME_SECRET` in a secure note in bitwarden vault.
 
 ```
 $ bw list items --search SOME_SECRET | jq
@@ -140,7 +166,7 @@ SOME_SECRET=<%= `bw get notes 123123123-1232-4224-222f-234234234234 --session #{
 <% else raise ArgumentError, "session_token token missing" end %>
 ```
 
-Then everyone deploying the app can run `mrsk envify` and mrsk will generate `.env` 
+Then everyone deploying the app can run `mrsk envify` and mrsk will generate `.env`
 
 
 ### Using another registry than Docker Hub
@@ -150,9 +176,9 @@ The default registry is Docker Hub, but you can change it using `registry/server
 ```yaml
 registry:
   server: registry.digitalocean.com
-  username:  
+  username:
     - DOCKER_REGISTRY_TOKEN
-  password: 
+  password:
     - DOCKER_REGISTRY_TOKEN
 ```
 
@@ -167,6 +193,15 @@ ssh:
   user: app
 ```
 
+If you are using non-root user, you need to bootstrap your servers manually, before using them with MRSK. On Ubuntu, you'd do:
+
+```bash
+sudo apt update
+sudo apt upgrade -y
+sudo apt install -y docker.io curl git
+sudo usermod -a -G docker ubuntu
+```
+
 ### Using a proxy SSH host
 
 If you need to connect to server through a proxy host, you can use `ssh/proxy`:
@@ -183,6 +218,13 @@ ssh:
   proxy: "app@192.168.0.1"
 ```
 
+Also if you need specific proxy command to connect to the server:
+
+```yaml
+ssh:
+  proxy_command: aws ssm start-session --target %h --document-name AWS-StartSSHSession --parameters 'portNumber=%p' --region=us-east-1 ## ssh via aws ssm
+```
+
 ### Using env variables
 
 You can inject env variables into the app containers using `env`:
@@ -222,6 +264,12 @@ volumes:
   - "/local/path:/container/path"
 ```
 
+### MRSK env variables
+
+The following env variables are set when your container runs:
+
+`MRSK_CONTAINER_NAME` : this contains the current container name and version
+
 ### Using different roles for servers
 
 If your application uses separate hosts for running jobs or other roles beyond the default web running, you can specify these hosts in a dedicated role with a new entrypoint command like so:
@@ -256,12 +304,13 @@ servers:
 
 You can specialize the default Traefik rules by setting labels on the containers that are being started:
 
-```
+```yaml
 labels:
-  traefik.http.routers.hey.rule: Host(\`app.hey.com\`)
+  traefik.http.routers.hey-web.rule: Host(`app.hey.com`)
 ```
+Traefik rules are in the "service-role-destination" format. The default role will be `web` if no rule is specified. If the destination is not specified, it is not included. To give an example, the above rule would become "traefik.http.routers.hey-web-staging.rule" if it was for the "staging" destination.
 
-Note: The escaped backticks are needed to ensure the rule is passed in correctly and not treated as command substitution by Bash!
+Note: The backticks are needed to ensure the rule is passed in correctly and not treated as command substitution by Bash!
 
 This allows you to run multiple applications on the same server sharing the same Traefik instance and port.
 See https://doc.traefik.io/traefik/routing/routers/#rule for a full list of available routing rules.
@@ -282,6 +331,21 @@ servers:
       my-label: "50"
 ```
 
+### Using shell expansion
+
+You can use shell expansion to interpolate values from the host machine into labels and env variables with the `${}` syntax.
+Anything within the curly braces will be executed on the host machine and the result will be interpolated into the label or env variable.
+
+```yaml
+labels:
+  host-machine: "${cat /etc/hostname}"
+
+env:
+  HOST_DEPLOYMENT_DIR: "${PWD}"
+```
+
+Note: Any other occurrence of `$` will be escaped to prevent unwanted shell expansion!
+
 ### Using container options
 
 You can specialize the options used to start containers using the `options` definitions:
@@ -303,6 +367,29 @@ servers:
 
 That'll start the job containers with `docker run ... --cap-add --cpu-count 4 ...`.
 
+### Configuring logging
+
+You can configure the logging driver and options passed to Docker using `logging`:
+
+```yaml
+logging:
+  driver: awslogs
+  options:
+    awslogs-region: "eu-central-2"
+    awslogs-group: "my-app"
+```
+
+If nothing is configured, the default option `max-size=10m` is used for all containers. The default logging driver of Docker is `json-file`.
+
+### Using a different stop wait time
+
+On a new deploy, each old running container is gracefully shut down with a `SIGTERM`, and after a grace period of `10` seconds a `SIGKILL` is sent.
+You can configure this value via the `stop_wait_time` option:
+
+```yaml
+stop_wait_time: 30
+```
+
 ### Using remote builder for native multi-arch
 
 If you're developing on ARM64 (like Apple Silicon), but you want to deploy on AMD64 (x86 64-bit), you can use multi-architecture images. By default, MRSK will setup a local buildx configuration that does this through QEMU emulation. But this can be quite slow, especially on the first build.
@@ -386,9 +473,9 @@ RUN --mount=type=secret,id=GITHUB_TOKEN \
   rm -rf /usr/local/bundle/cache
 ```
 
-### Using command arguments for Traefik
+### Traefik command arguments
 
-You can customize the traefik command line:
+Customize the Traefik command line using `args`:
 
 ```yaml
 traefik:
@@ -397,17 +484,90 @@ traefik:
     accesslog.format: json
 ```
 
-This will start the traefik container with `--accesslog=true accesslog.format=json`.
+This starts the Traefik container with `--accesslog=true --accesslog.format=json` arguments.
 
-### Traefik's host port binding
+### Traefik host port binding
 
-By default Traefik binds to port 80 of the host machine, it can be configured to use an alternative port:
+Traefik binds to port 80 by default. Specify an alternative port using `host_port`:
 
 ```yaml
 traefik:
   host_port: 8080
 ```
 
+### Traefik version, upgrades, and custom images
+
+MRSK runs the traefik:v2.9 image to track Traefik 2.9.x releases.
+
+To pin Traefik to a specific version or an image published to your registry,
+specify `image`:
+
+```yaml
+traefik:
+  image: traefik:v2.10.0-rc1
+```
+
+This is useful for downgrading Traefik if there's an unexpected breaking
+change in a minor version release, upgrading Traefik to test forthcoming
+releases, or running your own Traefik-derived image.
+
+MRSK has not been tested for compatibility with Traefik 3 betas. Please do!
+
+### Traefik container configuration
+
+Pass additional Docker configuration for the Traefik container using `options`:
+
+```yaml
+traefik:
+  options:
+    publish:
+      - 8080:8080
+    volumes:
+      - /tmp/example.json:/tmp/example.json
+    memory: 512m
+```
+
+This starts the Traefik container with `--volume /tmp/example.json:/tmp/example.json --publish 8080:8080 --memory 512m` arguments to `docker run`.
+
+### Traefik container labels
+
+Add labels to Traefik Docker container.
+
+```yaml
+traefik:
+  labels:
+    traefik.enable: true
+    traefik.http.routers.dashboard.rule: Host(`traefik.example.com`) && (PathPrefix(`/api`) || PathPrefix(`/dashboard`))
+    traefik.http.routers.dashboard.service: api@internal
+    traefik.http.routers.dashboard.middlewares: auth
+    traefik.http.middlewares.auth.basicauth.users: test:$2y$05$H2o72tMaO.TwY1wNQUV1K.fhjRgLHRDWohFvUZOJHBEtUXNKrqUKi # test:password
+```
+
+This labels Traefik container with `--label traefik.http.routers.dashboard.middlewares=\"auth\"` and so on.
+
+### Traefik alternate entrypoints
+
+You can configure multiple entrypoints for Traefik like so:
+
+```yaml
+service: myservice
+
+labels:
+  traefik.tcp.routers.other.rule: 'HostSNI(`*`)'
+  traefik.tcp.routers.other.entrypoints: otherentrypoint
+  traefik.tcp.services.other.loadbalancer.server.port: 9000
+  traefik.http.routers.myservice.entrypoints: web
+  traefik.http.services.myservice.loadbalancer.server.port: 8080
+
+traefik:
+  options:
+    publish:
+      - 9000:9000
+  args:
+    entrypoints.web.address: ':80'
+    entrypoints.otherentrypoint.address: ':9000'
+```
+
 ### Configuring build args for new images
 
 Build arguments that aren't secret can also be configured:
@@ -427,7 +587,7 @@ FROM ruby:$RUBY_VERSION-slim as base
 
 ### Using accessories for database, cache, search services
 
-You can manage your accessory services via MRSK as well. The services will build off public images, and will not be automatically updated when you deploy:
+You can manage your accessory services via MRSK as well. Accessories are long-lived services that your app depends on. They are not updated when you deploy.
 
 ```yaml
 accessories:
@@ -442,16 +602,44 @@ accessories:
         - MYSQL_ROOT_PASSWORD
     volumes:
       - /var/lib/mysql:/var/lib/mysql
+    options:
+      cpus: 4
+      memory: "2GB"
   redis:
     image: redis:latest
-    host: 1.1.1.4
+    roles:
+      - web
     port: "36379:6379"
     volumes:
       - /var/lib/redis:/data
+  internal-example:
+    image: registry.digitalocean.com/user/otherservice:latest
+    host: 1.1.1.5
+    port: 44444
+```
+
+The hosts that the accessories will run on can be specified by hosts or roles:
+
+```yaml
+  # Single host
+  mysql:
+    host: 1.1.1.1
+  # Multiple hosts
+  redis:
+    hosts:
+      - 1.1.1.1
+      - 1.1.1.2
+  # By role
+  monitoring:
+    roles:
+      - web
+      - jobs
 ```
 
 Now run `mrsk accessory start mysql` to start the MySQL server on 1.1.1.3. See `mrsk accessory` for all the commands possible.
 
+Accessory images must be public or tagged in your private registry.
+
 ### Using Cron
 
 You can use a specific container to run your Cron jobs:
@@ -489,18 +677,60 @@ That'll post a line like follows to a preconfigured chatbot in Basecamp:
 [My App] [dhh] Rolled back to version d264c4e92470ad1bd18590f04466787262f605de
 ```
 
-### Using custom healthcheck path or port
+`MRSK_*` environment variables are available to the broadcast command for
+fine-grained audit reporting, e.g. for triggering deployment reports or
+firing a JSON webhook. These variables include:
+- `MRSK_RECORDED_AT` - UTC timestamp in ISO 8601 format, e.g. `2023-04-14T17:07:31Z`
+- `MRSK_PERFORMER` - the local user performing the command (from `whoami`)
+- `MRSK_MESSAGE` - the full audit message, e.g. "Deployed app@150b24f"
+- `MRSK_DESTINATION` - optional: destination, e.g. "staging"
+- `MRSK_ROLE` - optional: role targeted, e.g. "web"
 
-MRSK defaults to checking the health of your application again `/up` on port 3000. You can tailor both with the `healthcheck` setting:
+Use `mrsk broadcast` to test and troubleshoot your broadcast command:
+
+```bash
+mrsk broadcast -m "test audit message"
+```
+
+### Healthcheck
+
+MRSK uses Docker healtchecks to check the health of your application during deployment. Traefik uses this same healthcheck status to determine when a container is ready to receive traffic.
+
+The healthcheck defaults to testing the HTTP response to the path `/up` on port 3000, up to 7 times. You can tailor this behaviour with the `healthcheck` setting:
 
 ```yaml
 healthcheck:
   path: /healthz
   port: 4000
+  max_attempts: 7
 ```
 
 This will ensure your application is configured with a traefik label for the healthcheck against `/healthz` and that the pre-deploy healthcheck that MRSK performs is done against the same path on port 4000.
 
+You can also specify a custom healthcheck command, which is useful for non-HTTP services:
+
+```yaml
+healthcheck:
+  cmd: /bin/check_health
+```
+
+The top-level healthcheck configuration applies to all services that use
+Traefik, by default. You can also specialize the configuration at the role
+level:
+
+```yaml
+servers:
+  job:
+    hosts: ...
+    cmd: bin/jobs
+    healthcheck:
+      cmd: bin/check
+```
+
+The healthcheck allows for an optional `max_attempts` setting, which will attempt the healthcheck up to the specified number of times before failing the deploy. This is useful for applications that take a while to start up. The default is 7.
+
+Note: The HTTP health checks assume that the `curl` command is available inside the container. If that's not the case, use the healthcheck's `cmd` option to specify an alternative check that the container supports.
+
 ## Commands
 
 ### Running commands on servers
@@ -616,6 +846,48 @@ Note that by default old containers are pruned after 3 days when you run `mrsk d
 
 If you wish to remove the entire application, including Traefik, containers, images, and registry session, you can run `mrsk remove`. This will leave the servers clean.
 
+## Locking
+
+Commands that are unsafe to run concurrently will take a deploy lock while they run. The lock is the `mrsk_lock` directory on the primary server.
+
+You can check the lock status with:
+
+```
+mrsk lock status
+
+Locked by: AN Other at 2023-03-24 09:49:03 UTC
+Version: 77f45c0686811c68989d6576748475a60bf53fc2
+Message: Automatic deploy lock
+```
+
+You can also manually acquire and release the lock
+
+```
+mrsk lock acquire -m "Doing maintanence"
+```
+
+```
+mrsk lock release
+```
+
+## Rolling deployments
+
+When deploying to large numbers of hosts, you might prefer not to restart your services on every host at the same time.
+
+MRSK's default is to boot new containers on all hosts in parallel. But you can control this by configuring `boot/limit` and `boot/wait` as options:
+
+```yaml
+service: myservice
+
+boot:
+  limit: 10 # Can also specify as a percentage of total hosts, such as "25%"
+  wait: 2
+```
+
+When `limit` is specified, containers will be booted on, at most, `limit` hosts at once. MRSK will pause for `wait` seconds between batches.
+
+These settings only apply when booting containers (using `mrsk deploy`, or `mrsk app boot`). For other commands, MRSK continues to run commands in parallel across all hosts.
+
 ## Stage of development
 
 This is beta software. Commands may still move around. But we're live in production at [37signals](https://37signals.com).

bin/mrsk

@@ -10,7 +10,9 @@ begin
 rescue SSHKit::Runner::ExecuteError => e
   puts "  \e[31mERROR (#{e.cause.class}): #{e.cause.message}\e[0m"
   puts e.cause.backtrace if ENV["VERBOSE"]
+  exit 1
 rescue => e
   puts "  \e[31mERROR (#{e.class}): #{e.message}\e[0m"
   puts e.backtrace if ENV["VERBOSE"]
+  exit 1
 end

gemfiles/rails_edge.gemfile

@@ -0,0 +1,9 @@
+source 'https://rubygems.org'
+git_source(:github) { |repo| "https://github.com/#{repo}.git" }
+
+git "https://github.com/rails/rails.git" do
+  gem "railties"
+  gem "activesupport"
+end
+
+gemspec path: "../"

lib/mrsk.rb

@@ -1,6 +1,7 @@
 module Mrsk
 end
 
+require "active_support"
 require "zeitwerk"
 
 loader = Zeitwerk::Loader.for_gem

lib/mrsk/cli.rb

@@ -1,4 +1,5 @@
 module Mrsk::Cli
+  class LockError < StandardError; end
 end
 
 # SSHKit uses instance eval, so we need a global const for ergonomics

lib/mrsk/cli/accessory.rb

@@ -1,33 +1,38 @@
 class Mrsk::Cli::Accessory < Mrsk::Cli::Base
   desc "boot [NAME]", "Boot new accessory service on host (use NAME=all to boot all accessories)"
   def boot(name)
-    if name == "all"
-      MRSK.accessory_names.each { |accessory_name| boot(accessory_name) }
-    else
-      with_accessory(name) do |accessory|
-        directories(name)
-        upload(name)
+    with_lock do
+      if name == "all"
+        MRSK.accessory_names.each { |accessory_name| boot(accessory_name) }
+      else
+        with_accessory(name) do |accessory|
+          directories(name)
+          upload(name)
 
-        on(accessory.host) do
-          execute *MRSK.auditor.record("Booted #{name} accessory"), verbosity: :debug
-          execute *accessory.run
+          on(accessory.hosts) do
+            execute *MRSK.registry.login
+            execute *MRSK.auditor.record("Booted #{name} accessory"), verbosity: :debug
+            execute *accessory.run
+          end
+
+          audit_broadcast "Booted accessory #{name}" unless options[:skip_broadcast]
         end
-
-        audit_broadcast "Booted accessory #{name}" unless options[:skip_broadcast]
       end
     end
   end
 
   desc "upload [NAME]", "Upload accessory files to host", hide: true
   def upload(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        accessory.files.each do |(local, remote)|
-          accessory.ensure_local_file_present(local)
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          accessory.files.each do |(local, remote)|
+            accessory.ensure_local_file_present(local)
 
-          execute *accessory.make_directory_for(remote)
-          upload! local, remote
-          execute :chmod, "755", remote
+            execute *accessory.make_directory_for(remote)
+            upload! local, remote
+            execute :chmod, "755", remote
+          end
         end
       end
     end
@@ -35,10 +40,12 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
 
   desc "directories [NAME]", "Create accessory directories on host", hide: true
   def directories(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        accessory.directories.keys.each do |host_path|
-          execute *accessory.make_directory(host_path)
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          accessory.directories.keys.each do |host_path|
+            execute *accessory.make_directory(host_path)
+          end
         end
       end
     end
@@ -46,38 +53,46 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
 
   desc "reboot [NAME]", "Reboot existing accessory on host (stop container, remove container, start new container)"
   def reboot(name)
-    with_accessory(name) do |accessory|
-      stop(name)
-      remove_container(name)
-      boot(name)
+    with_lock do
+      with_accessory(name) do |accessory|
+        stop(name)
+        remove_container(name)
+        boot(name)
+      end
     end
   end
 
   desc "start [NAME]", "Start existing accessory container on host"
   def start(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        execute *MRSK.auditor.record("Started #{name} accessory"), verbosity: :debug
-        execute *accessory.start
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *MRSK.auditor.record("Started #{name} accessory"), verbosity: :debug
+          execute *accessory.start
+        end
       end
     end
   end
 
   desc "stop [NAME]", "Stop existing accessory container on host"
   def stop(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        execute *MRSK.auditor.record("Stopped #{name} accessory"), verbosity: :debug
-        execute *accessory.stop, raise_on_non_zero_exit: false
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *MRSK.auditor.record("Stopped #{name} accessory"), verbosity: :debug
+          execute *accessory.stop, raise_on_non_zero_exit: false
+        end
       end
     end
   end
 
   desc "restart [NAME]", "Restart existing accessory container on host"
   def restart(name)
-    with_accessory(name) do
-      stop(name)
-      start(name)
+    with_lock do
+      with_accessory(name) do
+        stop(name)
+        start(name)
+      end
     end
   end
 
@@ -87,7 +102,7 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
       MRSK.accessory_names.each { |accessory_name| details(accessory_name) }
     else
       with_accessory(name) do |accessory|
-        on(accessory.host) { puts capture_with_info(*accessory.info) }
+        on(accessory.hosts) { puts capture_with_info(*accessory.info) }
       end
     end
   end
@@ -108,14 +123,14 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
 
       when options[:reuse]
         say "Launching command from existing container...", :magenta
-        on(accessory.host) do
+        on(accessory.hosts) do
           execute *MRSK.auditor.record("Executed cmd '#{cmd}' on #{name} accessory"), verbosity: :debug
           capture_with_info(*accessory.execute_in_existing_container(cmd))
         end
 
       else
         say "Launching command from new container...", :magenta
-        on(accessory.host) do
+        on(accessory.hosts) do
           execute *MRSK.auditor.record("Executed cmd '#{cmd}' on #{name} accessory"), verbosity: :debug
           capture_with_info(*accessory.execute_in_new_container(cmd))
         end
@@ -134,7 +149,7 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
 
       if options[:follow]
         run_locally do
-          info "Following logs on #{accessory.host}..."
+          info "Following logs on #{accessory.hosts}..."
           info accessory.follow_logs(grep: grep)
           exec accessory.follow_logs(grep: grep)
         end
@@ -142,25 +157,27 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
         since = options[:since]
         lines = options[:lines].presence || ((since || grep) ? nil : 100) # Default to 100 lines if since or grep isn't set
 
-        on(accessory.host) do
+        on(accessory.hosts) do
           puts capture_with_info(*accessory.logs(since: since, lines: lines, grep: grep))
         end
       end
     end
   end
 
-  desc "remove [NAME]", "Remove accessory container and image from host (use NAME=all to remove all accessories)"
+  desc "remove [NAME]", "Remove accessory container, image and data directory from host (use NAME=all to remove all accessories)"
   option :confirmed, aliases: "-y", type: :boolean, default: false, desc: "Proceed without confirmation question"
   def remove(name)
-    if name == "all"
-      MRSK.accessory_names.each { |accessory_name| remove(accessory_name) }
-    else
-      if options[:confirmed] || ask("This will remove all containers and images for #{name}. Are you sure?", limited_to: %w( y N ), default: "N") == "y"
-        with_accessory(name) do
-          stop(name)
-          remove_container(name)
-          remove_image(name)
-          remove_service_directory(name)
+    with_lock do
+      if name == "all"
+        MRSK.accessory_names.each { |accessory_name| remove(accessory_name) }
+      else
+        if options[:confirmed] || ask("This will remove all containers, images and data directories for #{name}. Are you sure?", limited_to: %w( y N ), default: "N") == "y"
+          with_accessory(name) do
+            stop(name)
+            remove_container(name)
+            remove_image(name)
+            remove_service_directory(name)
+          end
         end
       end
     end
@@ -168,29 +185,35 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
 
   desc "remove_container [NAME]", "Remove accessory container from host", hide: true
   def remove_container(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        execute *MRSK.auditor.record("Remove #{name} accessory container"), verbosity: :debug
-        execute *accessory.remove_container
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *MRSK.auditor.record("Remove #{name} accessory container"), verbosity: :debug
+          execute *accessory.remove_container
+        end
       end
     end
   end
 
   desc "remove_image [NAME]", "Remove accessory image from host", hide: true
   def remove_image(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        execute *MRSK.auditor.record("Removed #{name} accessory image"), verbosity: :debug
-        execute *accessory.remove_image
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *MRSK.auditor.record("Removed #{name} accessory image"), verbosity: :debug
+          execute *accessory.remove_image
+        end
       end
     end
   end
 
   desc "remove_service_directory [NAME]", "Remove accessory directory used for uploaded files and data directories from host", hide: true
   def remove_service_directory(name)
-    with_accessory(name) do |accessory|
-      on(accessory.host) do
-        execute *accessory.remove_service_directory
+    with_lock do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *accessory.remove_service_directory
+        end
       end
     end
   end

lib/mrsk/cli/app.rb

@@ -1,33 +1,38 @@
 class Mrsk::Cli::App < Mrsk::Cli::Base
   desc "boot", "Boot app on servers (or reboot app if already running)"
   def boot
-    say "Get most recent version available as an image...", :magenta unless options[:version]
-    using_version(options[:version] || most_recent_version_available) do |version|
-      say "Start container with version #{version} using a #{MRSK.config.readiness_delay}s readiness delay (or reboot if already running)...", :magenta
+    with_lock do
+      say "Get most recent version available as an image...", :magenta unless options[:version]
+      using_version(version_or_latest) do |version|
+        say "Start container with version #{version} using a #{MRSK.config.readiness_delay}s readiness delay (or reboot if already running)...", :magenta
 
-      cli = self
-      
-      MRSK.config.roles.each do |role|
-        on(role.hosts) do |host|
-          execute *MRSK.auditor.record("Booted app version #{version}"), verbosity: :debug
+        on(MRSK.hosts) do
+          execute *MRSK.auditor.record("Tagging #{MRSK.config.absolute_image} as the latest image"), verbosity: :debug
+          execute *MRSK.app.tag_current_as_latest
+        end
 
-          begin
-            old_version = capture_with_info(*MRSK.app.current_running_version).strip
-            execute *MRSK.app.run(role: role.name)
-            sleep MRSK.config.readiness_delay
-            execute *MRSK.app.stop(version: old_version), raise_on_non_zero_exit: false if old_version.present?
+        on(MRSK.hosts, **MRSK.boot_strategy) do |host|
+          roles = MRSK.roles_on(host)
 
-          rescue SSHKit::Command::Failed => e
-            if e.message =~ /already in use/
-              error "Rebooting container with same version #{version} already deployed on #{host} (may cause gap in zero-downtime promise!)"
-              execute *MRSK.auditor.record("Rebooted app version #{version}"), verbosity: :debug
+          roles.each do |role|
+            app = MRSK.app(role: role)
+            auditor = MRSK.auditor(role: role)
 
-              execute *MRSK.app.stop(version: version)
-              execute *MRSK.app.remove_container(version: version)
-              execute *MRSK.app.run(role: role.name)
-            else
-              raise
+            execute *auditor.record("Booted app version #{version}"), verbosity: :debug
+
+            if capture_with_info(*app.container_id_for_version(version), raise_on_non_zero_exit: false).present?
+              tmp_version = "#{version}_#{SecureRandom.hex(8)}"
+              info "Renaming container #{version} to #{tmp_version} as already deployed on #{host}"
+              execute *auditor.record("Renaming container #{version} to #{tmp_version}"), verbosity: :debug
+              execute *app.rename_container(version: version, new_version: tmp_version)
             end
+
+            old_version = capture_with_info(*app.current_running_version, raise_on_non_zero_exit: false).strip
+            execute *app.run
+
+            Mrsk::Utils::HealthcheckPoller.wait_for_healthy(pause_after_ready: true) { capture_with_info(*app.status(version: version)) }
+
+            execute *app.stop(version: old_version), raise_on_non_zero_exit: false if old_version.present?
           end
         end
       end
@@ -36,24 +41,42 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
 
   desc "start", "Start existing app container on servers"
   def start
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Started app version #{MRSK.version}"), verbosity: :debug
-      execute *MRSK.app.start, raise_on_non_zero_exit: false
+    with_lock do
+      on(MRSK.hosts) do |host|
+        roles = MRSK.roles_on(host)
+
+        roles.each do |role|
+          execute *MRSK.auditor.record("Started app version #{MRSK.config.version}"), verbosity: :debug
+          execute *MRSK.app(role: role).start, raise_on_non_zero_exit: false
+        end
+      end
     end
   end
 
   desc "stop", "Stop app container on servers"
   def stop
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Stopped app"), verbosity: :debug
-      execute *MRSK.app.stop, raise_on_non_zero_exit: false
+    with_lock do
+      on(MRSK.hosts) do |host|
+        roles = MRSK.roles_on(host)
+
+        roles.each do |role|
+          execute *MRSK.auditor.record("Stopped app", role: role), verbosity: :debug
+          execute *MRSK.app(role: role).stop, raise_on_non_zero_exit: false
+        end
+      end
     end
   end
 
   # FIXME: Drop in favor of just containers?
   desc "details", "Show details about app containers"
   def details
-    on(MRSK.hosts) { |host| puts_by_host host, capture_with_info(*MRSK.app.info) }
+    on(MRSK.hosts) do |host|
+      roles = MRSK.roles_on(host)
+
+      roles.each do |role|
+        puts_by_host host, capture_with_info(*MRSK.app(role: role).info)
+      end
+    end
   end
 
   desc "exec [CMD]", "Execute a custom command on servers (use --help to show options)"
@@ -65,12 +88,12 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
       say "Get current version of running container...", :magenta unless options[:version]
       using_version(options[:version] || current_running_version) do |version|
         say "Launching interactive command with version #{version} via SSH from existing container on #{MRSK.primary_host}...", :magenta
-        run_locally { exec MRSK.app.execute_in_existing_container_over_ssh(cmd, host: MRSK.primary_host) }
+        run_locally { exec MRSK.app(role: "web").execute_in_existing_container_over_ssh(cmd, host: MRSK.primary_host) }
       end
 
     when options[:interactive]
       say "Get most recent version available as an image...", :magenta unless options[:version]
-      using_version(options[:version] || most_recent_version_available) do |version|
+      using_version(version_or_latest) do |version|
         say "Launching interactive command with version #{version} via SSH from new container on #{MRSK.primary_host}...", :magenta
         run_locally { exec MRSK.app.execute_in_new_container_over_ssh(cmd, host: MRSK.primary_host) }
       end
@@ -81,14 +104,18 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
         say "Launching command with version #{version} from existing container...", :magenta
 
         on(MRSK.hosts) do |host|
-          execute *MRSK.auditor.record("Executed cmd '#{cmd}' on app version #{version}"), verbosity: :debug
-          puts_by_host host, capture_with_info(*MRSK.app.execute_in_existing_container(cmd))
+          roles = MRSK.roles_on(host)
+
+          roles.each do |role|
+            execute *MRSK.auditor.record("Executed cmd '#{cmd}' on app version #{version}", role: role), verbosity: :debug
+            puts_by_host host, capture_with_info(*MRSK.app(role: role).execute_in_existing_container(cmd))
+          end
         end
       end
 
     else
       say "Get most recent version available as an image...", :magenta unless options[:version]
-      using_version(options[:version] || most_recent_version_available) do |version|
+      using_version(version_or_latest) do |version|
         say "Launching command with version #{version} from new container...", :magenta
         on(MRSK.hosts) do |host|
           execute *MRSK.auditor.record("Executed cmd '#{cmd}' on app version #{version}"), verbosity: :debug
@@ -103,6 +130,31 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
     on(MRSK.hosts) { |host| puts_by_host host, capture_with_info(*MRSK.app.list_containers) }
   end
 
+  desc "stale_containers", "Detect app stale containers"
+  option :stop, aliases: "-s", type: :boolean, default: false, desc: "Stop the stale containers found"
+  def stale_containers
+    with_lock do
+      stop = options[:stop]
+
+      cli = self
+
+      on(MRSK.hosts) do |host|
+        roles = MRSK.roles_on(host)
+
+        roles.each do |role|
+          cli.send(:stale_versions, host: host, role: role).each do |version|
+            if stop
+              puts_by_host host, "Stopping stale container for role #{role} with version #{version}"
+              execute *MRSK.app(role: role).stop(version: version), raise_on_non_zero_exit: false
+            else
+              puts_by_host host,  "Detected stale container for role #{role} with version #{version} (use `mrsk app stale_containers --stop` to stop)"
+            end
+          end
+        end
+      end
+    end
+  end
+
   desc "images", "Show app images on servers"
   def images
     on(MRSK.hosts) { |host| puts_by_host host, capture_with_info(*MRSK.app.list_images) }
@@ -121,18 +173,26 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
     if options[:follow]
       run_locally do
         info "Following logs on #{MRSK.primary_host}..."
-        info MRSK.app.follow_logs(host: MRSK.primary_host, grep: grep)
-        exec MRSK.app.follow_logs(host: MRSK.primary_host, grep: grep)
+
+        MRSK.specific_roles ||= ["web"]
+        role = MRSK.roles_on(MRSK.primary_host).first
+
+        info MRSK.app(role: role).follow_logs(host: MRSK.primary_host, grep: grep)
+        exec MRSK.app(role: role).follow_logs(host: MRSK.primary_host, grep: grep)
       end
     else
       since = options[:since]
       lines = options[:lines].presence || ((since || grep) ? nil : 100) # Default to 100 lines if since or grep isn't set
 
       on(MRSK.hosts) do |host|
-        begin
-          puts_by_host host, capture_with_info(*MRSK.app.logs(since: since, lines: lines, grep: grep))
-        rescue SSHKit::Command::Failed
-          puts_by_host host, "Nothing found"
+        roles = MRSK.roles_on(host)
+
+        roles.each do |role|
+          begin
+            puts_by_host host, capture_with_info(*MRSK.app(role: role).logs(since: since, lines: lines, grep: grep))
+          rescue SSHKit::Command::Failed
+            puts_by_host host, "Nothing found"
+          end
         end
       end
     end
@@ -140,32 +200,48 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
 
   desc "remove", "Remove app containers and images from servers"
   def remove
-    stop
-    remove_containers
-    remove_images
+    with_lock do
+      stop
+      remove_containers
+      remove_images
+    end
   end
 
   desc "remove_container [VERSION]", "Remove app container with given version from servers", hide: true
   def remove_container(version)
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Removed app container with version #{version}"), verbosity: :debug
-      execute *MRSK.app.remove_container(version: version)
+    with_lock do
+      on(MRSK.hosts) do |host|
+        roles = MRSK.roles_on(host)
+
+        roles.each do |role|
+          execute *MRSK.auditor.record("Removed app container with version #{version}", role: role), verbosity: :debug
+          execute *MRSK.app(role: role).remove_container(version: version)
+        end
+      end
     end
   end
 
   desc "remove_containers", "Remove all app containers from servers", hide: true
   def remove_containers
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Removed all app containers"), verbosity: :debug
-      execute *MRSK.app.remove_containers
+    with_lock do
+      on(MRSK.hosts) do |host|
+        roles = MRSK.roles_on(host)
+
+        roles.each do |role|
+          execute *MRSK.auditor.record("Removed all app containers", role: role), verbosity: :debug
+          execute *MRSK.app(role: role).remove_containers
+        end
+      end
     end
   end
 
   desc "remove_images", "Remove all app images from servers", hide: true
   def remove_images
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Removed all app images"), verbosity: :debug
-      execute *MRSK.app.remove_images
+    with_lock do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Removed all app images"), verbosity: :debug
+        execute *MRSK.app.remove_images
+      end
     end
   end
 
@@ -189,20 +265,24 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
       end
     end
 
-    def most_recent_version_available(host: MRSK.primary_host)
-      version = nil
-      on(host) { version = capture_with_info(*MRSK.app.most_recent_version_from_available_images).strip }
-      
-      if version == "<none>"
-        raise "Most recent image available was not tagged with a version (returned <none>)"
-      else
-        version.presence
-      end
-    end
-
     def current_running_version(host: MRSK.primary_host)
       version = nil
       on(host) { version = capture_with_info(*MRSK.app.current_running_version).strip }
       version.presence
     end
+
+    def stale_versions(host:, role:)
+      versions = nil
+      on(host) do
+        versions = \
+          capture_with_info(*MRSK.app(role: role).list_versions, raise_on_non_zero_exit: false)
+          .split("\n")
+          .drop(1)
+      end
+      versions
+    end
+
+    def version_or_latest
+      options[:version] || "latest"
+    end
 end

lib/mrsk/cli/base.rb

@@ -25,7 +25,7 @@ module Mrsk::Cli
     def initialize(*)
       super
       load_envs
-      initialize_commander(options)
+      initialize_commander(options_with_subcommand_class_options)
     end
 
     private
@@ -37,16 +37,12 @@ module Mrsk::Cli
         end
       end
 
+      def options_with_subcommand_class_options
+        options.merge(@_initializer.last[:class_options] || {})
+      end
+
       def initialize_commander(options)
         MRSK.tap do |commander|
-          commander.config_file = Pathname.new(File.expand_path(options[:config_file]))
-          commander.destination = options[:destination]
-          commander.version     = options[:version]
-
-          commander.specific_hosts    = options[:hosts]&.split(",")
-          commander.specific_roles    = options[:roles]&.split(",")
-          commander.specific_primary! if options[:primary]
-
           if options[:verbose]
             ENV["VERBOSE"] = "1" # For backtraces via cli/start
             commander.verbosity = :debug
@@ -55,6 +51,15 @@ module Mrsk::Cli
           if options[:quiet]
             commander.verbosity = :error
           end
+
+          commander.configure \
+            config_file: Pathname.new(File.expand_path(options[:config_file])),
+            destination: options[:destination],
+            version: options[:version]
+
+          commander.specific_hosts    = options[:hosts]&.split(",")
+          commander.specific_roles    = options[:roles]&.split(",")
+          commander.specific_primary! if options[:primary]
         end
       end
 
@@ -70,5 +75,58 @@ module Mrsk::Cli
       def audit_broadcast(line)
         run_locally { execute *MRSK.auditor.broadcast(line), verbosity: :debug }
       end
+
+      def with_lock
+        if MRSK.holding_lock?
+          yield
+        else
+          acquire_lock
+
+          begin
+            yield
+          rescue
+            if MRSK.hold_lock_on_error?
+              error "  \e[31mDeploy lock was not released\e[0m"
+            else
+              release_lock
+            end
+
+            raise
+          end
+
+          release_lock
+        end
+      end
+
+      def acquire_lock
+        say "Acquiring the deploy lock"
+        on(MRSK.primary_host) { execute *MRSK.lock.acquire("Automatic deploy lock", MRSK.config.version) }
+
+        MRSK.holding_lock = true
+      rescue SSHKit::Runner::ExecuteError => e
+        if e.message =~ /cannot create directory/
+          on(MRSK.primary_host) { execute *MRSK.lock.status }
+          raise LockError, "Deploy lock found"
+        else
+          raise e
+        end
+      end
+
+      def release_lock
+        say "Releasing the deploy lock"
+        on(MRSK.primary_host) { execute *MRSK.lock.release }
+
+        MRSK.holding_lock = false
+      end
+
+      def hold_lock_on_error
+        if MRSK.hold_lock_on_error?
+          yield
+        else
+          MRSK.hold_lock_on_error = true
+          yield
+          MRSK.hold_lock_on_error = false
+        end
+      end
   end
 end

lib/mrsk/cli/build.rb

@@ -1,26 +1,34 @@
 class Mrsk::Cli::Build < Mrsk::Cli::Base
+  class BuildError < StandardError; end
+
   desc "deliver", "Build app and push app image to registry then pull image on servers"
   def deliver
-    push
-    pull
+    with_lock do
+      push
+      pull
+    end
   end
 
   desc "push", "Build and push app image to registry"
   def push
-    cli = self
+    with_lock do
+      cli = self
 
-    run_locally do
-      begin
-        MRSK.with_verbosity(:debug) { execute *MRSK.builder.push }
-      rescue SSHKit::Command::Failed => e
-        if e.message =~ /(no builder)|(no such file or directory)/
-          error "Missing compatible builder, so creating a new one first"
-
-          if cli.create
+      run_locally do
+        begin
+          if cli.verify_local_dependencies
             MRSK.with_verbosity(:debug) { execute *MRSK.builder.push }
           end
-        else
-          raise
+        rescue SSHKit::Command::Failed => e
+          if e.message =~ /(no builder)|(no such file or directory)/
+            error "Missing compatible builder, so creating a new one first"
+
+            if cli.create
+              MRSK.with_verbosity(:debug) { execute *MRSK.builder.push }
+            end
+          else
+            raise
+          end
         end
       end
     end
@@ -28,25 +36,29 @@ class Mrsk::Cli::Build < Mrsk::Cli::Base
 
   desc "pull", "Pull app image from registry onto servers"
   def pull
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Pulled image with version #{MRSK.version}"), verbosity: :debug
-      execute *MRSK.builder.clean, raise_on_non_zero_exit: false
-      execute *MRSK.builder.pull
+    with_lock do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Pulled image with version #{MRSK.config.version}"), verbosity: :debug
+        execute *MRSK.builder.clean, raise_on_non_zero_exit: false
+        execute *MRSK.builder.pull
+      end
     end
   end
 
   desc "create", "Create a build setup"
   def create
-    run_locally do
-      begin
-        debug "Using builder: #{MRSK.builder.name}"
-        execute *MRSK.builder.create
-      rescue SSHKit::Command::Failed => e
-        if e.message =~ /stderr=(.*)/
-          error "Couldn't create remote builder: #{$1}"
-          false
-        else
-          raise
+    with_lock do
+      run_locally do
+        begin
+          debug "Using builder: #{MRSK.builder.name}"
+          execute *MRSK.builder.create
+        rescue SSHKit::Command::Failed => e
+          if e.message =~ /stderr=(.*)/
+            error "Couldn't create remote builder: #{$1}"
+            false
+          else
+            raise
+          end
         end
       end
     end
@@ -54,9 +66,11 @@ class Mrsk::Cli::Build < Mrsk::Cli::Base
 
   desc "remove", "Remove build setup"
   def remove
-    run_locally do
-      debug "Using builder: #{MRSK.builder.name}"
-      execute *MRSK.builder.remove
+    with_lock do
+      run_locally do
+        debug "Using builder: #{MRSK.builder.name}"
+        execute *MRSK.builder.remove
+      end
     end
   end
 
@@ -67,4 +81,22 @@ class Mrsk::Cli::Build < Mrsk::Cli::Base
       puts capture(*MRSK.builder.info)
     end
   end
+
+
+  desc "", "" # Really a private method, but needed to be invoked from #push
+  def verify_local_dependencies
+    run_locally do
+      begin
+        execute *MRSK.builder.ensure_local_dependencies_installed
+      rescue SSHKit::Command::Failed => e
+        build_error = e.message =~ /command not found/ ?
+          "Docker is not installed locally" :
+          "Docker buildx plugin is not installed locally"
+
+        raise BuildError, build_error
+      end
+    end
+
+    true
+  end
 end

lib/mrsk/cli/healthcheck.rb

@@ -1,8 +1,4 @@
 class Mrsk::Cli::Healthcheck < Mrsk::Cli::Base
-  MAX_ATTEMPTS = 7
-
-  class HealthcheckError < StandardError; end
-
   default_command :perform
 
   desc "perform", "Health check current app version"
@@ -10,37 +6,11 @@ class Mrsk::Cli::Healthcheck < Mrsk::Cli::Base
     on(MRSK.primary_host) do
       begin
         execute *MRSK.healthcheck.run
-
-        target = "Health check against #{MRSK.config.healthcheck["path"]}"
-        attempt = 1
-
-        begin
-          status = capture_with_info(*MRSK.healthcheck.curl)
-
-          if status == "200"
-            info "#{target} succeeded with 200 OK!"
-          else
-            raise HealthcheckError, "#{target} failed with status #{status}"
-          end
-        rescue SSHKit::Command::Failed
-          if attempt <= MAX_ATTEMPTS
-            info "#{target} failed to respond, retrying in #{attempt}s..."
-            sleep attempt
-            attempt += 1
-
-            retry
-          else
-            raise
-          end
-        end
-      rescue SSHKit::Command::Failed, HealthcheckError => e
+        Mrsk::Utils::HealthcheckPoller.wait_for_healthy { capture_with_info(*MRSK.healthcheck.status) }
+      rescue Mrsk::Utils::HealthcheckPoller::HealthcheckError => e
         error capture_with_info(*MRSK.healthcheck.logs)
-
-        if e.message =~ /curl/
-          raise SSHKit::Command::Failed, "#{target} failed to return 200 OK!"
-        else
-          raise
-        end
+        error capture_with_pretty_json(*MRSK.healthcheck.container_health_log)
+        raise
       ensure
         execute *MRSK.healthcheck.stop, raise_on_non_zero_exit: false
         execute *MRSK.healthcheck.remove, raise_on_non_zero_exit: false

lib/mrsk/cli/lock.rb

@@ -0,0 +1,37 @@
+class Mrsk::Cli::Lock < Mrsk::Cli::Base
+  desc "status", "Report lock status"
+  def status
+    handle_missing_lock do
+      on(MRSK.primary_host) { puts capture_with_info(*MRSK.lock.status) }
+    end
+  end
+
+  desc "acquire", "Acquire the deploy lock"
+  option :message, aliases: "-m", type: :string, desc: "A lock mesasge", required: true
+  def acquire
+    message = options[:message]
+    handle_missing_lock do
+      on(MRSK.primary_host) { execute *MRSK.lock.acquire(message, MRSK.config.version) }
+      say "Acquired the deploy lock"
+    end
+  end
+
+  desc "release", "Release the deploy lock"
+  def release
+    handle_missing_lock do
+      on(MRSK.primary_host) { execute *MRSK.lock.release }
+      say "Released the deploy lock"
+    end
+  end
+
+  private
+    def handle_missing_lock
+      yield
+    rescue SSHKit::Runner::ExecuteError => e
+      if e.message =~ /No such file or directory/
+        say "There is no deploy lock"
+      else
+        raise
+      end
+    end
+end

lib/mrsk/cli/main.rb

@@ -1,77 +1,123 @@
 class Mrsk::Cli::Main < Mrsk::Cli::Base
   desc "setup", "Setup all accessories and deploy app to servers"
   def setup
-    print_runtime do
-      invoke "mrsk:cli:server:bootstrap"
-      invoke "mrsk:cli:accessory:boot", [ "all" ]
-      deploy
+    with_lock do
+      print_runtime do
+        invoke "mrsk:cli:server:bootstrap"
+        invoke "mrsk:cli:accessory:boot", [ "all" ]
+        deploy
+      end
     end
   end
 
   desc "deploy", "Deploy app to servers"
+  option :skip_push, aliases: "-P", type: :boolean, default: false, desc: "Skip image build and push"
   def deploy
-    runtime = print_runtime do
-      say "Ensure curl and Docker are installed...", :magenta
-      invoke "mrsk:cli:server:bootstrap"
+    with_lock do
+      invoke_options = deploy_options
 
-      say "Log into image registry...", :magenta
-      invoke "mrsk:cli:registry:login"
+      runtime = print_runtime do
+        say "Log into image registry...", :magenta
+        invoke "mrsk:cli:registry:login", [], invoke_options
 
-      say "Build and push app image...", :magenta
-      invoke "mrsk:cli:build:deliver"
+        if options[:skip_push]
+          say "Pull app image...", :magenta
+          invoke "mrsk:cli:build:pull", [], invoke_options
+        else
+          say "Build and push app image...", :magenta
+          invoke "mrsk:cli:build:deliver", [], invoke_options
+        end
 
-      say "Ensure Traefik is running...", :magenta
-      invoke "mrsk:cli:traefik:boot"
+        say "Ensure Traefik is running...", :magenta
+        invoke "mrsk:cli:traefik:boot", [], invoke_options
 
-      say "Ensure app can pass healthcheck...", :magenta
-      invoke "mrsk:cli:healthcheck:perform"
+        say "Ensure app can pass healthcheck...", :magenta
+        invoke "mrsk:cli:healthcheck:perform", [], invoke_options
 
-      invoke "mrsk:cli:app:boot"
+        say "Detect stale containers...", :magenta
+        invoke "mrsk:cli:app:stale_containers", [], invoke_options
 
-      say "Prune old containers and images...", :magenta
-      invoke "mrsk:cli:prune:all"
+        hold_lock_on_error do
+          invoke "mrsk:cli:app:boot", [], invoke_options
+        end
+
+        say "Prune old containers and images...", :magenta
+        invoke "mrsk:cli:prune:all", [], invoke_options
+      end
+
+      audit_broadcast "Deployed #{service_version} in #{runtime.round} seconds" unless options[:skip_broadcast]
     end
-
-    audit_broadcast "Deployed app in #{runtime.to_i} seconds" unless options[:skip_broadcast]
   end
 
   desc "redeploy", "Deploy app to servers without bootstrapping servers, starting Traefik, pruning, and registry login"
+  option :skip_push, aliases: "-P", type: :boolean, default: false, desc: "Skip image build and push"
   def redeploy
-    runtime = print_runtime do
-      say "Build and push app image...", :magenta
-      invoke "mrsk:cli:build:deliver"
+    with_lock do
+      invoke_options = deploy_options
 
-      say "Ensure app can pass healthcheck...", :magenta
-      invoke "mrsk:cli:healthcheck:perform"
+      runtime = print_runtime do
+        if options[:skip_push]
+          say "Pull app image...", :magenta
+          invoke "mrsk:cli:build:pull", [], invoke_options
+        else
+          say "Build and push app image...", :magenta
+          invoke "mrsk:cli:build:deliver", [], invoke_options
+        end
 
-      invoke "mrsk:cli:app:boot"
+        say "Ensure app can pass healthcheck...", :magenta
+        invoke "mrsk:cli:healthcheck:perform", [], invoke_options
+
+        say "Detect stale containers...", :magenta
+        invoke "mrsk:cli:app:stale_containers", [], invoke_options
+
+        hold_lock_on_error do
+          invoke "mrsk:cli:app:boot", [], invoke_options
+        end
+      end
+
+      audit_broadcast "Redeployed #{service_version} in #{runtime.round} seconds" unless options[:skip_broadcast]
     end
-
-    audit_broadcast "Redeployed app in #{runtime.to_i} seconds" unless options[:skip_broadcast]
   end
 
   desc "rollback [VERSION]", "Rollback app to VERSION"
   def rollback(version)
-    MRSK.version = version
+    with_lock do
+      invoke_options = deploy_options
 
-    if container_name_available?(MRSK.config.service_with_version)
-      say "Start version #{version}, then wait #{MRSK.config.readiness_delay}s for app to boot before stopping the old version...", :magenta
+      hold_lock_on_error do
+        MRSK.config.version = version
+        old_version = nil
 
-      cli = self
+        if container_available?(version)
+          say "Start version #{version}, then wait #{MRSK.config.readiness_delay}s for app to boot before stopping the old version...", :magenta
 
-      on(MRSK.hosts) do |host|
-        old_version = capture_with_info(*MRSK.app.current_running_version).strip.presence
+          on(MRSK.hosts) do
+            execute *MRSK.auditor.record("Tagging #{MRSK.config.absolute_image} as the latest image"), verbosity: :debug
+            execute *MRSK.app.tag_current_as_latest
+          end
 
-        execute *MRSK.app.start
+          on(MRSK.hosts) do |host|
+            roles = MRSK.roles_on(host)
 
-        sleep MRSK.config.readiness_delay
+            roles.each do |role|
+              app = MRSK.app(role: role)
+              old_version = capture_with_info(*app.current_running_version).strip.presence
 
-        execute *MRSK.app.stop(version: old_version), raise_on_non_zero_exit: false
+              execute *app.start
+
+              if old_version
+                sleep MRSK.config.readiness_delay
+
+                execute *app.stop(version: old_version), raise_on_non_zero_exit: false
+              end
+            end
+          end
+
+          audit_broadcast "Rolled back #{service_version(Mrsk::Utils.abbreviate_version(old_version))} to #{service_version}" unless options[:skip_broadcast]
+        else
+          say "The app version '#{version}' is not available as a container (use 'mrsk app containers' for available versions)", :red
+        end
       end
-
-      audit_broadcast "Rolled back app to version #{version}" unless options[:skip_broadcast]
-    else
-      say "The app version '#{version}' is not available as a container (use 'mrsk app containers' for available versions)", :red
     end
   end
 
@@ -92,7 +138,7 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
   desc "config", "Show combined config (including secrets!)"
   def config
     run_locally do
-      puts MRSK.config.to_h.to_yaml
+      puts Mrsk::Utils.redacted(MRSK.config.to_h).to_yaml
     end
   end
 
@@ -119,8 +165,10 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
         puts "Binstub already exists in bin/mrsk (remove first to create a new one)"
       else
         puts "Adding MRSK to Gemfile and bundle..."
-        `bundle add mrsk`
-        `bundle binstubs mrsk`
+        run_locally do
+          execute :bundle, :add, :mrsk
+          execute :bundle, :binstubs, :mrsk
+        end
         puts "Created binstub file in bin/mrsk"
       end
     end
@@ -142,14 +190,23 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
   desc "remove", "Remove Traefik, app, accessories, and registry session from servers"
   option :confirmed, aliases: "-y", type: :boolean, default: false, desc: "Proceed without confirmation question"
   def remove
-    if options[:confirmed] || ask("This will remove all containers and images. Are you sure?", limited_to: %w( y N ), default: "N") == "y"
-      invoke "mrsk:cli:traefik:remove", [], options.without(:confirmed)
-      invoke "mrsk:cli:app:remove", [], options.without(:confirmed)
-      invoke "mrsk:cli:accessory:remove", [ "all" ], options
-      invoke "mrsk:cli:registry:logout", [], options.without(:confirmed)
+    with_lock do
+      if options[:confirmed] || ask("This will remove all containers and images. Are you sure?", limited_to: %w( y N ), default: "N") == "y"
+        invoke "mrsk:cli:traefik:remove", [], options.without(:confirmed)
+        invoke "mrsk:cli:app:remove", [], options.without(:confirmed)
+        invoke "mrsk:cli:accessory:remove", [ "all" ], options
+        invoke "mrsk:cli:registry:logout", [], options.without(:confirmed)
+      end
     end
   end
 
+  desc "broadcast", "Broadcast an audit message"
+  option :message, aliases: "-m", type: :string, desc: "Audit mesasge", required: true
+  def broadcast
+    say "Broadcast: #{options[:message]}", :magenta
+    audit_broadcast options[:message]
+  end
+
   desc "version", "Show MRSK version"
   def version
     puts Mrsk::VERSION
@@ -179,10 +236,35 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
   desc "traefik", "Manage Traefik load balancer"
   subcommand "traefik", Mrsk::Cli::Traefik
 
+  desc "lock", "Manage the deploy lock"
+  subcommand "lock", Mrsk::Cli::Lock
+
   private
-    def container_name_available?(container_name, host: MRSK.primary_host)
-      container_names = nil
-      on(host) { container_names = capture_with_info(*MRSK.app.list_container_names).split("\n") }
-      Array(container_names).include?(container_name)
+    def container_available?(version)
+      begin
+        on(MRSK.hosts) do
+          MRSK.roles_on(host).each do |role|
+            container_id = capture_with_info(*MRSK.app(role: role).container_id_for_version(version))
+            raise "Container not found" unless container_id.present?
+          end
+        end
+      rescue SSHKit::Runner::ExecuteError => e
+        if e.message =~ /Container not found/
+          say "Error looking for container version #{version}: #{e.message}"
+          return false
+        else
+          raise
+        end
+      end
+
+      true
+    end
+
+    def deploy_options
+      { "version" => MRSK.config.version }.merge(options.without("skip_push"))
+    end
+
+    def service_version(version = MRSK.config.abbreviated_version)
+      [ MRSK.config.service, version ].compact.join("@")
     end
 end

lib/mrsk/cli/prune.rb

@@ -1,23 +1,29 @@
 class Mrsk::Cli::Prune < Mrsk::Cli::Base
   desc "all", "Prune unused images and stopped containers"
   def all
-    containers
-    images
-  end
-
-  desc "images", "Prune unused images older than 7 days"
-  def images
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Pruned images"), verbosity: :debug
-      execute *MRSK.prune.images
+    with_lock do
+      containers
+      images
     end
   end
 
-  desc "containers", "Prune stopped containers older than 3 days"
+  desc "images", "Prune dangling images"
+  def images
+    with_lock do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Pruned images"), verbosity: :debug
+        execute *MRSK.prune.images
+      end
+    end
+  end
+
+  desc "containers", "Prune all stopped containers, except the last 5"
   def containers
-    on(MRSK.hosts) do
-      execute *MRSK.auditor.record("Pruned containers"), verbosity: :debug
-      execute *MRSK.prune.containers
+    with_lock do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Pruned containers"), verbosity: :debug
+        execute *MRSK.prune.containers
+      end
     end
   end
 end

lib/mrsk/cli/server.rb

@@ -1,15 +1,21 @@
 class Mrsk::Cli::Server < Mrsk::Cli::Base
-  desc "bootstrap", "Ensure curl and Docker are installed on servers"
+  desc "bootstrap", "Set up Docker to run MRSK apps"
   def bootstrap
-    on(MRSK.hosts + MRSK.accessory_hosts) do
-      dependencies_to_install = Array.new.tap do |dependencies|
-        dependencies << "curl" unless execute "which curl", raise_on_non_zero_exit: false
-        dependencies << "docker.io" unless execute "which docker", raise_on_non_zero_exit: false
-      end
+    missing = []
 
-      if dependencies_to_install.any?
-        execute "apt-get update -y && apt-get install #{dependencies_to_install.join(" ")} -y"
+    on(MRSK.hosts | MRSK.accessory_hosts) do |host|
+      unless execute(*MRSK.docker.installed?, raise_on_non_zero_exit: false)
+        if execute(*MRSK.docker.superuser?, raise_on_non_zero_exit: false)
+          info "Missing Docker on #{host}. Installing…"
+          execute *MRSK.docker.install
+        else
+          missing << host
+        end
       end
     end
+
+    if missing.any?
+      raise "Docker is not installed on #{missing.join(", ")} and can't be automatically installed without having root access and the `curl` command available. Install Docker manually: https://docs.docker.com/engine/install/"
+    end
   end
 end

lib/mrsk/cli/templates/deploy.yml

@@ -13,6 +13,8 @@ registry:
   # Specify the registry server, if you're not using Docker Hub
   # server: registry.digitalocean.com / ghcr.io / ...
   username: my-user
+
+  # Always use an access token rather than real password when possible.
   password:
     - MRSK_REGISTRY_PASSWORD
 

lib/mrsk/cli/traefik.rb

@@ -1,36 +1,49 @@
 class Mrsk::Cli::Traefik < Mrsk::Cli::Base
   desc "boot", "Boot Traefik on servers"
   def boot
-    on(MRSK.traefik_hosts) { execute *MRSK.traefik.run, raise_on_non_zero_exit: false }
+    with_lock do
+      on(MRSK.traefik_hosts) do
+        execute *MRSK.registry.login
+        execute *MRSK.traefik.run, raise_on_non_zero_exit: false
+      end
+    end
   end
 
   desc "reboot", "Reboot Traefik on servers (stop container, remove container, start new container)"
   def reboot
-    stop
-    remove_container
-    boot
+    with_lock do
+      stop
+      remove_container
+      boot
+    end
   end
 
   desc "start", "Start existing Traefik container on servers"
   def start
-    on(MRSK.traefik_hosts) do
-      execute *MRSK.auditor.record("Started traefik"), verbosity: :debug
-      execute *MRSK.traefik.start, raise_on_non_zero_exit: false
+    with_lock do
+      on(MRSK.traefik_hosts) do
+        execute *MRSK.auditor.record("Started traefik"), verbosity: :debug
+        execute *MRSK.traefik.start, raise_on_non_zero_exit: false
+      end
     end
   end
 
   desc "stop", "Stop existing Traefik container on servers"
   def stop
-    on(MRSK.traefik_hosts) do
-      execute *MRSK.auditor.record("Stopped traefik"), verbosity: :debug
-      execute *MRSK.traefik.stop, raise_on_non_zero_exit: false
+    with_lock do
+      on(MRSK.traefik_hosts) do
+        execute *MRSK.auditor.record("Stopped traefik"), verbosity: :debug
+        execute *MRSK.traefik.stop, raise_on_non_zero_exit: false
+      end
     end
   end
 
   desc "restart", "Restart existing Traefik container on servers"
   def restart
-    stop
-    start
+    with_lock do
+      stop
+      start
+    end
   end
 
   desc "details", "Show details about Traefik container from servers"
@@ -64,24 +77,30 @@ class Mrsk::Cli::Traefik < Mrsk::Cli::Base
 
   desc "remove", "Remove Traefik container and image from servers"
   def remove
-    stop
-    remove_container
-    remove_image
+    with_lock do
+      stop
+      remove_container
+      remove_image
+    end
   end
 
   desc "remove_container", "Remove Traefik container from servers", hide: true
   def remove_container
-    on(MRSK.traefik_hosts) do
-      execute *MRSK.auditor.record("Removed traefik container"), verbosity: :debug
-      execute *MRSK.traefik.remove_container
+    with_lock do
+      on(MRSK.traefik_hosts) do
+        execute *MRSK.auditor.record("Removed traefik container"), verbosity: :debug
+        execute *MRSK.traefik.remove_container
+      end
     end
   end
 
-  desc "remove_container", "Remove Traefik image from servers", hide: true
+  desc "remove_image", "Remove Traefik image from servers", hide: true
   def remove_image
-    on(MRSK.traefik_hosts) do
-      execute *MRSK.auditor.record("Removed traefik image"), verbosity: :debug
-      execute *MRSK.traefik.remove_image
+    with_lock do
+      on(MRSK.traefik_hosts) do
+        execute *MRSK.auditor.record("Removed traefik image"), verbosity: :debug
+        execute *MRSK.traefik.remove_image
+      end
     end
   end
 end

lib/mrsk/commander.rb

@@ -1,35 +1,66 @@
 require "active_support/core_ext/enumerable"
+require "active_support/core_ext/module/delegation"
 
 class Mrsk::Commander
-  attr_accessor :config_file, :destination, :verbosity, :version
+  attr_accessor :verbosity, :holding_lock, :hold_lock_on_error
 
-  def initialize(config_file: nil, destination: nil, verbosity: :info)
-    @config_file, @destination, @verbosity = config_file, destination, verbosity
+  def initialize
+    self.verbosity = :info
+    self.holding_lock = false
+    self.hold_lock_on_error = false
   end
 
   def config
-    @config ||= \
-      Mrsk::Configuration
-        .create_from(config_file, destination: destination, version: cascading_version)
-        .tap { |config| configure_sshkit_with(config) }
+    @config ||= Mrsk::Configuration.create_from(**@config_kwargs).tap do |config|
+      @config_kwargs = nil
+      configure_sshkit_with(config)
+    end
   end
 
-  attr_accessor :specific_hosts
+  def configure(**kwargs)
+    @config, @config_kwargs = nil, kwargs
+  end
+
+  attr_reader :specific_roles, :specific_hosts
 
   def specific_primary!
     self.specific_hosts = [ config.primary_web_host ]
   end
 
   def specific_roles=(role_names)
-    self.specific_hosts = config.roles.select { |r| role_names.include?(r.name) }.flat_map(&:hosts) if role_names.present?
+    @specific_roles = config.roles.select { |r| role_names.include?(r.name) } if role_names.present?
+  end
+
+  def specific_hosts=(hosts)
+    @specific_hosts = config.all_hosts & hosts if hosts.present?
   end
 
   def primary_host
-    specific_hosts&.first || config.primary_web_host
+    specific_hosts&.first || specific_roles&.first&.primary_host || config.primary_web_host
+  end
+
+  def roles
+    (specific_roles || config.roles).select do |role|
+      ((specific_hosts || config.all_hosts) & role.hosts).any?
+    end
   end
 
   def hosts
-    specific_hosts || config.all_hosts
+    (specific_hosts || config.all_hosts).select do |host|
+      (specific_roles || config.roles).flat_map(&:hosts).include?(host)
+    end
+  end
+
+  def boot_strategy
+    if config.boot.limit.present?
+      { in: :groups, limit: config.boot.limit, wait: config.boot.wait }
+    else
+      {}
+    end
+  end
+
+  def roles_on(host)
+    roles.select { |role| role.hosts.include?(host.to_s) }.map(&:name)
   end
 
   def traefik_hosts
@@ -37,7 +68,7 @@ class Mrsk::Commander
   end
 
   def accessory_hosts
-    specific_hosts || config.accessories.collect(&:host)
+    specific_hosts || config.accessories.flat_map(&:hosts)
   end
 
   def accessory_names
@@ -45,22 +76,26 @@ class Mrsk::Commander
   end
 
 
-  def app
-    @app ||= Mrsk::Commands::App.new(config)
+  def app(role: nil)
+    Mrsk::Commands::App.new(config, role: role)
   end
 
   def accessory(name)
     Mrsk::Commands::Accessory.new(config, name: name)
   end
 
-  def auditor
-    @auditor ||= Mrsk::Commands::Auditor.new(config)
+  def auditor(**details)
+    Mrsk::Commands::Auditor.new(config, **details)
   end
 
   def builder
     @builder ||= Mrsk::Commands::Builder.new(config)
   end
 
+  def docker
+    @docker ||= Mrsk::Commands::Docker.new(config)
+  end
+
   def healthcheck
     @healthcheck ||= Mrsk::Commands::Healthcheck.new(config)
   end
@@ -77,6 +112,9 @@ class Mrsk::Commander
     @traefik ||= Mrsk::Commands::Traefik.new(config)
   end
 
+  def lock
+    @lock ||= Mrsk::Commands::Lock.new(config)
+  end
 
   def with_verbosity(level)
     old_level = self.verbosity
@@ -90,26 +128,15 @@ class Mrsk::Commander
     SSHKit.config.output_verbosity = old_level
   end
 
-  # Test-induced damage!
-  def reset
-    @config = @config_file = @destination = @version = nil
-    @app = @builder = @traefik = @registry = @prune = @auditor = nil
-    @verbosity = :info
+  def holding_lock?
+    self.holding_lock
+  end
+
+  def hold_lock_on_error?
+    self.hold_lock_on_error
   end
 
   private
-    def cascading_version
-      version.presence || ENV["VERSION"] || current_commit_hash
-    end
-
-    def current_commit_hash
-      if system("git rev-parse")
-        `git rev-parse HEAD`.strip
-      else
-        raise "Can't use commit hash as version, no git repository found in #{Dir.pwd}"
-      end
-    end
-
     # Lazy setup of SSHKit
     def configure_sshkit_with(config)
       SSHKit::Backend::Netssh.configure { |ssh| ssh.ssh_options = config.ssh_options }

lib/mrsk/commands/accessory.rb

@@ -1,6 +1,7 @@
 class Mrsk::Commands::Accessory < Mrsk::Commands::Base
   attr_reader :accessory_config
-  delegate :service_name, :image, :host, :port, :files, :directories, :env_args, :volume_args, :label_args, to: :accessory_config
+  delegate :service_name, :image, :hosts, :port, :files, :directories, :cmd,
+           :publish_args, :env_args, :volume_args, :label_args, :option_args, to: :accessory_config
 
   def initialize(config, name:)
     super(config)
@@ -12,12 +13,14 @@ class Mrsk::Commands::Accessory < Mrsk::Commands::Base
       "--name", service_name,
       "--detach",
       "--restart", "unless-stopped",
-      "--log-opt", "max-size=#{MAX_LOG_SIZE}",
-      "--publish", port,
+      *config.logging_args,
+      *publish_args,
       *env_args,
       *volume_args,
       *label_args,
-      image
+      *option_args,
+      image,
+      cmd
   end
 
   def start
@@ -73,7 +76,7 @@ class Mrsk::Commands::Accessory < Mrsk::Commands::Base
   end
 
   def run_over_ssh(command)
-    super command, host: host
+    super command, host: hosts.first
   end
 
 
@@ -100,7 +103,7 @@ class Mrsk::Commands::Accessory < Mrsk::Commands::Base
   end
 
   def remove_image
-    docker :image, :prune, "--all", "--force", *service_filter
+    docker :image, :rm, "--force", image
   end
 
   private

lib/mrsk/commands/app.rb

@@ -1,13 +1,22 @@
 class Mrsk::Commands::App < Mrsk::Commands::Base
-  def run(role: :web)
-    role = config.role(role)
+  attr_reader :role
+
+  def initialize(config, role: nil)
+    super(config)
+    @role = role
+  end
+
+  def run
+    role = config.role(self.role)
 
     docker :run,
       "--detach",
       "--restart unless-stopped",
-      "--log-opt", "max-size=#{MAX_LOG_SIZE}",
-      "--name", service_with_version,
+      "--name", container_name,
+      "-e", "MRSK_CONTAINER_NAME=\"#{container_name}\"",
       *role.env_args,
+      *role.health_check_args,
+      *config.logging_args,
       *config.volume_args,
       *role.label_args,
       *role.option_args,
@@ -16,23 +25,27 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   end
 
   def start
-    docker :start, service_with_version
+    docker :start, container_name
+  end
+
+  def status(version:)
+    pipe container_id_for_version(version), xargs(docker(:inspect, "--format", DOCKER_HEALTH_STATUS_FORMAT))
   end
 
   def stop(version: nil)
     pipe \
-      version ? container_id_for_version(version) : current_container_id,
-      xargs(docker(:stop))
+      version ? container_id_for_version(version) : current_running_container_id,
+      xargs(config.stop_wait_time ? docker(:stop, "-t", config.stop_wait_time) : docker(:stop))
   end
 
   def info
-    docker :ps, *service_filter
+    docker :ps, *filter_args
   end
 
 
   def logs(since: nil, lines: nil, grep: nil)
     pipe \
-      current_container_id,
+      current_running_container_id,
       "xargs docker logs#{" --since #{since}" if since}#{" --tail #{lines}" if lines} 2>&1",
       ("grep '#{grep}'" if grep)
   end
@@ -40,7 +53,7 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   def follow_logs(host:, grep: nil)
     run_over_ssh \
       pipe(
-        current_container_id,
+        current_running_container_id,
         "xargs docker logs --timestamps --tail 10 --follow 2>&1",
         (%(grep "#{grep}") if grep)
       ),
@@ -51,7 +64,7 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   def execute_in_existing_container(*command, interactive: false)
     docker :exec,
       ("-it" if interactive),
-      config.service_with_version,
+      container_name,
       *command
   end
 
@@ -74,33 +87,27 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   end
 
 
-  def current_container_id
-    docker :ps, "--quiet", *service_filter
+  def current_running_container_id
+    docker :ps, "--quiet", *filter_args(status: :running), "--latest"
+  end
+
+  def container_id_for_version(version)
+    container_id_for(container_name: container_name(version))
   end
 
   def current_running_version
-    # FIXME: Find more graceful way to extract the version from "app-version" than using sed and tail!
-    pipe \
-      docker(:ps, "--filter", "label=service=#{config.service}", "--format", '"{{.Names}}"'),
-      %(sed 's/-/\\n/g'),
-      "tail -n 1"
+    list_versions("--latest", status: :running)
   end
 
-  def most_recent_version_from_available_images
+  def list_versions(*docker_args, status: nil)
     pipe \
-      docker(:image, :ls, "--format", '"{{.Tag}}"', config.repository),
-      "head -n 1"
+      docker(:ps, *filter_args(status: status), *docker_args, "--format", '"{{.Names}}"'),
+      %(grep -oE "\\-[^-]+$"), # Extract SHA from "service-role-dest-SHA"
+      %(cut -c 2-)
   end
 
-  def all_versions_from_available_containers
-    pipe \
-      docker(:image, :ls, "--format", '"{{.Tag}}"', config.repository),
-      "head -n 1"
-  end
-
-
   def list_containers
-    docker :container, :ls, "--all", *service_filter
+    docker :container, :ls, "--all", *filter_args
   end
 
   def list_container_names
@@ -109,12 +116,16 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
 
   def remove_container(version:)
     pipe \
-      container_id_for(container_name: service_with_version(version)),
+      container_id_for(container_name: container_name(version)),
       xargs(docker(:container, :rm))
   end
 
+  def rename_container(version:, new_version:)
+    docker :rename, container_name(version), container_name(new_version)
+  end
+
   def remove_containers
-    docker :container, :prune, "--force", *service_filter
+    docker :container, :prune, "--force", *filter_args
   end
 
   def list_images
@@ -122,24 +133,28 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   end
 
   def remove_images
-    docker :image, :prune, "--all", "--force", *service_filter
+    docker :image, :prune, "--all", "--force", *filter_args
+  end
+
+  def tag_current_as_latest
+    docker :tag, config.absolute_image, config.latest_image
   end
 
 
   private
-    def service_with_version(version = nil)
-      if version
-        "#{config.service}-#{version}"
-      else
-        config.service_with_version
+    def container_name(version = nil)
+      [ config.service, role, config.destination, version || config.version ].compact.join("-")
+    end
+
+    def filter_args(status: nil)
+      argumentize "--filter", filters(status: status)
+    end
+
+    def filters(status: nil)
+      [ "label=service=#{config.service}" ].tap do |filters|
+        filters << "label=destination=#{config.destination}" if config.destination
+        filters << "label=role=#{role}" if role
+        filters << "status=#{status}" if status
       end
     end
-
-    def container_id_for_version(version)
-      container_id_for(container_name: service_with_version(version))    
-    end
-
-    def service_filter
-      [ "--filter", "label=service=#{config.service}" ]
-    end
 end

lib/mrsk/commands/auditor.rb

@@ -1,17 +1,24 @@
-require "active_support/core_ext/time/conversions"
+require "time"
 
 class Mrsk::Commands::Auditor < Mrsk::Commands::Base
+  attr_reader :details
+
+  def initialize(config, **details)
+    super(config)
+    @details = default_details.merge(details)
+  end
+
   # Runs remotely
-  def record(line)
+  def record(line, **details)
     append \
-      [ :echo, tagged_record_line(line) ],
+      [ :echo, *audit_tags(**details), line ],
       audit_log_file
   end
 
   # Runs locally
-  def broadcast(line)
+  def broadcast(line, **details)
     if broadcast_cmd = config.audit_broadcast_cmd
-      [ broadcast_cmd, tagged_broadcast_line(line) ]
+      [ broadcast_cmd, *broadcast_args(line, **details), env: env_for(event: line, **details) ]
     end
   end
 
@@ -21,22 +28,32 @@ class Mrsk::Commands::Auditor < Mrsk::Commands::Base
 
   private
     def audit_log_file
-      "mrsk-#{config.service}-audit.log"
+      [ "mrsk", config.service, config.destination, "audit.log" ].compact.join("-")
     end
 
-    def tagged_record_line(line)
-      "'#{recorded_at_tag} #{performer_tag} #{line}'"
+    def default_details
+      { recorded_at: Time.now.utc.iso8601,
+        performer: `whoami`.chomp,
+        destination: config.destination }
     end
 
-    def tagged_broadcast_line(line)
-      "'#{performer_tag} #{line}'"
+    def audit_tags(**details)
+      tags_for **self.details.merge(details)
     end
 
-    def performer_tag
-      "[#{`whoami`.strip}]"
+    def broadcast_args(line, **details)
+      "'#{broadcast_tags(**details).join(" ")} #{line}'"
     end
 
-    def recorded_at_tag
-      "[#{Time.now.to_fs(:db)}]"
+    def broadcast_tags(**details)
+      tags_for **self.details.merge(details).except(:recorded_at)
+    end
+
+    def tags_for(**details)
+      details.compact.values.map { |value| "[#{value}]" }
+    end
+
+    def env_for(**details)
+      self.details.merge(details).compact.transform_keys { |detail| "MRSK_#{detail.upcase}" }
     end
 end

lib/mrsk/commands/base.rb

@@ -1,8 +1,9 @@
 module Mrsk::Commands
   class Base
-    delegate :redact, to: Mrsk::Utils
+    delegate :sensitive, :argumentize, to: Mrsk::Utils
 
-    MAX_LOG_SIZE = "10m"
+    DOCKER_HEALTH_STATUS_FORMAT = "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'"
+    DOCKER_HEALTH_LOG_FORMAT    = "'{{json .State.Health}}'"
 
     attr_accessor :config
 
@@ -18,7 +19,7 @@ module Mrsk::Commands
     end
 
     def container_id_for(container_name:)
-      docker :container, :ls, "--all", "--filter", "name=#{container_name}", "--quiet"
+      docker :container, :ls, "--all", "--filter", "name=^#{container_name}$", "--quiet"
     end
 
     private
@@ -41,6 +42,10 @@ module Mrsk::Commands
         combine *commands, by: ">>"
       end
 
+      def write(*commands)
+        combine *commands, by: ">"
+      end
+
       def xargs(command)
         [ :xargs, command ].flatten
       end

lib/mrsk/commands/builder.rb

@@ -2,7 +2,7 @@ class Mrsk::Commands::Builder < Mrsk::Commands::Base
   delegate :create, :remove, :push, :clean, :pull, :info, to: :target
 
   def name
-    target.class.to_s.remove("Mrsk::Commands::Builder::").underscore
+    target.class.to_s.remove("Mrsk::Commands::Builder::").underscore.inquiry
   end
 
   def target
@@ -33,4 +33,24 @@ class Mrsk::Commands::Builder < Mrsk::Commands::Base
   def multiarch_remote
     @multiarch_remote ||= Mrsk::Commands::Builder::Multiarch::Remote.new(config)
   end
+
+
+  def ensure_local_dependencies_installed
+    if name.native?
+      ensure_local_docker_installed
+    else
+      combine \
+        ensure_local_docker_installed,
+        ensure_local_buildx_installed
+    end
+  end
+
+  private
+    def ensure_local_docker_installed
+      docker "--version"
+    end
+
+    def ensure_local_buildx_installed
+      docker :buildx, "version"
+    end
 end

lib/mrsk/commands/builder/base.rb

@@ -1,4 +1,7 @@
+
 class Mrsk::Commands::Builder::Base < Mrsk::Commands::Base
+  class BuilderError < StandardError; end
+
   delegate :argumentize, to: Mrsk::Utils
 
   def clean
@@ -17,6 +20,7 @@ class Mrsk::Commands::Builder::Base < Mrsk::Commands::Base
     context
   end
 
+
   private
     def build_tags
       [ "-t", config.absolute_image, "-t", config.latest_image ]
@@ -27,7 +31,7 @@ class Mrsk::Commands::Builder::Base < Mrsk::Commands::Base
     end
 
     def build_args
-      argumentize "--build-arg", args, redacted: true
+      argumentize "--build-arg", args, sensitive: true
     end
 
     def build_secrets
@@ -35,7 +39,11 @@ class Mrsk::Commands::Builder::Base < Mrsk::Commands::Base
     end
 
     def build_dockerfile
-      argumentize "--file", dockerfile
+      if Pathname.new(File.expand_path(dockerfile)).exist?
+        argumentize "--file", dockerfile
+      else
+        raise BuilderError, "Missing #{dockerfile}"
+      end
     end
 
     def args

lib/mrsk/commands/builder/native.rb

@@ -10,7 +10,8 @@ class Mrsk::Commands::Builder::Native < Mrsk::Commands::Builder::Base
   def push
     combine \
       docker(:build, *build_options, build_context),
-      docker(:push, config.absolute_image)
+      docker(:push, config.absolute_image),
+      docker(:push, config.latest_image)
   end
 
   def info

lib/mrsk/commands/docker.rb

@@ -0,0 +1,21 @@
+class Mrsk::Commands::Docker < Mrsk::Commands::Base
+  # Install Docker using the https://github.com/docker/docker-install convenience script.
+  def install
+    pipe [ :curl, "-fsSL", "https://get.docker.com" ], :sh
+  end
+
+  # Checks the Docker client version. Fails if Docker is not installed.
+  def installed?
+    docker "-v"
+  end
+
+  # Checks the Docker server version. Fails if Docker is not running.
+  def running?
+    docker :version
+  end
+
+  # Do we have superuser access to install Docker and start system services?
+  def superuser?
+    [ '[ "${EUID:-$(id -u)}" -eq 0 ]' ]
+  end
+end

lib/mrsk/commands/healthcheck.rb

@@ -9,14 +9,21 @@ class Mrsk::Commands::Healthcheck < Mrsk::Commands::Base
       "--name", container_name_with_version,
       "--publish", "#{EXPOSED_PORT}:#{config.healthcheck["port"]}",
       "--label", "service=#{container_name}",
+      "-e", "MRSK_CONTAINER_NAME=\"#{container_name}\"",
       *web.env_args,
+      *web.health_check_args,
       *config.volume_args,
+      *web.option_args,
       config.absolute_image,
       web.cmd
   end
 
-  def curl
-    [ :curl, "--silent", "--output", "/dev/null", "--write-out", "'%{http_code}'", "--max-time", "2", health_url ]
+  def status
+    pipe container_id, xargs(docker(:inspect, "--format", DOCKER_HEALTH_STATUS_FORMAT))
+  end
+
+  def container_health_log
+    pipe container_id, xargs(docker(:inspect, "--format", DOCKER_HEALTH_LOG_FORMAT))
   end
 
   def logs
@@ -33,15 +40,15 @@ class Mrsk::Commands::Healthcheck < Mrsk::Commands::Base
 
   private
     def container_name
-      "healthcheck-#{config.service}"
+      [ "healthcheck", config.service, config.destination ].compact.join("-")
     end
 
     def container_name_with_version
-      "healthcheck-#{config.service_with_version}"
+      "#{container_name}-#{config.version}"
     end
 
     def container_id
-      container_id_for(container_name: container_name)
+      container_id_for(container_name: container_name_with_version)
     end
 
     def health_url

lib/mrsk/commands/lock.rb

@@ -0,0 +1,63 @@
+require "active_support/duration"
+require "time"
+
+class Mrsk::Commands::Lock < Mrsk::Commands::Base
+  def acquire(message, version)
+    combine \
+      [:mkdir, lock_dir],
+      write_lock_details(message, version)
+  end
+
+  def release
+    combine \
+      [:rm, lock_details_file],
+      [:rm, "-r", lock_dir]
+  end
+
+  def status
+    combine \
+      stat_lock_dir,
+      read_lock_details
+  end
+
+  private
+    def write_lock_details(message, version)
+      write \
+        [:echo, "\"#{Base64.encode64(lock_details(message, version))}\""],
+        lock_details_file
+    end
+
+    def read_lock_details
+      pipe \
+        [:cat, lock_details_file],
+        [:base64, "-d"]
+    end
+
+    def stat_lock_dir
+      write \
+        [:stat, lock_dir],
+        "/dev/null"
+    end
+
+    def lock_dir
+      :mrsk_lock
+    end
+
+    def lock_details_file
+      [lock_dir, :details].join("/")
+    end
+
+    def lock_details(message, version)
+      <<~DETAILS.strip
+        Locked by: #{locked_by} at #{Time.now.utc.iso8601}
+        Version: #{version}
+        Message: #{message}
+      DETAILS
+    end
+
+    def locked_by
+      `git config user.name`.strip
+    rescue Errno::ENOENT
+      "Unknown"
+    end
+end

lib/mrsk/commands/prune.rb

@@ -2,11 +2,19 @@ require "active_support/duration"
 require "active_support/core_ext/numeric/time"
 
 class Mrsk::Commands::Prune < Mrsk::Commands::Base
-  def images(until_hours: 7.days.in_hours.to_i)
-    docker :image, :prune, "--all", "--force", "--filter", "label=service=#{config.service}", "--filter", "until=#{until_hours}h"
+  def images
+    docker :image, :prune, "--force", "--filter", "label=service=#{config.service}", "--filter", "dangling=true"
   end
 
-  def containers(until_hours: 3.days.in_hours.to_i)
-    docker :container, :prune, "--force", "--filter", "label=service=#{config.service}", "--filter", "until=#{until_hours}h"
+  def containers(keep_last: 5)
+    pipe \
+      docker(:ps, "-q", "-a", "--filter", "label=service=#{config.service}", *stopped_containers_filters),
+      "tail -n +#{keep_last + 1}",
+      "while read container_id; do docker rm $container_id; done"
   end
+
+  private
+    def stopped_containers_filters
+      [ "created", "exited", "dead" ].flat_map { |status| ["--filter", "status=#{status}"] }
+    end
 end

lib/mrsk/commands/registry.rb

@@ -2,7 +2,7 @@ class Mrsk::Commands::Registry < Mrsk::Commands::Base
   delegate :registry, to: :config
 
   def login
-    docker :login, registry["server"], "-u", redact(lookup("username")), "-p", redact(lookup("password"))
+    docker :login, registry["server"], "-u", sensitive(lookup("username")), "-p", sensitive(lookup("password"))
   end
 
   def logout

lib/mrsk/commands/traefik.rb

@@ -1,16 +1,19 @@
 class Mrsk::Commands::Traefik < Mrsk::Commands::Base
-  delegate :optionize, to: Mrsk::Utils
+  delegate :argumentize, :optionize, to: Mrsk::Utils
 
+  DEFAULT_IMAGE = "traefik:v2.9"
   CONTAINER_PORT = 80
 
   def run
     docker :run, "--name traefik",
       "--detach",
       "--restart", "unless-stopped",
-      "--log-opt", "max-size=#{MAX_LOG_SIZE}",
       "--publish", port,
       "--volume", "/var/run/docker.sock:/var/run/docker.sock",
-      "traefik",
+      *config.logging_args,
+      *label_args,
+      *docker_options_args,
+      image,
       "--providers.docker",
       "--log.level=DEBUG",
       *cmd_option_args
@@ -25,7 +28,7 @@ class Mrsk::Commands::Traefik < Mrsk::Commands::Base
   end
 
   def info
-    docker :ps, "--filter", "name=traefik"
+    docker :ps, "--filter", "name=^traefik$"
   end
 
   def logs(since: nil, lines: nil, grep: nil)
@@ -49,20 +52,36 @@ class Mrsk::Commands::Traefik < Mrsk::Commands::Base
     docker :image, :prune, "--all", "--force", "--filter", "label=org.opencontainers.image.title=Traefik"
   end
 
-  def port    
+  def port
     "#{host_port}:#{CONTAINER_PORT}"
   end
 
   private
+    def label_args
+      argumentize "--label", labels
+    end
+
+    def labels
+      config.traefik["labels"] || []
+    end
+
+    def image
+      config.traefik.fetch("image") { DEFAULT_IMAGE }
+    end
+
+    def docker_options_args
+      optionize(config.traefik["options"] || {})
+    end
+
     def cmd_option_args
-      if args = config.raw_config.dig(:traefik, "args")
-        optionize args
+      if args = config.traefik["args"]
+        optionize args, with: "="
       else
         []
       end
     end
 
     def host_port
-      config.raw_config.dig(:traefik, "host_port") || CONTAINER_PORT
+      config.traefik["host_port"] || CONTAINER_PORT
     end
 end

lib/mrsk/configuration.rb

@@ -6,23 +6,24 @@ require "erb"
 require "net/ssh/proxy/jump"
 
 class Mrsk::Configuration
-  delegate :service, :image, :servers, :env, :labels, :registry, :builder, to: :raw_config, allow_nil: true
-  delegate :argumentize, :argumentize_env_with_secrets, to: Mrsk::Utils
+  delegate :service, :image, :servers, :env, :labels, :registry, :builder, :stop_wait_time, to: :raw_config, allow_nil: true
+  delegate :argumentize, :argumentize_env_with_secrets, :optionize, to: Mrsk::Utils
 
-  attr_accessor :version
+  attr_accessor :destination
   attr_accessor :raw_config
 
   class << self
-    def create_from(base_config_file, destination: nil, version: "missing")
-      new(load_config_file(base_config_file).tap do |config|
-        if destination
-          config.deep_merge! \
-            load_config_file destination_config_file(base_config_file, destination)
-        end
-      end, version: version)
+    def create_from(config_file:, destination: nil, version: nil)
+      raw_config = load_config_files(config_file, *destination_config_file(config_file, destination))
+
+      new raw_config, destination: destination, version: version
     end
 
     private
+      def load_config_files(*files)
+        files.inject({}) { |config, file| config.deep_merge! load_config_file(file) }
+      end
+
       def load_config_file(file)
         if file.exist?
           YAML.load(ERB.new(IO.read(file)).result).symbolize_keys
@@ -32,18 +33,31 @@ class Mrsk::Configuration
       end
 
       def destination_config_file(base_config_file, destination)
-        dir, basename = base_config_file.split
-        dir.join basename.to_s.remove(".yml") + ".#{destination}.yml"
+        base_config_file.sub_ext(".#{destination}.yml") if destination
       end
   end
 
-  def initialize(raw_config, version: "missing", validate: true)
+  def initialize(raw_config, destination: nil, version: nil, validate: true)
     @raw_config = ActiveSupport::InheritableOptions.new(raw_config)
-    @version = version
+    @destination = destination
+    @declared_version = version
     valid? if validate
   end
 
 
+  def version=(version)
+    @declared_version = version
+  end
+
+  def version
+    @declared_version.presence || ENV["VERSION"] || current_commit_hash
+  end
+
+  def abbreviated_version
+    Mrsk::Utils.abbreviate_version(version)
+  end
+
+
   def roles
     @roles ||= role_names.collect { |role_name| Role.new(role_name, config: self) }
   end
@@ -62,15 +76,19 @@ class Mrsk::Configuration
 
 
   def all_hosts
-    roles.flat_map(&:hosts)
+    roles.flat_map(&:hosts).uniq
   end
 
   def primary_web_host
-    role(:web).hosts.first
+    role(:web).primary_host
   end
 
   def traefik_hosts
-    roles.select(&:running_traefik?).flat_map(&:hosts)
+    roles.select(&:running_traefik?).flat_map(&:hosts).uniq
+  end
+
+  def boot
+    Mrsk::Configuration::Boot.new(config: self)
   end
 
 
@@ -107,6 +125,15 @@ class Mrsk::Configuration
     end
   end
 
+  def logging_args
+    if raw_config.logging.present?
+      optionize({ "log-driver" => raw_config.logging["driver"] }.compact) +
+        argumentize("--log-opt", raw_config.logging["options"])
+    else
+      argumentize("--log-opt", { "max-size" => "10m" })
+    end
+  end
+
 
   def ssh_user
     if raw_config.ssh.present?
@@ -120,6 +147,8 @@ class Mrsk::Configuration
     if raw_config.ssh.present? && raw_config.ssh["proxy"]
       Net::SSH::Proxy::Jump.new \
         raw_config.ssh["proxy"].include?("@") ? raw_config.ssh["proxy"] : "root@#{raw_config.ssh["proxy"]}"
+    elsif raw_config.ssh.present? && raw_config.ssh["proxy_command"]
+      Net::SSH::Proxy::Command.new(raw_config.ssh["proxy_command"])
     end
   end
 
@@ -133,7 +162,7 @@ class Mrsk::Configuration
   end
 
   def healthcheck
-    { "path" => "/up", "port" => 3000 }.merge(raw_config.healthcheck || {})
+    { "path" => "/up", "port" => 3000, "max_attempts" => 7 }.merge(raw_config.healthcheck || {})
   end
 
   def readiness_delay
@@ -159,10 +188,14 @@ class Mrsk::Configuration
       ssh_options: ssh_options,
       builder: raw_config.builder,
       accessories: raw_config.accessories,
+      logging: logging_args,
       healthcheck: healthcheck
     }.compact
   end
 
+  def traefik
+    raw_config.traefik || {}
+  end
 
   private
     # Will raise ArgumentError if any required config keys are missing
@@ -179,6 +212,12 @@ class Mrsk::Configuration
         raise ArgumentError, "You must specify a password for the registry in config/deploy.yml (or set the ENV variable if that's used)"
       end
 
+      roles.each do |role|
+        if role.hosts.empty?
+          raise ArgumentError, "No servers specified for the #{role.name} role"
+        end
+      end
+
       true
     end
 
@@ -193,4 +232,13 @@ class Mrsk::Configuration
     def role_names
       raw_config.servers.is_a?(Array) ? [ "web" ] : raw_config.servers.keys.sort
     end
+
+    def current_commit_hash
+      @current_commit_hash ||=
+        if system("git rev-parse")
+          `git rev-parse HEAD`.strip
+        else
+          raise "Can't use commit hash as version, no git repository found in #{Dir.pwd}"
+        end
+    end
 end

lib/mrsk/configuration/accessory.rb

@@ -1,5 +1,5 @@
 class Mrsk::Configuration::Accessory
-  delegate :argumentize, :argumentize_env_with_secrets, to: Mrsk::Utils
+  delegate :argumentize, :argumentize_env_with_secrets, :optionize, to: Mrsk::Utils
 
   attr_accessor :name, :specifics
 
@@ -15,18 +15,24 @@ class Mrsk::Configuration::Accessory
     specifics["image"]
   end
 
-  def host
-    specifics["host"] || raise(ArgumentError, "Missing host for accessory")
+  def hosts
+    if (specifics.keys & ["host", "hosts", "roles"]).size != 1
+      raise ArgumentError, "Specify one of `host`, `hosts` or `roles` for accessory `#{name}`"
+    end
+
+    hosts_from_host || hosts_from_hosts || hosts_from_roles
   end
 
   def port
-    if specifics["port"].to_s.include?(":")
-      specifics["port"]
-    else
-      "#{specifics["port"]}:#{specifics["port"]}"
+    if port = specifics["port"]&.to_s
+      port.include?(":") ? port : "#{port}:#{port}"
     end
   end
 
+  def publish_args
+    argumentize "--publish", port if port
+  end
+
   def labels
     default_labels.merge(specifics["labels"] || {})
   end
@@ -65,6 +71,18 @@ class Mrsk::Configuration::Accessory
     argumentize "--volume", volumes
   end
 
+  def option_args
+    if args = specifics["options"]
+      optionize args
+    else
+      []
+    end
+  end
+
+  def cmd
+    specifics["cmd"]
+  end
+
   private
     attr_accessor :config
 
@@ -120,4 +138,32 @@ class Mrsk::Configuration::Accessory
     def service_data_directory
       "$PWD/#{service_name}"
     end
+
+    def hosts_from_host
+      if specifics.key?("host")
+        host = specifics["host"]
+        if host
+          [host]
+        else
+          raise ArgumentError, "Missing host for accessory `#{name}`"
+        end
+      end
+    end
+
+    def hosts_from_hosts
+      if specifics.key?("hosts")
+        hosts = specifics["hosts"]
+        if hosts.is_a?(Array)
+          hosts
+        else
+          raise ArgumentError, "Hosts should be an Array for accessory `#{name}`"
+        end
+      end
+    end
+
+    def hosts_from_roles
+      if specifics.key?("roles")
+        specifics["roles"].flat_map { |role| config.role(role).hosts }
+      end
+    end
 end

lib/mrsk/configuration/boot.rb

@@ -0,0 +1,20 @@
+class Mrsk::Configuration::Boot
+  def initialize(config:)
+    @options = config.raw_config.boot || {}
+    @host_count = config.all_hosts.count
+  end
+
+  def limit
+    limit = @options["limit"]
+
+    if limit.to_s.end_with?("%")
+      @host_count * limit.to_i / 100
+    else
+      limit
+    end
+  end
+
+  def wait
+    @options["wait"]
+  end
+end

lib/mrsk/configuration/role.rb

@@ -7,6 +7,10 @@ class Mrsk::Configuration::Role
    @name, @config = name.inquiry, config
   end
 
+  def primary_host
+    hosts.first
+  end
+
   def hosts
     @hosts ||= extract_hosts_from_config
   end
@@ -31,6 +35,21 @@ class Mrsk::Configuration::Role
     argumentize_env_with_secrets env
   end
 
+  def health_check_args
+    if health_check_cmd.present?
+      optionize({ "health-cmd" => health_check_cmd, "health-interval" => "1s" })
+    else
+      []
+    end
+  end
+
+  def health_check_cmd
+    options = specializations["healthcheck"] || {}
+    options = config.healthcheck.merge(options) if running_traefik?
+
+    options["cmd"] || http_health_check(port: options["port"], path: options["path"])
+  end
+
   def cmd
     specializations["cmd"]
   end
@@ -55,28 +74,38 @@ class Mrsk::Configuration::Role
         config.servers
       else
         servers = config.servers[name]
-        servers.is_a?(Array) ? servers : servers["hosts"]
+        servers.is_a?(Array) ? servers : Array(servers["hosts"])
       end
     end
 
     def default_labels
-      { "service" => config.service, "role" => name }
+      if config.destination
+        { "service" => config.service, "role" => name, "destination" => config.destination }
+      else
+        { "service" => config.service, "role" => name }
+      end
     end
 
     def traefik_labels
       if running_traefik?
         {
-          "traefik.http.routers.#{config.service}.rule" => "PathPrefix(`/`)",
-          "traefik.http.services.#{config.service}.loadbalancer.healthcheck.path" => config.healthcheck["path"],
-          "traefik.http.services.#{config.service}.loadbalancer.healthcheck.interval" => "1s",
-          "traefik.http.middlewares.#{config.service}.retry.attempts" => "5",
-          "traefik.http.middlewares.#{config.service}.retry.initialinterval" => "500ms"
+          # Setting a service property ensures that the generated service name will be consistent between versions
+          "traefik.http.services.#{traefik_service}.loadbalancer.server.scheme" => "http",
+
+          "traefik.http.routers.#{traefik_service}.rule" => "PathPrefix(`/`)",
+          "traefik.http.middlewares.#{traefik_service}-retry.retry.attempts" => "5",
+          "traefik.http.middlewares.#{traefik_service}-retry.retry.initialinterval" => "500ms",
+          "traefik.http.routers.#{traefik_service}.middlewares" => "#{traefik_service}-retry@docker"
         }
       else
         {}
       end
     end
 
+    def traefik_service
+      [ config.service, name, config.destination ].compact.join("-")
+    end
+
     def custom_labels
       Hash.new.tap do |labels|
         labels.merge!(config.labels) if config.labels.present?
@@ -112,4 +141,8 @@ class Mrsk::Configuration::Role
         new_env["clear"] = (clear_app_env + clear_role_env).uniq
       end
     end
+
+    def http_health_check(port:, path:)
+      "curl -f #{URI.join("http://localhost:#{port}", path)} || exit 1" if path.present? || port.present?
+    end
 end

lib/mrsk/sshkit_with_ext.rb

@@ -1,12 +1,52 @@
 require "sshkit"
 require "sshkit/dsl"
+require "active_support/core_ext/hash/deep_merge"
+require "json"
 
 class SSHKit::Backend::Abstract
-  def capture_with_info(*args)
-    capture(*args, verbosity: Logger::INFO)
+  def capture_with_info(*args, **kwargs)
+    capture(*args, **kwargs, verbosity: Logger::INFO)
+  end
+
+  def capture_with_pretty_json(*args, **kwargs)
+    JSON.pretty_generate(JSON.parse(capture(*args, **kwargs)))
   end
 
   def puts_by_host(host, output, type: "App")
     puts "#{type} Host: #{host}\n#{output}\n\n"
   end
+
+  # Our execution pattern is for the CLI execute args lists returned
+  # from commands, but this doesn't support returning execution options
+  # from the command.
+  #
+  # Support this by using kwargs for CLI options and merging with the
+  # args-extracted options.
+  module CommandEnvMerge
+    private
+
+    # Override to merge options returned by commands in the args list with
+    # options passed by the CLI and pass them along as kwargs.
+    def command(args, options)
+      more_options, args = args.partition { |a| a.is_a? Hash }
+      more_options << options
+
+      build_command(args, **more_options.reduce(:deep_merge))
+    end
+
+    # Destructure options to pluck out env for merge
+    def build_command(args, env: nil, **options)
+      # Rely on native Ruby kwargs precedence rather than explicit Hash merges
+      SSHKit::Command.new(*args, **default_command_options, **options, env: env_for(env))
+    end
+
+    def default_command_options
+      { in: pwd_path, host: @host, user: @user, group: @group }
+    end
+
+    def env_for(env)
+      @env.to_h.merge(env.to_h)
+    end
+  end
+  prepend CommandEnvMerge
 end

lib/mrsk/utils.rb

@@ -1,12 +1,15 @@
 module Mrsk::Utils
   extend self
 
+  DOLLAR_SIGN_WITHOUT_SHELL_EXPANSION_REGEX = /\$(?!{[^\}]*\})/
+
   # Return a list of escaped shell arguments using the same named argument against the passed attributes (hash or array).
-  def argumentize(argument, attributes, redacted: false)
+  def argumentize(argument, attributes, sensitive: false)
     Array(attributes).flat_map do |key, value|
       if value.present?
-        escaped_pair = [ key, escape_shell_value(value) ].join("=")
-        [ argument, redacted ? redact(escaped_pair) : escaped_pair ]
+        attr = "#{key}=#{escape_shell_value(value)}"
+        attr = self.sensitive(attr, redaction: "#{key}=[REDACTED]") if sensitive
+        [ argument, attr]
       else
         [ argument, key ]
       end
@@ -17,24 +20,70 @@ module Mrsk::Utils
   # but redacts and expands secrets.
   def argumentize_env_with_secrets(env)
     if (secrets = env["secret"]).present?
-      argumentize("-e", secrets.to_h { |key| [ key, ENV.fetch(key) ] }, redacted: true) + argumentize("-e", env["clear"])
+      argumentize("-e", secrets.to_h { |key| [ key, ENV.fetch(key) ] }, sensitive: true) + argumentize("-e", env["clear"])
     else
       argumentize "-e", env.fetch("clear", env)
     end
   end
 
   # Returns a list of shell-dashed option arguments. If the value is true, it's treated like a value-less option.
-  def optionize(args)
-    args.collect { |(key, value)| [ "--#{key}", value == true ? nil : escape_shell_value(value) ] }.flatten.compact
+  def optionize(args, with: nil)
+    options = if with
+      flatten_args(args).collect { |(key, value)| value == true ? "--#{key}" : "--#{key}#{with}#{escape_shell_value(value)}" }
+    else
+      flatten_args(args).collect { |(key, value)| [ "--#{key}", value == true ? nil : escape_shell_value(value) ] }
+    end
+
+    options.flatten.compact
   end
 
-  # Copied from SSHKit::Backend::Abstract#redact to be available inside Commands classes
-  def redact(arg) # Used in execute_command to hide redact() args a user passes in
-    arg.to_s.extend(SSHKit::Redaction) # to_s due to our inability to extend Integer, etc
+  # Flattens a one-to-many structure into an array of two-element arrays each containing a key-value pair
+  def flatten_args(args)
+    args.flat_map { |key, value| value.try(:map) { |entry| [key, entry] } || [ [ key, value ] ] }
+  end
+
+  # Marks sensitive values for redaction in logs and human-visible output.
+  # Pass `redaction:` to change the default `"[REDACTED]"` redaction, e.g.
+  # `sensitive "#{arg}=#{secret}", redaction: "#{arg}=xxxx"
+  def sensitive(...)
+    Mrsk::Utils::Sensitive.new(...)
+  end
+
+  def redacted(value)
+    case
+    when value.respond_to?(:redaction)
+      value.redaction
+    when value.respond_to?(:transform_values)
+      value.transform_values { |value| redacted value }
+    when value.respond_to?(:map)
+      value.map { |element| redacted element }
+    else
+      value
+    end
+  end
+
+  def unredacted(value)
+    case
+    when value.respond_to?(:unredacted)
+      value.unredacted
+    when value.respond_to?(:transform_values)
+      value.transform_values { |value| unredacted value }
+    when value.respond_to?(:map)
+      value.map { |element| unredacted element }
+    else
+      value
+    end
   end
 
   # Escape a value to make it safe for shell use.
   def escape_shell_value(value)
-    value.to_s.dump.gsub(/`/, '\\\\`')
+    value.to_s.dump
+      .gsub(/`/, '\\\\`')
+      .gsub(DOLLAR_SIGN_WITHOUT_SHELL_EXPANSION_REGEX, '\$')
+  end
+
+  # Abbreviate a git revhash for concise display
+  def abbreviate_version(version)
+    version[0...7] if version
   end
 end

lib/mrsk/utils/healthcheck_poller.rb

@@ -0,0 +1,39 @@
+class Mrsk::Utils::HealthcheckPoller
+  TRAEFIK_HEALTHY_DELAY = 2
+
+  class HealthcheckError < StandardError; end
+
+  class << self
+    def wait_for_healthy(pause_after_ready: false, &block)
+      attempt = 1
+      max_attempts = MRSK.config.healthcheck["max_attempts"]
+
+      begin
+        case status = block.call
+        when "healthy"
+          sleep TRAEFIK_HEALTHY_DELAY if pause_after_ready
+        when "running" # No health check configured
+          sleep MRSK.config.readiness_delay if pause_after_ready
+        else
+          raise HealthcheckError, "container not ready (#{status})"
+        end
+      rescue HealthcheckError => e
+        if attempt <= max_attempts
+          info "#{e.message}, retrying in #{attempt}s (attempt #{attempt}/#{max_attempts})..."
+          sleep attempt
+          attempt += 1
+          retry
+        else
+          raise
+        end
+      end
+
+      info "Container is healthy!"
+    end
+
+    private
+      def info(message)
+        SSHKit.config.output.info(message)
+      end
+  end
+end

lib/mrsk/utils/sensitive.rb

@@ -0,0 +1,19 @@
+require "active_support/core_ext/module/delegation"
+
+class Mrsk::Utils::Sensitive
+  # So SSHKit knows to redact these values.
+  include SSHKit::Redaction
+
+  attr_reader :unredacted, :redaction
+  delegate :to_s, to: :unredacted
+  delegate :inspect, to: :redaction
+
+  def initialize(value, redaction: "[REDACTED]")
+    @unredacted, @redaction = value, redaction
+  end
+
+  # Sensitive values won't leak into YAML output.
+  def encode_with(coder)
+    coder.represent_scalar nil, redaction
+  end
+end

lib/mrsk/version.rb

@@ -1,3 +1,3 @@
 module Mrsk
-  VERSION = "0.9.1"
+  VERSION = "0.12.1"
 end

mrsk.gemspec

@@ -14,9 +14,14 @@ Gem::Specification.new do |spec|
 
   spec.add_dependency "activesupport", ">= 7.0"
   spec.add_dependency "sshkit", "~> 1.21"
+  spec.add_dependency "net-ssh", "~> 7.0"
   spec.add_dependency "thor", "~> 1.2"
   spec.add_dependency "dotenv", "~> 2.8"
   spec.add_dependency "zeitwerk", "~> 2.5"
   spec.add_dependency "ed25519", "~> 1.2"
   spec.add_dependency "bcrypt_pbkdf", "~> 1.0"
+
+  spec.add_development_dependency "debug"
+  spec.add_development_dependency "mocha"
+  spec.add_development_dependency "railties"
 end

test/cli/accessory_test.rb

@@ -1,42 +1,138 @@
 require_relative "cli_test_case"
 
 class CliAccessoryTest < CliTestCase
+  test "boot" do
+    Mrsk::Cli::Accessory.any_instance.expects(:directories).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:upload).with("mysql")
+
+    run_command("boot", "mysql").tap do |output|
+      assert_match /docker login.*on 1.1.1.3/, output
+      assert_match "docker run --name app-mysql --detach --restart unless-stopped --log-opt max-size=\"10m\" --publish 3306:3306 -e [REDACTED] -e MYSQL_ROOT_HOST=\"%\" --volume $PWD/app-mysql/etc/mysql/my.cnf:/etc/mysql/my.cnf --volume $PWD/app-mysql/data:/var/lib/mysql --label service=\"app-mysql\" mysql:5.7 on 1.1.1.3", output
+    end
+  end
+
+  test "boot all" do
+    Mrsk::Cli::Accessory.any_instance.expects(:directories).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:upload).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:directories).with("redis")
+    Mrsk::Cli::Accessory.any_instance.expects(:upload).with("redis")
+
+    run_command("boot", "all").tap do |output|
+      assert_match /docker login.*on 1.1.1.3/, output
+      assert_match /docker login.*on 1.1.1.1/, output
+      assert_match /docker login.*on 1.1.1.2/, output
+      assert_match "docker run --name app-mysql --detach --restart unless-stopped --log-opt max-size=\"10m\" --publish 3306:3306 -e [REDACTED] -e MYSQL_ROOT_HOST=\"%\" --volume $PWD/app-mysql/etc/mysql/my.cnf:/etc/mysql/my.cnf --volume $PWD/app-mysql/data:/var/lib/mysql --label service=\"app-mysql\" mysql:5.7 on 1.1.1.3", output
+      assert_match "docker run --name app-redis --detach --restart unless-stopped --log-opt max-size=\"10m\" --publish 6379:6379 --volume $PWD/app-redis/data:/data --label service=\"app-redis\" redis:latest on 1.1.1.1", output
+      assert_match "docker run --name app-redis --detach --restart unless-stopped --log-opt max-size=\"10m\" --publish 6379:6379 --volume $PWD/app-redis/data:/data --label service=\"app-redis\" redis:latest on 1.1.1.2", output
+    end
+  end
+
   test "upload" do
-    assert_match "test/fixtures/files/my.cnf app-mysql/etc/mysql/my.cnf", run_command("upload", "mysql")
+    run_command("upload", "mysql").tap do |output|
+      assert_match "mkdir -p app-mysql/etc/mysql", output
+      assert_match "test/fixtures/files/my.cnf app-mysql/etc/mysql/my.cnf", output
+      assert_match "chmod 755 app-mysql/etc/mysql/my.cnf", output
+    end
   end
 
   test "directories" do
     assert_match "mkdir -p $PWD/app-mysql/data", run_command("directories", "mysql")
   end
 
-  test "remove service direcotry" do
-    assert_match "rm -rf app-mysql", run_command("remove_service_directory", "mysql")
+  test "reboot" do
+    Mrsk::Cli::Accessory.any_instance.expects(:stop).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_container).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:boot).with("mysql")
+
+    run_command("reboot", "mysql")
   end
 
-  test "boot" do
-    assert_match "Running docker run --name app-mysql --detach --restart unless-stopped --log-opt max-size=10m --publish 3306:3306 -e [REDACTED] -e MYSQL_ROOT_HOST=\"%\" --volume $PWD/app-mysql/etc/mysql/my.cnf:/etc/mysql/my.cnf --volume $PWD/app-mysql/data:/var/lib/mysql --label service=\"app-mysql\" mysql:5.7 on 1.1.1.3", run_command("boot", "mysql")
+  test "start" do
+    assert_match "docker container start app-mysql", run_command("start", "mysql")
+  end
+
+  test "stop" do
+    assert_match "docker container stop app-mysql", run_command("stop", "mysql")
+  end
+
+  test "restart" do
+    Mrsk::Cli::Accessory.any_instance.expects(:stop).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:start).with("mysql")
+
+    run_command("restart", "mysql")
+  end
+
+  test "details" do
+    assert_match "docker ps --filter label=service=app-mysql", run_command("details", "mysql")
+  end
+
+  test "details with all" do
+    run_command("details", "all").tap do |output|
+      assert_match "docker ps --filter label=service=app-mysql", output
+      assert_match "docker ps --filter label=service=app-redis", output
+    end
   end
 
   test "exec" do
     run_command("exec", "mysql", "mysql -v").tap do |output|
-      assert_match /Launching command from new container/, output
-      assert_match /mysql -v/, output
+      assert_match "Launching command from new container", output
+      assert_match "mysql -v", output
     end
   end
 
   test "exec with reuse" do
     run_command("exec", "mysql", "--reuse", "mysql -v").tap do |output|
-      assert_match /Launching command from existing container/, output
-      assert_match %r[docker exec app-mysql mysql -v], output
+      assert_match "Launching command from existing container", output
+      assert_match "docker exec app-mysql mysql -v", output
     end
   end
 
+  test "logs" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.3 'docker logs app-mysql --timestamps --tail 10 2>&1'")
+
+    assert_match "docker logs app-mysql  --tail 100 --timestamps 2>&1", run_command("logs", "mysql")
+  end
+
+  test "logs with follow" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.3 'docker logs app-mysql --timestamps --tail 10 --follow 2>&1'")
+
+    assert_match "docker logs app-mysql --timestamps --tail 10 --follow 2>&1", run_command("logs", "mysql", "--follow")
+  end
+
   test "remove with confirmation" do
-    run_command("remove", "mysql", "-y").tap do |output|
-      assert_match /docker container stop app-mysql/, output
-      assert_match /docker image prune --all --force --filter label=service=app-mysql/, output
-      assert_match /rm -rf app-mysql/, output
-    end
+    Mrsk::Cli::Accessory.any_instance.expects(:stop).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_container).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_image).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_service_directory).with("mysql")
+
+    run_command("remove", "mysql", "-y")
+  end
+
+  test "remove all with confirmation" do
+    Mrsk::Cli::Accessory.any_instance.expects(:stop).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_container).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_image).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_service_directory).with("mysql")
+    Mrsk::Cli::Accessory.any_instance.expects(:stop).with("redis")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_container).with("redis")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_image).with("redis")
+    Mrsk::Cli::Accessory.any_instance.expects(:remove_service_directory).with("redis")
+
+    run_command("remove", "all", "-y")
+  end
+
+  test "remove_container" do
+    assert_match "docker container prune --force --filter label=service=app-mysql", run_command("remove_container", "mysql")
+  end
+
+  test "remove_image" do
+    assert_match "docker image rm --force mysql", run_command("remove_image", "mysql")
+  end
+
+  test "remove_service_directory" do
+    assert_match "rm -rf app-mysql", run_command("remove_service_directory", "mysql")
   end
 
   private

test/cli/app_test.rb

@@ -2,88 +2,173 @@ require_relative "cli_test_case"
 
 class CliAppTest < CliTestCase
   test "boot" do
-    # Stub current version fetch
-    SSHKit::Backend::Abstract.any_instance.stubs(:capture)
-      .returns("999") # new version
-      .then
-      .returns("123") # old version
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture_with_info).returns("123") # old version
+
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+    .with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-latest$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+    .returns("running") # health check
 
     run_command("boot").tap do |output|
-      assert_match /docker run --detach --restart unless-stopped/, output
-      assert_match /docker container ls --all --filter name=app-123 --quiet | xargs docker stop/, output
+      assert_match "docker tag dhh/app:latest dhh/app:latest", output
+      assert_match "docker run --detach --restart unless-stopped", output
+      assert_match "docker container ls --all --filter name=^app-web-123$ --quiet | xargs docker stop", output
     end
   end
 
-  test "boot will reboot if same version is already running" do
+  test "boot will rename if same version is already running" do
     run_command("details") # Preheat MRSK const
 
-    # Prevent expected failures from outputting to terminal
-    Thread.report_on_exception = false
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-latest$", "--quiet", raise_on_non_zero_exit: false)
+      .returns("12345678") # running version
 
-    MRSK.app.stubs(:run)
-      .raises(SSHKit::Command::Failed.new("already in use"))
-      .then
-      .raises(SSHKit::Command::Failed.new("already in use"))
-      .then
-      .returns([ :docker, :run ])
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-latest$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+      .returns("running") # health check
+
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-", raise_on_non_zero_exit: false)
+      .returns("123") # old version
 
     run_command("boot").tap do |output|
-      assert_match /Rebooting container with same version 999 already deployed/, output # Can't start what's already running
-      assert_match /docker container ls --all --filter name=app-999 --quiet | xargs docker container rm/, output # Stop old running
-      assert_match /docker container ls --all --filter name=app-999 --quiet | xargs docker container rm/, output # Remove old container
-      assert_match /docker run/, output # Start new container
+      assert_match /Renaming container .* to .* as already deployed on 1.1.1.1/, output # Rename
+      assert_match /docker rename .* .*/, output
+      assert_match "docker run --detach --restart unless-stopped", output
+      assert_match "docker container ls --all --filter name=^app-web-123$ --quiet | xargs docker stop", output
     end
   ensure
     Thread.report_on_exception = true
   end
 
+  test "boot uses group strategy when specified" do
+    Mrsk::Cli::App.any_instance.stubs(:on).with("1.1.1.1").twice # acquire & release lock
+    Mrsk::Cli::App.any_instance.stubs(:on).with([ "1.1.1.1" ]) # tag container
+
+    # Strategy is used when booting the containers
+    Mrsk::Cli::App.any_instance.expects(:on).with([ "1.1.1.1" ], in: :groups, limit: 3, wait: 2).with_block_given
+
+    run_command("boot", config: :with_boot_strategy)
+  end
+
   test "start" do
     run_command("start").tap do |output|
-      assert_match /docker start app-999/, output
+      assert_match "docker start app-web-999", output
     end
   end
 
   test "stop" do
     run_command("stop").tap do |output|
-      assert_match /docker ps --quiet --filter label=service=app \| xargs docker stop/, output
+      assert_match "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker stop", output
+    end
+  end
+
+  test "stale_containers" do
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-", raise_on_non_zero_exit: false)
+      .returns("12345678\n87654321")
+
+    run_command("stale_containers").tap do |output|
+      assert_match /Detected stale container for role web with version 87654321/, output
+    end
+  end
+
+  test "stop stale_containers" do
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-", raise_on_non_zero_exit: false)
+      .returns("12345678\n87654321")
+
+    run_command("stale_containers", "--stop").tap do |output|
+      assert_match /Stopping stale container for role web with version 87654321/, output
+      assert_match /#{Regexp.escape("docker container ls --all --filter name=^app-web-87654321$ --quiet | xargs docker stop")}/, output
     end
   end
 
   test "details" do
     run_command("details").tap do |output|
-      assert_match /docker ps --filter label=service=app/, output
+      assert_match "docker ps --filter label=service=app --filter label=role=web", output
     end
   end
 
   test "remove" do
     run_command("remove").tap do |output|
-      assert_match /docker ps --quiet --filter label=service=app | xargs docker stop/, output
-      assert_match /docker container prune --force --filter label=service=app/, output
-      assert_match /docker image prune --all --force --filter label=service=app/, output
+      assert_match /#{Regexp.escape("docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker stop")}/, output
+      assert_match /#{Regexp.escape("docker container prune --force --filter label=service=app")}/, output
+      assert_match /#{Regexp.escape("docker image prune --all --force --filter label=service=app")}/, output
     end
   end
 
   test "remove_container" do
     run_command("remove_container", "1234567").tap do |output|
-      assert_match /docker container ls --all --filter name=app-1234567 --quiet \| xargs docker container rm/, output
+      assert_match "docker container ls --all --filter name=^app-web-1234567$ --quiet | xargs docker container rm", output
+    end
+  end
+
+  test "remove_containers" do
+    run_command("remove_containers").tap do |output|
+      assert_match "docker container prune --force --filter label=service=app", output
+    end
+  end
+
+  test "remove_images" do
+    run_command("remove_images").tap do |output|
+      assert_match "docker image prune --all --force --filter label=service=app", output
     end
   end
 
   test "exec" do
     run_command("exec", "ruby -v").tap do |output|
-      assert_match /ruby -v/, output
+      assert_match "docker run --rm dhh/app:latest ruby -v", output
     end
   end
 
   test "exec with reuse" do
     run_command("exec", "--reuse", "ruby -v").tap do |output|
-      assert_match %r[docker ps --filter label=service=app --format \"{{.Names}}\" | sed 's/-/\\n/g' | tail -n 1], output # Get current version
-      assert_match %r[docker exec app-999 ruby -v], output
+      assert_match "docker ps --filter label=service=app --filter status=running --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-", output # Get current version
+      assert_match "docker exec app-web-999 ruby -v", output
+    end
+  end
+
+  test "containers" do
+    run_command("containers").tap do |output|
+      assert_match "docker container ls --all --filter label=service=app", output
+    end
+  end
+
+  test "images" do
+    run_command("images").tap do |output|
+      assert_match "docker image ls dhh/app", output
+    end
+  end
+
+  test "logs" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.1 'docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest| xargs docker logs --timestamps --tail 10 2>&1'")
+
+    assert_match "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --tail 100 2>&1", run_command("logs")
+  end
+
+  test "logs with follow" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.1 'docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1'")
+
+    assert_match "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1", run_command("logs", "--follow")
+  end
+
+  test "version" do
+    run_command("version").tap do |output|
+      assert_match "docker ps --filter label=service=app --filter status=running --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-", output
+    end
+  end
+
+
+  test "version through main" do
+    stdouted { Mrsk::Cli::Main.start(["app", "version", "-c", "test/fixtures/deploy_with_accessories.yml", "--hosts", "1.1.1.1"]) }.tap do |output|
+      assert_match "docker ps --filter label=service=app --filter status=running --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-", output
     end
   end
 
   private
-    def run_command(*command)
-      stdouted { Mrsk::Cli::App.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    def run_command(*command, config: :with_accessories)
+      stdouted { Mrsk::Cli::App.start([*command, "-c", "test/fixtures/deploy_#{config}.yml", "--hosts", "1.1.1.1"]) }
     end
 end

test/cli/build_test.rb

@@ -1,6 +1,34 @@
 require_relative "cli_test_case"
 
 class CliBuildTest < CliTestCase
+  test "deliver" do
+    Mrsk::Cli::Build.any_instance.expects(:push)
+    Mrsk::Cli::Build.any_instance.expects(:pull)
+
+    run_command("deliver")
+  end
+
+  test "push" do
+    Mrsk::Cli::Build.any_instance.stubs(:verify_local_dependencies).returns(true)
+    run_command("push").tap do |output|
+      assert_match /docker buildx build --push --platform linux\/amd64,linux\/arm64 --builder mrsk-app-multiarch -t dhh\/app:999 -t dhh\/app:latest --label service="app" --file Dockerfile \. as .*@localhost/, output
+    end
+  end
+
+  test "push without builder" do
+    stub_locking
+    Mrsk::Cli::Build.any_instance.stubs(:verify_local_dependencies).returns(true)
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with { |arg| arg == :docker }
+      .raises(SSHKit::Command::Failed.new("no builder"))
+      .then
+      .returns(true)
+
+    run_command("push").tap do |output|
+      assert_match /Missing compatible builder, so creating a new one first/, output
+    end
+  end
+
   test "pull" do
     run_command("pull").tap do |output|
       assert_match /docker image rm --force dhh\/app:999/, output
@@ -8,8 +36,66 @@ class CliBuildTest < CliTestCase
     end
   end
 
+  test "create" do
+    run_command("create").tap do |output|
+      assert_match /docker buildx create --use --name mrsk-app-multiarch/, output
+    end
+  end
+
+  test "create with error" do
+    stub_locking
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with { |arg| arg == :docker }
+      .raises(SSHKit::Command::Failed.new("stderr=error"))
+
+    run_command("create").tap do |output|
+      assert_match /Couldn't create remote builder: error/, output
+    end
+  end
+
+  test "remove" do
+    run_command("remove").tap do |output|
+      assert_match /docker buildx rm mrsk-app-multiarch/, output
+    end
+  end
+
+  test "details" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture)
+      .with(:docker, :context, :ls, "&&", :docker, :buildx, :ls)
+      .returns("docker builder info")
+
+    run_command("details").tap do |output|
+      assert_match /Builder: multiarch/, output
+      assert_match /docker builder info/, output
+    end
+  end
+
+  test "verify local dependencies" do
+    Mrsk::Commands::Builder.any_instance.stubs(:name).returns("remote".inquiry)
+
+    run_command("verify_local_dependencies").tap do |output|
+      assert_match /docker --version && docker buildx version/, output
+    end
+  end
+
+  test "verify local dependencies with no buildx plugin" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, "--version", "&&", :docker, :buildx, "version")
+      .raises(SSHKit::Command::Failed.new("no buildx"))
+
+    Mrsk::Commands::Builder.any_instance.stubs(:native_and_local?).returns(false)
+    assert_raises(Mrsk::Cli::Build::BuildError) { run_command("verify_local_dependencies") }
+  end
+
   private
     def run_command(*command)
       stdouted { Mrsk::Cli::Build.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
     end
+
+    def stub_locking
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |arg1, arg2| arg1 == :mkdir && arg2 == :mrsk_lock }
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |arg1, arg2| arg1 == :rm && arg2 == "mrsk_lock/details" }
+    end
 end

test/cli/cli_test_case.rb

@@ -1,5 +1,4 @@
 require "test_helper"
-require "active_support/testing/stream"
 
 class CliTestCase < ActiveSupport::TestCase
   include ActiveSupport::Testing::Stream
@@ -8,17 +7,13 @@ class CliTestCase < ActiveSupport::TestCase
     ENV["VERSION"]             = "999"
     ENV["RAILS_MASTER_KEY"]    = "123"
     ENV["MYSQL_ROOT_PASSWORD"] = "secret123"
+    Object.send(:remove_const, :MRSK)
+    Object.const_set(:MRSK, Mrsk::Commander.new)
   end
 
   teardown do
     ENV.delete("RAILS_MASTER_KEY")
     ENV.delete("MYSQL_ROOT_PASSWORD")
     ENV.delete("VERSION")
-    MRSK.reset
   end
-
-  private
-    def stdouted
-      capture(:stdout) { yield }.strip
-    end
 end

test/cli/healthcheck_test.rb

@@ -0,0 +1,71 @@
+require_relative "cli_test_case"
+
+class CliHealthcheckTest < CliTestCase
+  test "perform" do
+    # Prevent expected failures from outputting to terminal
+    Thread.report_on_exception = false
+
+    Mrsk::Utils::HealthcheckPoller.stubs(:sleep) # No sleeping when retrying
+
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :stop, raise_on_non_zero_exit: false)
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, :run, "--detach", "--name", "healthcheck-app-999", "--publish", "3999:3000", "--label", "service=healthcheck-app", "-e", "MRSK_CONTAINER_NAME=\"healthcheck-app\"", "--health-cmd", "\"curl -f http://localhost:3000/up || exit 1\"", "--health-interval", "\"1s\"", "dhh/app:999")
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :container, :rm, raise_on_non_zero_exit: false)
+
+    # Fail twice to test retry logic
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+      .returns("starting")
+      .then
+      .returns("unhealthy")
+      .then
+      .returns("healthy")
+
+    run_command("perform").tap do |output|
+      assert_match "container not ready (starting), retrying in 1s (attempt 1/7)...", output
+      assert_match "container not ready (unhealthy), retrying in 2s (attempt 2/7)...", output
+      assert_match "Container is healthy!", output
+    end
+  end
+
+  test "perform failing to become healthy" do
+    # Prevent expected failures from outputting to terminal
+    Thread.report_on_exception = false
+
+    Mrsk::Utils::HealthcheckPoller.stubs(:sleep) # No sleeping when retrying
+
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :stop, raise_on_non_zero_exit: false)
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, :run, "--detach", "--name", "healthcheck-app-999", "--publish", "3999:3000", "--label", "service=healthcheck-app", "-e", "MRSK_CONTAINER_NAME=\"healthcheck-app\"", "--health-cmd", "\"curl -f http://localhost:3000/up || exit 1\"", "--health-interval", "\"1s\"", "dhh/app:999")
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :container, :rm, raise_on_non_zero_exit: false)
+
+    # Continually report unhealthy
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+      .returns("unhealthy")
+
+    # Capture logs when failing
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :logs, "--tail", 50, "2>&1")
+      .returns("some log output")
+
+    # Capture container health log when failing
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture_with_pretty_json)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^healthcheck-app-999$", "--quiet", "|", :xargs, :docker, :inspect, "--format",  "'{{json .State.Health}}'")
+      .returns('{"Status":"unhealthy","Log":[{"ExitCode": 1,"Output": "/bin/sh: 1: curl: not found\n"}]}"')
+
+    exception = assert_raises do
+      run_command("perform")
+    end
+    assert_match "container not ready (unhealthy)", exception.message
+  end
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Healthcheck.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+end

test/cli/lock_test.rb

@@ -0,0 +1,20 @@
+require_relative "cli_test_case"
+
+class CliLockTest < CliTestCase
+  test "status" do
+    run_command("status") do |output|
+      assert_match "stat lock", output
+    end
+  end
+
+  test "release" do
+    run_command("release") do |output|
+      assert_match "rm -rf lock", output
+    end
+  end
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Lock.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+end

test/cli/main_test.rb

@@ -1,32 +1,304 @@
 require_relative "cli_test_case"
 
 class CliMainTest < CliTestCase
-  test "version" do
-    version = stdouted { Mrsk::Cli::Main.new.version }
-    assert_equal Mrsk::VERSION, version
+  test "setup" do
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:server:bootstrap")
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:accessory:boot", [ "all" ])
+    Mrsk::Cli::Main.any_instance.expects(:deploy)
+
+    run_command("setup")
+  end
+
+  test "deploy" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "skip_broadcast" => false, "version" => "999" }
+
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:registry:login", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:build:deliver", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:traefik:boot", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:healthcheck:perform", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:stale_containers", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:boot", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:prune:all", [], invoke_options)
+
+    run_command("deploy").tap do |output|
+      assert_match /Log into image registry/, output
+      assert_match /Build and push app image/, output
+      assert_match /Ensure Traefik is running/, output
+      assert_match /Ensure app can pass healthcheck/, output
+      assert_match /Detect stale containers/, output
+      assert_match /Prune old containers and images/, output
+    end
+  end
+
+  test "deploy with skip_push" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "skip_broadcast" => false, "version" => "999" }
+
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:registry:login", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:build:pull", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:traefik:boot", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:healthcheck:perform", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:stale_containers", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:boot", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:prune:all", [], invoke_options)
+
+    run_command("deploy", "--skip_push").tap do |output|
+      assert_match /Acquiring the deploy lock/, output
+      assert_match /Log into image registry/, output
+      assert_match /Pull app image/, output
+      assert_match /Ensure Traefik is running/, output
+      assert_match /Ensure app can pass healthcheck/, output
+      assert_match /Detect stale containers/, output
+      assert_match /Prune old containers and images/, output
+      assert_match /Releasing the deploy lock/, output
+    end
+  end
+
+  test "deploy when locked" do
+    Thread.report_on_exception = false
+
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with { |*arg| arg[0..1] == [:mkdir, :mrsk_lock] }
+      .raises(RuntimeError, "mkdir: cannot create directory ‘mrsk_lock’: File exists")
+
+    SSHKit::Backend::Abstract.any_instance.expects(:execute)
+      .with(:stat, :mrsk_lock, ">", "/dev/null", "&&", :cat, "mrsk_lock/details", "|", :base64, "-d")
+
+    assert_raises(Mrsk::Cli::LockError) do
+      run_command("deploy")
+    end
+  end
+
+  test "deploy error when locking" do
+    Thread.report_on_exception = false
+
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with { |*arg| arg[0..1] == [:mkdir, :mrsk_lock] }
+      .raises(SocketError, "getaddrinfo: nodename nor servname provided, or not known")
+
+    assert_raises(SSHKit::Runner::ExecuteError) do
+      run_command("deploy")
+    end
+  end
+
+  test "deploy errors during critical section leave lock in place" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "skip_broadcast" => false, "version" => "999" }
+
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:registry:login", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:build:deliver", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:stale_containers", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:traefik:boot", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:healthcheck:perform", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:boot", [], invoke_options).raises(RuntimeError)
+
+    assert !MRSK.holding_lock?
+    assert_raises(RuntimeError) do
+      stderred { run_command("deploy") }
+    end
+    assert MRSK.holding_lock?
+  end
+
+  test "deploy errors during outside section leave remove lock" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "skip_broadcast" => false, "version" => "999" }
+
+    Mrsk::Cli::Main.any_instance.expects(:invoke)
+      .with("mrsk:cli:registry:login", [], invoke_options)
+      .raises(RuntimeError)
+
+    assert !MRSK.holding_lock?
+    assert_raises(RuntimeError) do
+      stderred { run_command("deploy") }
+    end
+    assert !MRSK.holding_lock?
+  end
+
+  test "redeploy" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "skip_broadcast" => false, "version" => "999" }
+
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:build:deliver", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:healthcheck:perform", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:stale_containers", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:boot", [], invoke_options)
+
+    run_command("redeploy").tap do |output|
+      assert_match /Build and push app image/, output
+      assert_match /Ensure app can pass healthcheck/, output
+    end
+  end
+
+  test "redeploy with skip_push" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "skip_broadcast" => false, "version" => "999" }
+
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:build:pull", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:healthcheck:perform", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:stale_containers", [], invoke_options)
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:boot", [], invoke_options)
+
+    run_command("redeploy", "--skip_push").tap do |output|
+      assert_match /Pull app image/, output
+      assert_match /Ensure app can pass healthcheck/, output
+    end
   end
 
   test "rollback bad version" do
+    Thread.report_on_exception = false
+
     run_command("details") # Preheat MRSK const
 
     run_command("rollback", "nonsense").tap do |output|
-      assert_match /docker container ls --all --filter label=service=app --format '{{ .Names }}'/, output
+      assert_match /docker container ls --all --filter name=\^app-web-nonsense\$ --quiet/, output
       assert_match /The app version 'nonsense' is not available as a container/, output
     end
   end
 
   test "rollback good version" do
-    Mrsk::Cli::Main.any_instance.stubs(:container_name_available?).returns(true)
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-123$", "--quiet")
+      .returns("version-to-rollback\n").at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^app-workers-123$", "--quiet")
+      .returns("version-to-rollback\n").at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-")
+      .returns("version-to-rollback\n").at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=workers", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-")
+      .returns("version-to-rollback\n").at_least_once
 
-    run_command("rollback", "123").tap do |output|
-      assert_match /Start version 123/, output
-      assert_match /docker ps -q --filter label=service=app | xargs docker stop/, output
-      assert_match /docker start app-123/, output
+
+    run_command("rollback", "123", config_file: "deploy_with_accessories").tap do |output|
+      assert_match "Start version 123", output
+      assert_match "docker tag dhh/app:123 dhh/app:latest", output
+      assert_match "docker start app-web-123", output
+      assert_match "docker container ls --all --filter name=^app-web-version-to-rollback$ --quiet | xargs docker stop", output, "Should stop the container that was previously running"
     end
   end
 
+  test "rollback without old version" do
+    Mrsk::Cli::Main.any_instance.stubs(:container_available?).returns(true)
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info).with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-").returns("").at_least_once
+
+    run_command("rollback", "123").tap do |output|
+      assert_match "Start version 123", output
+      assert_match "docker start app-web-123", output
+      assert_no_match "docker stop", output
+    end
+  end
+
+  test "details" do
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:traefik:details")
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:app:details")
+    Mrsk::Cli::Main.any_instance.expects(:invoke).with("mrsk:cli:accessory:details", [ "all" ])
+
+    run_command("details")
+  end
+
+  test "audit" do
+    run_command("audit").tap do |output|
+      assert_match /tail -n 50 mrsk-app-audit.log on 1.1.1.1/, output
+      assert_match /App Host: 1.1.1.1/, output
+    end
+  end
+
+  test "config" do
+    run_command("config", config_file: "deploy_simple").tap do |output|
+      config = YAML.load(output)
+
+      assert_equal ["web"], config[:roles]
+      assert_equal ["1.1.1.1", "1.1.1.2"], config[:hosts]
+      assert_equal "999", config[:version]
+      assert_equal "dhh/app", config[:repository]
+      assert_equal "dhh/app:999", config[:absolute_image]
+      assert_equal "app-999", config[:service_with_version]
+    end
+  end
+
+  test "config with roles" do
+    run_command("config", config_file: "deploy_with_roles").tap do |output|
+      config = YAML.load(output)
+
+      assert_equal ["web", "workers"], config[:roles]
+      assert_equal ["1.1.1.1", "1.1.1.2", "1.1.1.3", "1.1.1.4"], config[:hosts]
+      assert_equal "999", config[:version]
+      assert_equal "registry.digitalocean.com/dhh/app", config[:repository]
+      assert_equal "registry.digitalocean.com/dhh/app:999", config[:absolute_image]
+      assert_equal "app-999", config[:service_with_version]
+    end
+  end
+
+  test "config with destination" do
+    run_command("config", "-d", "world", config_file: "deploy_for_dest").tap do |output|
+      config = YAML.load(output)
+
+      assert_equal ["web"], config[:roles]
+      assert_equal ["1.1.1.1", "1.1.1.2"], config[:hosts]
+      assert_equal "999", config[:version]
+      assert_equal "registry.digitalocean.com/dhh/app", config[:repository]
+      assert_equal "registry.digitalocean.com/dhh/app:999", config[:absolute_image]
+      assert_equal "app-999", config[:service_with_version]
+    end
+  end
+
+  test "init" do
+    Pathname.any_instance.expects(:exist?).returns(false).twice
+    FileUtils.stubs(:mkdir_p)
+    FileUtils.stubs(:cp_r)
+
+    run_command("init").tap do |output|
+      assert_match /Created configuration file in config\/deploy.yml/, output
+      assert_match /Created \.env file/, output
+    end
+  end
+
+  test "init with existing config" do
+    Pathname.any_instance.expects(:exist?).returns(true).twice
+
+    run_command("init").tap do |output|
+      assert_match /Config file already exists in config\/deploy.yml \(remove first to create a new one\)/, output
+    end
+  end
+
+  test "init with bundle option" do
+    Pathname.any_instance.expects(:exist?).returns(false).times(3)
+    FileUtils.stubs(:mkdir_p)
+    FileUtils.stubs(:cp_r)
+
+    run_command("init", "--bundle").tap do |output|
+      assert_match /Created configuration file in config\/deploy.yml/, output
+      assert_match /Created \.env file/, output
+      assert_match /Adding MRSK to Gemfile and bundle/, output
+      assert_match /bundle add mrsk/, output
+      assert_match /bundle binstubs mrsk/, output
+      assert_match /Created binstub file in bin\/mrsk/, output
+    end
+  end
+
+  test "init with bundle option and existing binstub" do
+    Pathname.any_instance.expects(:exist?).returns(true).times(3)
+    FileUtils.stubs(:mkdir_p)
+    FileUtils.stubs(:cp_r)
+
+    run_command("init", "--bundle").tap do |output|
+      assert_match /Config file already exists in config\/deploy.yml \(remove first to create a new one\)/, output
+      assert_match /Binstub already exists in bin\/mrsk \(remove first to create a new one\)/, output
+    end
+  end
+
+  test "envify" do
+    File.expects(:read).with(".env.erb").returns("HELLO=<%= 'world' %>")
+    File.expects(:write).with(".env", "HELLO=world", perm: 0600)
+
+    run_command("envify")
+  end
+
+  test "envify with destination" do
+    File.expects(:read).with(".env.staging.erb").returns("HELLO=<%= 'world' %>")
+    File.expects(:write).with(".env.staging", "HELLO=world", perm: 0600)
+
+    run_command("envify", "-d", "staging")
+  end
+
   test "remove with confirmation" do
-    run_command("remove", "-y").tap do |output|
+    run_command("remove", "-y", config_file: "deploy_with_accessories").tap do |output|
       assert_match /docker container stop traefik/, output
       assert_match /docker container prune --force --filter label=org.opencontainers.image.title=Traefik/, output
       assert_match /docker image prune --all --force --filter label=org.opencontainers.image.title=Traefik/, output
@@ -37,20 +309,38 @@ class CliMainTest < CliTestCase
 
       assert_match /docker container stop app-mysql/, output
       assert_match /docker container prune --force --filter label=service=app-mysql/, output
-      assert_match /docker image prune --all --force --filter label=service=app-mysql/, output
+      assert_match /docker image rm --force mysql/, output
       assert_match /rm -rf app-mysql/, output
 
       assert_match /docker container stop app-redis/, output
       assert_match /docker container prune --force --filter label=service=app-redis/, output
-      assert_match /docker image prune --all --force --filter label=service=app-redis/, output
+      assert_match /docker image rm --force redis/, output
       assert_match /rm -rf app-redis/, output
 
       assert_match /docker logout/, output
     end
   end
 
+  test "broadcast" do
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with do |command, line, options, verbosity:|
+      command == "bin/audit_broadcast" &&
+        line =~ /\A'\[[^\]]+\] message'\z/ &&
+        options[:env].keys == %w[ MRSK_RECORDED_AT MRSK_PERFORMER MRSK_EVENT ] &&
+        verbosity == :debug
+    end.returns("Broadcast audit message: message")
+
+    run_command("broadcast", "-m", "message").tap do |output|
+      assert_match "Broadcast: message", output
+    end
+  end
+
+  test "version" do
+    version = stdouted { Mrsk::Cli::Main.new.version }
+    assert_equal Mrsk::VERSION, version
+  end
+
   private
-    def run_command(*command)
-      stdouted { Mrsk::Cli::Main.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    def run_command(*command, config_file: "deploy_simple")
+      stdouted { Mrsk::Cli::Main.start([*command, "-c", "test/fixtures/#{config_file}.yml"]) }
     end
 end

test/cli/prune_test.rb

@@ -0,0 +1,27 @@
+require_relative "cli_test_case"
+
+class CliPruneTest < CliTestCase
+  test "all" do
+    Mrsk::Cli::Prune.any_instance.expects(:containers)
+    Mrsk::Cli::Prune.any_instance.expects(:images)
+
+    run_command("all")
+  end
+
+  test "images" do
+    run_command("images").tap do |output|
+      assert_match /docker image prune --force --filter label=service=app --filter dangling=true on 1.1.1.\d/, output
+    end
+  end
+
+  test "containers" do
+    run_command("containers").tap do |output|
+      assert_match /docker ps -q -a --filter label=service=app --filter status=created --filter status=exited --filter status=dead | tail -n +6 | while read container_id; do docker rm $container_id; done on 1.1.1.\d/, output
+    end
+  end
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Prune.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+end

test/cli/registry_test.rb

@@ -0,0 +1,21 @@
+require_relative "cli_test_case"
+
+class CliRegistryTest < CliTestCase
+  test "login" do
+    run_command("login").tap do |output|
+      assert_match /docker login -u \[REDACTED\] -p \[REDACTED\] as .*@localhost/, output
+      assert_match /docker login -u \[REDACTED\] -p \[REDACTED\] on 1.1.1.\d/, output
+    end
+  end
+
+  test "logout" do
+    run_command("logout").tap do |output|
+      assert_match /docker logout on 1.1.1.\d/, output
+    end
+  end
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Registry.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+end

test/cli/server_test.rb

@@ -1,11 +1,30 @@
 require_relative "cli_test_case"
 
 class CliServerTest < CliTestCase
-  test "bootstrap" do
+  test "bootstrap already installed" do
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with(:docker, "-v", raise_on_non_zero_exit: false).returns(true).at_least_once
+
+    assert_equal "", run_command("bootstrap")
+  end
+
+  test "bootstrap install as non-root user" do
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with(:docker, "-v", raise_on_non_zero_exit: false).returns(false).at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with('[ "${EUID:-$(id -u)}" -eq 0 ]', raise_on_non_zero_exit: false).returns(false).at_least_once
+
+    assert_raise RuntimeError, "Docker is not installed on 1.1.1.1, 1.1.1.3, 1.1.1.4, 1.1.1.2 and can't be automatically intalled without having root access and the `curl` command available. Install Docker manually: https://docs.docker.com/engine/install/" do
+      run_command("bootstrap")
+    end
+  end
+
+  test "bootstrap install as root user" do
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with(:docker, "-v", raise_on_non_zero_exit: false).returns(false).at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with('[ "${EUID:-$(id -u)}" -eq 0 ]', raise_on_non_zero_exit: false).returns(true).at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:execute).with(:curl, "-fsSL", "https://get.docker.com", "|", :sh).at_least_once
+
     run_command("bootstrap").tap do |output|
-      assert_match /which curl/, output
-      assert_match /which docker/, output
-      assert_match /apt-get update -y && apt-get install curl docker.io -y/, output
+      ("1.1.1.1".."1.1.1.4").map do |host|
+        assert_match "Missing Docker on #{host}. Installing…", output
+      end
     end
   end
 

test/cli/traefik_test.rb

@@ -0,0 +1,86 @@
+require_relative "cli_test_case"
+
+class CliTraefikTest < CliTestCase
+  test "boot" do
+    run_command("boot").tap do |output|
+      assert_match "docker login", output
+      assert_match "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{Mrsk::Commands::Traefik::DEFAULT_IMAGE} --providers.docker --log.level=DEBUG", output
+    end
+  end
+
+  test "reboot" do
+    Mrsk::Cli::Traefik.any_instance.expects(:stop)
+    Mrsk::Cli::Traefik.any_instance.expects(:remove_container)
+    Mrsk::Cli::Traefik.any_instance.expects(:boot)
+
+    run_command("reboot")
+  end
+
+  test "start" do
+    run_command("start").tap do |output|
+      assert_match "docker container start traefik", output
+    end
+  end
+
+  test "stop" do
+    run_command("stop").tap do |output|
+      assert_match "docker container stop traefik", output
+    end
+  end
+
+  test "restart" do
+    Mrsk::Cli::Traefik.any_instance.expects(:stop)
+    Mrsk::Cli::Traefik.any_instance.expects(:start)
+
+    run_command("restart")
+  end
+
+  test "details" do
+    run_command("details").tap do |output|
+      assert_match "docker ps --filter name=^traefik$", output
+    end
+  end
+
+  test "logs" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:capture)
+      .with(:docker, :logs, "traefik", " --tail 100", "--timestamps", "2>&1")
+      .returns("Log entry")
+
+    run_command("logs").tap do |output|
+      assert_match "Traefik Host: 1.1.1.1", output
+      assert_match "Log entry", output
+    end
+  end
+
+  test "logs with follow" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.1 'docker logs traefik --timestamps --tail 10 --follow 2>&1'")
+
+    assert_match "docker logs traefik --timestamps --tail 10 --follow", run_command("logs", "--follow")
+  end
+
+  test "remove" do
+    Mrsk::Cli::Traefik.any_instance.expects(:stop)
+    Mrsk::Cli::Traefik.any_instance.expects(:remove_container)
+    Mrsk::Cli::Traefik.any_instance.expects(:remove_image)
+
+    run_command("remove")
+  end
+
+  test "remove_container" do
+    run_command("remove_container").tap do |output|
+      assert_match "docker container prune --force --filter label=org.opencontainers.image.title=Traefik", output
+    end
+  end
+
+  test "remove_image" do
+    run_command("remove_image").tap do |output|
+      assert_match "docker image prune --all --force --filter label=org.opencontainers.image.title=Traefik", output
+    end
+  end
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Traefik.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+end

test/commander_test.rb

@@ -2,38 +2,39 @@ require "test_helper"
 
 class CommanderTest < ActiveSupport::TestCase
   setup do
-    @mrsk = Mrsk::Commander.new config_file: Pathname.new(File.expand_path("fixtures/deploy_with_roles.yml", __dir__))
+    configure_with(:deploy_with_roles)
   end
 
   test "lazy configuration" do
     assert_equal Mrsk::Configuration, @mrsk.config.class
   end
 
-  test "commit hash as version" do
-    assert_equal `git rev-parse HEAD`.strip, @mrsk.config.version
-  end
-
-  test "commit hash as version but not in git" do
-    @mrsk.expects(:system).with("git rev-parse").returns(nil)
-    error = assert_raises(RuntimeError) { @mrsk.config }
-    assert_match /no git repository found/, error.message
-  end
-
   test "overwriting hosts" do
     assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3", "1.1.1.4" ], @mrsk.hosts
 
-    @mrsk.specific_hosts = [ "1.2.3.4", "1.2.3.5" ]
-    assert_equal [ "1.2.3.4", "1.2.3.5" ], @mrsk.hosts
+    @mrsk.specific_hosts = [ "1.1.1.1", "1.1.1.2" ]
+    assert_equal [ "1.1.1.1", "1.1.1.2" ], @mrsk.hosts
   end
 
-  test "overwriting hosts with roles" do
+  test "filtering hosts by filtering roles" do
     assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3", "1.1.1.4" ], @mrsk.hosts
 
-    @mrsk.specific_roles = [ "workers", "web" ]
-    assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3", "1.1.1.4" ], @mrsk.hosts
+    @mrsk.specific_roles = [ "web" ]
+    assert_equal [ "1.1.1.1", "1.1.1.2" ], @mrsk.hosts
+  end
+
+  test "filtering roles" do
+    assert_equal [ "web", "workers" ], @mrsk.roles.map(&:name)
 
     @mrsk.specific_roles = [ "workers" ]
-    assert_equal [ "1.1.1.3", "1.1.1.4" ], @mrsk.hosts
+    assert_equal [ "workers" ], @mrsk.roles.map(&:name)
+  end
+
+  test "filtering roles by filtering hosts" do
+    assert_equal [ "web", "workers" ], @mrsk.roles.map(&:name)
+
+    @mrsk.specific_hosts = [ "1.1.1.3" ]
+    assert_equal [ "workers" ], @mrsk.roles.map(&:name)
   end
 
   test "overwriting hosts with primary" do
@@ -44,7 +45,35 @@ class CommanderTest < ActiveSupport::TestCase
   end
 
   test "primary_host with specific hosts via role" do
-    @mrsk.specific_roles = "web"
-    assert_equal "1.1.1.1", @mrsk.primary_host
+    @mrsk.specific_roles = "workers"
+    assert_equal "1.1.1.3", @mrsk.primary_host
   end
+
+  test "roles_on" do
+    assert_equal [ "web" ], @mrsk.roles_on("1.1.1.1")
+    assert_equal [ "workers" ], @mrsk.roles_on("1.1.1.3")
+  end
+
+  test "default group strategy" do
+    assert_empty @mrsk.boot_strategy
+  end
+
+  test "specific limit group strategy" do
+    configure_with(:deploy_with_boot_strategy)
+
+    assert_equal({ in: :groups, limit: 3, wait: 2 }, @mrsk.boot_strategy)
+  end
+
+  test "percentage-based group strategy" do
+    configure_with(:deploy_with_precentage_boot_strategy)
+
+    assert_equal({ in: :groups, limit: 1, wait: 2 }, @mrsk.boot_strategy)
+  end
+
+  private
+    def configure_with(variant)
+      @mrsk = Mrsk::Commander.new.tap do |mrsk|
+        mrsk.configure config_file: Pathname.new(File.expand_path("fixtures/#{variant}.yml", __dir__))
+      end
+    end
 end

test/commands/accessory_test.rb

@@ -3,11 +3,11 @@ require "test_helper"
 class CommandsAccessoryTest < ActiveSupport::TestCase
   setup do
     @config = {
-      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" },
+      service: "app", image: "dhh/app", registry: { "server" => "private.registry", "username" => "dhh", "password" => "secret" },
       servers: [ "1.1.1.1" ],
       accessories: {
         "mysql" => {
-          "image" => "mysql:8.0",
+          "image" => "private.registry/mysql:8.0",
           "host" => "1.1.1.5",
           "port" => "3306",
           "env" => {
@@ -32,14 +32,14 @@ class CommandsAccessoryTest < ActiveSupport::TestCase
           "volumes" => [
             "/var/lib/redis:/data"
           ]
+        },
+        "busybox" => {
+          "image" => "busybox:latest",
+          "host" => "1.1.1.7"
         }
       }
     }
 
-    @config = Mrsk::Configuration.new(@config)
-    @mysql  = Mrsk::Commands::Accessory.new(@config, name: :mysql)
-    @redis  = Mrsk::Commands::Accessory.new(@config, name: :redis)
-
     ENV["MYSQL_ROOT_PASSWORD"] = "secret123"
   end
 
@@ -49,56 +49,68 @@ class CommandsAccessoryTest < ActiveSupport::TestCase
 
   test "run" do
     assert_equal \
-      "docker run --name app-mysql --detach --restart unless-stopped --log-opt max-size=10m --publish 3306:3306 -e MYSQL_ROOT_PASSWORD=\"secret123\" -e MYSQL_ROOT_HOST=\"%\" --label service=\"app-mysql\" mysql:8.0",
-      @mysql.run.join(" ")
+      "docker run --name app-mysql --detach --restart unless-stopped --log-opt max-size=\"10m\" --publish 3306:3306 -e MYSQL_ROOT_PASSWORD=\"secret123\" -e MYSQL_ROOT_HOST=\"%\" --label service=\"app-mysql\" private.registry/mysql:8.0",
+      new_command(:mysql).run.join(" ")
 
     assert_equal \
-      "docker run --name app-redis --detach --restart unless-stopped --log-opt max-size=10m --publish 6379:6379 -e SOMETHING=\"else\" --volume /var/lib/redis:/data --label service=\"app-redis\" --label cache=\"true\" redis:latest",
-      @redis.run.join(" ")
+      "docker run --name app-redis --detach --restart unless-stopped --log-opt max-size=\"10m\" --publish 6379:6379 -e SOMETHING=\"else\" --volume /var/lib/redis:/data --label service=\"app-redis\" --label cache=\"true\" redis:latest",
+      new_command(:redis).run.join(" ")
+
+    assert_equal \
+      "docker run --name app-busybox --detach --restart unless-stopped --log-opt max-size=\"10m\" --label service=\"app-busybox\" busybox:latest",
+      new_command(:busybox).run.join(" ")
+  end
+
+  test "run with logging config" do
+    @config[:logging] = { "driver" => "local", "options" => { "max-size" => "100m", "max-file" => "3" } }
+
+    assert_equal \
+      "docker run --name app-busybox --detach --restart unless-stopped --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" --label service=\"app-busybox\" busybox:latest",
+      new_command(:busybox).run.join(" ")
   end
 
   test "start" do
     assert_equal \
       "docker container start app-mysql",
-      @mysql.start.join(" ")
+      new_command(:mysql).start.join(" ")
   end
 
   test "stop" do
     assert_equal \
       "docker container stop app-mysql",
-      @mysql.stop.join(" ")
+      new_command(:mysql).stop.join(" ")
   end
 
   test "info" do
     assert_equal \
       "docker ps --filter label=service=app-mysql",
-      @mysql.info.join(" ")
+      new_command(:mysql).info.join(" ")
   end
 
 
   test "execute in new container" do
     assert_equal \
-      "docker run --rm -e MYSQL_ROOT_PASSWORD=\"secret123\" -e MYSQL_ROOT_HOST=\"%\" mysql:8.0 mysql -u root",
-      @mysql.execute_in_new_container("mysql", "-u", "root").join(" ")
+      "docker run --rm -e MYSQL_ROOT_PASSWORD=\"secret123\" -e MYSQL_ROOT_HOST=\"%\" private.registry/mysql:8.0 mysql -u root",
+      new_command(:mysql).execute_in_new_container("mysql", "-u", "root").join(" ")
   end
 
   test "execute in existing container" do
     assert_equal \
       "docker exec app-mysql mysql -u root",
-      @mysql.execute_in_existing_container("mysql", "-u", "root").join(" ")
+      new_command(:mysql).execute_in_existing_container("mysql", "-u", "root").join(" ")
   end
 
   test "execute in new container over ssh" do
-    @mysql.stub(:run_over_ssh, ->(cmd) { cmd.join(" ") }) do
-      assert_match %r|docker run -it --rm -e MYSQL_ROOT_PASSWORD=\"secret123\" -e MYSQL_ROOT_HOST=\"%\" mysql:8.0 mysql -u root|,
-        @mysql.execute_in_new_container_over_ssh("mysql", "-u", "root")
+    new_command(:mysql).stub(:run_over_ssh, ->(cmd) { cmd.join(" ") }) do
+      assert_match %r|docker run -it --rm -e MYSQL_ROOT_PASSWORD=\"secret123\" -e MYSQL_ROOT_HOST=\"%\" private.registry/mysql:8.0 mysql -u root|,
+        new_command(:mysql).execute_in_new_container_over_ssh("mysql", "-u", "root")
     end
   end
 
   test "execute in existing container over ssh" do
-    @mysql.stub(:run_over_ssh, ->(cmd) { cmd.join(" ") }) do
+    new_command(:mysql).stub(:run_over_ssh, ->(cmd) { cmd.join(" ") }) do
       assert_match %r|docker exec -it app-mysql mysql -u root|,
-        @mysql.execute_in_existing_container_over_ssh("mysql", "-u", "root")
+        new_command(:mysql).execute_in_existing_container_over_ssh("mysql", "-u", "root")
     end
   end
 
@@ -107,28 +119,33 @@ class CommandsAccessoryTest < ActiveSupport::TestCase
   test "logs" do
     assert_equal \
       "docker logs app-mysql --timestamps 2>&1",
-      @mysql.logs.join(" ")
+      new_command(:mysql).logs.join(" ")
 
     assert_equal \
       "docker logs app-mysql  --since 5m  --tail 100 --timestamps 2>&1 | grep 'thing'",
-      @mysql.logs(since: "5m", lines: 100, grep: "thing").join(" ")
+      new_command(:mysql).logs(since: "5m", lines: 100, grep: "thing").join(" ")
   end
 
   test "follow logs" do
     assert_equal \
       "ssh -t root@1.1.1.5 'docker logs app-mysql --timestamps --tail 10 --follow 2>&1'",
-      @mysql.follow_logs
+      new_command(:mysql).follow_logs
   end
 
   test "remove container" do
     assert_equal \
       "docker container prune --force --filter label=service=app-mysql",
-      @mysql.remove_container.join(" ")
+      new_command(:mysql).remove_container.join(" ")
   end
 
   test "remove image" do
     assert_equal \
-      "docker image prune --all --force --filter label=service=app-mysql",
-      @mysql.remove_image.join(" ")
+      "docker image rm --force private.registry/mysql:8.0",
+      new_command(:mysql).remove_image.join(" ")
   end
+
+  private
+    def new_command(accessory)
+      Mrsk::Commands::Accessory.new(Mrsk::Configuration.new(@config), name: accessory)
+    end
 end

test/commands/app_test.rb

@@ -5,7 +5,6 @@ class CommandsAppTest < ActiveSupport::TestCase
     ENV["RAILS_MASTER_KEY"] = "456"
 
     @config = { service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ], env: { "secret" => [ "RAILS_MASTER_KEY" ] } }
-    @app = Mrsk::Commands::App.new Mrsk::Configuration.new(@config).tap { |c| c.version = "999" }
   end
 
   teardown do
@@ -14,165 +13,294 @@ class CommandsAppTest < ActiveSupport::TestCase
 
   test "run" do
     assert_equal \
-      "docker run --detach --restart unless-stopped --log-opt max-size=10m --name app-999 -e RAILS_MASTER_KEY=\"456\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.services.app.loadbalancer.healthcheck.path=\"/up\" --label traefik.http.services.app.loadbalancer.healthcheck.interval=\"1s\" --label traefik.http.middlewares.app.retry.attempts=\"5\" --label traefik.http.middlewares.app.retry.initialinterval=\"500ms\" dhh/app:999",
-      @app.run.join(" ")
+      "docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
+      new_command.run.join(" ")
   end
 
   test "run with volumes" do
     @config[:volumes] = ["/local/path:/container/path" ]
 
     assert_equal \
-      "docker run --detach --restart unless-stopped --log-opt max-size=10m --name app-999 -e RAILS_MASTER_KEY=\"456\" --volume /local/path:/container/path --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.services.app.loadbalancer.healthcheck.path=\"/up\" --label traefik.http.services.app.loadbalancer.healthcheck.interval=\"1s\" --label traefik.http.middlewares.app.retry.attempts=\"5\" --label traefik.http.middlewares.app.retry.initialinterval=\"500ms\" dhh/app:999",
-      @app.run.join(" ")
+      "docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --volume /local/path:/container/path --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
+      new_command.run.join(" ")
   end
 
   test "run with custom healthcheck path" do
     @config[:healthcheck] = { "path" => "/healthz" }
 
     assert_equal \
-      "docker run --detach --restart unless-stopped --log-opt max-size=10m --name app-999 -e RAILS_MASTER_KEY=\"456\" --label service=\"app\" --label role=\"web\" --label traefik.http.routers.app.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.services.app.loadbalancer.healthcheck.path=\"/healthz\" --label traefik.http.services.app.loadbalancer.healthcheck.interval=\"1s\" --label traefik.http.middlewares.app.retry.attempts=\"5\" --label traefik.http.middlewares.app.retry.initialinterval=\"500ms\" dhh/app:999",
-      @app.run.join(" ")
+      "docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/healthz || exit 1\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
+      new_command.run.join(" ")
+  end
+
+  test "run with custom healthcheck command" do
+    @config[:healthcheck] = { "cmd" => "/bin/up" }
+
+    assert_equal \
+      "docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"/bin/up\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
+      new_command.run.join(" ")
+  end
+
+  test "run with role-specific healthcheck options" do
+    @config[:servers] = { "web" => { "hosts" => [ "1.1.1.1" ], "healthcheck" => { "cmd" => "/bin/healthy" } } }
+
+    assert_equal \
+      "docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"/bin/healthy\" --health-interval \"1s\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
+      new_command.run.join(" ")
   end
 
   test "run with custom options" do
     @config[:servers] = { "web" => [ "1.1.1.1" ], "jobs" => { "hosts" => [ "1.1.1.2" ], "cmd" => "bin/jobs", "options" => { "mount" => "somewhere", "cap-add" => true } } }
-    @app = Mrsk::Commands::App.new Mrsk::Configuration.new(@config).tap { |c| c.version = "999" }
+    assert_equal \
+      "docker run --detach --restart unless-stopped --name app-jobs-999 -e MRSK_CONTAINER_NAME=\"app-jobs-999\" -e RAILS_MASTER_KEY=\"456\" --log-opt max-size=\"10m\" --label service=\"app\" --label role=\"jobs\" --mount \"somewhere\" --cap-add dhh/app:999 bin/jobs",
+      new_command(role: "jobs").run.join(" ")
+  end
+
+  test "run with logging config" do
+    @config[:logging] = { "driver" => "local", "options" => { "max-size" => "100m", "max-file" => "3" } }
 
     assert_equal \
-      "docker run --detach --restart unless-stopped --log-opt max-size=10m --name app-999 -e RAILS_MASTER_KEY=\"456\" --label service=\"app\" --label role=\"jobs\" --mount \"somewhere\" --cap-add dhh/app:999 bin/jobs",
-      @app.run(role: :jobs).join(" ")
+      "docker run --detach --restart unless-stopped --name app-web-999 -e MRSK_CONTAINER_NAME=\"app-web-999\" -e RAILS_MASTER_KEY=\"456\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" --label service=\"app\" --label role=\"web\" --label traefik.http.services.app-web.loadbalancer.server.scheme=\"http\" --label traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\" --label traefik.http.middlewares.app-web-retry.retry.attempts=\"5\" --label traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\" --label traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\" dhh/app:999",
+      new_command.run.join(" ")
   end
 
   test "start" do
     assert_equal \
-      "docker start app-999",
-      @app.start.join(" ")
+      "docker start app-web-999",
+      new_command.start.join(" ")
+  end
+
+  test "start with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker start app-web-staging-999",
+      new_command.start.join(" ")
   end
 
   test "stop" do
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker stop",
-      @app.stop.join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker stop",
+      new_command.stop.join(" ")
+  end
+
+  test "stop with custom stop wait time" do
+    @config[:stop_wait_time] = 30
+    assert_equal \
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker stop -t 30",
+      new_command.stop.join(" ")
+  end
+
+  test "stop with version" do
+    assert_equal \
+      "docker container ls --all --filter name=^app-web-123$ --quiet | xargs docker stop",
+      new_command.stop(version: "123").join(" ")
   end
 
   test "info" do
     assert_equal \
-      "docker ps --filter label=service=app",
-      @app.info.join(" ")
+      "docker ps --filter label=service=app --filter label=role=web",
+      new_command.info.join(" ")
+  end
+
+  test "info with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker ps --filter label=service=app --filter label=destination=staging --filter label=role=web",
+      new_command.info.join(" ")
   end
 
 
   test "logs" do
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker logs 2>&1",
-      @app.logs.join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs 2>&1",
+      new_command.logs.join(" ")
 
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker logs --since 5m 2>&1",
-      @app.logs(since: "5m").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --since 5m 2>&1",
+      new_command.logs(since: "5m").join(" ")
 
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker logs --tail 100 2>&1",
-      @app.logs(lines: "100").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --tail 100 2>&1",
+      new_command.logs(lines: "100").join(" ")
 
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker logs --since 5m --tail 100 2>&1",
-      @app.logs(since: "5m", lines: "100").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --since 5m --tail 100 2>&1",
+      new_command.logs(since: "5m", lines: "100").join(" ")
 
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker logs 2>&1 | grep 'my-id'",
-      @app.logs(grep: "my-id").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs 2>&1 | grep 'my-id'",
+      new_command.logs(grep: "my-id").join(" ")
 
     assert_equal \
-      "docker ps --quiet --filter label=service=app | xargs docker logs --since 5m 2>&1 | grep 'my-id'",
-      @app.logs(since: "5m", grep: "my-id").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --since 5m 2>&1 | grep 'my-id'",
+      new_command.logs(since: "5m", grep: "my-id").join(" ")
   end
 
   test "follow logs" do
-    @app.stub(:run_over_ssh, ->(cmd, host:) { cmd.join(" ") }) do
-      assert_equal \
-        "docker ps --quiet --filter label=service=app | xargs docker logs --timestamps --tail 10 --follow 2>&1",
-        @app.follow_logs(host: "app-1")
+    assert_match \
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1",
+      new_command.follow_logs(host: "app-1")
 
-      assert_equal \
-        "docker ps --quiet --filter label=service=app | xargs docker logs --timestamps --tail 10 --follow 2>&1 | grep \"Completed\"",
-        @app.follow_logs(host: "app-1", grep: "Completed")
-    end
+    assert_match \
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1 | grep \"Completed\"",
+      new_command.follow_logs(host: "app-1", grep: "Completed")
   end
 
 
   test "execute in new container" do
     assert_equal \
       "docker run --rm -e RAILS_MASTER_KEY=\"456\" dhh/app:999 bin/rails db:setup",
-      @app.execute_in_new_container("bin/rails", "db:setup").join(" ")
+      new_command.execute_in_new_container("bin/rails", "db:setup").join(" ")
   end
 
   test "execute in existing container" do
     assert_equal \
-      "docker exec app-999 bin/rails db:setup",
-      @app.execute_in_existing_container("bin/rails", "db:setup").join(" ")
+      "docker exec app-web-999 bin/rails db:setup",
+      new_command.execute_in_existing_container("bin/rails", "db:setup").join(" ")
   end
 
   test "execute in new container over ssh" do
-    @app.stub(:run_over_ssh, ->(cmd, host:) { cmd.join(" ") }) do
-      assert_match %r|docker run -it --rm -e RAILS_MASTER_KEY=\"456\" dhh/app:999 bin/rails c|,
-        @app.execute_in_new_container_over_ssh("bin/rails", "c", host: "app-1")
-    end
+    assert_match %r|docker run -it --rm -e RAILS_MASTER_KEY=\"456\" dhh/app:999 bin/rails c|,
+      new_command.execute_in_new_container_over_ssh("bin/rails", "c", host: "app-1")
   end
 
   test "execute in existing container over ssh" do
-    @app.stub(:run_over_ssh, ->(cmd, host:) { cmd.join(" ") }) do
-      assert_match %r|docker exec -it app-999 bin/rails c|,
-        @app.execute_in_existing_container_over_ssh("bin/rails", "c", host: "app-1")
-    end
+    assert_match %r|docker exec -it app-web-999 bin/rails c|,
+      new_command.execute_in_existing_container_over_ssh("bin/rails", "c", host: "app-1")
   end
 
   test "run over ssh" do
-    assert_equal "ssh -t root@1.1.1.1 'ls'", @app.run_over_ssh("ls", host: "1.1.1.1")
+    assert_equal "ssh -t root@1.1.1.1 'ls'", new_command.run_over_ssh("ls", host: "1.1.1.1")
   end
 
   test "run over ssh with custom user" do
-    @app = Mrsk::Commands::App.new Mrsk::Configuration.new(@config.tap { |c| c[:ssh] = { "user" => "app" } })
-    assert_equal "ssh -t app@1.1.1.1 'ls'", @app.run_over_ssh("ls", host: "1.1.1.1")
+    @config[:ssh] = { "user" => "app" }
+    assert_equal "ssh -t app@1.1.1.1 'ls'", new_command.run_over_ssh("ls", host: "1.1.1.1")
   end
 
   test "run over ssh with proxy" do
-    @app = Mrsk::Commands::App.new Mrsk::Configuration.new(@config.tap { |c| c[:ssh] = { "proxy" => "2.2.2.2" } })
-    assert_equal "ssh -J root@2.2.2.2 -t root@1.1.1.1 'ls'", @app.run_over_ssh("ls", host: "1.1.1.1")
+    @config[:ssh] = { "proxy" => "2.2.2.2" }
+    assert_equal "ssh -J root@2.2.2.2 -t root@1.1.1.1 'ls'", new_command.run_over_ssh("ls", host: "1.1.1.1")
   end
 
   test "run over ssh with proxy user" do
-    @app = Mrsk::Commands::App.new Mrsk::Configuration.new(@config.tap { |c| c[:ssh] = { "proxy" => "app@2.2.2.2" } })
-    assert_equal "ssh -J app@2.2.2.2 -t root@1.1.1.1 'ls'", @app.run_over_ssh("ls", host: "1.1.1.1")
+    @config[:ssh] = { "proxy" => "app@2.2.2.2" }
+    assert_equal "ssh -J app@2.2.2.2 -t root@1.1.1.1 'ls'", new_command.run_over_ssh("ls", host: "1.1.1.1")
   end
 
   test "run over ssh with custom user with proxy" do
-    @app = Mrsk::Commands::App.new Mrsk::Configuration.new(@config.tap { |c| c[:ssh] = { "user" => "app", "proxy" => "2.2.2.2" } })
-    assert_equal "ssh -J root@2.2.2.2 -t app@1.1.1.1 'ls'", @app.run_over_ssh("ls", host: "1.1.1.1")
+    @config[:ssh] = { "user" => "app", "proxy" => "2.2.2.2" }
+    assert_equal "ssh -J root@2.2.2.2 -t app@1.1.1.1 'ls'", new_command.run_over_ssh("ls", host: "1.1.1.1")
   end
 
 
-  test "current_container_id" do
+  test "current_running_container_id" do
     assert_equal \
-      "docker ps --quiet --filter label=service=app",
-      @app.current_container_id.join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --latest",
+      new_command.current_running_container_id.join(" ")
+  end
+
+  test "current_running_container_id with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker ps --quiet --filter label=service=app --filter label=destination=staging --filter label=role=web --filter status=running --latest",
+      new_command.current_running_container_id.join(" ")
   end
 
   test "container_id_for" do
     assert_equal \
-      "docker container ls --all --filter name=app-999 --quiet",
-      @app.container_id_for(container_name: "app-999").join(" ")
+      "docker container ls --all --filter name=^app-999$ --quiet",
+      new_command.container_id_for(container_name: "app-999").join(" ")
   end
 
   test "current_running_version" do
     assert_equal \
-      "docker ps --filter label=service=app --format \"{{.Names}}\" | sed 's/-/\\n/g' | tail -n 1",
-      @app.current_running_version.join(" ")
+      "docker ps --filter label=service=app --filter label=role=web --filter status=running --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-",
+      new_command.current_running_version.join(" ")
   end
 
-  test "most_recent_version_from_available_images" do
+  test "list_versions" do
     assert_equal \
-      "docker image ls --format \"{{.Tag}}\" dhh/app | head -n 1",
-      @app.most_recent_version_from_available_images.join(" ")
+      "docker ps --filter label=service=app --filter label=role=web --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-",
+      new_command.list_versions.join(" ")
+
+    assert_equal \
+      "docker ps --filter label=service=app --filter label=role=web --filter status=running --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-",
+      new_command.list_versions("--latest", status: :running).join(" ")
   end
+
+  test "list_containers" do
+    assert_equal \
+      "docker container ls --all --filter label=service=app --filter label=role=web",
+      new_command.list_containers.join(" ")
+  end
+
+  test "list_containers with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker container ls --all --filter label=service=app --filter label=destination=staging --filter label=role=web",
+      new_command.list_containers.join(" ")
+  end
+
+  test "list_container_names" do
+    assert_equal \
+      "docker container ls --all --filter label=service=app --filter label=role=web --format '{{ .Names }}'",
+      new_command.list_container_names.join(" ")
+  end
+
+  test "remove_container" do
+    assert_equal \
+      "docker container ls --all --filter name=^app-web-999$ --quiet | xargs docker container rm",
+      new_command.remove_container(version: "999").join(" ")
+  end
+
+  test "remove_container with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker container ls --all --filter name=^app-web-staging-999$ --quiet | xargs docker container rm",
+      new_command.remove_container(version: "999").join(" ")
+  end
+
+  test "remove_containers" do
+    assert_equal \
+      "docker container prune --force --filter label=service=app --filter label=role=web",
+      new_command.remove_containers.join(" ")
+  end
+
+  test "remove_containers with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker container prune --force --filter label=service=app --filter label=destination=staging --filter label=role=web",
+      new_command.remove_containers.join(" ")
+  end
+
+  test "list_images" do
+    assert_equal \
+      "docker image ls dhh/app",
+      new_command.list_images.join(" ")
+  end
+
+  test "remove_images" do
+    assert_equal \
+      "docker image prune --all --force --filter label=service=app --filter label=role=web",
+      new_command.remove_images.join(" ")
+  end
+
+  test "remove_images with destination" do
+    @destination = "staging"
+    assert_equal \
+      "docker image prune --all --force --filter label=service=app --filter label=destination=staging --filter label=role=web",
+      new_command.remove_images.join(" ")
+  end
+
+  test "tag_current_as_latest" do
+    assert_equal \
+      "docker tag dhh/app:999 dhh/app:latest",
+      new_command.tag_current_as_latest.join(" ")
+  end
+
+  private
+    def new_command(role: "web")
+      Mrsk::Commands::App.new(Mrsk::Configuration.new(@config, destination: @destination, version: "999"), role: role)
+    end
 end

test/commands/auditor_test.rb

@@ -6,22 +6,65 @@ class CommandsAuditorTest < ActiveSupport::TestCase
       service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ],
       audit_broadcast_cmd: "bin/audit_broadcast"
     }
+
+    @auditor = new_command
   end
 
   test "record" do
-    assert_match \
-      /echo '.* app removed container' >> mrsk-app-audit.log/,
-      new_command.record("app removed container").join(" ")
+    assert_equal [
+      :echo,
+      "[#{@auditor.details[:recorded_at]}]", "[#{@auditor.details[:performer]}]",
+      "app removed container",
+      ">>", "mrsk-app-audit.log"
+    ], @auditor.record("app removed container")
+  end
+
+  test "record with destination" do
+    new_command(destination: "staging").tap do |auditor|
+      assert_equal [
+        :echo,
+        "[#{auditor.details[:recorded_at]}]", "[#{auditor.details[:performer]}]", "[#{auditor.details[:destination]}]",
+        "app removed container",
+        ">>", "mrsk-app-staging-audit.log"
+      ], auditor.record("app removed container")
+    end
+  end
+
+  test "record with command details" do
+    new_command(role: "web").tap do |auditor|
+      assert_equal [
+        :echo,
+        "[#{auditor.details[:recorded_at]}]", "[#{auditor.details[:performer]}]", "[#{auditor.details[:role]}]",
+        "app removed container",
+        ">>", "mrsk-app-audit.log"
+      ], auditor.record("app removed container")
+    end
+  end
+
+  test "record with arg details" do
+    assert_equal [
+      :echo,
+      "[#{@auditor.details[:recorded_at]}]", "[#{@auditor.details[:performer]}]", "[value]",
+      "app removed container",
+      ">>", "mrsk-app-audit.log"
+    ], @auditor.record("app removed container", detail: "value")
   end
 
   test "broadcast" do
-    assert_match \
-      /bin\/audit_broadcast '\[.*\] app removed container'/,
-      new_command.broadcast("app removed container").join(" ")
+    assert_equal [
+      "bin/audit_broadcast",
+      "'[#{@auditor.details[:performer]}] [value] app removed container'",
+      env: {
+        "MRSK_RECORDED_AT" => @auditor.details[:recorded_at],
+        "MRSK_PERFORMER" => @auditor.details[:performer],
+        "MRSK_EVENT" => "app removed container",
+        "MRSK_DETAIL" => "value"
+      }
+    ], @auditor.broadcast("app removed container", detail: "value")
   end
 
   private
-    def new_command
-      Mrsk::Commands::Auditor.new(Mrsk::Configuration.new(@config, version: "123"))
+    def new_command(destination: nil, **details)
+      Mrsk::Commands::Auditor.new(Mrsk::Configuration.new(@config, destination: destination, version: "123"), **details)
     end
 end

test/commands/builder_test.rb

@@ -17,7 +17,7 @@ class CommandsBuilderTest < ActiveSupport::TestCase
     builder = new_builder_command(builder: { "multiarch" => false })
     assert_equal "native", builder.name
     assert_equal \
-      "docker build -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --file Dockerfile . && docker push dhh/app:123",
+      "docker build -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --file Dockerfile . && docker push dhh/app:123 && docker push dhh/app:latest",
       builder.push.join(" ")
   end
 
@@ -52,12 +52,21 @@ class CommandsBuilderTest < ActiveSupport::TestCase
   end
 
   test "build dockerfile" do
+    Pathname.any_instance.expects(:exist?).returns(true).once
     builder = new_builder_command(builder: { "dockerfile" => "Dockerfile.xyz" })
     assert_equal \
       "-t dhh/app:123 -t dhh/app:latest --label service=\"app\" --file Dockerfile.xyz",
       builder.target.build_options.join(" ")
   end
 
+  test "missing dockerfile" do
+    Pathname.any_instance.expects(:exist?).returns(false).once
+    builder = new_builder_command(builder: { "dockerfile" => "Dockerfile.xyz" })
+    assert_raises(Mrsk::Commands::Builder::Base::BuilderError) do
+      builder.target.build_options.join(" ")
+    end
+  end
+
   test "build context" do
     builder = new_builder_command(builder: { "context" => ".." })
     assert_equal \
@@ -68,7 +77,7 @@ class CommandsBuilderTest < ActiveSupport::TestCase
   test "native push with build args" do
     builder = new_builder_command(builder: { "multiarch" => false, "args" => { "a" => 1, "b" => 2 } })
     assert_equal \
-      "docker build -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --build-arg a=\"1\" --build-arg b=\"2\" --file Dockerfile . && docker push dhh/app:123",
+      "docker build -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --build-arg a=\"1\" --build-arg b=\"2\" --file Dockerfile . && docker push dhh/app:123 && docker push dhh/app:latest",
       builder.push.join(" ")
   end
 
@@ -82,7 +91,7 @@ class CommandsBuilderTest < ActiveSupport::TestCase
   test "native push with with build secrets" do
     builder = new_builder_command(builder: { "multiarch" => false, "secrets" => [ "a", "b" ] })
     assert_equal \
-      "docker build -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --secret id=\"a\" --secret id=\"b\" --file Dockerfile . && docker push dhh/app:123",
+      "docker build -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --secret id=\"a\" --secret id=\"b\" --file Dockerfile . && docker push dhh/app:123 && docker push dhh/app:latest",
       builder.push.join(" ")
   end
 

test/commands/docker_test.rb

@@ -0,0 +1,26 @@
+require "test_helper"
+
+class CommandsDockerTest < ActiveSupport::TestCase
+  setup do
+    @config = {
+      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ]
+    }
+    @docker = Mrsk::Commands::Docker.new(Mrsk::Configuration.new(@config))
+  end
+
+  test "install" do
+    assert_equal "curl -fsSL https://get.docker.com | sh", @docker.install.join(" ")
+  end
+
+  test "installed?" do
+    assert_equal "docker -v", @docker.installed?.join(" ")
+  end
+
+  test "running?" do
+    assert_equal "docker version", @docker.running?.join(" ")
+  end
+
+  test "superuser?" do
+    assert_equal '[ "${EUID:-$(id -u)}" -eq 0 ]', @docker.superuser?.join(" ")
+  end
+end

test/commands/healthcheck_test.rb

@@ -10,7 +10,7 @@ class CommandsHealthcheckTest < ActiveSupport::TestCase
 
   test "run" do
     assert_equal \
-      "docker run --detach --name healthcheck-app-123 --publish 3999:3000 --label service=healthcheck-app dhh/app:123",
+      "docker run --detach --name healthcheck-app-123 --publish 3999:3000 --label service=healthcheck-app -e MRSK_CONTAINER_NAME=\"healthcheck-app\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" dhh/app:123",
       new_command.run.join(" ")
   end
 
@@ -18,38 +18,89 @@ class CommandsHealthcheckTest < ActiveSupport::TestCase
     @config[:healthcheck] = { "port" => 3001 }
 
     assert_equal \
-      "docker run --detach --name healthcheck-app-123 --publish 3999:3001 --label service=healthcheck-app dhh/app:123",
+      "docker run --detach --name healthcheck-app-123 --publish 3999:3001 --label service=healthcheck-app -e MRSK_CONTAINER_NAME=\"healthcheck-app\" --health-cmd \"curl -f http://localhost:3001/up || exit 1\" --health-interval \"1s\" dhh/app:123",
       new_command.run.join(" ")
   end
 
-  test "curl" do
+  test "run with destination" do
+    @destination = "staging"
+
     assert_equal \
-      "curl --silent --output /dev/null --write-out '%{http_code}' --max-time 2 http://localhost:3999/up",
-      new_command.curl.join(" ")
+      "docker run --detach --name healthcheck-app-staging-123 --publish 3999:3000 --label service=healthcheck-app-staging -e MRSK_CONTAINER_NAME=\"healthcheck-app-staging\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" dhh/app:123",
+      new_command.run.join(" ")
   end
 
-  test "curl with custom path" do
-    @config[:healthcheck] = { "path" => "/healthz" }
+  test "run with custom healthcheck" do
+    @config[:healthcheck] = { "cmd" => "/bin/up" }
 
     assert_equal \
-      "curl --silent --output /dev/null --write-out '%{http_code}' --max-time 2 http://localhost:3999/healthz",
-      new_command.curl.join(" ")
+      "docker run --detach --name healthcheck-app-123 --publish 3999:3000 --label service=healthcheck-app -e MRSK_CONTAINER_NAME=\"healthcheck-app\" --health-cmd \"/bin/up\" --health-interval \"1s\" dhh/app:123",
+      new_command.run.join(" ")
+  end
+
+  test "run with custom options" do
+    @config[:servers] = { "web" => { "hosts" => [ "1.1.1.1" ], "options" => { "mount" => "somewhere" } } }
+    assert_equal \
+      "docker run --detach --name healthcheck-app-123 --publish 3999:3000 --label service=healthcheck-app -e MRSK_CONTAINER_NAME=\"healthcheck-app\" --health-cmd \"curl -f http://localhost:3000/up || exit 1\" --health-interval \"1s\" --mount \"somewhere\" dhh/app:123",
+      new_command.run.join(" ")
+  end
+
+  test "status" do
+    assert_equal \
+      "docker container ls --all --filter name=^healthcheck-app-123$ --quiet | xargs docker inspect --format '{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'",
+      new_command.status.join(" ")
+  end
+
+  test "container_health_log" do
+    assert_equal \
+      "docker container ls --all --filter name=^healthcheck-app-123$ --quiet | xargs docker inspect --format '{{json .State.Health}}'",
+      new_command.container_health_log.join(" ")
   end
 
   test "stop" do
     assert_equal \
-      "docker container ls --all --filter name=healthcheck-app --quiet | xargs docker stop",
+      "docker container ls --all --filter name=^healthcheck-app-123$ --quiet | xargs docker stop",
+      new_command.stop.join(" ")
+  end
+
+  test "stop with destination" do
+    @destination = "staging"
+
+    assert_equal \
+      "docker container ls --all --filter name=^healthcheck-app-staging-123$ --quiet | xargs docker stop",
       new_command.stop.join(" ")
   end
 
   test "remove" do
     assert_equal \
-      "docker container ls --all --filter name=healthcheck-app --quiet | xargs docker container rm",
+      "docker container ls --all --filter name=^healthcheck-app-123$ --quiet | xargs docker container rm",
       new_command.remove.join(" ")
   end
 
+  test "remove with destination" do
+    @destination = "staging"
+
+    assert_equal \
+      "docker container ls --all --filter name=^healthcheck-app-staging-123$ --quiet | xargs docker container rm",
+      new_command.remove.join(" ")
+  end
+
+  test "logs" do
+    assert_equal \
+      "docker container ls --all --filter name=^healthcheck-app-123$ --quiet | xargs docker logs --tail 50 2>&1",
+      new_command.logs.join(" ")
+  end
+
+  test "logs with destination" do
+    @destination = "staging"
+
+    assert_equal \
+      "docker container ls --all --filter name=^healthcheck-app-staging-123$ --quiet | xargs docker logs --tail 50 2>&1",
+      new_command.logs.join(" ")
+  end
+
   private
     def new_command
-      Mrsk::Commands::Healthcheck.new(Mrsk::Configuration.new(@config, version: "123"))
+      Mrsk::Commands::Healthcheck.new(Mrsk::Configuration.new(@config, destination: @destination, version: "123"))
     end
 end

test/commands/lock_test.rb

@@ -0,0 +1,33 @@
+require "test_helper"
+
+class CommandsLockTest < ActiveSupport::TestCase
+  setup do
+    @config = {
+      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ],
+      traefik: { "args" => { "accesslog.format" => "json", "metrics.prometheus.buckets" => "0.1,0.3,1.2,5.0" } }
+    }
+  end
+
+  test "status" do
+    assert_equal \
+      "stat mrsk_lock > /dev/null && cat mrsk_lock/details | base64 -d",
+      new_command.status.join(" ")
+  end
+
+  test "acquire" do
+    assert_match \
+      /mkdir mrsk_lock && echo ".*" > mrsk_lock\/details/m,
+      new_command.acquire("Hello", "123").join(" ")
+  end
+
+  test "release" do
+    assert_match \
+      "rm mrsk_lock/details && rm -r mrsk_lock",
+      new_command.release.join(" ")
+  end
+
+  private
+    def new_command
+      Mrsk::Commands::Lock.new(Mrsk::Configuration.new(@config, version: "123"))
+    end
+end

test/commands/prune_test.rb

@@ -10,13 +10,13 @@ class CommandsPruneTest < ActiveSupport::TestCase
 
   test "images" do
     assert_equal \
-      "docker image prune --all --force --filter label=service=app --filter until=168h",
+      "docker image prune --force --filter label=service=app --filter dangling=true",
       new_command.images.join(" ")
   end
 
   test "containers" do
     assert_equal \
-      "docker container prune --force --filter label=service=app --filter until=72h",
+      "docker ps -q -a --filter label=service=app --filter status=created --filter status=exited --filter status=dead | tail -n +6 | while read container_id; do docker rm $container_id; done",
       new_command.containers.join(" ")
   end
 

test/commands/traefik_test.rb

@@ -2,20 +2,66 @@ require "test_helper"
 
 class CommandsTraefikTest < ActiveSupport::TestCase
   setup do
+    @image = "traefik:test"
+
     @config = {
       service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ],
-      traefik: { "args" => { "accesslog.format" => "json", "metrics.prometheus.buckets" => "0.1,0.3,1.2,5.0" } }
+      traefik: { "image" => @image, "args" => { "accesslog.format" => "json", "api.insecure" => true, "metrics.prometheus.buckets" => "0.1,0.3,1.2,5.0" } }
     }
   end
 
   test "run" do
     assert_equal \
-      "docker run --name traefik --detach --restart unless-stopped --log-opt max-size=10m --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock traefik --providers.docker --log.level=DEBUG --accesslog.format \"json\" --metrics.prometheus.buckets \"0.1,0.3,1.2,5.0\"",
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
       new_command.run.join(" ")
 
     @config[:traefik]["host_port"] = "8080"
     assert_equal \
-      "docker run --name traefik --detach --restart unless-stopped --log-opt max-size=10m --publish 8080:80 --volume /var/run/docker.sock:/var/run/docker.sock traefik --providers.docker --log.level=DEBUG --accesslog.format \"json\" --metrics.prometheus.buckets \"0.1,0.3,1.2,5.0\"",
+      "docker run --name traefik --detach --restart unless-stopped --publish 8080:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+  end
+
+  test "run with ports configured" do
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+
+    @config[:traefik]["options"] = {"publish" => %w[9000:9000 9001:9001]}
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" --publish \"9000:9000\" --publish \"9001:9001\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+  end
+
+  test "run with volumes configured" do
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+
+    @config[:traefik]["options"] = {"volume" => %w[./letsencrypt/acme.json:/letsencrypt/acme.json] }
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" --volume \"./letsencrypt/acme.json:/letsencrypt/acme.json\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+  end
+
+  test "run with several options configured" do
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+
+    @config[:traefik]["options"] = {"volume" => %w[./letsencrypt/acme.json:/letsencrypt/acme.json], "publish" => %w[8080:8080], "memory" => "512m"}
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" --volume \"./letsencrypt/acme.json:/letsencrypt/acme.json\" --publish \"8080:8080\" --memory \"512m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+  end
+
+  test "run with labels configured" do
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
+      new_command.run.join(" ")
+
+    @config[:traefik]["labels"] = { "traefik.http.routers.dashboard.service" => "api@internal", "traefik.http.routers.dashboard.middlewares" => "auth" }
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" --label traefik.http.routers.dashboard.service=\"api@internal\" --label traefik.http.routers.dashboard.middlewares=\"auth\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
       new_command.run.join(" ")
   end
 
@@ -23,7 +69,15 @@ class CommandsTraefikTest < ActiveSupport::TestCase
     @config.delete(:traefik)
 
     assert_equal \
-      "docker run --name traefik --detach --restart unless-stopped --log-opt max-size=10m --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock traefik --providers.docker --log.level=DEBUG",
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-opt max-size=\"10m\" #{Mrsk::Commands::Traefik::DEFAULT_IMAGE} --providers.docker --log.level=DEBUG",
+      new_command.run.join(" ")
+  end
+
+  test "run with logging config" do
+    @config[:logging] = { "driver" => "local", "options" => { "max-size" => "100m", "max-file" => "3" } }
+
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock --log-driver \"local\" --log-opt max-size=\"100m\" --log-opt max-file=\"3\" #{@image} --providers.docker --log.level=DEBUG --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
       new_command.run.join(" ")
   end
 
@@ -41,7 +95,7 @@ class CommandsTraefikTest < ActiveSupport::TestCase
 
   test "traefik info" do
     assert_equal \
-      "docker ps --filter name=traefik",
+      "docker ps --filter name=^traefik$",
       new_command.info.join(" ")
   end
 

test/configuration/accessory_test.rb

@@ -4,7 +4,10 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
   setup do
     @deploy = {
       service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" },
-      servers: [ "1.1.1.1", "1.1.1.2" ],
+      servers: {
+        "web" => [ "1.1.1.1", "1.1.1.2" ],
+        "workers" => [ "1.1.1.3", "1.1.1.4" ]
+      },
       env: { "REDIS_URL" => "redis://x/y" },
       accessories: {
         "mysql" => {
@@ -29,7 +32,7 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
         },
         "redis" => {
           "image" => "redis:latest",
-          "host" => "1.1.1.6",
+          "hosts" => [ "1.1.1.6", "1.1.1.7" ],
           "port" => "6379:6379",
           "labels" => {
             "cache" => true
@@ -39,7 +42,26 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
           },
           "volumes" => [
             "/var/lib/redis:/data"
-          ]
+          ],
+          "options" => {
+            "cpus" => 4,
+            "memory" => "2GB"
+          }
+        },
+        "monitoring" => {
+          "image" => "monitoring:latest",
+          "roles" => [ "web" ],
+          "port" => "4321:4321",
+          "labels" => {
+            "cache" => true
+          },
+          "env" => {
+            "STATSD_PORT" => "8126"
+          },
+          "options" => {
+            "cpus" => 4,
+            "memory" => "2GB"
+          }
         }
       }
     }
@@ -58,8 +80,9 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
   end
 
   test "host" do
-    assert_equal "1.1.1.5", @config.accessory(:mysql).host
-    assert_equal "1.1.1.6", @config.accessory(:redis).host
+    assert_equal ["1.1.1.5"], @config.accessory(:mysql).hosts
+    assert_equal ["1.1.1.6", "1.1.1.7"], @config.accessory(:redis).hosts
+    assert_equal ["1.1.1.1", "1.1.1.2"], @config.accessory(:monitoring).hosts
   end
 
   test "missing host" do
@@ -67,10 +90,21 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
     @config = Mrsk::Configuration.new(@deploy)
 
     assert_raises(ArgumentError) do
-      @config.accessory(:mysql).host
+      @config.accessory(:mysql).hosts
     end
   end
 
+  test "setting host, hosts and roles" do
+    @deploy[:accessories]["mysql"]["hosts"] = true
+    @deploy[:accessories]["mysql"]["roles"] = true
+    @config = Mrsk::Configuration.new(@deploy)
+
+    exception = assert_raises(ArgumentError) do
+      @config.accessory(:mysql).hosts
+    end
+    assert_equal "Specify one of `host`, `hosts` or `roles` for accessory `mysql`", exception.message
+  end
+
   test "label args" do
     assert_equal ["--label", "service=\"app-mysql\""], @config.accessory(:mysql).label_args
     assert_equal ["--label", "service=\"app-redis\"", "--label", "cache=\"true\""], @config.accessory(:redis).label_args
@@ -78,8 +112,11 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
 
   test "env args with secret" do
     ENV["MYSQL_ROOT_PASSWORD"] = "secret123"
-    assert_equal ["-e", "MYSQL_ROOT_PASSWORD=\"secret123\"", "-e", "MYSQL_ROOT_HOST=\"%\""], @config.accessory(:mysql).env_args
-    assert @config.accessory(:mysql).env_args[1].is_a?(SSHKit::Redaction)
+
+    @config.accessory(:mysql).env_args.tap do |env_args|
+      assert_equal ["-e", "MYSQL_ROOT_PASSWORD=\"secret123\"", "-e", "MYSQL_ROOT_HOST=\"%\""], Mrsk::Utils.unredacted(env_args)
+      assert_equal ["-e", "MYSQL_ROOT_PASSWORD=[REDACTED]", "-e", "MYSQL_ROOT_HOST=\"%\""], Mrsk::Utils.redacted(env_args)
+    end
   ensure
     ENV["MYSQL_ROOT_PASSWORD"] = nil
   end
@@ -104,4 +141,8 @@ class ConfigurationAccessoryTest < ActiveSupport::TestCase
   test "directories" do
     assert_equal({"$PWD/app-mysql/data"=>"/var/lib/mysql"}, @config.accessory(:mysql).directories)
   end
+
+  test "options" do
+    assert_equal ["--cpus", "\"4\"", "--memory", "\"2GB\""], @config.accessory(:redis).option_args
+  end
 end

test/configuration/role_test.rb

@@ -42,7 +42,7 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
   end
 
   test "special label args for web" do
-    assert_equal [ "--label", "service=\"app\"", "--label", "role=\"web\"", "--label", "traefik.http.routers.app.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.services.app.loadbalancer.healthcheck.path=\"/up\"", "--label", "traefik.http.services.app.loadbalancer.healthcheck.interval=\"1s\"", "--label", "traefik.http.middlewares.app.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app.retry.initialinterval=\"500ms\""], @config.role(:web).label_args
+    assert_equal [ "--label", "service=\"app\"", "--label", "role=\"web\"", "--label", "traefik.http.services.app-web.loadbalancer.server.scheme=\"http\"", "--label", "traefik.http.routers.app-web.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.middlewares.app-web-retry.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app-web-retry.retry.initialinterval=\"500ms\"", "--label", "traefik.http.routers.app-web.middlewares=\"app-web-retry@docker\"" ], @config.role(:web).label_args
   end
 
   test "custom labels" do
@@ -57,8 +57,8 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
   end
 
   test "overwriting default traefik label" do
-    @deploy[:labels] = { "traefik.http.routers.app.rule" => "\"Host(\\`example.com\\`) || (Host(\\`example.org\\`) && Path(\\`/traefik\\`))\"" }
-    assert_equal "\"Host(\\`example.com\\`) || (Host(\\`example.org\\`) && Path(\\`/traefik\\`))\"", @config.role(:web).labels["traefik.http.routers.app.rule"]
+    @deploy[:labels] = { "traefik.http.routers.app-web.rule" => "\"Host(\\`example.com\\`) || (Host(\\`example.org\\`) && Path(\\`/traefik\\`))\"" }
+    assert_equal "\"Host(\\`example.com\\`) || (Host(\\`example.org\\`) && Path(\\`/traefik\\`))\"", @config.role(:web).labels["traefik.http.routers.app-web.rule"]
   end
 
   test "default traefik label on non-web role" do
@@ -66,7 +66,7 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
       c[:servers]["beta"] = { "traefik" => "true", "hosts" => [ "1.1.1.5" ] }
     })
 
-    assert_equal [ "--label", "service=\"app\"", "--label", "role=\"beta\"", "--label", "traefik.http.routers.app.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.services.app.loadbalancer.healthcheck.path=\"/up\"", "--label", "traefik.http.services.app.loadbalancer.healthcheck.interval=\"1s\"", "--label", "traefik.http.middlewares.app.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app.retry.initialinterval=\"500ms\"" ], config.role(:beta).label_args
+    assert_equal [ "--label", "service=\"app\"", "--label", "role=\"beta\"", "--label", "traefik.http.services.app-beta.loadbalancer.server.scheme=\"http\"", "--label", "traefik.http.routers.app-beta.rule=\"PathPrefix(\\`/\\`)\"", "--label", "traefik.http.middlewares.app-beta-retry.retry.attempts=\"5\"", "--label", "traefik.http.middlewares.app-beta-retry.retry.initialinterval=\"500ms\"", "--label", "traefik.http.routers.app-beta.middlewares=\"app-beta-retry@docker\"" ], config.role(:beta).label_args
   end
 
   test "env overwritten by role" do
@@ -97,7 +97,10 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
     ENV["REDIS_PASSWORD"] = "secret456"
     ENV["DB_PASSWORD"] = "secret&\"123"
 
-    assert_equal ["-e", "REDIS_PASSWORD=\"secret456\"", "-e", "DB_PASSWORD=\"secret&\\\"123\"", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], @config_with_roles.role(:workers).env_args
+    @config_with_roles.role(:workers).env_args.tap do |env_args|
+      assert_equal ["-e", "REDIS_PASSWORD=\"secret456\"", "-e", "DB_PASSWORD=\"secret&\\\"123\"", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], Mrsk::Utils.unredacted(env_args)
+      assert_equal ["-e", "REDIS_PASSWORD=[REDACTED]", "-e", "DB_PASSWORD=[REDACTED]", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], Mrsk::Utils.redacted(env_args)
+    end
   ensure
     ENV["REDIS_PASSWORD"] = nil
     ENV["DB_PASSWORD"] = nil
@@ -116,7 +119,10 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
 
     ENV["DB_PASSWORD"] = "secret123"
 
-    assert_equal ["-e", "DB_PASSWORD=\"secret123\"", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], @config_with_roles.role(:workers).env_args
+    @config_with_roles.role(:workers).env_args.tap do |env_args|
+      assert_equal ["-e", "DB_PASSWORD=\"secret123\"", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], Mrsk::Utils.unredacted(env_args)
+      assert_equal ["-e", "DB_PASSWORD=[REDACTED]", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], Mrsk::Utils.redacted(env_args)
+    end
   ensure
     ENV["DB_PASSWORD"] = nil
   end
@@ -133,7 +139,10 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
 
     ENV["REDIS_PASSWORD"] = "secret456"
 
-    assert_equal ["-e", "REDIS_PASSWORD=\"secret456\"", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], @config_with_roles.role(:workers).env_args
+    @config_with_roles.role(:workers).env_args.tap do |env_args|
+      assert_equal ["-e", "REDIS_PASSWORD=\"secret456\"", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], Mrsk::Utils.unredacted(env_args)
+      assert_equal ["-e", "REDIS_PASSWORD=[REDACTED]", "-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], Mrsk::Utils.redacted(env_args)
+    end
   ensure
     ENV["REDIS_PASSWORD"] = nil
   end

test/configuration_test.rb

@@ -3,6 +3,7 @@ require "test_helper"
 class ConfigurationTest < ActiveSupport::TestCase
   setup do
     ENV["RAILS_MASTER_KEY"] = "456"
+    ENV["VERSION"] = "missing"
 
     @deploy = {
       service: "app", image: "dhh/app",
@@ -15,23 +16,29 @@ class ConfigurationTest < ActiveSupport::TestCase
     @config = Mrsk::Configuration.new(@deploy)
 
     @deploy_with_roles = @deploy.dup.merge({
-      servers: { "web" => [ "1.1.1.1", "1.1.1.2" ], "workers" => { "hosts" => [ "1.1.1.3", "1.1.1.4" ] } } })
+      servers: { "web" => [ "1.1.1.1", "1.1.1.2" ], "workers" => { "hosts" => [ "1.1.1.1", "1.1.1.3" ] } } })
 
     @config_with_roles = Mrsk::Configuration.new(@deploy_with_roles)
   end
 
   teardown do
-    ENV["RAILS_MASTER_KEY"] = nil
+    ENV.delete("RAILS_MASTER_KEY")
+    ENV.delete("VERSION")
   end
 
-  test "ensure valid keys" do
-    assert_raise(ArgumentError) do
-      Mrsk::Configuration.new(@deploy.tap { _1.delete(:service) })
-      Mrsk::Configuration.new(@deploy.tap { _1.delete(:image) })
-      Mrsk::Configuration.new(@deploy.tap { _1.delete(:registry) })
+  %i[ service image registry ].each do |key|
+    test "#{key} config required" do
+      assert_raise(ArgumentError) do
+        Mrsk::Configuration.new @deploy.tap { _1.delete key }
+      end
+    end
+  end
 
-      Mrsk::Configuration.new(@deploy.tap { _1[:registry].delete("username") })
-      Mrsk::Configuration.new(@deploy.tap { _1[:registry].delete("password") })
+  %w[ username password ].each do |key|
+    test "registry #{key} required" do
+      assert_raise(ArgumentError) do
+        Mrsk::Configuration.new @deploy.tap { _1[:registry].delete key }
+      end
     end
   end
 
@@ -41,14 +48,14 @@ class ConfigurationTest < ActiveSupport::TestCase
   end
 
   test "role" do
-    assert_equal "web", @config.role(:web).name
+    assert @config.role(:web).name.web?
     assert_equal "workers", @config_with_roles.role(:workers).name
     assert_nil @config.role(:missing)
   end
 
   test "all hosts" do
     assert_equal [ "1.1.1.1", "1.1.1.2"], @config.all_hosts
-    assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3", "1.1.1.4" ], @config_with_roles.all_hosts
+    assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3" ], @config_with_roles.all_hosts
   end
 
   test "primary web host" do
@@ -62,12 +69,24 @@ class ConfigurationTest < ActiveSupport::TestCase
     @deploy_with_roles[:servers]["workers"]["traefik"] = true
     config = Mrsk::Configuration.new(@deploy_with_roles)
 
-    assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3", "1.1.1.4" ], config.traefik_hosts
+    assert_equal [ "1.1.1.1", "1.1.1.2", "1.1.1.3" ], config.traefik_hosts
   end
 
   test "version" do
-    assert_equal "missing", @config.version
-    assert_equal "123", Mrsk::Configuration.new(@deploy, version: "123").version
+    ENV.delete("VERSION")
+
+    @config.expects(:system).with("git rev-parse").returns(nil)
+    error = assert_raises(RuntimeError) { @config.version}
+    assert_match /no git repository found/, error.message
+
+    @config.expects(:current_commit_hash).returns("git-version")
+    assert_equal "git-version", @config.version
+
+    ENV["VERSION"] = "env-version"
+    assert_equal "env-version", @config.version
+
+    @config.version = "arg-version"
+    assert_equal "arg-version", @config.version
   end
 
   test "repository" do
@@ -94,12 +113,13 @@ class ConfigurationTest < ActiveSupport::TestCase
 
   test "env args with clear and secrets" do
     ENV["PASSWORD"] = "secret123"
+
     config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!({
       env: { "clear" => { "PORT" => "3000" }, "secret" => [ "PASSWORD" ] }
     }) })
 
-    assert_equal [ "-e", "PASSWORD=\"secret123\"", "-e", "PORT=\"3000\"" ], config.env_args
-    assert config.env_args[1].is_a?(SSHKit::Redaction)
+    assert_equal [ "-e", "PASSWORD=\"secret123\"", "-e", "PORT=\"3000\"" ], Mrsk::Utils.unredacted(config.env_args)
+    assert_equal [ "-e", "PASSWORD=[REDACTED]", "-e", "PORT=\"3000\"" ], Mrsk::Utils.redacted(config.env_args)
   ensure
     ENV["PASSWORD"] = nil
   end
@@ -114,12 +134,13 @@ class ConfigurationTest < ActiveSupport::TestCase
 
   test "env args with only secrets" do
     ENV["PASSWORD"] = "secret123"
+
     config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!({
       env: { "secret" => [ "PASSWORD" ] }
     }) })
 
-    assert_equal [ "-e", "PASSWORD=\"secret123\"" ], config.env_args
-    assert config.env_args[1].is_a?(SSHKit::Redaction)
+    assert_equal [ "-e", "PASSWORD=\"secret123\"" ], Mrsk::Utils.unredacted(config.env_args)
+    assert_equal [ "-e", "PASSWORD=[REDACTED]" ], Mrsk::Utils.redacted(config.env_args)
   ensure
     ENV["PASSWORD"] = nil
   end
@@ -134,6 +155,39 @@ class ConfigurationTest < ActiveSupport::TestCase
 
   test "valid config" do
     assert @config.valid?
+    assert @config_with_roles.valid?
+  end
+
+  test "hosts required for all roles" do
+    # Empty server list for implied web role
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new @deploy.merge(servers: [])
+    end
+
+    # Empty server list
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new @deploy.merge(servers: { "web" => [] })
+    end
+
+    # Missing hosts key
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new @deploy.merge(servers: { "web" => {} })
+    end
+
+    # Empty hosts list
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new @deploy.merge(servers: { "web" => { "hosts" => [] } })
+    end
+
+    # Nil hosts
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new @deploy.merge(servers: { "web" => { "hosts" => nil } })
+    end
+
+    # One role with hosts, one without
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new @deploy.merge(servers: { "web" => %w[ web ], "workers" => { "hosts" => %w[ ] } })
+    end
   end
 
   test "ssh options" do
@@ -157,18 +211,32 @@ class ConfigurationTest < ActiveSupport::TestCase
     assert_equal ["--volume", "/local/path:/container/path"], @config.volume_args
   end
 
+  test "logging args default" do
+    assert_equal ["--log-opt", "max-size=\"10m\""], @config.logging_args
+  end
+
+  test "logging args with configured options" do
+    config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!(logging: { "options" => { "max-size" => "100m", "max-file" => 5 } }) })
+    assert_equal ["--log-opt", "max-size=\"100m\"", "--log-opt", "max-file=\"5\""], @config.logging_args
+  end
+
+  test "logging args with configured driver and options" do
+    config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!(logging: { "driver" => "local", "options" => { "max-size" => "100m", "max-file" => 5 } }) })
+    assert_equal ["--log-driver", "\"local\"", "--log-opt", "max-size=\"100m\"", "--log-opt", "max-file=\"5\""], @config.logging_args
+  end
+
   test "erb evaluation of yml config" do
-    config = Mrsk::Configuration.create_from Pathname.new(File.expand_path("fixtures/deploy.erb.yml", __dir__))
+    config = Mrsk::Configuration.create_from config_file: Pathname.new(File.expand_path("fixtures/deploy.erb.yml", __dir__))
     assert_equal "my-user", config.registry["username"]
   end
 
   test "destination yml config merge" do
     dest_config_file = Pathname.new(File.expand_path("fixtures/deploy_for_dest.yml", __dir__))
 
-    config = Mrsk::Configuration.create_from dest_config_file, destination: "world"
+    config = Mrsk::Configuration.create_from config_file: dest_config_file, destination: "world"
     assert_equal "1.1.1.1", config.all_hosts.first
 
-    config = Mrsk::Configuration.create_from dest_config_file, destination: "mars"
+    config = Mrsk::Configuration.create_from config_file: dest_config_file, destination: "mars"
     assert_equal "1.1.1.3", config.all_hosts.first
   end
 
@@ -176,11 +244,11 @@ class ConfigurationTest < ActiveSupport::TestCase
     dest_config_file = Pathname.new(File.expand_path("fixtures/deploy_for_dest.yml", __dir__))
 
     assert_raises(RuntimeError) do
-      config = Mrsk::Configuration.create_from dest_config_file, destination: "missing"
+      config = Mrsk::Configuration.create_from config_file: dest_config_file, destination: "missing"
     end
   end
 
   test "to_h" do
-    assert_equal({ :roles=>["web"], :hosts=>["1.1.1.1", "1.1.1.2"], :primary_host=>"1.1.1.1", :version=>"missing", :repository=>"dhh/app", :absolute_image=>"dhh/app:missing", :service_with_version=>"app-missing", :env_args=>["-e", "REDIS_URL=\"redis://x/y\""], :ssh_options=>{:user=>"root", :auth_methods=>["publickey"]}, :volume_args=>["--volume", "/local/path:/container/path"], :healthcheck=>{"path"=>"/up", "port"=>3000 }}, @config.to_h)
+    assert_equal({ :roles=>["web"], :hosts=>["1.1.1.1", "1.1.1.2"], :primary_host=>"1.1.1.1", :version=>"missing", :repository=>"dhh/app", :absolute_image=>"dhh/app:missing", :service_with_version=>"app-missing", :env_args=>["-e", "REDIS_URL=\"redis://x/y\""], :ssh_options=>{:user=>"root", :auth_methods=>["publickey"]}, :volume_args=>["--volume", "/local/path:/container/path"], :logging=>["--log-opt", "max-size=\"10m\""], :healthcheck=>{"path"=>"/up", "port"=>3000, "max_attempts" => 7 }}, @config.to_h)
   end
 end

test/fixtures/deploy_simple.yml

@@ -0,0 +1,9 @@
+service: app
+image: dhh/app
+servers:
+  - "1.1.1.1"
+  - "1.1.1.2"
+registry:
+  username: user
+  password: pw
+audit_broadcast_cmd: "bin/audit_broadcast"

test/fixtures/deploy_with_accessories.yml

@@ -1,8 +1,12 @@
 service: app
 image: dhh/app
 servers:
-  - 1.1.1.1
-  - 1.1.1.2
+  web:
+    - "1.1.1.1"
+    - "1.1.1.2"
+  workers:
+    - "1.1.1.3"
+    - "1.1.1.4"
 registry:
   username: user
   password: pw
@@ -23,9 +27,10 @@ accessories:
       - data:/var/lib/mysql
   redis:
     image: redis:latest
-    host: 1.1.1.4
+    roles:
+      - web
     port: 6379
     directories:
       - data:/data
 
-readiness_delay: 0
+readiness_delay: 0

test/fixtures/deploy_with_boot_strategy.yml

@@ -0,0 +1,17 @@
+service: app
+image: dhh/app
+servers:
+  web:
+    - "1.1.1.1"
+    - "1.1.1.2"
+  workers:
+    - "1.1.1.3"
+    - "1.1.1.4"
+
+registry:
+  username: user
+  password: pw
+
+boot:
+  limit: 3
+  wait: 2

test/fixtures/deploy_with_precentage_boot_strategy.yml

@@ -0,0 +1,17 @@
+service: app
+image: dhh/app
+servers:
+  web:
+    - "1.1.1.1"
+    - "1.1.1.2"
+  workers:
+    - "1.1.1.3"
+    - "1.1.1.4"
+
+registry:
+  username: user
+  password: pw
+
+boot:
+  limit: 25%
+  wait: 2

test/fixtures/deploy_with_roles.yml

@@ -5,8 +5,9 @@ servers:
     - 1.1.1.1
     - 1.1.1.2
   workers:
-    - 1.1.1.3
-    - 1.1.1.4
+    hosts:
+      - 1.1.1.3
+      - 1.1.1.4
 env:
   REDIS_URL: redis://x/y
 registry:

test/integration/deploy_test.rb

@@ -0,0 +1,132 @@
+require "net/http"
+require "test_helper"
+
+class DeployTest < ActiveSupport::TestCase
+
+  setup do
+    docker_compose "up --build --force-recreate -d"
+    wait_for_healthy
+  end
+
+  teardown do
+    docker_compose "down -v"
+  end
+
+  test "deploy" do
+    first_version = latest_app_version
+
+    assert_app_is_down
+
+    mrsk :deploy
+
+    assert_app_is_up version: first_version
+
+    second_version = update_app_rev
+
+    mrsk :redeploy
+
+    assert_app_is_up version: second_version
+
+    mrsk :rollback, first_version
+
+    assert_app_is_up version: first_version
+
+    details = mrsk :details, capture: true
+
+    assert_match /Traefik Host: vm1/, details
+    assert_match /Traefik Host: vm2/, details
+    assert_match /App Host: vm1/, details
+    assert_match /App Host: vm2/, details
+    assert_match /traefik:v2.9/, details
+    assert_match /registry:4443\/app:#{first_version}/, details
+
+    audit = mrsk :audit, capture: true
+
+    assert_match /Booted app version #{first_version}.*Booted app version #{second_version}.*Booted app version #{first_version}.*/m, audit
+  end
+
+  private
+    def docker_compose(*commands, capture: false)
+      command = "docker compose #{commands.join(" ")}"
+      succeeded = false
+      if capture
+        result = stdouted { succeeded = system("cd test/integration && #{command}") }
+      else
+        succeeded = system("cd test/integration && #{command}")
+      end
+
+      raise "Command `#{command}` failed with error code `#{$?}`" unless succeeded
+      result
+    end
+
+    def deployer_exec(*commands, **options)
+      docker_compose("exec deployer #{commands.join(" ")}", **options)
+    end
+
+    def mrsk(*commands, **options)
+      deployer_exec(:mrsk, *commands, **options)
+    end
+
+    def assert_app_is_down
+      assert_equal "502", app_response.code
+    end
+
+    def assert_app_is_up(version: nil)
+      code = app_response.code
+      if code != "200"
+        puts "Got response code #{code}, here are the traefik logs:"
+        mrsk :traefik, :logs
+        puts "And here are the load balancer logs"
+        docker_compose :logs, :load_balancer
+        puts "Tried to get the response code again and got #{app_response.code}"
+      end
+      assert_equal "200", code
+      assert_app_version(version) if version
+    end
+
+    def assert_app_not_found
+      assert_equal "404", app_response.code
+    end
+
+    def wait_for_app_to_be_up(timeout: 10, up_count: 3)
+      timeout_at = Time.now + timeout
+      up_times = 0
+      response = app_response
+      while up_times < up_count && timeout_at > Time.now
+        sleep 0.1
+        up_times += 1 if response.code == "200"
+        response = app_response
+      end
+      assert_equal up_times, up_count
+    end
+
+    def app_response
+      Net::HTTP.get_response(URI.parse("http://localhost:12345"))
+    end
+
+    def update_app_rev
+      deployer_exec "./update_app_rev.sh"
+      latest_app_version
+    end
+
+    def latest_app_version
+      deployer_exec("cat version", capture: true)
+    end
+
+    def assert_app_version(version)
+      actual_version = Net::HTTP.get_response(URI.parse("http://localhost:12345/version")).body.strip
+
+      assert_equal version, actual_version
+    end
+
+    def wait_for_healthy(timeout: 20)
+      timeout_at = Time.now + timeout
+      while docker_compose("ps -a | tail -n +2 | grep -v '(healthy)' | wc -l", capture: true) != "0"
+        if timeout_at < Time.now
+          docker_compose("ps -a | tail -n +2 | grep -v '(healthy)'")
+          raise "Container not healthy after #{timeout} seconds" if timeout_at < Time.now
+        end
+        sleep 0.1
+      end
+    end
+end

test/integration/docker-compose.yml

@@ -0,0 +1,50 @@
+version: "3.7"
+name: "mrsk-test"
+
+volumes:
+  shared:
+
+services:
+  shared:
+    build:
+      context: docker/shared
+    volumes:
+      - shared:/shared
+
+  deployer:
+    privileged: true
+    build:
+      context: docker/deployer
+    volumes:
+      - ../..:/mrsk
+      - shared:/shared
+
+  registry:
+    build:
+      context: docker/registry
+    environment:
+      - REGISTRY_HTTP_ADDR=0.0.0.0:4443
+      - REGISTRY_HTTP_TLS_CERTIFICATE=/certs/domain.crt
+      - REGISTRY_HTTP_TLS_KEY=/certs/domain.key
+    volumes:
+      - shared:/shared
+
+  vm1:
+    privileged: true
+    build:
+      context: docker/vm
+    volumes:
+      - shared:/shared
+
+  vm2:
+    privileged: true
+    build:
+      context: docker/vm
+    volumes:
+      - shared:/shared
+
+  load_balancer:
+    build:
+      context: docker/load_balancer
+    ports:
+      - "12345:80"

test/integration/docker/deployer/Dockerfile

@@ -0,0 +1,30 @@
+FROM ruby:3.2
+
+WORKDIR /app
+
+RUN apt-get update --fix-missing && apt-get install -y ca-certificates openssh-client curl gnupg docker.io
+
+RUN install -m 0755 -d /etc/apt/keyrings
+RUN curl -fsSL https://download.docker.com/linux/debian/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
+RUN chmod a+r /etc/apt/keyrings/docker.gpg
+RUN echo \
+  "deb [arch="$(dpkg --print-architecture)" signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/debian \
+  "$(. /etc/os-release && echo "$VERSION_CODENAME")" stable" | \
+  tee /etc/apt/sources.list.d/docker.list > /dev/null
+
+RUN apt-get update --fix-missing && apt-get install -y docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
+
+COPY *.sh .
+COPY app/ .
+
+RUN ln -s /shared/ssh /root/.ssh
+RUN mkdir -p /etc/docker/certs.d/registry:4443 && ln -s /shared/certs/domain.crt /etc/docker/certs.d/registry:4443/ca.crt
+
+RUN git config --global user.email "deployer@example.com"
+RUN git config --global user.name "Deployer"
+RUN git init && git add . && git commit -am "Initial version"
+RUN git rev-parse HEAD > version
+
+HEALTHCHECK --interval=1s CMD pgrep sleep
+
+CMD ["./boot.sh"]

test/integration/docker/deployer/app/Dockerfile

@@ -0,0 +1,4 @@
+FROM nginx:1-alpine-slim
+
+COPY default.conf /etc/nginx/conf.d/default.conf
+COPY version /usr/share/nginx/html/version

test/integration/docker/deployer/app/config/deploy.yml

@@ -0,0 +1,17 @@
+service: app
+image: app
+servers:
+  - vm1
+  - vm2
+registry:
+  server: registry:4443
+  username: root
+  password: root
+builder:
+  multiarch: false
+healthcheck:
+  cmd: wget -qO- http://localhost > /dev/null
+traefik:
+  args:
+    accesslog: true
+    accesslog.format: json

test/integration/docker/deployer/app/default.conf

@@ -0,0 +1,17 @@
+server {
+    listen       80;
+    listen  [::]:80;
+    server_name  localhost;
+
+    location / {
+        root   /usr/share/nginx/html;
+        index  index.html index.htm;
+    }
+
+    # redirect server error pages to the static page /50x.html
+    #
+    error_page   500 502 503 504  /50x.html;
+    location = /50x.html {
+        root   /usr/share/nginx/html;
+    }
+}

test/integration/docker/deployer/boot.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+
+cd /mrsk && gem build mrsk.gemspec -o /tmp/mrsk.gem && gem install /tmp/mrsk.gem
+
+dockerd &
+
+trap "pkill -f sleep" term
+
+sleep infinity & wait

test/integration/docker/deployer/update_app_rev.sh

@@ -0,0 +1,4 @@
+#!/bin/bash
+
+git commit -am 'Update rev' --amend
+git rev-parse HEAD > version

test/integration/docker/load_balancer/Dockerfile

@@ -0,0 +1,5 @@
+FROM nginx:1-alpine-slim
+
+COPY default.conf /etc/nginx/conf.d/default.conf
+
+HEALTHCHECK --interval=1s CMD pgrep nginx

test/integration/docker/load_balancer/default.conf

@@ -0,0 +1,12 @@
+upstream loadbalancer {
+  server vm1:80;
+  server vm2:80;
+}
+
+server {
+  listen 80;
+
+  location / {
+    proxy_pass http://loadbalancer;
+  }
+}

test/integration/docker/registry/Dockerfile

@@ -0,0 +1,9 @@
+FROM registry
+
+COPY boot.sh .
+
+RUN ln -s /shared/certs /certs
+
+HEALTHCHECK --interval=1s CMD pgrep registry
+
+ENTRYPOINT ["./boot.sh"]

test/integration/docker/registry/boot.sh

@@ -0,0 +1,7 @@
+#!/bin/sh
+
+while [ ! -f /certs/domain.crt ]; do sleep 1; done
+
+trap "pkill -f registry" term
+
+/entrypoint.sh /etc/docker/registry/config.yml & wait

test/integration/docker/shared/Dockerfile

@@ -0,0 +1,17 @@
+FROM ubuntu:22.10
+
+WORKDIR /work
+
+RUN apt-get update --fix-missing && apt-get -y install openssh-client openssl
+
+RUN mkdir ssh && \
+  ssh-keygen -t rsa -f ssh/id_rsa -N ""
+
+COPY registry-dns.conf .
+COPY boot.sh .
+
+RUN mkdir certs && openssl req -newkey rsa:4096 -nodes -sha256 -keyout certs/domain.key   -x509 -days 365 -out certs/domain.crt   -subj '/CN=registry' -extensions EXT -config registry-dns.conf
+
+HEALTHCHECK --interval=1s CMD pgrep sleep
+
+CMD ["./boot.sh"]

test/integration/docker/shared/boot.sh

@@ -0,0 +1,7 @@
+#!/bin/bash
+
+cp -r * /shared
+
+trap "pkill -f sleep" term
+
+sleep infinity & wait

test/integration/docker/shared/registry-dns.conf

@@ -0,0 +1,7 @@
+[dn]
+CN=registry
+[req]
+distinguished_name = dn
+[EXT]
+subjectAltName=DNS:registry
+keyUsage=digitalSignature

test/integration/docker/vm/Dockerfile

@@ -0,0 +1,14 @@
+FROM ubuntu:22.10
+
+WORKDIR /work
+
+RUN apt-get update --fix-missing && apt-get -y install openssh-client openssh-server docker.io
+
+RUN mkdir /root/.ssh && ln -s /shared/ssh/id_rsa.pub /root/.ssh/authorized_keys
+RUN mkdir -p /etc/docker/certs.d/registry:4443 && ln -s /shared/certs/domain.crt /etc/docker/certs.d/registry:4443/ca.crt
+
+COPY boot.sh .
+
+HEALTHCHECK --interval=1s CMD pgrep dockerd
+
+CMD ["./boot.sh"]

test/integration/docker/vm/boot.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+
+while [ ! -f /root/.ssh/authorized_keys ]; do echo "Waiting for ssh keys"; sleep 1; done
+
+service ssh restart
+
+dockerd &
+
+trap "pkill -f sleep" term
+
+sleep infinity & wait

test/test_helper.rb

@@ -1,6 +1,7 @@
 require "bundler/setup"
 require "active_support/test_case"
 require "active_support/testing/autorun"
+require "active_support/testing/stream"
 require "debug"
 require "mocha/minitest" # using #stubs that can alter returns
 require "minitest/autorun" # using #stub that take args
@@ -9,7 +10,28 @@ require "mrsk"
 
 ActiveSupport::LogSubscriber.logger = ActiveSupport::Logger.new(STDOUT) if ENV["VERBOSE"]
 
+# Applies to remote commands only.
 SSHKit.config.backend = SSHKit::Backend::Printer
 
-class ActiveSupport::TestCase
+# Ensure local commands use the printer backend too.
+# See https://github.com/capistrano/sshkit/blob/master/lib/sshkit/dsl.rb#L9
+module SSHKit
+  module DSL
+    def run_locally(&block)
+      SSHKit::Backend::Printer.new(SSHKit::Host.new(:local), &block).run
+    end
+  end
+end
+
+class ActiveSupport::TestCase
+  include ActiveSupport::Testing::Stream
+
+  private
+    def stdouted
+      capture(:stdout) { yield }.strip
+    end
+
+    def stderred
+      capture(:stderr) { yield }.strip
+    end
 end

test/utils_test.rb

@@ -0,0 +1,64 @@
+require "test_helper"
+
+class UtilsTest < ActiveSupport::TestCase
+  test "argumentize" do
+    assert_equal [ "--label", "foo=\"\\`bar\\`\"", "--label", "baz=\"qux\"", "--label", :quux ], \
+      Mrsk::Utils.argumentize("--label", { foo: "`bar`", baz: "qux", quux: nil })
+  end
+
+  test "argumentize with redacted" do
+    assert_kind_of SSHKit::Redaction, \
+      Mrsk::Utils.argumentize("--label", { foo: "bar" }, sensitive: true).last
+  end
+
+  test "argumentize_env_with_secrets" do
+    ENV.expects(:fetch).with("FOO").returns("secret")
+
+    args = Mrsk::Utils.argumentize_env_with_secrets({ "secret" => [ "FOO" ], "clear" => { BAZ: "qux" } })
+
+    assert_equal [ "-e", "FOO=[REDACTED]", "-e", "BAZ=\"qux\"" ], Mrsk::Utils.redacted(args)
+    assert_equal [ "-e", "FOO=\"secret\"", "-e", "BAZ=\"qux\"" ], Mrsk::Utils.unredacted(args)
+  end
+
+  test "optionize" do
+    assert_equal [ "--foo", "\"bar\"", "--baz", "\"qux\"", "--quux" ], \
+      Mrsk::Utils.optionize({ foo: "bar", baz: "qux", quux: true })
+  end
+
+  test "optionize with" do
+    assert_equal [ "--foo=\"bar\"", "--baz=\"qux\"", "--quux" ], \
+      Mrsk::Utils.optionize({ foo: "bar", baz: "qux", quux: true }, with: "=")
+  end
+
+  test "no redaction from #to_s" do
+    assert_equal "secret", Mrsk::Utils.sensitive("secret").to_s
+  end
+
+  test "redact from #inspect" do
+    assert_equal "[REDACTED]".inspect, Mrsk::Utils.sensitive("secret").inspect
+  end
+
+  test "redact from SSHKit output" do
+    assert_kind_of SSHKit::Redaction, Mrsk::Utils.sensitive("secret")
+  end
+
+  test "redact from YAML output" do
+    assert_equal "--- ! '[REDACTED]'\n", YAML.dump(Mrsk::Utils.sensitive("secret"))
+  end
+
+  test "escape_shell_value" do
+    assert_equal "\"foo\"", Mrsk::Utils.escape_shell_value("foo")
+    assert_equal "\"\\`foo\\`\"", Mrsk::Utils.escape_shell_value("`foo`")
+
+    assert_equal "\"${PWD}\"", Mrsk::Utils.escape_shell_value("${PWD}")
+    assert_equal "\"${cat /etc/hostname}\"", Mrsk::Utils.escape_shell_value("${cat /etc/hostname}")
+    assert_equal "\"\\${PWD]\"", Mrsk::Utils.escape_shell_value("${PWD]")
+    assert_equal "\"\\$(PWD)\"", Mrsk::Utils.escape_shell_value("$(PWD)")
+    assert_equal "\"\\$PWD\"", Mrsk::Utils.escape_shell_value("$PWD")
+
+    assert_equal "\"^(https?://)www.example.com/(.*)\\$\"",
+      Mrsk::Utils.escape_shell_value("^(https?://)www.example.com/(.*)$")
+    assert_equal "\"https://example.com/\\$2\"",
+      Mrsk::Utils.escape_shell_value("https://example.com/$2")
+  end
+end