Bump version for 0.15.1

Revert "Configurable SSH log levels"

.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

@@ -0,0 +1,41 @@
+name: Docker
+
+on:
+  release:
+    types: [created]
+    tags:
+      - 'v*'
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Login to GitHub Container Registry
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: Build and push
+        uses: docker/build-push-action@v3
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ghcr.io/mrsked/mrsk:latest
+            ghcr.io/mrsked/mrsk:${{ github.ref_name }}

.gitignore

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

CODE_OF_CONDUCT.md

@@ -0,0 +1,41 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of the MRSK project, we pledge to create a welcoming and inclusive environment for everyone. We value the participation of each member of our community and want all contributors to feel respected and valued.
+
+We are committed to providing a harassment-free experience for everyone, regardless of gender, gender identity and expression, sexual orientation, disability, physical appearance, body size, race, age, or religion (or lack thereof). We do not tolerate harassment of participants in any form.
+
+This code of conduct applies to all MRSK project spaces, including but not limited to project code, issue trackers, chat rooms, and mailing lists. Violations of this code of conduct may result in removal from the project community.
+
+## Our standards
+
+Examples of behavior that contributes to creating a positive environment include:
+
+- Using welcoming and inclusive language
+- Being respectful of differing viewpoints and experiences
+- Gracefully accepting constructive criticism
+- Focusing on what is best for the community
+- Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+- The use of sexualized language or imagery and unwelcome sexual attention or advances
+- Trolling, insulting/derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or electronic address, without explicit permission
+- Other conduct which could reasonably be considered inappropriate in a professional setting
+
+## Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned with this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful.
+
+## Reporting
+
+If you are subject to or witness unacceptable behavior, or have any other concerns, please notify a project maintainer. All reports will be kept confidential and will be reviewed and investigated promptly.
+
+We will investigate every complaint and take appropriate action. We reserve the right to remove any content that violates this Code of Conduct, or to temporarily or permanently ban any contributor for other behaviors that we deem inappropriate, threatening, offensive, or harmful.
+
+## Attribution
+
+This Code of Conduct is adapted from the Contributor Covenant, version 1.4, available at <https://www.contributor-covenant.org/version/1/4/code-of-conduct.html>.

CONTRIBUTING.md

@@ -0,0 +1,49 @@
+# Contributing to MRSK development
+
+Thank you for considering contributing to MRSK! This document outlines some guidelines for contributing to this open source project.
+
+Please make sure to review our [Code of Conduct](CODE_OF_CONDUCT.md) before contributing to MRSK.
+
+There are several ways you can contribute to the betterment of the project:
+
+- **Report an issue?** - If the issue isn’t reported, we can’t fix it. Please report any bugs, feature, and/or improvement requests on the [MRSK GitHub Issues tracker](https://github.com/mrsked/mrsk/issues).
+- **Submit patches** - Do you have a new feature or a fix you'd like to share? [Submit a pull request](https://github.com/mrsked/mrsk/pulls)!
+- **Write blog articles** - Are you using MRSK? We'd love to hear how you're using it with your projects. Write a tutorial and post it on your blog!
+
+## Issues
+
+If you encounter any issues with the project, please check the [existing issues](https://github.com/mrsked/mrsk/issues) first to see if the issue has already been reported. If the issue hasn't been reported, please open a new issue with a clear description of the problem and steps to reproduce it.
+
+## Pull Requests
+
+Please keep the following guidelines in mind when opening a pull request:
+
+- Ensure that your code passes the project's minitests by running ./bin/test.
+- Provide a clear and detailed description of your changes.
+- Keep your changes focused on a single concern.
+- Write clean and readable code that follows the project's code style.
+- Use descriptive variable and function names.
+- Write clear and concise commit messages.
+- Add tests for your changes, if possible.
+- Ensure that your changes don't break existing functionality.
+
+#### Commit message guidelines
+
+A good commit message should describe what changed and why.
+
+## Development
+
+The `main` branch is regularly built and tested, but it is not guaranteed to be completely stable. Tags are created regularly from release branches to indicate new official, stable release versions of MRSK.
+
+MRSK is written in Ruby. You should have Ruby 3.2+ installed on your machine in order to work on MRSK. If that's already setup, run `bundle` in the root directory to install all dependencies. Then you can run `bin/test` to run all tests.
+
+1. Fork the project repository.
+2. Create a new branch for your contribution.
+3. Write your code or make the desired changes.
+4. **Ensure that your code passes the project's minitests by running ./bin/test.**
+5. Commit your changes and push them to your forked repository.
+6. [Open a pull request](https://github.com/mrsked/mrsk/pulls) to the main project repository with a detailed description of your changes.
+
+## License
+
+MRSK is released under the MIT License. By contributing to this project, you agree to license your contributions under the same license.

Dockerfile

@@ -0,0 +1,40 @@
+# 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
+
+# Copy the Gemfile, Gemfile.lock into the container
+COPY Gemfile Gemfile.lock mrsk.gemspec ./
+
+# Required in 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 openssh-client-default \
+    && rc-update add docker boot \
+    && gem install bundler --version=2.4.3 \
+    && bundle install
+
+# Copy the rest of our application code into the container.
+# We do this after bundle install, to avoid having to run bundle
+# every time we do small fixes in the source code.
+COPY . .
+
+# Install the gem locally from the project folder
+RUN gem build mrsk.gemspec && \
+    gem install ./mrsk-*.gem --no-document
+
+# 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

@@ -1,9 +1,12 @@
 PATH
   remote: .
   specs:
-    mrsk (0.6.4)
+    mrsk (0.15.1)
       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)
@@ -11,88 +14,86 @@ 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)
+    ed25519 (1.3.0)
     erubi (1.12.0)
     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

@@ -1,10 +1,28 @@
 # MRSK
 
-MRSK deploys web apps in containers to servers running Docker with zero downtime. It uses the dynamic reverse-proxy Traefik to hold requests while the new application container is started and the old one is stopped. It works seamlessly across multiple hosts, using SSHKit to execute commands. It was built for Rails applications, but works with any type of web app that can be bundled with Docker.
+MRSK deploys web apps anywhere from bare metal to cloud VMs using Docker with zero downtime. It uses the dynamic reverse-proxy Traefik to hold requests while the new application container is started and the old one is stopped. It works seamlessly across multiple hosts, using SSHKit to execute commands. It was built for Rails applications, but works with any type of web app that can be containerized with Docker.
+
+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
@@ -14,54 +32,84 @@ servers:
   - 192.168.0.2
 registry:
   username: registry-user-name
-  password: <%= ENV.fetch("MRSK_REGISTRY_PASSWORD") %>
+  password:
+    - MRSK_REGISTRY_PASSWORD
 env:
   secret:
     - 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). 
-
-Finally, you have to ensure your application can answer `200 OK` to a `GET /up` request. That's how the zero-downtime deploy process knows that your new version is ready to serve traffic.
+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:
 
 ```
-mrsk deploy
+mrsk setup
 ```
 
 This will:
 
-1. Connect to the servers over SSH (using root by default, authenticated by your loaded ssh key)
-2. Install Docker on any server that might be missing it (using apt-get)
+1. Connect to the servers over SSH (using root by default, authenticated by your ssh key)
+2. Install Docker and curl 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.
-6. Pull the image from the registry on the servers.
+6. Pull the image from the registry onto the servers.
 7. Ensure Traefik is running and accepting traffic on port 80.
-8. Stop any containers running a previous versions of the app.
+8. Ensure your app responds with `200 OK` to `GET /up` (you must have curl installed inside your app image!).
 9. Start a new container with the version of the app that matches the current git version hash.
-10. Prune unused images and stopped containers to ensure servers don't fill up.
+10. Stop the old container running the previous version of the app.
+11. Prune unused images and stopped containers to ensure servers don't fill up.
 
-Voila! All the servers are now serving the app on port 80. If you're just running a single server, you're ready to go. If you're running multiple servers, you need to put a load balancer in front of them.
+Voila! All the servers are now serving the app on port 80. If you're just running a single server, you're ready to go. If you're running multiple servers, you need to put a load balancer in front of them. For subsequent deploys, or if your servers already have Docker and curl installed, you can just run `mrsk deploy`.
+
+### Rails <7 usage
+
+MRSK is not needed to be in your application Gemfile to be used. However, if you want to guarantee specific MRSK version in your CI/CD workflows, you can create a separate Gemfile for MRSK, for example, `gemfile/mrsk.gemfile`:
+
+```ruby
+source 'https://rubygems.org'
+
+gem 'mrsk', '~> 0.14'
+```
+
+Bundle with `BUNDLE_GEMFILE=gemfiles/mrsk.gemfile bundle`.
+
+After this MRSK can be used for deployment:
+
+```sh
+BUNDLE_GEMFILE=gemfiles/mrsk.gemfile bundle exec mrsk deploy
+```
 
 ## Vision
 
-In the past decade+, there's been an explosion in commercial offerings that make deploying web apps easier. Heroku kicked it off with an incredible offering that stayed ahead of the competition seemingly forever. These days we have excellent alternatives like Fly.io and Render. And hosted Kubernetes is making things easier too on AWS, GCP, Digital Ocean, and elsewhere. But these are all offerings that have you renting computers in the cloud at a premium. If you want to run on our own hardware, or even just have a clear migration path to do so, you need to carefully consider how locked in you get to these commercial platforms. Preferably before the bills swallow your business whole!
+In the past decade+, there's been an explosion in commercial offerings that make deploying web apps easier. Heroku kicked it off with an incredible offering that stayed ahead of the competition seemingly forever. These days we have excellent alternatives like Fly.io and Render. And hosted Kubernetes is making things easier too on AWS, GCP, Digital Ocean, and elsewhere. But these are all offerings that have you renting computers in the cloud at a premium. If you want to run on your own hardware, or even just have a clear migration path to do so in the future, you need to carefully consider how locked in you get to these commercial platforms. Preferably before the bills swallow your business whole!
 
-MRSK seeks to bring the advance in ergonomics pioneered by these commercial offerings to deploying web apps anywhere. Whether that's low-cost cloud options without the managed-service markup from the likes of Digital Ocean, Hetzner, OVH, etc, or it's your own colocated metal. To MRSK, it's all the same. Feed the config file a list of IP addresses with vanilla Ubuntu servers that have seen no prep beyond an added SSH key, and you'll be running in literally minutes.
+MRSK seeks to bring the advance in ergonomics pioneered by these commercial offerings to deploying web apps anywhere. Whether that's low-cost cloud options without the managed-service markup from the likes of Digital Ocean, Hetzner, OVH, etc., or it's your own colocated bare metal. To MRSK, it's all the same. Feed the config file a list of IP addresses with vanilla Ubuntu servers that have seen no prep beyond an added SSH key, and you'll be running in literally minutes.
 
-This structure also gives you enormous portability. You can have your web app deployed on several clouds at ease like this. Or you can buy the baseline with your own hardware, then deploy to a cloud before a big seasonal spike to get more capacity. When you're not locked into a single provider from a tooling perspective, there's a lot of compelling options available.
+This approach gives you enormous portability. You can have your web app deployed on several clouds at ease like this. Or you can buy the baseline with your own hardware, then deploy to a cloud before a big seasonal spike to get more capacity. When you're not locked into a single provider from a tooling perspective, there are a lot of compelling options available.
 
-Ultimately, MRSK is meant to compress the complexity of going to production using open source tooling that isn't tied to any commercial offering. Not to zero, though. You're probably still better off with a fully managed service if basic Linux or Docker is still difficult, but from an early stage when those concepts are familiar.
+Ultimately, MRSK is meant to compress the complexity of going to production using open source tooling that isn't tied to any commercial offering. Not to zero, mind you. You're probably still better off with a fully managed service if basic Linux or Docker is still difficult, but as soon as those concepts are familiar, you'll be ready to go with MRSK.
 
 ## Why not just run Capistrano, Kubernetes or Docker Swarm?
 
-MRSK basically is Capistrano for Containers, which allow us to use vanilla servers as the hosts. No need to ensure that the servers have just the right version of Ruby or other dependencies you need. That all lives in the Docker image now. You can boot a brand new Ubuntu (or whatever) server, add it to the deploy servers of MRSK, and it'll be auto-provisioned with Docker, and run right away. Docker's layer caching also allows for quicker deployments with less mucking about on the server. And the images built for MRSK can be used for CI or later introspection.
+MRSK basically is Capistrano for Containers, without the need to carefully prepare servers in advance. No need to ensure that the servers have just the right version of Ruby or other dependencies you need. That all lives in the Docker image now. You can boot a brand new Ubuntu (or whatever) server, add it to the list of servers in MRSK, and it'll be auto-provisioned with Docker, and run right away. Docker's layer caching also speeds up deployments with less mucking about on the server. And the images built for MRSK can be used for CI or later introspection.
 
 Kubernetes is a beast. Running it yourself on your own hardware is not for the faint of heart. It's a fine option if you want to run on someone else's platform, either transparently [like Render](https://thenewstack.io/render-cloud-deployment-with-less-engineering/) or explicitly on AWS/GCP, but if you'd like the freedom to move between cloud and your own hardware, or even mix the two, MRSK is much simpler. You can see everything that's going on, it's just basic Docker commands being called.
 
-Docker Swarm is much simpler than Kubernetes, but it's still built on the same declarative model that uses state reconciliation. MRSK is intentionally designed to around imperative commands, like Capistrano.
+Docker Swarm is much simpler than Kubernetes, but it's still built on the same declarative model that uses state reconciliation. MRSK is intentionally designed around imperative commands, like Capistrano.
+
+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
 
@@ -74,6 +122,73 @@ MRSK_REGISTRY_PASSWORD=pw
 DB_PASSWORD=secret123
 ```
 
+### Using a generated .env file
+
+#### 1Password as a secret store
+
+If you're using a centralized secret store, like 1Password, you can create `.env.erb` as a template which looks up the secrets. Example of a .env.erb file:
+
+```erb
+<% if (session_token = `op signin --account my-one-password-account --raw`.strip) != "" %># Generated by mrsk envify
+GITHUB_TOKEN=<%= `gh config get -h github.com oauth_token`.strip %>
+MRSK_REGISTRY_PASSWORD=<%= `op read "op://Vault/Docker Hub/password" -n --session  #{session_token}` %>
+RAILS_MASTER_KEY=<%= `op read "op://Vault/My App/RAILS_MASTER_SECRET" -n --session #{session_token}` %>
+MYSQL_ROOT_PASSWORD=<%= `op read "op://Vault/My App/MYSQL_ROOT_PASSWORD" -n --session #{session_token}` %>
+<% else raise ArgumentError, "Session token missing" end %>
+```
+
+This template can safely be checked into git. Then everyone deploying the app can run `mrsk envify` when they setup the app for the first time or passwords change to get the correct `.env` file.
+
+If you need separate env variables for different destinations, you can set them with `.env.destination.erb` for the template, which will generate `.env.staging` when run with `mrsk envify -d staging`.
+
+Note: If you utilize biometrics with 1Password you can remove the `session_token` related parts in the example and just call `op read op://Vault/Docker Hub/password -n`.
+
+#### 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.
+
+You can store `SOME_SECRET` in a secure note in bitwarden vault.
+
+```
+$ bw list items --search SOME_SECRET | jq
+? Master password: [hidden]
+
+[
+  {
+    "object": "item",
+    "id": "123123123-1232-4224-222f-234234234234",
+    "organizationId": null,
+    "folderId": null,
+    "type": 2,
+    "reprompt": 0,
+    "name": "SOME_SECRET",
+    "notes": "yyy",
+    "favorite": false,
+    "secureNote": {
+      "type": 0
+    },
+    "collectionIds": [],
+    "revisionDate": "2023-02-28T23:54:47.868Z",
+    "creationDate": "2022-11-07T03:16:05.828Z",
+    "deletedDate": null
+  }
+]
+```
+
+and extract the `id` of `SOME_SECRET` from the `json` above and use in the `erb` below.
+
+
+Example `.env.erb` file:
+
+```erb
+<% if (session_token=`bw unlock --raw`.strip) != "" %># Generated by mrsk envify
+SOME_SECRET=<%= `bw get notes 123123123-1232-4224-222f-234234234234 --session #{session_token}` %>
+<% else raise ArgumentError, "session_token token missing" end %>
+```
+
+Then everyone deploying the app can run `mrsk envify` and mrsk will generate `.env`
+
+
 ### Using another registry than Docker Hub
 
 The default registry is Docker Hub, but you can change it using `registry/server`:
@@ -81,10 +196,27 @@ The default registry is Docker Hub, but you can change it using `registry/server
 ```yaml
 registry:
   server: registry.digitalocean.com
-  username: registry-user-name
-  password: <%= ENV.fetch("MRSK_REGISTRY_PASSWORD") %>
+  username:
+    - DOCKER_REGISTRY_TOKEN
+  password:
+    - DOCKER_REGISTRY_TOKEN
 ```
 
+A reference to secret `DOCKER_REGISTRY_TOKEN` will look for `ENV["DOCKER_REGISTRY_TOKEN"]` on the machine running MRSK.
+
+#### Using AWS ECR as the container registry
+
+AWS ECR's access token is only valid for 12hrs. In order to not have to manually regenerate the token every time, you can use ERB in the `deploy.yml` file to shell out to the `aws` cli command, and obtain the token:
+
+```yaml
+registry:
+  server: <your aws account id>.dkr.ecr.<your aws region id>.amazonaws.com
+  username: AWS
+  password: <%= %x(aws ecr get-login-password) %>
+```
+
+You will need to have the `aws` CLI installed locally for this to work.
+
 ### Using a different SSH user than root
 
 The default SSH user is root, but you can change it using `ssh/user`:
@@ -94,6 +226,15 @@ ssh:
   user: app
 ```
 
+If you are using non-root user (`app` as above example), 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 app
+```
+
 ### Using a proxy SSH host
 
 If you need to connect to server through a proxy host, you can use `ssh/proxy`:
@@ -110,6 +251,13 @@ 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`:
@@ -149,6 +297,12 @@ 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:
@@ -183,12 +337,13 @@ 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 extra quotes are needed to ensure the rule is passed in correctly!
+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.
@@ -209,9 +364,78 @@ 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:
+
+```yaml
+servers:
+  web:
+    - 192.168.0.1
+    - 192.168.0.2
+  job:
+    hosts:
+      - 192.168.0.3
+      - 192.168.0.4
+    cmd: bin/jobs
+    options:
+      cap-add: true
+      cpu-count: 4
+```
+
+That'll start the job containers with `docker run ... --cap-add --cpu-count 4 ...`.
+
+### Setting a minimum version
+
+You can set the minimum MRSK version with:
+
+```yaml
+minimum_version: 0.13.3
+```
+
+Note: versions <= 0.13.2 will ignore this setting.
+
+### 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-archecture 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.
+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.
 
 If you want to speed up this process by using a remote AMD64 host to natively build the AMD64 part of the image, while natively building the ARM64 part locally, you can do so using builder options:
 
@@ -249,9 +473,60 @@ builder:
 
 This is also a good option if you're running MRSK from a CI server that shares architecture with the deployment servers.
 
+### Using a different Dockerfile or context when building
+
+If you need to pass a different Dockerfile or context to the build command (e.g. if you're using a monorepo or you have
+different Dockerfiles), you can do so in the builder options:
+
+```yaml
+# Use a different Dockerfile
+builder:
+  dockerfile: Dockerfile.xyz
+
+# Set context
+builder:
+  context: ".."
+
+# Set Dockerfile and context
+builder:
+  dockerfile: "../Dockerfile.xyz"
+  context: ".."
+```
+
+### Using multistage builder cache
+
+Docker multistage build cache can singlehandedly speed up your builds by a lot. Currently MRSK only supports using the GHA cache or the Registry cache:
+
+```yaml
+# Using GHA cache
+builder:
+  cache:
+    type: gha
+
+# Using Registry cache
+builder:
+  cache:
+    type: registry
+
+# Using Registry cache with different cache image
+builder:
+  cache:
+    type: registry
+    # default image name is <image>-build-cache
+    image: application-cache-image
+
+# Using Registry cache with additinonal cache-to options
+builder:
+  cache:
+    type: registry
+    options: mode=max,image-manifest=true,oci-mediatypes=true
+```
+
+For further insights into build cache optimization, check out documentation on Docker's official website: https://docs.docker.com/build/cache/.
+
 ### Using build secrets for new images
 
-Some images need a secret passed in during build time, like a GITHUB_TOKEN to give access to private gem repositories. This can be done by having the secret in ENV, then referencing it in the builder configuration:
+Some images need a secret passed in during build time, like a GITHUB_TOKEN, to give access to private gem repositories. This can be done by having the secret in ENV, then referencing it in the builder configuration:
 
 ```yaml
 builder:
@@ -272,9 +547,9 @@ 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:
@@ -283,7 +558,99 @@ 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 host port binding
+
+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
+    volume:
+      - /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'
+```
+
+### Rebooting Traefik
+
+If you make changes to Traefik args or labels, you'll need to reboot with:
+
+`mrsk traefik reboot`
+
+In production, reboot the Traefik containers one by one with a slower but safer approach, using a rolling reboot:
+
+`mrsk traefik reboot --rolling`
 
 ### Configuring build args for new images
 
@@ -298,14 +665,13 @@ builder:
 This build argument can then be used in the Dockerfile:
 
 ```
-# Private repositories need an access token during the build
 ARG RUBY_VERSION
 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:
@@ -320,56 +686,99 @@ 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.
 
-### Using a generated .env file
+Accessory images must be public or tagged in your private registry.
 
-If you're using a centralized secret store, like 1Password, you can create `.env.erb` as a template which looks up the secrets. Example of a .env.erb file:
+### Using Cron
 
-```erb
-<% if (session_token = `op signin --account my-one-password-account --raw`.strip) != "" %># Generated by mrsk envify
-GITHUB_TOKEN=<%= `gh config get -h github.com oauth_token`.strip %>
-MRSK_REGISTRY_PASSWORD=<%= `op read "op://Vault/Docker Hub/password" -n --session  #{session_token}` %>
-RAILS_MASTER_KEY=<%= `op read "op://Vault/My App/RAILS_MASTER_SECRET" -n --session #{session_token}` %>
-MYSQL_ROOT_PASSWORD=<%= `op read "op://Vault/My App/MYSQL_ROOT_PASSWORD" -n --session #{session_token}` %>
-<% else raise ArgumentError, "Session token missing" end %>
-```
-
-This template can safely be checked into git. Then everyone deploying the app can run `mrsk envify` when they setup the app for the first time or passwords change to get the correct `.env` file.
-
-If you need separate env variables for different destinations, you can set them with `.env.destination.erb` for the template, which will generate `.env.staging` when run with `mrsk envify -d staging`.
-
-### Using audit broadcasts
-
-If you'd like to broadcast audits of deploys, rollbacks, etc to a chatroom or elsewhere, you can configure the `audit_broadcast_cmd` setting with the path to a bin file that reads the audit line from STDIN, and then does whatever with it:
+You can use a specific container to run your Cron jobs:
 
 ```yaml
-audit_broadcast_cmd:
-  bin/audit_broadcast
+servers:
+  cron:
+    hosts:
+      - 192.168.0.1
+    cmd:
+      bash -c "cat config/crontab | crontab - && cron -f"
 ```
 
-The broadcast command could look something like:
+This assumes the Cron settings are stored in `config/crontab`.
 
-```bash
-#!/usr/bin/env bash
-read
-curl -q -d content="[My app] ${REPLY}" https://3.basecamp.com/XXXXX/integrations/XXXXX/buckets/XXXXX/chats/XXXXX/lines
+### Healthcheck
+
+MRSK uses Docker healthchecks 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
+  interval: 20s
 ```
 
-That'll post a line like follows to a preconfigured chatbot in Basecamp:
+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
 ```
-[My App] [2023-02-18 11:29:52] [dhh] Rolled back to version d264c4e92470ad1bd18590f04466787262f605de
+
+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
@@ -437,7 +846,7 @@ mrsk app exec -i 'bin/rails console'
 ```
 
 
-### Running details to see state of containers
+### Running details to show state of containers
 
 You can see the state of your servers by running `mrsk details`:
 
@@ -485,9 +894,105 @@ 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-<service>` 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 maintenance"
+```
+
+```
+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.
+
+## Hooks
+
+You can run custom scripts at specific points with hooks.
+
+Hooks should be stored in the .mrsk/hooks folder. Running mrsk init will build that folder and add some sample scripts.
+
+You can change their location by setting `hooks_path` in the configuration file.
+
+If the script returns a non-zero exit code the command will be aborted.
+
+`MRSK_*` environment variables are available to the hooks 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_SERVICE_VERSION` - an abbreviated service and version for use in messages, e.g. app@150b24f
+- `MRSK_VERSION` - the full version being deployed
+- `MRSK_HOSTS` - a comma-separated list of the hosts targeted by the command
+- `MRSK_COMMAND` - The command we are running
+- `MRSK_SUBCOMMAND` - optional: The subcommand we are running
+- `MRSK_DESTINATION` - optional: destination, e.g. "staging"
+- `MRSK_ROLE` - optional: role targeted, e.g. "web"
+
+There are four hooks:
+
+1. pre-connect
+Called before taking the deploy lock. For checks that need to run before connecting to remote hosts - e.g. DNS warming.
+
+2. pre-build
+Used for pre-build checks - e.g. there are no uncommitted changes or that CI has passed.
+
+3. pre-deploy
+For final checks before deploying, e.g. checking CI completed
+
+3. post-deploy - run after a deploy, redeploy or rollback.
+This hook is also passed a `MRSK_RUNTIME` env variable set to the total seconds the deploy took.
+
+This could be used to broadcast a deployment message, or register the new version with an APM.
+
+The command could look something like:
+
+```bash
+#!/usr/bin/env bash
+curl -q -d content="[My App] ${MRSK_PERFORMER} Rolled back to version ${MRSK_VERSION}" https://3.basecamp.com/XXXXX/integrations/XXXXX/buckets/XXXXX/chats/XXXXX/lines
+```
+
+That'll post a line like the following to a preconfigured chatbot in Basecamp:
+
+```
+[My App] [dhh] Rolled back to version d264c4e92470ad1bd18590f04466787262f605de
+```
+
+Set `--skip_hooks` to avoid running the hooks.
+
 ## Stage of development
 
-This is alpha software. Lots of stuff is missing. Lots of stuff will keep moving around for a while.
+This is beta software. Commands may still move around. But we're live in production at [37signals](https://37signals.com).
 
 ## License
 

bin/mrsk

@@ -8,9 +8,11 @@ require "mrsk"
 begin
   Mrsk::Cli::Main.start(ARGV)
 rescue SSHKit::Runner::ExecuteError => e
-  puts "  \e[31mERROR (#{e.cause.class}): #{e.cause.message}\e[0m"
+  puts "  \e[31mERROR (#{e.cause.class}): #{e.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 +1,6 @@
 module Mrsk::Cli
+  class LockError < StandardError; end
+  class HookError < StandardError; end
 end
 
 # SSHKit uses instance eval, so we need a global const for ergonomics

lib/mrsk/cli/accessory.rb

@@ -1,98 +1,115 @@
 class Mrsk::Cli::Accessory < Mrsk::Cli::Base
-  desc "boot [NAME]", "Boot 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)
+  desc "boot [NAME]", "Boot new accessory service on host (use NAME=all to boot all accessories)"
+  def boot(name, login: true)
+    mutating 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 if login
+            execute *MRSK.auditor.record("Booted #{name} accessory"), verbosity: :debug
+            execute *accessory.run
+          end
         end
-
-        audit_broadcast "Booted accessory #{name}"
       end
     end
   end
 
-  desc "upload [NAME]", "Upload accessory files to host"
+  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)
+    mutating 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
   end
 
-  desc "directories [NAME]", "Create accessory directories on host"
+  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)
+    mutating 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
   end
 
-  desc "reboot [NAME]", "Reboot accessory on host (stop container, remove container, start new container)"
+  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)
+    mutating do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *MRSK.registry.login
+        end
+
+        stop(name)
+        remove_container(name)
+        boot(name, login: false)
+      end
     end
   end
 
-  desc "start [NAME]", "Start existing accessory on host"
+  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
+    mutating 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 accessory on host"
+  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
+    mutating 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 accessory on host"
+  desc "restart [NAME]", "Restart existing accessory container on host"
   def restart(name)
-    with_accessory(name) do
-      stop(name)
-      start(name)
+    mutating do
+      with_accessory(name) do
+        stop(name)
+        start(name)
+      end
     end
   end
 
-  desc "details [NAME]", "Display details about accessory on host (use NAME=all to boot all accessories)"
+  desc "details [NAME]", "Show details about accessory on host (use NAME=all to show all accessories)"
   def details(name)
     if name == "all"
       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
 
-  desc "exec [NAME] [CMD]", "Execute a custom command on servers"
+  desc "exec [NAME] [CMD]", "Execute a custom command on servers (use --help to show options)"
   option :interactive, aliases: "-i", type: :boolean, default: false, desc: "Execute command over ssh for an interactive shell (use for console/bash)"
   option :reuse, type: :boolean, default: false, desc: "Reuse currently running container instead of starting a new one"
   def exec(name, cmd)
@@ -108,14 +125,14 @@ 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
@@ -123,7 +140,7 @@ class Mrsk::Cli::Accessory < Mrsk::Cli::Base
     end
   end
 
-  desc "logs [NAME]", "Show log lines from accessory on host"
+  desc "logs [NAME]", "Show log lines from accessory on host (use --help to show options)"
   option :since, aliases: "-s", desc: "Show logs since timestamp (e.g. 2013-01-02T13:23:37Z) or relative (e.g. 42m for 42 minutes)"
   option :lines, type: :numeric, aliases: "-n", desc: "Number of log lines to pull from each server"
   option :grep, aliases: "-g", desc: "Show lines with grep match only (use this to fetch specific requests by id)"
@@ -134,7 +151,7 @@ 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
@@ -142,52 +159,63 @@ 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 boot 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
-      with_accessory(name) do
-        stop(name)
-        remove_container(name)
-        remove_image(name)
-        remove_service_directory(name)
+    mutating 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
   end
 
-  desc "remove_container [NAME]", "Remove accessory container from host"
+  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
+    mutating 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"
+  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
+    mutating 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"
+  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
+    mutating do
+      with_accessory(name) do |accessory|
+        on(accessory.hosts) do
+          execute *accessory.remove_service_directory
+        end
       end
     end
   end

lib/mrsk/cli/app.rb

@@ -1,26 +1,39 @@
 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} (or reboot if already running)...", :magenta
+    mutating do
+      hold_lock_on_error 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
 
-      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
-            execute *MRSK.app.stop, raise_on_non_zero_exit: false
-            execute *MRSK.app.run(role: role.name)
-          rescue SSHKit::Command::Failed => e
-            if e.message =~ /already in use/
-              error "Rebooting container with same version already deployed on #{host}"
-              execute *MRSK.auditor.record("Rebooted app version #{version}"), verbosity: :debug
+          on(MRSK.hosts, **MRSK.boot_strategy) do |host|
+            roles = MRSK.roles_on(host)
 
-              execute *MRSK.app.remove_container(version: version)
-              execute *MRSK.app.run(role: role.name)
-            else
-              raise
+            roles.each do |role|
+              app = MRSK.app(role: role)
+              auditor = MRSK.auditor(role: role)
+
+              if capture_with_info(*app.container_id_for_version(version, only_running: true), raise_on_non_zero_exit: false).present?
+                tmp_version = "#{version}_replaced_#{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
+
+              execute *auditor.record("Booted app version #{version}"), verbosity: :debug
+
+              old_version = capture_with_info(*app.current_running_version, raise_on_non_zero_exit: false).strip
+              execute *app.start_or_run(hostname: "#{host}-#{SecureRandom.hex(6)}")
+
+              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
@@ -28,28 +41,47 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
     end
   end
 
-  desc "start", "Start existing app on servers (use --version=<git-hash> to designate specific version)"
+  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
+    mutating 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 on servers"
+  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
+    mutating 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
 
-  desc "details", "Display details about app containers"
+  # 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"
+  desc "exec [CMD]", "Execute a custom command on servers (use --help to show options)"
   option :interactive, aliases: "-i", type: :boolean, default: false, desc: "Execute command over ssh for an interactive shell (use for console/bash)"
   option :reuse, type: :boolean, default: false, desc: "Reuse currently running container instead of starting a new one"
   def exec(cmd)
@@ -58,12 +90,12 @@ 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
@@ -74,14 +106,18 @@ 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
@@ -91,21 +127,46 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
     end
   end
 
-  desc "containers", "List all the app containers currently on servers"
+  desc "containers", "Show app containers on servers"
   def containers
     on(MRSK.hosts) { |host| puts_by_host host, capture_with_info(*MRSK.app.list_containers) }
   end
 
-  desc "images", "List all the app images currently on servers"
+  desc "stale_containers", "Detect app stale containers"
+  option :stop, aliases: "-s", type: :boolean, default: false, desc: "Stop the stale containers found"
+  def stale_containers
+    mutating 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) }
   end
 
-  desc "logs", "Show lines from app on servers"
-  option :since, aliases: "-s", desc: "Show logs since timestamp (e.g. 2013-01-02T13:23:37Z) or relative (e.g. 42m for 42 minutes)"
-  option :lines, type: :numeric, aliases: "-n", desc: "Number of log lines to pull from each server"
+  desc "logs", "Show log lines from app on servers (use --help to show options)"
+  option :since, aliases: "-s", desc: "Show lines since timestamp (e.g. 2013-01-02T13:23:37Z) or relative (e.g. 42m for 42 minutes)"
+  option :lines, type: :numeric, aliases: "-n", desc: "Number of lines to show from each server"
   option :grep, aliases: "-g", desc: "Show lines with grep match only (use this to fetch specific requests by id)"
-  option :follow, aliases: "-f", desc: "Follow logs on primary server (or specific host set by --hosts)"
+  option :follow, aliases: "-f", desc: "Follow log on primary server (or specific host set by --hosts)"
   def logs
     # FIXME: Catch when app containers aren't running
 
@@ -114,18 +175,26 @@ 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
@@ -133,36 +202,53 @@ class Mrsk::Cli::App < Mrsk::Cli::Base
 
   desc "remove", "Remove app containers and images from servers"
   def remove
-    remove_containers
-    remove_images
+    mutating do
+      stop
+      remove_containers
+      remove_images
+    end
   end
 
-  desc "remove_container [VERSION]", "Remove app container with given version from servers"
+  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)
+    mutating 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"
+  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
+    mutating 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"
+  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
+    mutating do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Removed all app images"), verbosity: :debug
+        execute *MRSK.app.remove_images
+      end
     end
   end
 
-  desc "current_version", "Shows the version currently running"
-  def current_version
+  desc "version", "Show app version currently running on servers"
+  def version
     on(MRSK.hosts) { |host| puts_by_host host, capture_with_info(*MRSK.app.current_running_version).strip }
   end
 
@@ -181,15 +267,24 @@ 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 }
-      version.presence
-    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

@@ -17,13 +17,15 @@ module Mrsk::Cli
     class_option :hosts, aliases: "-h", desc: "Run commands on these hosts instead of all (separate by comma)"
     class_option :roles, aliases: "-r", desc: "Run commands on these roles instead of all (separate by comma)"
 
-    class_option :config_file, aliases: "-c", default: "config/deploy.yml", desc: "Path to config file (default: config/deploy.yml)"
-    class_option :destination, aliases: "-d", desc: "Specify destination to be used for config file (west -> deploy.west.yml)"
+    class_option :config_file, aliases: "-c", default: "config/deploy.yml", desc: "Path to config file"
+    class_option :destination, aliases: "-d", desc: "Specify destination to be used for config file (staging -> deploy.staging.yml)"
+
+    class_option :skip_hooks, aliases: "-H", type: :boolean, default: false, desc: "Don't run hooks"
 
     def initialize(*)
       super
       load_envs
-      initialize_commander(options)
+      initialize_commander(options_with_subcommand_class_options)
     end
 
     private
@@ -35,16 +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
@@ -53,6 +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
 
@@ -65,8 +72,100 @@ module Mrsk::Cli
         puts "  Finished all in #{sprintf("%.1f seconds", runtime)}"
       end
 
-      def audit_broadcast(line)
-        run_locally { execute *MRSK.auditor.broadcast(line), verbosity: :debug }
+      def mutating
+        return yield if MRSK.holding_lock?
+
+        MRSK.config.ensure_env_available
+
+        run_hook "pre-connect"
+
+        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
+        raise_if_locked do
+          say "Acquiring the deploy lock...", :magenta
+          on(MRSK.primary_host) { execute *MRSK.lock.acquire("Automatic deploy lock", MRSK.config.version), verbosity: :debug }
+        end
+
+        MRSK.holding_lock = true
+      end
+
+      def release_lock
+        say "Releasing the deploy lock...", :magenta
+        on(MRSK.primary_host) { execute *MRSK.lock.release, verbosity: :debug }
+
+        MRSK.holding_lock = false
+      end
+
+      def raise_if_locked
+        yield
+      rescue SSHKit::Runner::ExecuteError => e
+        if e.message =~ /cannot create directory/
+          on(MRSK.primary_host) { puts capture_with_debug(*MRSK.lock.status) }
+          raise LockError, "Deploy lock found"
+        else
+          raise e
+        end
+      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
+
+      def run_hook(hook, **extra_details)
+        if !options[:skip_hooks] && MRSK.hook.hook_exists?(hook)
+          details = { hosts: MRSK.hosts.join(","), command: command, subcommand: subcommand }
+
+          say "Running the #{hook} hook...", :magenta
+          run_locally do
+            MRSK.with_verbosity(:debug) { execute *MRSK.hook.run(hook, **details, **extra_details) }
+          rescue SSHKit::Command::Failed
+            raise HookError.new("Hook `#{hook}` failed")
+          end
+        end
+      end
+
+      def command
+        @mrsk_command ||= begin
+          invocation_class, invocation_commands = *first_invocation
+          if invocation_class == Mrsk::Cli::Main
+            invocation_commands[0]
+          else
+            Mrsk::Cli::Main.subcommand_classes.find { |command, clazz| clazz == invocation_class }[0]
+          end
+        end
+      end
+
+      def subcommand
+        @mrsk_subcommand ||= begin
+          invocation_class, invocation_commands = *first_invocation
+          invocation_commands[0] if invocation_class != Mrsk::Cli::Main
+        end
+      end
+
+      def first_invocation
+        instance_variable_get("@_invocations").first
+      end
+    end
 end

lib/mrsk/cli/build.rb

@@ -1,69 +1,100 @@
 class Mrsk::Cli::Build < Mrsk::Cli::Base
-  desc "deliver", "Deliver a newly built app image to servers"
+  class BuildError < StandardError; end
+
+  desc "deliver", "Build app and push app image to registry then pull image on servers"
   def deliver
-    invoke :push
-    invoke :pull
+    mutating do
+      push
+      pull
+    end
   end
 
-  desc "push", "Build locally and push app image to registry"
+  desc "push", "Build and push app image to registry"
   def push
-    cli = self
+    mutating 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"
+      verify_local_dependencies
+      run_hook "pre-build"
 
-          if cli.create
-            MRSK.with_verbosity(:debug) { execute *MRSK.builder.push }
+      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
+              MRSK.with_verbosity(:debug) { execute *MRSK.builder.push }
+            end
+          else
+            raise
           end
-        else
-          raise
         end
       end
     end
   end
 
-  desc "pull", "Pull app image from the registry onto servers"
+  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.pull
+    mutating 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 local build setup"
+  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
+    mutating 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
   end
 
-  desc "remove", "Remove local build setup"
+  desc "remove", "Remove build setup"
   def remove
-    run_locally do
-      debug "Using builder: #{MRSK.builder.name}"
-      execute *MRSK.builder.remove
+    mutating do
+      run_locally do
+        debug "Using builder: #{MRSK.builder.name}"
+        execute *MRSK.builder.remove
+      end
     end
   end
 
-  desc "details", "Show the name of the configured builder"
+  desc "details", "Show build setup"
   def details
     run_locally do
       puts "Builder: #{MRSK.builder.name}"
       puts capture(*MRSK.builder.info)
     end
   end
+
+  private
+    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
+    end
 end

lib/mrsk/cli/healthcheck.rb

@@ -0,0 +1,20 @@
+class Mrsk::Cli::Healthcheck < Mrsk::Cli::Base
+  default_command :perform
+
+  desc "perform", "Health check current app version"
+  def perform
+    on(MRSK.primary_host) do
+      begin
+        execute *MRSK.healthcheck.run
+        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)
+        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
+      end
+    end
+  end
+end

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_debug(*MRSK.lock.status) }
+    end
+  end
+
+  desc "acquire", "Acquire the deploy lock"
+  option :message, aliases: "-m", type: :string, desc: "A lock message", required: true
+  def acquire
+    message = options[:message]
+    raise_if_locked do
+      on(MRSK.primary_host) { execute *MRSK.lock.acquire(message, MRSK.config.version), verbosity: :debug }
+      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, verbosity: :debug }
+      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

@@ -1,65 +1,109 @@
 class Mrsk::Cli::Main < Mrsk::Cli::Base
-  desc "setup", "Setup all accessories and deploy the app to servers"
+  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
+      mutating do
+        invoke "mrsk:cli:server:bootstrap"
+        invoke "mrsk:cli:accessory:boot", [ "all" ]
+        deploy
+      end
     end
   end
 
-  desc "deploy", "Deploy the app to servers"
+  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 Docker is installed...", :magenta
-      invoke "mrsk:cli:server:bootstrap"
+      mutating do
+        invoke_options = deploy_options
 
-      say "Log into image registry...", :magenta
-      invoke "mrsk:cli:registry:login"
+        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"
+        run_hook "pre-deploy"
 
-      invoke "mrsk:cli:app:boot"
+        say "Ensure Traefik is running...", :magenta
+        invoke "mrsk:cli:traefik:boot", [], invoke_options
 
-      say "Prune old containers and images...", :magenta
-      invoke "mrsk:cli:prune:all"
+        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
+
+        invoke "mrsk:cli:app:boot", [], invoke_options
+
+        say "Prune old containers and images...", :magenta
+        invoke "mrsk:cli:prune:all", [], invoke_options
+      end
     end
 
-    audit_broadcast "Deployed in #{runtime.to_i} seconds"
+    run_hook "post-deploy", runtime: runtime.round
   end
 
-  desc "redeploy", "Deploy new version of the app to servers (without bootstrapping servers, starting Traefik, pruning, and registry login)"
+  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"
+      mutating do
+        invoke_options = deploy_options
 
-      invoke "mrsk:cli:app:boot"
+        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
+
+        run_hook "pre-deploy"
+
+        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
+
+        invoke "mrsk:cli:app:boot", [], invoke_options
+      end
     end
 
-    audit_broadcast "Redeployed in #{runtime.to_i} seconds"
+    run_hook "post-deploy", runtime: runtime.round
   end
 
-  desc "rollback [VERSION]", "Rollback the app to VERSION"
+  desc "rollback [VERSION]", "Rollback app to VERSION"
   def rollback(version)
-    MRSK.version = version
+    rolled_back = false
+    runtime = print_runtime do
+      mutating do
+        invoke_options = deploy_options
 
-    cli = self
+        MRSK.config.version = version
+        old_version = nil
 
-    cli.say "Stop current version, then start version #{version}...", :magenta
-    on(MRSK.hosts) do
-      execute *MRSK.app.stop, raise_on_non_zero_exit: false
-      execute *MRSK.app.start
+        if container_available?(version)
+          run_hook "pre-deploy"
+
+          invoke "mrsk:cli:app:boot", [], invoke_options.merge(version: version)
+          rolled_back = true
+        else
+          say "The app version '#{version}' is not available as a container (use 'mrsk app containers' for available versions)", :red
+        end
+      end
     end
 
-    audit_broadcast "Rolled back to version #{version}"
+    run_hook "post-deploy", runtime: runtime.round if rolled_back
   end
 
-  desc "details", "Display details about Traefik and app containers"
+  desc "details", "Show details about all containers"
   def details
     invoke "mrsk:cli:traefik:details"
     invoke "mrsk:cli:app:details"
@@ -73,10 +117,10 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
     end
   end
 
-  desc "config", "Show combined config"
+  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
 
@@ -98,13 +142,23 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
       puts "Created .env file"
     end
 
+    unless (hooks_dir = Pathname.new(File.expand_path(".mrsk/hooks"))).exist?
+      hooks_dir.mkpath
+      Pathname.new(File.expand_path("templates/sample_hooks", __dir__)).each_child do |sample_hook|
+        FileUtils.cp sample_hook, hooks_dir, preserve: true
+      end
+      puts "Created sample hooks in .mrsk/hooks"
+    end
+
     if options[:bundle]
       if (binstub = Pathname.new(File.expand_path("bin/mrsk"))).exist?
         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
@@ -123,36 +177,73 @@ class Mrsk::Cli::Main < Mrsk::Cli::Base
     File.write(env_path, ERB.new(File.read(env_template_path)).result, perm: 0600)
   end
 
-  desc "remove", "Remove Traefik, app, and registry session from servers"
+  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
-    invoke "mrsk:cli:traefik:remove"
-    invoke "mrsk:cli:app:remove"
-    invoke "mrsk:cli:registry:logout"
+    mutating 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 "version", "Display the MRSK version"
+  desc "version", "Show MRSK version"
   def version
     puts Mrsk::VERSION
   end
 
-  desc "accessory", "Manage the accessories"
+  desc "accessory", "Manage accessories (db/redis/search)"
   subcommand "accessory", Mrsk::Cli::Accessory
 
-  desc "app", "Manage the application"
+  desc "app", "Manage application"
   subcommand "app", Mrsk::Cli::App
 
-  desc "build", "Build the application image"
+  desc "build", "Build application image"
   subcommand "build", Mrsk::Cli::Build
 
+  desc "healthcheck", "Healthcheck application"
+  subcommand "healthcheck", Mrsk::Cli::Healthcheck
+
+  desc "lock", "Manage the deploy lock"
+  subcommand "lock", Mrsk::Cli::Lock
+
   desc "prune", "Prune old application images and containers"
   subcommand "prune", Mrsk::Cli::Prune
 
-  desc "registry", "Login and out of the image registry"
+  desc "registry", "Login and -out of the image registry"
   subcommand "registry", Mrsk::Cli::Registry
 
-  desc "server", "Bootstrap servers with Docker"
+  desc "server", "Bootstrap servers with curl and Docker"
   subcommand "server", Mrsk::Cli::Server
 
-  desc "traefik", "Manage the Traefik load balancer"
+  desc "traefik", "Manage Traefik load balancer"
   subcommand "traefik", Mrsk::Cli::Traefik
+
+  private
+    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
 end

lib/mrsk/cli/prune.rb

@@ -1,23 +1,30 @@
 class Mrsk::Cli::Prune < Mrsk::Cli::Base
   desc "all", "Prune unused images and stopped containers"
   def all
-    invoke :containers
-    invoke :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
+    mutating do
+      containers
+      images
     end
   end
 
-  desc "containers", "Prune stopped containers for the service older than 3 days"
+  desc "images", "Prune dangling images"
+  def images
+    mutating do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Pruned images"), verbosity: :debug
+        execute *MRSK.prune.dangling_images
+        execute *MRSK.prune.tagged_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
+    mutating do
+      on(MRSK.hosts) do
+        execute *MRSK.auditor.record("Pruned containers"), verbosity: :debug
+        execute *MRSK.prune.containers
+      end
     end
   end
 end

lib/mrsk/cli/registry.rb

@@ -1,15 +1,17 @@
 class Mrsk::Cli::Registry < Mrsk::Cli::Base
-  desc "login", "Login to the registry locally and remotely"
+  desc "login", "Log in to registry locally and remotely"
   def login
     run_locally    { execute *MRSK.registry.login }
     on(MRSK.hosts) { execute *MRSK.registry.login }
+  # FIXME: This rescue needed?
   rescue ArgumentError => e
     puts e.message
   end
 
-  desc "logout", "Logout of the registry remotely"
+  desc "logout", "Log out of registry remotely"
   def logout
     on(MRSK.hosts) { execute *MRSK.registry.logout }
+  # FIXME: This rescue needed?
   rescue ArgumentError => e
     puts e.message
   end

lib/mrsk/cli/server.rb

@@ -1,6 +1,21 @@
 class Mrsk::Cli::Server < Mrsk::Cli::Base
-  desc "bootstrap", "Ensure Docker is installed on the servers"
+  desc "bootstrap", "Set up Docker to run MRSK apps"
   def bootstrap
-    on(MRSK.hosts + MRSK.accessory_hosts) { execute "which docker || (apt-get update -y && apt-get install docker.io -y)" }
+    missing = []
+
+    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

@@ -1,5 +1,4 @@
-# Name of your application. Used to uniquely configuring Traefik and app containers.
-# Your Dockerfile should set LABEL service=the-same-value to ensure image pruning works.
+# Name of your application. Used to uniquely configure containers.
 service: my-app
 
 # Name of the container image.
@@ -14,4 +13,62 @@ registry:
   # Specify the registry server, if you're not using Docker Hub
   # server: registry.digitalocean.com / ghcr.io / ...
   username: my-user
-  password: my-password-should-go-somewhere-safe
+
+  # Always use an access token rather than real password when possible.
+  password:
+    - MRSK_REGISTRY_PASSWORD
+
+# Inject ENV variables into containers (secrets come from .env).
+# env:
+#   clear:
+#     DB_HOST: 192.168.0.2
+#   secret:
+#     - RAILS_MASTER_KEY
+
+# Use a different ssh user than root
+# ssh:
+#   user: app
+
+# Configure builder setup.
+# builder:
+#   args:
+#     RUBY_VERSION: 3.2.0
+#   secrets:
+#     - GITHUB_TOKEN
+#   remote:
+#     arch: amd64
+#     host: ssh://app@192.168.0.1
+
+# Use accessory services (secrets come from .env).
+# accessories:
+#   db:
+#     image: mysql:8.0
+#     host: 192.168.0.2
+#     port: 3306
+#     env:
+#       clear:
+#         MYSQL_ROOT_HOST: '%'
+#       secret:
+#         - MYSQL_ROOT_PASSWORD
+#     files:
+#       - config/mysql/production.cnf:/etc/mysql/my.cnf
+#       - db/production.sql.erb:/docker-entrypoint-initdb.d/setup.sql
+#     directories:
+#       - data:/var/lib/mysql
+#   redis:
+#     image: redis:7.0
+#     host: 192.168.0.2
+#     port: 6379
+#     directories:
+#       - data:/data
+
+# Configure custom arguments for Traefik
+# traefik:
+#   args:
+#     accesslog: true
+#     accesslog.format: json
+
+# Configure a custom healthcheck (default is /up on port 3000)
+# healthcheck:
+#   path: /healthz
+#   port: 4000

lib/mrsk/cli/templates/sample_hooks/post-deploy.sample

@@ -0,0 +1,14 @@
+#!/bin/sh
+
+# A sample post-deploy hook
+#
+# These environment variables are available:
+# MRSK_RECORDED_AT
+# MRSK_PERFORMER
+# MRSK_VERSION
+# MRSK_HOSTS
+# MRSK_ROLE (if set)
+# MRSK_DESTINATION (if set)
+# MRSK_RUNTIME
+
+echo "$MRSK_PERFORMER deployed $MRSK_VERSION to $MRSK_DESTINATION in $MRSK_RUNTIME seconds"

lib/mrsk/cli/templates/sample_hooks/pre-build.sample

@@ -0,0 +1,51 @@
+#!/bin/sh
+
+# A sample pre-build hook
+#
+# Checks:
+# 1. We have a clean checkout
+# 2. A remote is configured
+# 3. The branch has been pushed to the remote
+# 4. The version we are deploying matches the remote
+#
+# These environment variables are available:
+# MRSK_RECORDED_AT
+# MRSK_PERFORMER
+# MRSK_VERSION
+# MRSK_HOSTS
+# MRSK_ROLE (if set)
+# MRSK_DESTINATION (if set)
+
+if [ -n "$(git status --porcelain)" ]; then
+  echo "Git checkout is not clean, aborting..." >&2
+  git status --porcelain >&2
+  exit 1
+fi
+
+first_remote=$(git remote)
+
+if [ -z "$first_remote" ]; then
+  echo "No git remote set, aborting..." >&2
+  exit 1
+fi
+
+current_branch=$(git branch --show-current)
+
+if [ -z "$current_branch" ]; then
+  echo "No git remote set, aborting..." >&2
+  exit 1
+fi
+
+remote_head=$(git ls-remote $first_remote --tags $current_branch | cut -f1)
+
+if [ -z "$remote_head" ]; then
+  echo "Branch not pushed to remote, aborting..." >&2
+  exit 1
+fi
+
+if [ "$MRSK_VERSION" != "$remote_head" ]; then
+  echo "Version ($MRSK_VERSION) does not match remote HEAD ($remote_head), aborting..." >&2
+  exit 1
+fi
+
+exit 0

lib/mrsk/cli/templates/sample_hooks/pre-connect.sample

@@ -0,0 +1,47 @@
+#!/usr/bin/env ruby
+
+# A sample pre-connect check
+#
+# Warms DNS before connecting to hosts in parallel
+#
+# These environment variables are available:
+# MRSK_RECORDED_AT
+# MRSK_PERFORMER
+# MRSK_VERSION
+# MRSK_HOSTS
+# MRSK_ROLE (if set)
+# MRSK_DESTINATION (if set)
+# MRSK_RUNTIME
+
+hosts = ENV["MRSK_HOSTS"].split(",")
+results = nil
+max = 3
+
+elapsed = Benchmark.realtime do
+  results = hosts.map do |host|
+    Thread.new do
+      tries = 1
+
+      begin
+        Socket.getaddrinfo(host, 0, Socket::AF_UNSPEC, Socket::SOCK_STREAM, nil, Socket::AI_CANONNAME)
+      rescue SocketError
+        if tries < max
+          puts "Retrying DNS warmup: #{host}"
+          tries += 1
+          sleep rand
+          retry
+        else
+          puts "DNS warmup failed: #{host}"
+          host
+        end
+      end
+
+      tries
+    end
+  end.map(&:value)
+end
+
+retries = results.sum - hosts.size
+nopes = results.count { |r| r == max }
+
+puts "Prewarmed %d DNS lookups in %.2f sec: %d retries, %d failures" % [ hosts.size, elapsed, retries, nopes ]

lib/mrsk/cli/templates/sample_hooks/pre-deploy.sample

@@ -0,0 +1,109 @@
+#!/usr/bin/env ruby
+
+# A sample pre-deploy hook
+#
+# Checks the Github status of the build, waiting for a pending build to complete for up to 720 seconds.
+#
+# Fails unless the combined status is "success"
+#
+# These environment variables are available:
+# MRSK_RECORDED_AT
+# MRSK_PERFORMER
+# MRSK_VERSION
+# MRSK_HOSTS
+# MRSK_COMMAND
+# MRSK_SUBCOMMAND
+# MRSK_ROLE (if set)
+# MRSK_DESTINATION (if set)
+
+# Only check the build status for production deployments
+if ENV["MRSK_COMMAND"] == "rollback" || ENV["MRSK_DESTINATION"] != "production"
+  exit 0
+end
+
+require "bundler/inline"
+
+# true = install gems so this is fast on repeat invocations
+gemfile(true, quiet: true) do
+  source "https://rubygems.org"
+
+  gem "octokit"
+  gem "faraday-retry"
+end
+
+MAX_ATTEMPTS = 72
+ATTEMPTS_GAP = 10
+
+def exit_with_error(message)
+  $stderr.puts message
+  exit 1
+end
+
+class GithubStatusChecks
+  attr_reader :remote_url, :git_sha, :github_client, :combined_status
+
+  def initialize
+    @remote_url = `git config --get remote.origin.url`.strip.delete_prefix("https://github.com/")
+    @git_sha = `git rev-parse HEAD`.strip
+    @github_client = Octokit::Client.new(access_token: ENV["GITHUB_TOKEN"])
+    refresh!
+  end
+
+  def refresh!
+    @combined_status = github_client.combined_status(remote_url, git_sha)
+  end
+
+  def state
+    combined_status[:state]
+  end
+
+  def first_status_url
+    first_status = combined_status[:statuses].find { |status| status[:state] == state }
+    first_status && first_status[:target_url]
+  end
+
+  def complete_count
+    combined_status[:statuses].count { |status| status[:state] != "pending"}
+  end
+
+  def total_count
+    combined_status[:statuses].count
+  end
+
+  def current_status
+    if total_count > 0
+      "Completed #{complete_count}/#{total_count} checks, see #{first_status_url} ..."
+    else
+      "Build not started..."
+    end
+  end
+end
+
+
+$stdout.sync = true
+
+puts "Checking build status..."
+attempts = 0
+checks = GithubStatusChecks.new
+
+begin
+  loop do
+    case checks.state
+    when "success"
+      puts "Checks passed, see #{checks.first_status_url}"
+      exit 0
+    when "failure"
+      exit_with_error "Checks failed, see #{checks.first_status_url}"
+    when "pending"
+      attempts += 1
+    end
+
+    exit_with_error "Checks are still pending, gave up after #{MAX_ATTEMPTS * ATTEMPTS_GAP} seconds" if attempts == MAX_ATTEMPTS
+
+    puts checks.current_status
+    sleep(ATTEMPTS_GAP)
+    checks.refresh!
+  end
+rescue Octokit::NotFound
+  exit_with_error "Build status could not be found"
+end

lib/mrsk/cli/traefik.rb

@@ -1,39 +1,57 @@
 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 }
+    mutating 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)"
+  option :rolling, type: :boolean, default: false, desc: "Reboot traefik on hosts in sequence, rather than in parallel"
   def reboot
-    invoke :stop
-    invoke :remove_container
-    invoke :boot
+    mutating do
+      on(MRSK.traefik_hosts, in: options[:rolling] ? :sequence : :parallel) do
+        execute *MRSK.auditor.record("Rebooted traefik"), verbosity: :debug
+        execute *MRSK.registry.login
+        execute *MRSK.traefik.stop, raise_on_non_zero_exit: false
+        execute *MRSK.traefik.remove_container
+        execute *MRSK.traefik.run, raise_on_non_zero_exit: false
+      end
+    end
   end
 
-  desc "start", "Start existing Traefik on servers"
+  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
+    mutating 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 Traefik on servers"
+  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
+    mutating 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 Traefik on servers"
+  desc "restart", "Restart existing Traefik container on servers"
   def restart
-    invoke :stop
-    invoke :start
+    mutating do
+      stop
+      start
+    end
   end
 
-  desc "details", "Display details about Traefik containers from servers"
+  desc "details", "Show details about Traefik container from servers"
   def details
     on(MRSK.traefik_hosts) { |host| puts_by_host host, capture_with_info(*MRSK.traefik.info), type: "Traefik" }
   end
@@ -64,24 +82,30 @@ class Mrsk::Cli::Traefik < Mrsk::Cli::Base
 
   desc "remove", "Remove Traefik container and image from servers"
   def remove
-    invoke :stop
-    invoke :remove_container
-    invoke :remove_image
-  end
-
-  desc "remove_container", "Remove Traefik container from servers"
-  def remove_container
-    on(MRSK.traefik_hosts) do
-      execute *MRSK.auditor.record("Removed traefik container"), verbosity: :debug
-      execute *MRSK.traefik.remove_container
+    mutating do
+      stop
+      remove_container
+      remove_image
     end
   end
 
-  desc "remove_container", "Remove Traefik image from servers"
+  desc "remove_container", "Remove Traefik container from servers", hide: true
+  def remove_container
+    mutating 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_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
+    mutating 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&.sole || 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
@@ -45,34 +76,49 @@ class Mrsk::Commander
   end
 
 
-  def app
-    @app ||= Mrsk::Commands::App.new(config)
-  end
-
-  def builder
-    @builder ||= Mrsk::Commands::Builder.new(config)
-  end
-
-  def traefik
-    @traefik ||= Mrsk::Commands::Traefik.new(config)
-  end
-
-  def registry
-    @registry ||= Mrsk::Commands::Registry.new(config)
-  end
-
-  def prune
-    @prune ||= Mrsk::Commands::Prune.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
+
+  def hook
+    @hook ||= Mrsk::Commands::Hook.new(config)
+  end
+
+  def lock
+    @lock ||= Mrsk::Commands::Lock.new(config)
+  end
+
+  def prune
+    @prune ||= Mrsk::Commands::Prune.new(config)
+  end
+
+  def registry
+    @registry ||= Mrsk::Commands::Registry.new(config)
+  end
+
+  def traefik
+    @traefik ||= Mrsk::Commands::Traefik.new(config)
+  end
 
   def with_verbosity(level)
     old_level = self.verbosity
@@ -86,26 +132,15 @@ 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)
@@ -10,14 +11,16 @@ class Mrsk::Commands::Accessory < Mrsk::Commands::Base
   def run
     docker :run,
       "--name", service_name,
-      "-d",
+      "--detach",
       "--restart", "unless-stopped",
-      "--log-opt", "max-size=#{MAX_LOG_SIZE}",
-      "-p", port,
+      *config.logging_args,
+      *publish_args,
       *env_args,
       *volume_args,
       *label_args,
-      image
+      *option_args,
+      image,
+      cmd
   end
 
   def start
@@ -35,14 +38,14 @@ class Mrsk::Commands::Accessory < Mrsk::Commands::Base
 
   def logs(since: nil, lines: nil, grep: nil)
     pipe \
-      docker(:logs, service_name, (" --since #{since}" if since), (" -n #{lines}" if lines), "-t", "2>&1"),
+      docker(:logs, service_name, (" --since #{since}" if since), (" --tail #{lines}" if lines), "--timestamps", "2>&1"),
       ("grep '#{grep}'" if grep)
   end
 
   def follow_logs(grep: nil)
     run_over_ssh \
       pipe \
-        docker(:logs, service_name, "-t", "-n", "10", "-f", "2>&1"),
+        docker(:logs, service_name, "--timestamps", "--tail", "10", "--follow", "2>&1"),
         (%(grep "#{grep}") if grep)
   end
 
@@ -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
 
 
@@ -96,11 +99,11 @@ class Mrsk::Commands::Accessory < Mrsk::Commands::Base
   end
 
   def remove_container
-    docker :container, :prune, "-f", *service_filter
+    docker :container, :prune, "--force", *service_filter
   end
 
   def remove_image
-    docker :image, :prune, "-a", "-f", *service_filter
+    docker :image, :rm, "--force", image
   end
 
   private

lib/mrsk/commands/app.rb

@@ -1,44 +1,67 @@
 class Mrsk::Commands::App < Mrsk::Commands::Base
-  def run(role: :web)
-    role = config.role(role)
+  ACTIVE_DOCKER_STATUSES = [ :running, :restarting ]
+
+  attr_reader :role
+
+  def initialize(config, role: nil)
+    super(config)
+    @role = role
+  end
+
+  def start_or_run(hostname: nil)
+    combine start, run(hostname: hostname), by: "||"
+  end
+
+  def run(hostname: nil)
+    role = config.role(self.role)
 
     docker :run,
-      "-d",
+      "--detach",
       "--restart unless-stopped",
-      "--log-opt", "max-size=#{MAX_LOG_SIZE}",
-      "--name", service_with_version,
+      "--name", container_name,
+      *(["--hostname", hostname] if hostname),
+      "-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,
       config.absolute_image,
       role.cmd
   end
 
   def start
-    docker :start, service_with_version
+    docker :start, container_name
   end
 
-  def stop
-    pipe current_container_id, xargs(docker(:stop))
+  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_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,
-      "xargs docker logs#{" --since #{since}" if since}#{" -n #{lines}" if lines} 2>&1",
+      current_running_container_id,
+      "xargs docker logs#{" --since #{since}" if since}#{" --tail #{lines}" if lines} 2>&1",
       ("grep '#{grep}'" if grep)
   end
 
   def follow_logs(host:, grep: nil)
     run_over_ssh \
       pipe(
-        current_container_id,
-        "xargs docker logs -t -n 10 -f 2>&1",
+        current_running_container_id,
+        "xargs docker logs --timestamps --tail 10 --follow 2>&1",
         (%(grep "#{grep}") if grep)
       ),
       host: host
@@ -48,7 +71,7 @@ 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
 
@@ -71,41 +94,45 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   end
 
 
-  def current_container_id
-    docker :ps, "-q", *service_filter
+  def current_running_container_id
+    docker :ps, "--quiet", *filter_args(statuses: ACTIVE_DOCKER_STATUSES), "--latest"
   end
 
-  def container_id_for(container_name:)
-    docker :container, :ls, "-a", "-f", "name=#{container_name}", "-q"
+  def container_id_for_version(version, only_running: false)
+    container_id_for(container_name: container_name(version), only_running: only_running)
   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", statuses: ACTIVE_DOCKER_STATUSES)
   end
 
-  def most_recent_version_from_available_images
+  def list_versions(*docker_args, statuses: nil)
     pipe \
-      docker(:image, :ls, "--format", '"{{.Tag}}"', config.repository),
-      "head -n 1"
+      docker(:ps, *filter_args(statuses: statuses), *docker_args, "--format", '"{{.Names}}"'),
+      %(grep -oE "\\-[^-]+$"), # Extract SHA from "service-role-dest-SHA"
+      %(cut -c 2-)
   end
 
-
   def list_containers
-    docker :container, :ls, "-a", *service_filter
+    docker :container, :ls, "--all", *filter_args
+  end
+
+  def list_container_names
+    [ *list_containers, "--format", "'{{ .Names }}'" ]
   end
 
   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, "-f", *service_filter
+    docker :container, :prune, "--force", *filter_args
   end
 
   def list_images
@@ -113,20 +140,30 @@ class Mrsk::Commands::App < Mrsk::Commands::Base
   end
 
   def remove_images
-    docker :image, :prune, "-a", "-f", *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
-      end
+    def container_name(version = nil)
+      [ config.service, role, config.destination, version || config.version ].compact.join("-")
     end
 
-    def service_filter
-      [ "--filter", "label=service=#{config.service}" ]
+    def filter_args(statuses: nil)
+      argumentize "--filter", filters(statuses: statuses)
+    end
+
+    def filters(statuses: nil)
+      [ "label=service=#{config.service}" ].tap do |filters|
+        filters << "label=destination=#{config.destination}" if config.destination
+        filters << "label=role=#{role}" if role
+        statuses&.each do |status|
+          filters << "status=#{status}"
+        end
+      end
     end
 end

lib/mrsk/commands/auditor.rb

@@ -1,20 +1,16 @@
-require "active_support/core_ext/time/conversions"
-
 class Mrsk::Commands::Auditor < Mrsk::Commands::Base
-  # Runs remotely
-  def record(line)
-    append \
-      [ :echo, tagged_line(line) ],
-      audit_log_file
+  attr_reader :details
+
+  def initialize(config, **details)
+    super(config)
+    @details = details
   end
 
-  # Runs locally
-  def broadcast(line)
-    if broadcast_cmd = config.audit_broadcast_cmd
-      pipe \
-        [ :echo, tagged_line(line) ],
-        broadcast_cmd
-    end
+  # Runs remotely
+  def record(line, **details)
+    append \
+      [ :echo, audit_tags(**details).except(:version, :service_version).to_s, line ],
+      audit_log_file
   end
 
   def reveal
@@ -23,22 +19,10 @@ 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_line(line)
-      "'#{tags} #{line}'"
-    end
-
-    def tags
-      "[#{recorded_at}] [#{performer}]"
-    end
-
-    def performer
-      @performer ||= `whoami`.strip
-    end
-
-    def recorded_at
-      Time.now.to_fs(:db)
+    def audit_tags(**details)
+      tags(**self.details, **details)
     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
 
@@ -12,11 +13,19 @@ module Mrsk::Commands
 
     def run_over_ssh(*command, host:)
       "ssh".tap do |cmd|
-        cmd << " -J #{config.ssh_proxy.jump_proxies}" if config.ssh_proxy
+        if config.ssh_proxy && config.ssh_proxy.is_a?(Net::SSH::Proxy::Jump)
+          cmd << " -J #{config.ssh_proxy.jump_proxies}"
+        elsif config.ssh_proxy && config.ssh_proxy.is_a?(Net::SSH::Proxy::Command)
+          cmd << " -o ProxyCommand='#{config.ssh_proxy.command_line_template}'"
+        end
         cmd << " -t #{config.ssh_user}@#{host} '#{command.join(" ")}'"
       end
     end
 
+    def container_id_for(container_name:, only_running: false)
+      docker :container, :ls, *("--all" unless only_running), "--filter", "name=^#{container_name}$", "--quiet"
+    end
+
     private
       def combine(*commands, by: "&&")
         commands
@@ -37,6 +46,10 @@ module Mrsk::Commands
         combine *commands, by: ">>"
       end
 
+      def write(*commands)
+        combine *commands, by: ">"
+      end
+
       def xargs(command)
         [ :xargs, command ].flatten
       end
@@ -44,5 +57,9 @@ module Mrsk::Commands
       def docker(*args)
         args.compact.unshift :docker
       end
+
+      def tags(**details)
+        Mrsk::Tags.from_config(config, **details)
+      end
   end
 end

lib/mrsk/commands/builder.rb

@@ -1,17 +1,19 @@
 class Mrsk::Commands::Builder < Mrsk::Commands::Base
-  delegate :create, :remove, :push, :pull, :info, to: :target
+  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
     case
-    when config.builder && config.builder["multiarch"] == false
+    when !config.builder.multiarch? && !config.builder.cached?
       native
-    when config.builder && config.builder["local"] && config.builder["remote"]
+    when !config.builder.multiarch? && config.builder.cached?
+      native_cached
+    when config.builder.local? && config.builder.remote?
       multiarch_remote
-    when config.builder && config.builder["remote"]
+    when config.builder.remote?
       native_remote
     else
       multiarch
@@ -22,6 +24,10 @@ class Mrsk::Commands::Builder < Mrsk::Commands::Base
     @native ||= Mrsk::Commands::Builder::Native.new(config)
   end
 
+  def native_cached
+    @native ||= Mrsk::Commands::Builder::Native::Cached.new(config)
+  end
+
   def native_remote
     @native ||= Mrsk::Commands::Builder::Native::Remote.new(config)
   end
@@ -33,4 +39,24 @@ 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

@@ -1,36 +1,60 @@
+
 class Mrsk::Commands::Builder::Base < Mrsk::Commands::Base
+  class BuilderError < StandardError; end
+
   delegate :argumentize, to: Mrsk::Utils
+  delegate :args, :secrets, :dockerfile, :local_arch, :local_host, :remote_arch, :remote_host, :cache_from, :cache_to, to: :builder_config
+
+  def clean
+    docker :image, :rm, "--force", config.absolute_image
+  end
 
   def pull
     docker :pull, config.absolute_image
   end
 
   def build_options
-    [ *build_tags, *build_labels, *build_args, *build_secrets ]
+    [ *build_tags, *build_cache, *build_labels, *build_args, *build_secrets, *build_dockerfile ]
   end
 
+  def build_context
+    config.builder.context
+  end
+
+
   private
     def build_tags
       [ "-t", config.absolute_image, "-t", config.latest_image ]
     end
 
+    def build_cache
+      if cache_to && cache_from
+        ["--cache-to", cache_to,
+          "--cache-from", cache_from]
+      end
+    end
+
     def build_labels
       argumentize "--label", { service: config.service }
     end
 
     def build_args
-      argumentize "--build-arg", args, redacted: true
+      argumentize "--build-arg", args, sensitive: true
     end
 
     def build_secrets
       argumentize "--secret", secrets.collect { |secret| [ "id", secret ] }
     end
 
-    def args
-      (config.builder && config.builder["args"]) || {}
+    def build_dockerfile
+      if Pathname.new(File.expand_path(dockerfile)).exist?
+        argumentize "--file", dockerfile
+      else
+        raise BuilderError, "Missing #{dockerfile}"
+      end
     end
 
-    def secrets
-      (config.builder && config.builder["secrets"]) || []
+    def builder_config
+      config.builder
     end
 end

lib/mrsk/commands/builder/multiarch.rb

@@ -13,7 +13,7 @@ class Mrsk::Commands::Builder::Multiarch < Mrsk::Commands::Builder::Base
       "--platform", "linux/amd64,linux/arm64",
       "--builder", builder_name,
       *build_options,
-      "."
+      build_context
   end
 
   def info

lib/mrsk/commands/builder/multiarch/remote.rb

@@ -22,17 +22,17 @@ class Mrsk::Commands::Builder::Multiarch::Remote < Mrsk::Commands::Builder::Mult
     end
 
     def create_local_buildx
-      docker :buildx, :create, "--name", builder_name, builder_name_with_arch(local["arch"]), "--platform", "linux/#{local["arch"]}"
+      docker :buildx, :create, "--name", builder_name, builder_name_with_arch(local_arch), "--platform", "linux/#{local_arch}"
     end
 
     def append_remote_buildx
-      docker :buildx, :create, "--append", "--name", builder_name, builder_name_with_arch(remote["arch"]), "--platform", "linux/#{remote["arch"]}"
+      docker :buildx, :create, "--append", "--name", builder_name, builder_name_with_arch(remote_arch), "--platform", "linux/#{remote_arch}"
     end
 
     def create_contexts
       combine \
-        create_context(local["arch"], local["host"]),
-        create_context(remote["arch"], remote["host"])
+        create_context(local_arch, local_host),
+        create_context(remote_arch, remote_host)
     end
 
     def create_context(arch, host)
@@ -41,19 +41,11 @@ class Mrsk::Commands::Builder::Multiarch::Remote < Mrsk::Commands::Builder::Mult
 
     def remove_contexts
       combine \
-        remove_context(local["arch"]),
-        remove_context(remote["arch"])
+        remove_context(local_arch),
+        remove_context(remote_arch)
     end
 
     def remove_context(arch)
       docker :context, :rm, builder_name_with_arch(arch)
     end
-
-    def local
-      config.builder["local"]
-    end
-
-    def remote
-      config.builder["remote"]
-    end
 end

lib/mrsk/commands/builder/native.rb

@@ -1,16 +1,17 @@
 class Mrsk::Commands::Builder::Native < Mrsk::Commands::Builder::Base
   def create
-    # No-op on native
+    # No-op on native without cache
   end
 
   def remove
-    # No-op on native
+    # No-op on native without cache
   end
 
   def push
     combine \
-      docker(:build, *build_options, "."),
-      docker(:push, config.absolute_image)
+      docker(:build, *build_options, build_context),
+      docker(:push, config.absolute_image),
+      docker(:push, config.latest_image)
   end
 
   def info

lib/mrsk/commands/builder/native/cached.rb

@@ -0,0 +1,16 @@
+class Mrsk::Commands::Builder::Native::Cached < Mrsk::Commands::Builder::Native
+  def create
+    docker :buildx, :create, "--use", "--driver=docker-container"
+  end
+
+  def remove
+    docker :buildx, :rm, builder_name
+  end
+
+  def push
+    docker :buildx, :build,
+      "--push",
+      *build_options,
+      build_context
+  end
+end

lib/mrsk/commands/builder/native/remote.rb

@@ -17,7 +17,7 @@ class Mrsk::Commands::Builder::Native::Remote < Mrsk::Commands::Builder::Native
       "--platform", platform,
       "--builder", builder_name,
       *build_options,
-      "."
+      build_context
   end
 
   def info
@@ -28,29 +28,21 @@ class Mrsk::Commands::Builder::Native::Remote < Mrsk::Commands::Builder::Native
 
 
   private
-    def arch
-      config.builder["remote"]["arch"]
-    end
-
-    def host
-      config.builder["remote"]["host"]
-    end
-
     def builder_name
       "mrsk-#{config.service}-native-remote"
     end
 
     def builder_name_with_arch
-      "#{builder_name}-#{arch}"
+      "#{builder_name}-#{remote_arch}"
     end
 
     def platform
-      "linux/#{arch}"
+      "linux/#{remote_arch}"
     end
 
     def create_context
       docker :context, :create,
-        builder_name_with_arch, "--description", "'#{builder_name} #{arch} native host'", "--docker", "'host=#{host}'"
+        builder_name_with_arch, "--description", "'#{builder_name} #{remote_arch} native host'", "--docker", "'host=#{remote_host}'"
     end
 
     def remove_context

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

@@ -0,0 +1,57 @@
+class Mrsk::Commands::Healthcheck < Mrsk::Commands::Base
+  EXPOSED_PORT = 3999
+
+  def run
+    web = config.role(:web)
+
+    docker :run,
+      "--detach",
+      "--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 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
+    pipe container_id, xargs(docker(:logs, "--tail", 50, "2>&1"))
+  end
+
+  def stop
+    pipe container_id, xargs(docker(:stop))
+  end
+
+  def remove
+    pipe container_id, xargs(docker(:container, :rm))
+  end
+
+  private
+    def container_name
+      [ "healthcheck", config.service, config.destination ].compact.join("-")
+    end
+
+    def container_name_with_version
+      "#{container_name}-#{config.version}"
+    end
+
+    def container_id
+      container_id_for(container_name: container_name_with_version)
+    end
+
+    def health_url
+      "http://localhost:#{EXPOSED_PORT}#{config.healthcheck["path"]}"
+    end
+end

lib/mrsk/commands/hook.rb

@@ -0,0 +1,14 @@
+class Mrsk::Commands::Hook < Mrsk::Commands::Base
+  def run(hook, **details)
+    [ hook_file(hook), env: tags(**details).env ]
+  end
+
+  def hook_exists?(hook)
+    Pathname.new(hook_file(hook)).exist?
+  end
+
+  private
+    def hook_file(hook)
+      "#{config.hooks_path}/#{hook}"
+    end
+end

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-#{config.service}"
+    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 +2,37 @@ 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 dangling_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 tagged_images
+    pipe \
+      docker(:image, :ls, *service_filter, "--format", "'{{.ID}} {{.Repository}}:{{.Tag}}'"),
+      "grep -v -w \"#{active_image_list}\"",
+      "while read image tag; do docker rmi $tag; done"
   end
+
+  def containers(keep_last: 5)
+    pipe \
+      docker(:ps, "-q", "-a", *service_filter, *stopped_containers_filters),
+      "tail -n +#{keep_last + 1}",
+      "while read container_id; do docker rm $container_id; done"
+  end
+
+  private
+    def stopped_containers_filters
+      [ "created", "exited", "dead" ].flat_map { |status| ["--filter", "status=#{status}"] }
+    end
+
+    def active_image_list
+      # Pull the images that are used by any containers
+      # Append repo:latest - to avoid deleting the latest tag
+      # Append repo:<none> - to avoid deleting dangling images that are in use. Unused dangling images are deleted separately
+      "$(docker container ls -a --format '{{.Image}}\\|' --filter label=service=#{config.service} | tr -d '\\n')#{config.latest_image}\\|#{config.repository}:<none>"
+    end
+
+    def service_filter
+      [ "--filter", "label=service=#{config.service}" ]
+    end
 end

lib/mrsk/commands/registry.rb

@@ -2,10 +2,19 @@ class Mrsk::Commands::Registry < Mrsk::Commands::Base
   delegate :registry, to: :config
 
   def login
-    docker :login, registry["server"], "-u", redact(registry["username"]), "-p", redact(registry["password"])
+    docker :login, registry["server"], "-u", sensitive(lookup("username")), "-p", sensitive(lookup("password"))
   end
 
   def logout
     docker :logout, registry["server"]
   end
+
+  private
+    def lookup(key)
+      if registry[key].is_a?(Array)
+        ENV.fetch(registry[key].first).dup
+      else
+        registry[key]
+      end
+    end
 end

lib/mrsk/commands/traefik.rb

@@ -1,15 +1,25 @@
 class Mrsk::Commands::Traefik < Mrsk::Commands::Base
+  delegate :argumentize, :argumentize_env_with_secrets, :optionize, to: Mrsk::Utils
+
+  DEFAULT_IMAGE = "traefik:v2.9"
+  CONTAINER_PORT = 80
+  DEFAULT_ARGS = {
+    'log.level' => 'DEBUG'
+  }
+
   def run
     docker :run, "--name traefik",
-      "-d",
+      "--detach",
       "--restart", "unless-stopped",
-      "--log-opt", "max-size=#{MAX_LOG_SIZE}",
-      "-p 80:80",
-      "-v /var/run/docker.sock:/var/run/docker.sock",
-      "traefik",
+      "--publish", port,
+      "--volume", "/var/run/docker.sock:/var/run/docker.sock",
+      *env_args,
+      *config.logging_args,
+      *label_args,
+      *docker_options_args,
+      image,
       "--providers.docker",
-      "--log.level=DEBUG",
-      *cmd_args
+      *cmd_option_args
   end
 
   def start
@@ -21,32 +31,70 @@ 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)
     pipe \
-      docker(:logs, "traefik", (" --since #{since}" if since), (" -n #{lines}" if lines), "-t", "2>&1"),
+      docker(:logs, "traefik", (" --since #{since}" if since), (" --tail #{lines}" if lines), "--timestamps", "2>&1"),
       ("grep '#{grep}'" if grep)
   end
 
   def follow_logs(host:, grep: nil)
     run_over_ssh pipe(
-      docker(:logs, "traefik", "-t", "-n", "10", "-f", "2>&1"),
+      docker(:logs, "traefik", "--timestamps", "--tail", "10", "--follow", "2>&1"),
       (%(grep "#{grep}") if grep)
     ).join(" "), host: host
   end
 
   def remove_container
-    docker :container, :prune, "-f", "--filter", "label=org.opencontainers.image.title=Traefik"
+    docker :container, :prune, "--force", "--filter", "label=org.opencontainers.image.title=Traefik"
   end
 
   def remove_image
-    docker :image, :prune, "-a", "-f", "--filter", "label=org.opencontainers.image.title=Traefik"
+    docker :image, :prune, "--all", "--force", "--filter", "label=org.opencontainers.image.title=Traefik"
+  end
+
+  def port
+    "#{host_port}:#{CONTAINER_PORT}"
   end
 
   private
-    def cmd_args
-      (config.raw_config.dig(:traefik, "args") || { }).collect { |(key, value)| [ "--#{key}", value ] }.flatten
+    def label_args
+      argumentize "--label", labels
+    end
+
+    def env_args
+      env_config = config.traefik["env"] || {}
+
+      if env_config.present?
+        argumentize_env_with_secrets(env_config)
+      else
+        []
+      end
+    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.traefik["args"]
+        optionize DEFAULT_ARGS.merge(args), with: "="
+      else
+        optionize DEFAULT_ARGS, with: "="
+      end
+    end
+
+    def host_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, :stop_wait_time, :hooks_path, 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"] || git_version
+  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 +125,16 @@ 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?
       raw_config.ssh["user"] || "root"
@@ -119,6 +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
 
@@ -126,13 +156,21 @@ class Mrsk::Configuration
     { user: ssh_user, proxy: ssh_proxy, auth_methods: [ "publickey" ] }.compact
   end
 
-  def audit_broadcast_cmd
-    raw_config.audit_broadcast_cmd
+
+  def healthcheck
+    { "path" => "/up", "port" => 3000, "max_attempts" => 7 }.merge(raw_config.healthcheck || {})
   end
 
+  def readiness_delay
+    raw_config.readiness_delay || 7
+  end
+
+  def minimum_version
+    raw_config.minimum_version
+  end
 
   def valid?
-    ensure_required_keys_present && ensure_env_available
+    ensure_required_keys_present && ensure_valid_mrsk_version
   end
 
 
@@ -148,11 +186,32 @@ class Mrsk::Configuration
       env_args: env_args,
       volume_args: volume_args,
       ssh_options: ssh_options,
-      builder: raw_config.builder,
-      accessories: raw_config.accessories
+      builder: builder.to_h,
+      accessories: raw_config.accessories,
+      logging: logging_args,
+      healthcheck: healthcheck
     }.compact
   end
 
+  def traefik
+    raw_config.traefik || {}
+  end
+
+  def hooks_path
+    raw_config.hooks_path || ".mrsk/hooks"
+  end
+
+  def builder
+    Mrsk::Configuration::Builder.new(config: self)
+  end
+
+  # Will raise KeyError if any secret ENVs are missing
+  def ensure_env_available
+    env_args
+    roles.each(&:env_args)
+
+    true
+  end
 
   private
     # Will raise ArgumentError if any required config keys are missing
@@ -169,18 +228,36 @@ 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
 
-      true
-    end
-
-    # Will raise KeyError if any secret ENVs are missing
-    def ensure_env_available
-      env_args
-      roles.each(&:env_args)
+      roles.each do |role|
+        if role.hosts.empty?
+          raise ArgumentError, "No servers specified for the #{role.name} role"
+        end
+      end
 
       true
     end
 
+    def ensure_valid_mrsk_version
+      if minimum_version && Gem::Version.new(minimum_version) > Gem::Version.new(Mrsk::VERSION)
+        raise ArgumentError, "Current version is #{Mrsk::VERSION}, minimum required is #{minimum_version}"
+      end
+
+      true
+    end
+
+
     def role_names
       raw_config.servers.is_a?(Array) ? [ "web" ] : raw_config.servers.keys.sort
     end
+
+    def git_version
+      @git_version ||=
+        if system("git rev-parse")
+          uncommitted_suffix = `git status --porcelain`.strip.present? ? "_uncommitted_#{SecureRandom.hex(8)}" : ""
+
+          "#{`git rev-parse HEAD`.strip}#{uncommitted_suffix}"
+        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/builder.rb

@@ -0,0 +1,114 @@
+class Mrsk::Configuration::Builder
+  def initialize(config:)
+    @options = config.raw_config.builder || {}
+    @image = config.image
+    @server = config.registry["server"]
+
+    valid?
+  end
+
+  def to_h
+    @options
+  end
+
+  def multiarch?
+    @options["multiarch"] != false
+  end
+
+  def local?
+    !!@options["local"]
+  end
+
+  def remote?
+    !!@options["remote"]
+  end
+
+  def cached?
+    !!@options["cache"]
+  end
+
+  def args
+    @options["args"] || {}
+  end
+
+  def secrets
+    @options["secrets"] || []
+  end
+
+  def dockerfile
+    @options["dockerfile"] || "Dockerfile"
+  end
+
+  def context
+    @options["context"] || "."
+  end
+
+  def local_arch
+    @options["local"]["arch"] if local?
+  end
+
+  def local_host
+    @options["local"]["host"] if local?
+  end
+
+  def remote_arch
+    @options["remote"]["arch"] if remote?
+  end
+
+  def remote_host
+    @options["remote"]["host"] if remote?
+  end
+
+  def cache_from
+    if cached?
+      case @options["cache"]["type"]
+      when "gha"
+        cache_from_config_for_gha
+      when "registry"
+        cache_from_config_for_registry
+      end
+    end
+  end
+
+  def cache_to
+    if cached?
+      case @options["cache"]["type"]
+      when "gha"
+        cache_to_config_for_gha
+      when "registry"
+        cache_to_config_for_registry
+      end
+    end
+  end
+
+  private
+    def valid?
+      if @options["local"] && !@options["remote"]
+        raise ArgumentError, "You must specify both local and remote builder config for remote multiarch builds"
+      end
+
+      if @options["cache"] && @options["cache"]["type"]
+        raise ArgumentError, "Invalid cache type: #{@options["cache"]["type"]}" unless ["gha", "registry"].include?(@options["cache"]["type"])
+      end
+    end
+
+    def cache_image
+      @options["cache"]&.fetch("image", nil) || "#{@image}-build-cache"
+    end
+
+    def cache_from_config_for_gha
+      "type=gha"
+    end
+
+    def cache_from_config_for_registry
+      [ "type=registry", "ref=#{@server}/#{cache_image}" ].compact.join(",")
+    end
+
+    def cache_to_config_for_gha
+      [ "type=gha", @options["cache"]&.fetch("options", nil)].compact.join(",")
+    end
+
+    def cache_to_config_for_registry
+      [ "type=registry", @options["cache"]&.fetch("options", nil), "ref=#{@server}/#{cache_image}" ].compact.join(",")
+    end
+end

lib/mrsk/configuration/role.rb

@@ -1,5 +1,5 @@
 class Mrsk::Configuration::Role
-  delegate :argumentize, :argumentize_env_with_secrets, to: Mrsk::Utils
+  delegate :argumentize, :argumentize_env_with_secrets, :optionize, to: Mrsk::Utils
 
   attr_accessor :name
 
@@ -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
@@ -31,10 +35,40 @@ 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" => health_check_interval })
+    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 health_check_interval
+    options = specializations["healthcheck"] || {}
+    options = config.healthcheck.merge(options) if running_traefik?
+
+    options["interval"] || "1s"
+  end
+
   def cmd
     specializations["cmd"]
   end
 
+  def option_args
+    if args = specializations["options"]
+      optionize args
+    else
+      []
+    end
+  end
+
   def running_traefik?
     name.web? || specializations["traefik"]
   end
@@ -47,28 +81,38 @@ 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" => "/up",
-          "traefik.http.services.#{config.service}.loadbalancer.healthcheck.interval" => "1s",
-          "traefik.http.middlewares.#{config.service}.retry.attempts" => "3",
-          "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?
@@ -104,4 +148,8 @@ 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 +1,56 @@
 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_debug(*args, **kwargs)
+    capture(*args, **kwargs, verbosity: Logger::DEBUG)
+  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/tags.rb

@@ -0,0 +1,39 @@
+require "time"
+
+class Mrsk::Tags
+  attr_reader :config, :tags
+
+  class << self
+    def from_config(config, **extra)
+      new(**default_tags(config), **extra)
+    end
+
+    def default_tags(config)
+      { recorded_at: Time.now.utc.iso8601,
+        performer: `whoami`.chomp,
+        destination: config.destination,
+        version: config.version,
+        service_version: service_version(config) }
+    end
+
+    def service_version(config)
+      [ config.service, config.abbreviated_version ].compact.join("@")
+    end
+  end
+
+  def initialize(**tags)
+    @tags = tags.compact
+  end
+
+  def env
+    tags.transform_keys { |detail| "MRSK_#{detail.upcase}" }
+  end
+
+  def to_s
+    tags.values.map { |value| "[#{value}]" }.join(" ")
+  end
+
+  def except(*tags)
+    self.class.new(**self.tags.except(*tags))
+  end
+end

lib/mrsk/utils.rb

@@ -1,13 +1,17 @@
 module Mrsk::Utils
   extend self
 
-  # Return a list of shell arguments using the same named argument against the passed attributes (hash or array).
-  def argumentize(argument, attributes, redacted: false)
-    Array(attributes).flat_map do |k, v|
-      if v.present?
-        [ argument, redacted ? redact("#{k}=#{v}") : "#{k}=#{v}" ]
+  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, sensitive: false)
+    Array(attributes).flat_map do |key, value|
+      if value.present?
+        attr = "#{key}=#{escape_shell_value(value)}"
+        attr = self.sensitive(attr, redaction: "#{key}=[REDACTED]") if sensitive
+        [ argument, attr]
       else
-        [ argument, k ]
+        [ argument, key ]
       end
     end
   end
@@ -16,14 +20,77 @@ 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
 
-  # 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
+  # Returns a list of shell-dashed option arguments. If the value is true, it's treated like a value-less option.
+  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
+
+  # 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(/`/, '\\\\`')
+      .gsub(DOLLAR_SIGN_WITHOUT_SHELL_EXPANSION_REGEX, '\$')
+  end
+
+  # Abbreviate a git revhash for concise display
+  def abbreviate_version(version)
+    if version
+      # Don't abbreviate <sha>_uncommitted_<etc>
+      if version.include?("_")
+        version
+      else
+        version[0...7]
+      end
+    end
   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 = "0.6.4"
+  VERSION = "0.15.1"
 end

mrsk.gemspec

@@ -14,7 +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

@@ -1,36 +1,141 @@
 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::Commands::Registry.any_instance.expects(:login)
+    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", login: false)
+
+    run_command("reboot", "mysql")
   end
 
-  test "boot" do
-    assert_match "Running docker run --name app-mysql -d --restart unless-stopped --log-opt max-size=10m -p 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
+    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
     def run_command(*command)
       stdouted { Mrsk::Cli::Accessory.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }

test/cli/app_test.rb

@@ -2,66 +2,188 @@ require_relative "cli_test_case"
 
 class CliAppTest < CliTestCase
   test "boot" do
-    assert_match /Running docker run -d --restart unless-stopped/, run_command("boot")
+    stub_running
+    run_command("boot").tap do |output|
+      assert_match "docker tag dhh/app:latest dhh/app:latest", output
+      assert_match /docker run --detach --restart unless-stopped --name app-web-latest --hostname 1.1.1.1-[0-9a-f]{12} /, 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, "--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.returns([ :docker, :run ])
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-latest$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+      .returns("running") # health check
+
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--filter", "status=restarting", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "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 already deployed/, output # Can't start what's already running
-      assert_match /docker ps -q --filter label=service=app \| xargs docker stop/, output # Stop what's running
-      assert_match /docker container ls -a -f name=app-999 -q \| 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 app-web-latest app-web-latest_replaced_[0-9a-f]{16}/, output
+      assert_match /docker run --detach --restart unless-stopped --name app-web-latest --hostname 1.1.1.1-[0-9a-f]{12} /, 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 "boot errors leave lock in place" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "version" => "999" }
+
+    Mrsk::Cli::App.any_instance.expects(:using_version).raises(RuntimeError)
+
+    assert !MRSK.holding_lock?
+    assert_raises(RuntimeError) do
+      stderred { run_command("boot") }
+    end
+    assert MRSK.holding_lock?
+  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 -q --filter label=service=app \| xargs docker stop/, output
+      assert_match "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --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 /#{Regexp.escape("docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --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 -a -f name=app-1234567 -q \| 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 --filter status=restarting --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-", output # Get current version
+      assert_match "docker exec app-web-999 ruby -v", output
+    end
+  end
+
+  test "containers" do
+    run_command("containers").tap do |output|
+      assert_match "docker container ls --all --filter label=service=app", output
+    end
+  end
+
+  test "images" do
+    run_command("images").tap do |output|
+      assert_match "docker image ls dhh/app", output
+    end
+  end
+
+  test "logs" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.1 'docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest| xargs docker logs --timestamps --tail 10 2>&1'")
+
+    assert_match "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker logs --tail 100 2>&1", run_command("logs")
+  end
+
+  test "logs with follow" do
+    SSHKit::Backend::Abstract.any_instance.stubs(:exec)
+      .with("ssh -t root@1.1.1.1 'docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1'")
+
+    assert_match "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1", run_command("logs", "--follow")
+  end
+
+  test "version" do
+    run_command("version").tap do |output|
+      assert_match "docker ps --filter label=service=app --filter status=running --filter status=restarting --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | 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 --filter status=restarting --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
+
+    def stub_running
+      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
     end
 end

test/cli/build_test.rb

@@ -0,0 +1,108 @@
+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::Commands::Hook.any_instance.stubs(:hook_exists?).returns(true)
+    hook_variables = { version: 999, service_version: "app@999", hosts: "1.1.1.1,1.1.1.2,1.1.1.3,1.1.1.4", command: "build", subcommand: "push" }
+
+    run_command("push").tap do |output|
+      assert_hook_ran "pre-build", output, **hook_variables
+      assert_match /docker --version && docker buildx version/, 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
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with(:docker, "--version", "&&", :docker, :buildx, "version")
+
+    SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+      .with { |*args| args[0..1] == [:docker, :buildx] }
+      .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 "push with no buildx plugin" do
+    stub_locking
+    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("push") }
+  end
+
+  test "push pre-build hook failure" do
+    fail_hook("pre-build")
+
+    assert_raises(Mrsk::Cli::HookError) { run_command("push") }
+
+    assert @executions.none? { |args| args[0..2] == [:docker, :buildx, :build] }
+  end
+
+  test "pull" do
+    run_command("pull").tap do |output|
+      assert_match /docker image rm --force dhh\/app:999/, output
+      assert_match /docker pull dhh\/app:999/, output
+    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
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Build.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+
+    def stub_dependency_checks
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with(:docker, "--version", "&&", :docker, :buildx, "version")
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |*args| args[0..1] == [:docker, :buildx] }
+    end
+end

test/cli/cli_test_case.rb

@@ -1,24 +1,56 @@
 require "test_helper"
-require "active_support/testing/stream"
 
 class CliTestCase < ActiveSupport::TestCase
-  include ActiveSupport::Testing::Stream
-
   setup do
     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
+    def fail_hook(hook)
+      @executions = []
+      Mrsk::Commands::Hook.any_instance.stubs(:hook_exists?).returns(true)
+
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |*args| @executions << args; args != [".mrsk/hooks/#{hook}"] }
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |*args| args.first == ".mrsk/hooks/#{hook}" }
+        .raises(SSHKit::Command::Failed.new("failed"))
+    end
+
+    def stub_locking
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |arg1, arg2| arg1 == :mkdir && arg2 == "mrsk_lock-app" }
+      SSHKit::Backend::Abstract.any_instance.stubs(:execute)
+        .with { |arg1, arg2| arg1 == :rm && arg2 == "mrsk_lock-app/details" }
+    end
+
+    def assert_hook_ran(hook, output, version:, service_version:, hosts:, command:, subcommand: nil, runtime: nil)
+      performer = `whoami`.strip
+
+      assert_match "Running the #{hook} hook...\n", output
+
+      expected = %r{Running\s/usr/bin/env\s\.mrsk/hooks/#{hook}\sas\s#{performer}@localhost\n\s
+        DEBUG\s\[[0-9a-f]*\]\sCommand:\s\(\sexport\s
+        MRSK_RECORDED_AT=\"\d\d\d\d-\d\d-\d\dT\d\d:\d\d:\d\dZ\"\s
+        MRSK_PERFORMER=\"#{performer}\"\s
+        MRSK_VERSION=\"#{version}\"\s
+        MRSK_SERVICE_VERSION=\"#{service_version}\"\s
+        MRSK_HOSTS=\"#{hosts}\"\s
+        MRSK_COMMAND=\"#{command}\"\s
+        #{"MRSK_SUBCOMMAND=\\\"#{subcommand}\\\"\\s" if subcommand}
+        #{"MRSK_RUNTIME=\\\"#{runtime}\\\"\\s" if runtime}
+        ;\s/usr/bin/env\s\.mrsk/hooks/#{hook} }x
+
+      assert_match expected, output
     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

@@ -1,8 +1,375 @@
 require_relative "cli_test_case"
 
 class CliMainTest < CliTestCase
+  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", "version" => "999", "skip_hooks" => false }
+
+    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)
+
+    Mrsk::Commands::Hook.any_instance.stubs(:hook_exists?).returns(true)
+    hook_variables = { version: 999, service_version: "app@999", hosts: "1.1.1.1,1.1.1.2", command: "deploy" }
+
+    run_command("deploy").tap do |output|
+      assert_hook_ran "pre-connect", output, **hook_variables
+      assert_match /Log into image registry/, output
+      assert_match /Build and push app image/, output
+      assert_hook_ran "pre-deploy", output, **hook_variables
+      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_hook_ran "post-deploy", output, **hook_variables, runtime: 0
+    end
+  end
+
+  test "deploy with skip_push" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "version" => "999", "skip_hooks" => false }
+
+    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-app'] }
+      .raises(RuntimeError, "mkdir: cannot create directory ‘mrsk_lock-app’: File exists")
+
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_debug)
+      .with(:stat, 'mrsk_lock-app', ">", "/dev/null", "&&", :cat, "mrsk_lock-app/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-app'] }
+      .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 outside section leave remove lock" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "version" => "999", "skip_hooks" => false }
+
+    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 "deploy with skipped hooks" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "version" => "999", "skip_hooks" => true }
+
+    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", "--skip_hooks") do
+      refute_match /Running the post-deploy hook.../, output
+    end
+  end
+
+  test "deploy with missing secrets" do
+    assert_raises(KeyError) do
+      run_command("deploy", config_file: "deploy_with_secrets")
+    end
+  end
+
+  test "redeploy" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "version" => "999", "skip_hooks" => false }
+
+    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)
+
+    Mrsk::Commands::Hook.any_instance.stubs(:hook_exists?).returns(true)
+
+    hook_variables = { version: 999, service_version: "app@999", hosts: "1.1.1.1,1.1.1.2", command: "redeploy" }
+
+    run_command("redeploy").tap do |output|
+      assert_hook_ran "pre-connect", output, **hook_variables
+      assert_match /Build and push app image/, output
+      assert_hook_ran "pre-deploy", output, **hook_variables
+      assert_match /Running the pre-deploy hook.../, output
+      assert_match /Ensure app can pass healthcheck/, output
+      assert_hook_ran "post-deploy", output, **hook_variables, runtime: "0"
+    end
+  end
+
+  test "redeploy with skip_push" do
+    invoke_options = { "config_file" => "test/fixtures/deploy_simple.yml", "version" => "999", "skip_hooks" => false }
+
+    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 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
+    [ "web", "workers" ].each do |role|
+      SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+        .with(:docker, :container, :ls, "--filter", "name=^app-#{role}-123$", "--quiet", raise_on_non_zero_exit: false)
+        .returns("").at_least_once
+      SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+        .with(:docker, :container, :ls, "--all", "--filter", "name=^app-#{role}-123$", "--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=#{role}", "--filter", "status=running", "--filter", "status=restarting", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-", raise_on_non_zero_exit: false)
+        .returns("version-to-rollback\n").at_least_once
+      SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+        .with(:docker, :container, :ls, "--all", "--filter", "name=^app-#{role}-123$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+        .returns("running").at_least_once # health check
+    end
+
+    Mrsk::Commands::Hook.any_instance.stubs(:hook_exists?).returns(true)
+    hook_variables = { version: 123, service_version: "app@123", hosts: "1.1.1.1,1.1.1.2,1.1.1.3,1.1.1.4", command: "rollback" }
+
+    run_command("rollback", "123", config_file: "deploy_with_accessories").tap do |output|
+      assert_match "Start container with version 123", output
+      assert_hook_ran "pre-deploy", output, **hook_variables
+      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"
+      assert_hook_ran "post-deploy", output, **hook_variables, runtime: "0"
+    end
+  end
+
+  test "rollback without old version" do
+    Mrsk::Cli::Main.any_instance.stubs(:container_available?).returns(true)
+
+    Mrsk::Utils::HealthcheckPoller.stubs(:sleep)
+
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--filter", "name=^app-web-123$", "--quiet", raise_on_non_zero_exit: false)
+      .returns("").at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :ps, "--filter", "label=service=app", "--filter", "label=role=web", "--filter", "status=running", "--filter", "status=restarting", "--latest", "--format", "\"{{.Names}}\"", "|", "grep -oE \"\\-[^-]+$\"", "|", "cut -c 2-", raise_on_non_zero_exit: false)
+      .returns("").at_least_once
+    SSHKit::Backend::Abstract.any_instance.expects(:capture_with_info)
+      .with(:docker, :container, :ls, "--all", "--filter", "name=^app-web-123$", "--quiet", "|", :xargs, :docker, :inspect, "--format", "'{{if .State.Health}}{{.State.Health.Status}}{{else}}{{.State.Status}}{{end}}'")
+      .returns("running").at_least_once # health check
+
+    run_command("rollback", "123").tap do |output|
+      assert_match "Start container with version 123", output
+      assert_match "docker start app-web-123 || docker run --detach --restart unless-stopped --name 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).times(3)
+    Pathname.any_instance.stubs(:mkpath)
+    FileUtils.stubs(:mkdir_p)
+    FileUtils.stubs(:cp_r)
+    FileUtils.stubs(:cp)
+
+    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).times(3)
+
+    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(4)
+    Pathname.any_instance.stubs(:mkpath)
+    FileUtils.stubs(:mkdir_p)
+    FileUtils.stubs(:cp_r)
+    FileUtils.stubs(:cp)
+
+    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(4)
+    Pathname.any_instance.stubs(:mkpath)
+    FileUtils.stubs(:mkdir_p)
+    FileUtils.stubs(:cp_r)
+    FileUtils.stubs(:cp)
+
+    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", 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
+
+      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 /docker container stop app-mysql/, output
+      assert_match /docker container prune --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 rm --force redis/, output
+      assert_match /rm -rf app-redis/, output
+
+      assert_match /docker logout/, output
+    end
+  end
+
   test "version" do
     version = stdouted { Mrsk::Cli::Main.new.version }
     assert_equal Mrsk::VERSION, version
   end
+
+  private
+    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 +1,28 @@
+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.", output
+      assert_match "docker image ls --filter label=service=app --format '{{.ID}} {{.Repository}}:{{.Tag}}' | grep -v -w \"$(docker container ls -a --format '{{.Image}}\\|' --filter label=service=app | tr -d '\\n')dhh/app:latest\\|dhh/app:<none>\" | while read image tag; do docker rmi $tag; done on 1.1.1.", 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

@@ -0,0 +1,35 @@
+require_relative "cli_test_case"
+
+class CliServerTest < CliTestCase
+  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 installed 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|
+      ("1.1.1.1".."1.1.1.4").map do |host|
+        assert_match "Missing Docker on #{host}. Installing…", output
+      end
+    end
+  end
+
+  private
+    def run_command(*command)
+      stdouted { Mrsk::Cli::Server.start([*command, "-c", "test/fixtures/deploy_with_accessories.yml"]) }
+    end
+end

test/cli/traefik_test.rb

@@ -0,0 +1,94 @@
+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::Commands::Registry.any_instance.expects(:login).twice
+
+    run_command("reboot").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 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 --rolling" do
+    run_command("reboot", "--rolling").tap do |output|
+      assert_match "Running docker container prune --force --filter label=org.opencontainers.image.title=Traefik on 1.1.1.1", output.lines[3]
+    end
+  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
@@ -42,4 +43,37 @@ class CommanderTest < ActiveSupport::TestCase
     @mrsk.specific_primary!
     assert_equal [ "1.1.1.1" ], @mrsk.hosts
   end
+
+  test "primary_host with specific hosts via role" do
+    @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_percentage_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 -d --restart unless-stopped --log-opt max-size=10m -p 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 -d --restart unless-stopped --log-opt max-size=10m -p 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
 
@@ -106,29 +118,34 @@ class CommandsAccessoryTest < ActiveSupport::TestCase
 
   test "logs" do
     assert_equal \
-      "docker logs app-mysql -t 2>&1",
-      @mysql.logs.join(" ")
+      "docker logs app-mysql --timestamps 2>&1",
+      new_command(:mysql).logs.join(" ")
 
     assert_equal \
-      "docker logs app-mysql  --since 5m  -n 100 -t 2>&1 | grep 'thing'",
-      @mysql.logs(since: "5m", lines: 100, grep: "thing").join(" ")
+      "docker logs app-mysql  --since 5m  --tail 100 --timestamps 2>&1 | grep 'thing'",
+      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 -t -n 10 -f 2>&1'",
-      @mysql.follow_logs
+      "ssh -t root@1.1.1.5 'docker logs app-mysql --timestamps --tail 10 --follow 2>&1'",
+      new_command(:mysql).follow_logs
   end
 
   test "remove container" do
     assert_equal \
-      "docker container prune -f --filter label=service=app-mysql",
-      @mysql.remove_container.join(" ")
+      "docker container prune --force --filter label=service=app-mysql",
+      new_command(:mysql).remove_container.join(" ")
   end
 
   test "remove image" do
     assert_equal \
-      "docker image prune -a -f --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
@@ -14,148 +13,316 @@ class CommandsAppTest < ActiveSupport::TestCase
 
   test "run" do
     assert_equal \
-      "docker run -d --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=3 --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 hostname" do
+    assert_equal \
+      "docker run --detach --restart unless-stopped --name app-web-999 --hostname myhost -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(hostname: "myhost").join(" ")
   end
 
   test "run with volumes" do
     @config[:volumes] = ["/local/path:/container/path" ]
 
     assert_equal \
-      "docker run -d --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=3 --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 --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 } } }
+    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 --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 "start_or_run" do
+    assert_equal \
+      "docker start app-web-999 || 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.start_or_run.join(" ")
+  end
+
+  test "start_or_run with hostname" do
+    assert_equal \
+      "docker start app-web-999 || docker run --detach --restart unless-stopped --name app-web-999 --hostname myhost -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.start_or_run(hostname: "myhost").join(" ")
   end
 
   test "stop" do
     assert_equal \
-      "docker ps -q --filter label=service=app | xargs docker stop",
-      @app.stop.join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --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 --filter status=restarting --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 -q --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 --filter status=restarting --latest | xargs docker logs 2>&1",
+      new_command.logs.join(" ")
 
     assert_equal \
-      "docker ps -q --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 --filter status=restarting --latest | xargs docker logs --since 5m 2>&1",
+      new_command.logs(since: "5m").join(" ")
 
     assert_equal \
-      "docker ps -q --filter label=service=app | xargs docker logs -n 100 2>&1",
-      @app.logs(lines: "100").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker logs --tail 100 2>&1",
+      new_command.logs(lines: "100").join(" ")
 
     assert_equal \
-      "docker ps -q --filter label=service=app | xargs docker logs --since 5m -n 100 2>&1",
-      @app.logs(since: "5m", lines: "100").join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker logs --since 5m --tail 100 2>&1",
+      new_command.logs(since: "5m", lines: "100").join(" ")
 
     assert_equal \
-      "docker ps -q --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 --filter status=restarting --latest | xargs docker logs 2>&1 | grep 'my-id'",
+      new_command.logs(grep: "my-id").join(" ")
 
     assert_equal \
-      "docker ps -q --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 --filter status=restarting --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 -q --filter label=service=app | xargs docker logs -t -n 10 -f 2>&1",
-        @app.follow_logs(host: "app-1")
+    assert_match \
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest | xargs docker logs --timestamps --tail 10 --follow 2>&1",
+      new_command.follow_logs(host: "app-1")
 
-      assert_equal \
-        "docker ps -q --filter label=service=app | xargs docker logs -t -n 10 -f 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 --filter status=restarting --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(" ")
+      "docker run --rm -e RAILS_MASTER_KEY=\"456\" dhh/app:999 bin/rails db:setup",
+      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 "run over ssh with proxy_command" do
+    @config[:ssh] = { "proxy_command" => "ssh -W %h:%p user@proxy-server" }
+    assert_equal "ssh -o ProxyCommand='ssh -W %h:%p user@proxy-server' -t root@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 -q --filter label=service=app",
-      @app.current_container_id.join(" ")
+      "docker ps --quiet --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --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 --filter status=restarting --latest",
+      new_command.current_running_container_id.join(" ")
   end
 
   test "container_id_for" do
     assert_equal \
-      "docker container ls -a -f name=app-999 -q",
-      @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 --filter status=restarting --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 \"\\-[^-]+$\" | cut -c 2-",
+      new_command.list_versions.join(" ")
+
+    assert_equal \
+      "docker ps --filter label=service=app --filter label=role=web --filter status=running --filter status=restarting --latest --format \"{{.Names}}\" | grep -oE \"\\-[^-]+$\" | cut -c 2-",
+      new_command.list_versions("--latest", statuses: [ :running, :restarting ]).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

@@ -1,27 +1,64 @@
 require "test_helper"
+require "active_support/testing/time_helpers"
 
 class CommandsAuditorTest < ActiveSupport::TestCase
+  include ActiveSupport::Testing::TimeHelpers
+
   setup do
+    freeze_time
+
     @config = {
-      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ],
-      audit_broadcast_cmd: "bin/audit_broadcast"
+      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" }, servers: [ "1.1.1.1" ]
     }
+
+    @auditor = new_command
+    @performer = `whoami`.strip
+    @recorded_at = Time.now.utc.iso8601
   end
 
   test "record" do
-    assert_match \
-      /echo '.* app removed container' >> mrsk-app-audit.log/,
-      new_command.record("app removed container").join(" ")
+    assert_equal [
+      :echo,
+      "[#{@recorded_at}] [#{@performer}]",
+      "app removed container",
+      ">>", "mrsk-app-audit.log"
+    ], @auditor.record("app removed container")
   end
 
-  test "broadcast" do
-    assert_match \
-      /echo '.* app removed container' \| bin\/audit_broadcast/,
-      new_command.broadcast("app removed container").join(" ")
+  test "record with destination" do
+    new_command(destination: "staging").tap do |auditor|
+      assert_equal [
+        :echo,
+        "[#{@recorded_at}] [#{@performer}] [staging]",
+        "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,
+        "[#{@recorded_at}] [#{@performer}] [web]",
+        "app removed container",
+        ">>", "mrsk-app-audit.log"
+      ], auditor.record("app removed container")
+    end
+  end
+
+  test "record with arg details" do
+    assert_equal [
+      :echo,
+      "[#{@recorded_at}] [#{@performer}] [value]",
+      "app removed container",
+      ">>", "mrsk-app-audit.log"
+    ], @auditor.record("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

@@ -6,10 +6,10 @@ class CommandsBuilderTest < ActiveSupport::TestCase
   end
 
   test "target multiarch by default" do
-    builder = new_builder_command
+    builder = new_builder_command(builder: { "cache" => { "type" => "gha" }})
     assert_equal "multiarch", builder.name
     assert_equal \
-      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch -t dhh/app:123 -t dhh/app:latest --label service=app .",
+      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch -t dhh/app:123 -t dhh/app:latest --cache-to type=gha --cache-from type=gha --label service=\"app\" --file Dockerfile .",
       builder.push.join(" ")
   end
 
@@ -17,58 +17,89 @@ 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 . && 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
+
+  test "target native cached when multiarch is off and cache is set" do
+    builder = new_builder_command(builder: { "multiarch" => false, "cache" => { "type" => "gha" }})
+    assert_equal "native/cached", builder.name
+    assert_equal \
+      "docker buildx build --push -t dhh/app:123 -t dhh/app:latest --cache-to type=gha --cache-from type=gha --label service=\"app\" --file Dockerfile .",
       builder.push.join(" ")
   end
 
   test "target multiarch remote when local and remote is set" do
-    builder = new_builder_command(builder: { "local" => { }, "remote" => { } })
+    builder = new_builder_command(builder: { "local" => { }, "remote" => { }, "cache" => { "type" => "gha" } })
     assert_equal "multiarch/remote", builder.name
     assert_equal \
-      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch-remote -t dhh/app:123 -t dhh/app:latest --label service=app .",
+      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch-remote -t dhh/app:123 -t dhh/app:latest --cache-to type=gha --cache-from type=gha --label service=\"app\" --file Dockerfile .",
       builder.push.join(" ")
   end
 
   test "target native remote when only remote is set" do
-    builder = new_builder_command(builder: { "remote" => { "arch" => "amd64" } })
+    builder = new_builder_command(builder: { "remote" => { "arch" => "amd64" }, "cache" => { "type" => "gha" } })
     assert_equal "native/remote", builder.name
     assert_equal \
-      "docker buildx build --push --platform linux/amd64 --builder mrsk-app-native-remote -t dhh/app:123 -t dhh/app:latest --label service=app .",
+      "docker buildx build --push --platform linux/amd64 --builder mrsk-app-native-remote -t dhh/app:123 -t dhh/app:latest --cache-to type=gha --cache-from type=gha --label service=\"app\" --file Dockerfile .",
       builder.push.join(" ")
   end
 
   test "build args" do
     builder = new_builder_command(builder: { "args" => { "a" => 1, "b" => 2 } })
     assert_equal \
-      "-t dhh/app:123 -t dhh/app:latest --label service=app --build-arg a=1 --build-arg b=2",
+      "-t dhh/app:123 -t dhh/app:latest --label service=\"app\" --build-arg a=\"1\" --build-arg b=\"2\" --file Dockerfile",
       builder.target.build_options.join(" ")
   end
 
   test "build secrets" do
     builder = new_builder_command(builder: { "secrets" => ["token_a", "token_b"] })
     assert_equal \
-      "-t dhh/app:123 -t dhh/app:latest --label service=app --secret id=token_a --secret id=token_b",
+      "-t dhh/app:123 -t dhh/app:latest --label service=\"app\" --secret id=\"token_a\" --secret id=\"token_b\" --file Dockerfile",
       builder.target.build_options.join(" ")
   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 \
+      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --file Dockerfile ..",
+      builder.push.join(" ")
+  end
+
   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 . && 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
 
   test "multiarch push with build args" do
     builder = new_builder_command(builder: { "args" => { "a" => 1, "b" => 2 } })
     assert_equal \
-      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch -t dhh/app:123 -t dhh/app:latest --label service=app --build-arg a=1 --build-arg b=2 .",
+      "docker buildx build --push --platform linux/amd64,linux/arm64 --builder mrsk-app-multiarch -t dhh/app:123 -t dhh/app:latest --label service=\"app\" --build-arg a=\"1\" --build-arg b=\"2\" --file Dockerfile .",
       builder.push.join(" ")
   end
 
-  test "native push with with build secrets" do
+  test "native push 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 . && 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

@@ -0,0 +1,106 @@
+require "test_helper"
+
+class CommandsHealthcheckTest < 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 "run" do
+    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\" dhh/app:123",
+      new_command.run.join(" ")
+  end
+
+  test "run with custom port" do
+    @config[:healthcheck] = { "port" => 3001 }
+
+    assert_equal \
+      "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 "run with destination" do
+    @destination = "staging"
+
+    assert_equal \
+      "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 "run with custom healthcheck" do
+    @config[:healthcheck] = { "cmd" => "/bin/up" }
+
+    assert_equal \
+      "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-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-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, destination: @destination, version: "123"))
+    end
+end

test/commands/hook_test.rb

@@ -0,0 +1,44 @@
+require "test_helper"
+
+class CommandsHookTest < ActiveSupport::TestCase
+  include ActiveSupport::Testing::TimeHelpers
+
+  setup do
+    freeze_time
+
+    @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" } }
+    }
+
+    @performer = `whoami`.strip
+    @recorded_at = Time.now.utc.iso8601
+  end
+
+  test "run" do
+    assert_equal [
+      ".mrsk/hooks/foo",
+      { env: {
+        "MRSK_RECORDED_AT" => @recorded_at,
+        "MRSK_PERFORMER" => @performer,
+        "MRSK_VERSION" => "123",
+        "MRSK_SERVICE_VERSION" => "app@123" } }
+    ], new_command.run("foo")
+  end
+
+  test "run with custom hooks_path" do
+    assert_equal [
+      "custom/hooks/path/foo",
+      { env: {
+        "MRSK_RECORDED_AT" => @recorded_at,
+        "MRSK_PERFORMER" => @performer,
+        "MRSK_VERSION" => "123",
+        "MRSK_SERVICE_VERSION" => "app@123" } }
+    ], new_command(hooks_path: "custom/hooks/path").run("foo")
+  end
+
+  private
+    def new_command(**extra_config)
+      Mrsk::Commands::Hook.new(Mrsk::Configuration.new(@config.merge(**extra_config), 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-app > /dev/null && cat mrsk_lock-app/details | base64 -d",
+      new_command.status.join(" ")
+  end
+
+  test "acquire" do
+    assert_match \
+      /mkdir mrsk_lock-app && echo ".*" > mrsk_lock-app\/details/m,
+      new_command.acquire("Hello", "123").join(" ")
+  end
+
+  test "release" do
+    assert_match \
+      "rm mrsk_lock-app/details && rm -r mrsk_lock-app",
+      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

@@ -8,15 +8,21 @@ class CommandsPruneTest < ActiveSupport::TestCase
     }
   end
 
-  test "images" do
+  test "dangling images" do
     assert_equal \
-      "docker image prune --all --force --filter label=service=app --filter until=168h",
-      new_command.images.join(" ")
+      "docker image prune --force --filter label=service=app --filter dangling=true",
+      new_command.dangling_images.join(" ")
+  end
+
+  test "tagged images" do
+    assert_equal \
+      "docker image ls --filter label=service=app --format '{{.ID}} {{.Repository}}:{{.Tag}}' | grep -v -w \"$(docker container ls -a --format '{{.Image}}\\|' --filter label=service=app | tr -d '\\n')dhh/app:latest\\|dhh/app:<none>\" | while read image tag; do docker rmi $tag; done",
+      new_command.tagged_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/registry_test.rb

@@ -14,10 +14,36 @@ class CommandsRegistryTest < ActiveSupport::TestCase
   end
 
   test "registry login" do
-    assert_equal [ :docker, :login, "hub.docker.com", "-u", "dhh", "-p", "secret" ], @registry.login
+    assert_equal \
+      "docker login hub.docker.com -u dhh -p secret",
+      @registry.login.join(" ")
+  end
+
+  test "registry login with ENV password" do
+    ENV["MRSK_REGISTRY_PASSWORD"] = "more-secret"
+    @config[:registry]["password"] = [ "MRSK_REGISTRY_PASSWORD" ]
+
+    assert_equal \
+      "docker login hub.docker.com -u dhh -p more-secret",
+      @registry.login.join(" ")
+  ensure
+    ENV.delete("MRSK_REGISTRY_PASSWORD")
+  end
+
+  test "registry login with ENV username" do
+    ENV["MRSK_REGISTRY_USERNAME"] = "also-secret"
+    @config[:registry]["username"] = [ "MRSK_REGISTRY_USERNAME" ]
+
+    assert_equal \
+      "docker login hub.docker.com -u also-secret -p secret",
+      @registry.login.join(" ")
+  ensure
+    ENV.delete("MRSK_REGISTRY_USERNAME")
   end
 
   test "registry logout" do
-    assert_equal [:docker, :logout, "hub.docker.com"], @registry.logout
+    assert_equal \
+      "docker logout hub.docker.com",
+      @registry.logout.join(" ")
   end
 end

test/commands/traefik_test.rb

@@ -2,15 +2,107 @@ 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" } }
     }
+
+    ENV["EXAMPLE_API_KEY"] = "456"
+  end
+
+  teardown do
+    ENV.delete("EXAMPLE_API_KEY")
   end
 
   test "run" do
     assert_equal \
-      "docker run --name traefik -d --restart unless-stopped --log-opt max-size=10m -p 80:80 -v /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 --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
+
+  test "run with env 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]["env"] = { "secret" => %w[EXAMPLE_API_KEY] }
+    assert_equal \
+      "docker run --name traefik --detach --restart unless-stopped --publish 80:80 --volume /var/run/docker.sock:/var/run/docker.sock -e EXAMPLE_API_KEY=\"456\" --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 without configuration" do
+    @config.delete(:traefik)
+
+    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\" #{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
+
+  test "run with default args overriden" do
+    @config[:traefik]["args"]["log.level"] = "ERROR"
+
+    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=\"ERROR\" --accesslog.format=\"json\" --api.insecure --metrics.prometheus.buckets=\"0.1,0.3,1.2,5.0\"",
       new_command.run.join(" ")
   end
 
@@ -28,55 +120,55 @@ 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 "traefik logs" do
     assert_equal \
-      "docker logs traefik -t 2>&1",
+      "docker logs traefik --timestamps 2>&1",
       new_command.logs.join(" ")
   end
 
   test "traefik logs since 2h" do
     assert_equal \
-      "docker logs traefik  --since 2h -t 2>&1",
+      "docker logs traefik  --since 2h --timestamps 2>&1",
       new_command.logs(since: '2h').join(" ")
   end
 
   test "traefik logs last 10 lines" do
     assert_equal \
-      "docker logs traefik  -n 10 -t 2>&1",
+      "docker logs traefik  --tail 10 --timestamps 2>&1",
       new_command.logs(lines: 10).join(" ")
   end
 
   test "traefik logs with grep hello!" do
     assert_equal \
-      "docker logs traefik -t 2>&1 | grep 'hello!'",
+      "docker logs traefik --timestamps 2>&1 | grep 'hello!'",
       new_command.logs(grep: 'hello!').join(" ")
   end
 
   test "traefik remove container" do
     assert_equal \
-      "docker container prune -f --filter label=org.opencontainers.image.title=Traefik",
+      "docker container prune --force --filter label=org.opencontainers.image.title=Traefik",
       new_command.remove_container.join(" ")
   end
 
   test "traefik remove image" do
     assert_equal \
-      "docker image prune -a -f --filter label=org.opencontainers.image.title=Traefik",
+      "docker image prune --all --force --filter label=org.opencontainers.image.title=Traefik",
       new_command.remove_image.join(" ")
   end
 
   test "traefik follow logs" do
     assert_equal \
-      "ssh -t root@1.1.1.1 'docker logs traefik -t -n 10 -f 2>&1'",
+      "ssh -t root@1.1.1.1 'docker logs traefik --timestamps --tail 10 --follow 2>&1'",
       new_command.follow_logs(host: @config[:servers].first)
   end
 
   test "traefik follow logs with grep hello!" do
     assert_equal \
-      "ssh -t root@1.1.1.1 'docker logs traefik -t -n 10 -f 2>&1 | grep \"hello!\"'",
+      "ssh -t root@1.1.1.1 'docker logs traefik --timestamps --tail 10 --follow 2>&1 | grep \"hello!\"'",
       new_command.follow_logs(host: @config[:servers].first, grep: 'hello!')
   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
@@ -67,25 +90,39 @@ 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
+    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
   end
 
   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
 
   test "env args without secret" do
-    assert_equal ["-e", "SOMETHING=else"], @config.accessory(:redis).env_args
+    assert_equal ["-e", "SOMETHING=\"else\""], @config.accessory(:redis).env_args
   end
 
   test "volume args" do
@@ -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/builder_test.rb

@@ -0,0 +1,151 @@
+require "test_helper"
+
+class ConfigurationBuilderTest < ActiveSupport::TestCase
+  setup do
+    @deploy = {
+      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" },
+      servers: [ "1.1.1.1" ]
+    }
+
+    @config = Mrsk::Configuration.new(@deploy)
+
+    @deploy_with_builder_option = {
+      service: "app", image: "dhh/app", registry: { "username" => "dhh", "password" => "secret" },
+      servers: [ "1.1.1.1" ],
+      builder: {}
+    }
+
+    @config_with_builder_option = Mrsk::Configuration.new(@deploy_with_builder_option)
+  end
+
+  test "multiarch?" do
+    assert_equal true, @config.builder.multiarch?
+  end
+
+  test "setting multiarch to false" do
+    @deploy_with_builder_option[:builder] = { "multiarch" => false }
+
+    assert_equal false, @config_with_builder_option.builder.multiarch?
+  end
+
+  test "local?" do
+    assert_equal false, @config.builder.local?
+  end
+
+  test "remote?" do
+    assert_equal false, @config.builder.remote?
+  end
+
+  test "remote_arch" do
+    assert_nil @config.builder.remote_arch
+  end
+
+  test "remote_host" do
+    assert_nil @config.builder.remote_host
+  end
+
+  test "remote config is missing when local is specified" do
+    @deploy_with_builder_option[:builder] = { "local" => { "arch" => "arm64", "host" => "unix:///Users/<%= `whoami`.strip %>/.docker/run/docker.sock" } }
+
+    assert_raises(ArgumentError) do
+      @config_with_builder_option.builder
+    end
+  end
+
+  test "setting both local and remote configs" do
+    @deploy_with_builder_option[:builder] = {
+      "local" => { "arch" => "arm64", "host" => "unix:///Users/<%= `whoami`.strip %>/.docker/run/docker.sock" },
+      "remote" => { "arch" => "amd64", "host" => "ssh://root@192.168.0.1" }
+    }
+
+    assert_equal true, @config_with_builder_option.builder.local?
+    assert_equal true, @config_with_builder_option.builder.remote?
+
+    assert_equal "amd64", @config_with_builder_option.builder.remote_arch
+    assert_equal "ssh://root@192.168.0.1", @config_with_builder_option.builder.remote_host
+
+    assert_equal "arm64", @config_with_builder_option.builder.local_arch
+    assert_equal "unix:///Users/<%= `whoami`.strip %>/.docker/run/docker.sock", @config_with_builder_option.builder.local_host
+  end
+
+  test "cached?" do
+    assert_equal false, @config.builder.cached?
+  end
+
+  test "invalid cache type specified" do
+    @deploy_with_builder_option[:builder] = { "cache" => { "type" => "invalid" } }
+
+    assert_raises(ArgumentError) do
+      @config_with_builder_option.builder
+    end
+  end
+
+  test "cache_from" do
+    assert_nil @config.builder.cache_from
+  end
+
+  test "cache_to" do
+    assert_nil @config.builder.cache_to
+  end
+
+  test "setting gha cache" do
+    @deploy_with_builder_option[:builder] = { "cache" => { "type" => "gha", "options" => "mode=max" } }
+
+    assert_equal "type=gha", @config_with_builder_option.builder.cache_from
+    assert_equal "type=gha,mode=max", @config_with_builder_option.builder.cache_to
+  end
+
+  test "setting registry cache" do
+    @deploy_with_builder_option[:builder] = { "cache" => { "type" => "registry", "options" => "mode=max,image-manifest=true,oci-mediatypes=true" } }
+
+    assert_equal "type=registry,ref=/dhh/app-build-cache", @config_with_builder_option.builder.cache_from
+    assert_equal "type=registry,mode=max,image-manifest=true,oci-mediatypes=true,ref=/dhh/app-build-cache", @config_with_builder_option.builder.cache_to
+  end
+
+  test "setting registry cache with image" do
+    @deploy_with_builder_option[:builder] = { "cache" => { "type" => "registry", "image" => "mrsk", "options" => "mode=max" } }
+
+    assert_equal "type=registry,ref=/mrsk", @config_with_builder_option.builder.cache_from
+    assert_equal "type=registry,mode=max,ref=/mrsk", @config_with_builder_option.builder.cache_to
+  end
+
+  test "args" do
+    assert_equal({}, @config.builder.args)
+  end
+
+  test "setting args" do
+    @deploy_with_builder_option[:builder] = { "args" => { "key" => "value" } }
+
+    assert_equal({ "key" => "value" }, @config_with_builder_option.builder.args)
+  end
+
+  test "secrets" do
+    assert_equal [], @config.builder.secrets
+  end
+
+  test "setting secrets" do
+    @deploy_with_builder_option[:builder] = { "secrets" => ["GITHUB_TOKEN"] }
+
+    assert_equal ["GITHUB_TOKEN"], @config_with_builder_option.builder.secrets
+  end
+
+  test "dockerfile" do
+    assert_equal "Dockerfile", @config.builder.dockerfile
+  end
+
+  test "setting dockerfile" do
+    @deploy_with_builder_option[:builder] = { "dockerfile" => "Dockerfile.dev" }
+
+    assert_equal "Dockerfile.dev", @config_with_builder_option.builder.dockerfile
+  end
+
+  test "context" do
+    assert_equal ".", @config.builder.context
+  end
+
+  test "setting context" do
+    @deploy_with_builder_option[:builder] = { "context" => ".." }
+
+    assert_equal "..", @config_with_builder_option.builder.context
+  end
+end

test/configuration/role_test.rb

@@ -38,11 +38,11 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
   end
 
   test "label args" do
-    assert_equal [ "--label", "service=app", "--label", "role=workers" ], @config_with_roles.role(:workers).label_args
+    assert_equal [ "--label", "service=\"app\"", "--label", "role=\"workers\"" ], @config_with_roles.role(:workers).label_args
   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=3", "--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
@@ -66,12 +66,12 @@ 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=3", "--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
     assert_equal "redis://a/b", @config_with_roles.role(:workers).env["REDIS_URL"]
-    assert_equal ["-e", "REDIS_URL=redis://a/b", "-e", "WEB_CONCURRENCY=4"], @config_with_roles.role(:workers).env_args
+    assert_equal ["-e", "REDIS_URL=\"redis://a/b\"", "-e", "WEB_CONCURRENCY=\"4\""], @config_with_roles.role(:workers).env_args
   end
 
   test "env secret overwritten by role" do
@@ -95,9 +95,12 @@ class ConfigurationRoleTest < ActiveSupport::TestCase
     }
 
     ENV["REDIS_PASSWORD"] = "secret456"
-    ENV["DB_PASSWORD"] = "secret123"
+    ENV["DB_PASSWORD"] = "secret&\"123"
 
-    assert_equal ["-e", "REDIS_PASSWORD=secret456", "-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", "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 +69,41 @@ 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
+  test "version no git repo" do
+    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
+  end
+
+  test "version from git committed" do
+    ENV.delete("VERSION")
+
+    @config.expects(:`).with("git rev-parse HEAD").returns("git-version")
+    @config.expects(:`).with("git status --porcelain").returns("")
+    assert_equal "git-version", @config.version
+  end
+
+  test "version from git uncommitted" do
+    ENV.delete("VERSION")
+
+    @config.expects(:`).with("git rev-parse HEAD").returns("git-version")
+    @config.expects(:`).with("git status --porcelain").returns("M   file\n")
+    assert_match /^git-version_uncommitted_[0-9a-f]{16}$/, @config.version
+  end
+
+  test "version from env" do
+    ENV["VERSION"] = "env-version"
+    assert_equal "env-version", @config.version
+  end
+
+  test "version from arg" do
+    @config.version = "arg-version"
+    assert_equal "arg-version", @config.version
   end
 
   test "repository" do
@@ -89,17 +125,18 @@ class ConfigurationTest < ActiveSupport::TestCase
   end
 
   test "env args" do
-    assert_equal [ "-e", "REDIS_URL=redis://x/y" ], @config.env_args
+    assert_equal [ "-e", "REDIS_URL=\"redis://x/y\"" ], @config.env_args
   end
 
   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
@@ -109,17 +146,18 @@ class ConfigurationTest < ActiveSupport::TestCase
       env: { "clear" => { "PORT" => "3000" } }
     }) })
 
-    assert_equal [ "-e", "PORT=3000" ], config.env_args
+    assert_equal [ "-e", "PORT=\"3000\"" ], config.env_args
   end
 
   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
@@ -128,12 +166,45 @@ class ConfigurationTest < ActiveSupport::TestCase
     assert_raises(KeyError) do
       config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!({
         env: { "secret" => [ "PASSWORD" ] }
-      }) })
+      }) }).ensure_env_available
     end
   end
 
   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 +228,32 @@ 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 +261,27 @@ 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"] }, @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"], :builder=>{}, :logging=>["--log-opt", "max-size=\"10m\""], :healthcheck=>{"path"=>"/up", "port"=>3000, "max_attempts" => 7 }}, @config.to_h)
+  end
+
+  test "min version is lower" do
+    config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!(minimum_version: "0.0.1") })
+    assert_equal "0.0.1", config.minimum_version
+  end
+
+  test "min version is equal" do
+    config = Mrsk::Configuration.new(@deploy.tap { |c| c.merge!(minimum_version: Mrsk::VERSION) })
+    assert_equal Mrsk::VERSION, config.minimum_version
+  end
+
+  test "min version is higher" do
+    assert_raises(ArgumentError) do
+      Mrsk::Configuration.new(@deploy.tap { |c| c.merge!(minimum_version: "10000.0.0") })
+    end
   end
 end

test/fixtures/deploy_simple.yml

@@ -0,0 +1,8 @@
+service: app
+image: dhh/app
+servers:
+  - "1.1.1.1"
+  - "1.1.1.2"
+registry:
+  username: user
+  password: pw

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
@@ -23,7 +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

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_percentage_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/fixtures/deploy_with_secrets.yml

@@ -0,0 +1,11 @@
+service: app
+image: dhh/app
+servers:
+  - "1.1.1.1"
+  - "1.1.1.2"
+registry:
+  username: user
+  password: pw
+env:
+  secret:
+    - PASSWORD

test/integration/accessory_test.rb

@@ -0,0 +1,36 @@
+require_relative "integration_test"
+
+class AccessoryTest < IntegrationTest
+  test "boot, stop, start, restart, logs, remove" do
+    mrsk :accessory, :boot, :busybox
+    assert_accessory_running :busybox
+
+    mrsk :accessory, :stop, :busybox
+    assert_accessory_not_running :busybox
+
+    mrsk :accessory, :start, :busybox
+    assert_accessory_running :busybox
+
+    mrsk :accessory, :restart, :busybox
+    assert_accessory_running :busybox
+
+    logs = mrsk :accessory, :logs, :busybox, capture: true
+    assert_match /Starting busybox.../, logs
+
+    mrsk :accessory, :remove, :busybox, "-y"
+    assert_accessory_not_running :busybox
+  end
+
+  private
+    def assert_accessory_running(name)
+      assert_match /registry:4443\/busybox:1.36.0   "sh -c 'echo \\"Start/, accessory_details(name)
+    end
+
+    def assert_accessory_not_running(name)
+      refute_match /registry:4443\/busybox:1.36.0   "sh -c 'echo \\"Start/, accessory_details(name)
+    end
+
+    def accessory_details(name)
+      mrsk :accessory, :details, name, capture: true
+    end
+end

test/integration/app_test.rb

@@ -0,0 +1,55 @@
+require_relative "integration_test"
+
+class AppTest < IntegrationTest
+  test "stop, start, boot, logs, images, containers, exec, remove" do
+    mrsk :deploy
+
+    assert_app_is_up
+
+    mrsk :app, :stop
+
+    # traefik is up and returns 404s when it can't match a route
+    assert_app_not_found
+
+    mrsk :app, :start
+
+    # mrsk app start does not wait
+    wait_for_app_to_be_up
+
+    mrsk :app, :boot
+
+    wait_for_app_to_be_up
+
+    logs = mrsk :app, :logs, capture: true
+    assert_match /App Host: vm1/, logs
+    assert_match /App Host: vm2/, logs
+    assert_match /GET \/ HTTP\/1.1/, logs
+
+    images = mrsk :app, :images, capture: true
+    assert_match /App Host: vm1/, images
+    assert_match /App Host: vm2/, images
+    assert_match /registry:4443\/app\s+#{latest_app_version}/, images
+    assert_match /registry:4443\/app\s+latest/, images
+
+    containers = mrsk :app, :containers, capture: true
+    assert_match /App Host: vm1/, containers
+    assert_match /App Host: vm2/, containers
+    assert_match /registry:4443\/app:#{latest_app_version}/, containers
+    assert_match /registry:4443\/app:latest/, containers
+
+    exec_output = mrsk :app, :exec, :ps, capture: true
+    assert_match /App Host: vm1/, exec_output
+    assert_match /App Host: vm2/, exec_output
+    assert_match /1 root      0:\d\d ps/, exec_output
+
+    exec_output = mrsk :app, :exec, "--reuse", :ps, capture: true
+    assert_match /App Host: vm1/, exec_output
+    assert_match /App Host: vm2/, exec_output
+    assert_match /1 root      0:\d\d nginx/, exec_output
+
+    mrsk :app, :remove
+
+    # traefik is up and returns 404s when it can't match a route
+    assert_app_not_found
+  end
+end

test/integration/docker-compose.yml

@@ -0,0 +1,57 @@
+version: "3.7"
+name: "mrsk-test"
+
+volumes:
+  shared:
+  registry:
+  deployer_bundle:
+
+services:
+  shared:
+    build:
+      context: docker/shared
+    volumes:
+      - shared:/shared
+
+  deployer:
+    privileged: true
+    build:
+      context: docker/deployer
+    environment:
+      - TEST_ID=${TEST_ID}
+    volumes:
+      - ../..:/mrsk
+      - shared:/shared
+      - registry:/registry
+      - deployer_bundle:/usr/local/bundle/
+
+  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
+      - registry:/var/lib/registry/
+
+  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 rm -rf /root/.ssh
+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"
+
+HEALTHCHECK --interval=1s CMD pgrep sleep
+
+CMD ["./boot.sh"]

test/integration/docker/deployer/app/.env.erb

@@ -0,0 +1 @@
+SECRET_TOKEN=1234

test/integration/docker/deployer/app/.mrsk/hooks/post-deploy

@@ -0,0 +1,3 @@
+#!/bin/sh
+echo "Deployed!"
+mkdir -p /tmp/${TEST_ID} && touch /tmp/${TEST_ID}/post-deploy

test/integration/docker/deployer/app/.mrsk/hooks/pre-build

@@ -0,0 +1,3 @@
+#!/bin/sh
+echo "About to build and push..."
+mkdir -p /tmp/${TEST_ID} && touch /tmp/${TEST_ID}/pre-build