Bump chart version to 0.20.0 for ARC 0.25.0 (#1600)

We'll be merging this immediately after ARC 0.25.0 gets released.

.dockerignore

@@ -11,3 +11,4 @@ charts
 *.md
 *.txt
 *.sh
+test/e2e/.docker-build

.github/ISSUE_TEMPLATE/bug_report.md

@@ -1,36 +0,0 @@
----
-name: Bug report
-about: Create a report to help us improve
-title: ''
-assignees: ''
-
----
-
-**Describe the bug**
-A clear and concise description of what the bug is.
-
-**Checks**
-
-- [ ] My actions-runner-controller version (v0.x.y) does support the feature
-- [ ] I'm using an unreleased version of the controller I built from HEAD of the default branch
-
-**To Reproduce**
-Steps to reproduce the behavior:
-1. Go to '...'
-2. Click on '....'
-3. Scroll down to '....'
-4. See error
-
-**Expected behavior**
-A clear and concise description of what you expected to happen.
-
-**Screenshots**
-If applicable, add screenshots to help explain your problem.
-
-**Environment (please complete the following information):**
- - Controller Version [e.g. 0.18.2]
- - Deployment Method [e.g. Helm and Kustomize ]
- - Helm Chart Version [e.g. 0.11.0, if applicable]
-
-**Additional context**
-Add any other context about the problem here.

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -0,0 +1,177 @@
+name: Bug Report
+description: File a bug report
+title: "Bug"
+labels: ["bug"]
+body:
+- type: input
+  id: controller-version
+  attributes:
+    label: Controller Version
+    description: Refer to semver-like release tags for controller versions. Any release tags prefixed with `actions-runner-controller-` are for chart releases
+    placeholder: ex. 0.18.2 or git commit ID
+  validations:
+    required: true
+- type: input
+  id: chart-version
+  attributes:
+    label: Helm Chart Version
+    description: Run `helm list` and see what's shown under CHART VERSION. Any release tags prefixed with `actions-runner-controller-` are for chart releases
+    placeholder: ex. 0.11.0
+- type: input
+  id: cert-manager-version
+  attributes:
+    label: CertManager Version
+    description: Run `kubectl get po -o yaml $CERT_MANAGER_POD` and see the image tag, or run `helm list` and see what's shown under APP VERSION for your cert-manager Helm release.
+    placeholder: ex. 1.8
+- type: dropdown
+  id: deployment-method
+  attributes:
+    label: Deployment Method
+    description: Which deployment method did you use to install ARC?
+    options:
+      - Helm
+      - Kustomize
+      - ArgoCD
+      - Other
+  validations:
+    required: true
+- type: textarea
+  id: cert-manager
+  attributes:
+    label: cert-manager installation
+    description: Confirm that you've installed cert-manager correctly by answering a few questions
+    placeholder: |
+      - Did you follow https://github.com/actions-runner-controller/actions-runner-controller#installation? If not, describe the installation process so that we can reproduce your environment.
+      - Are you sure you've installed cert-manager from an official source?
+      (Note that we won't provide user support for cert-manager itself. Make sure cert-manager is fully working before testing ARC or reporting a bug
+  validations:
+    required: true
+- type: checkboxes
+  id: checks
+  attributes:
+    label: Checks
+    description: Please check the boxes below before submitting
+    options:
+    - label: This isn't a question or user support case (For Q&A and community support, go to [Discussions](https://github.com/actions-runner-controller/actions-runner-controller/discussions). It might also be a good idea to contract with any of contributors and maintainers if your business is so critical and therefore you need priority support
+      required: true
+    - label: I've read [releasenotes](https://github.com/actions-runner-controller/actions-runner-controller/tree/master/docs/releasenotes) before submitting this issue and I'm sure it's not due to any recently-introduced backward-incompatible changes
+      required: true
+    - label: My actions-runner-controller version (v0.x.y) does support the feature
+      required: true
+    - label: I've already upgraded ARC (including the CRDs, see charts/actions-runner-controller/docs/UPGRADING.md for details) to the latest and it didn't fix the issue
+      required: true
+- type: textarea
+  id: resource-definitions
+  attributes:
+    label: Resource Definitions
+    description: "Add copy(s) of your resource definition(s) (RunnerDeployment or RunnerSet, and HorizontalRunnerAutoscaler. If RunnerSet, also include the StorageClass being used)"
+    render: yaml
+    placeholder: |
+      apiVersion: actions.summerwind.dev/v1alpha1
+      kind: RunnerDeployment
+      metadata:
+        name: example
+      spec:
+        #snip
+      ---
+      apiVersion: actions.summerwind.dev/v1alpha1
+      kind: RunnerSet
+      metadata:
+        name: example
+      spec:
+        #snip
+      ---
+      apiVersion: storage.k8s.io/v1
+      kind: StorageClass
+      metadata:
+        name: example
+      provisioner: ...
+      reclaimPolicy: ...
+      volumeBindingMode: ...
+      ---
+      apiVersion: actions.summerwind.dev/v1alpha1
+      kind: HorizontalRunnerAutoscaler
+      metadata:
+        name:
+      spec:
+        #snip
+  validations:
+    required: true
+- type: textarea
+  id: reproduction-steps
+  attributes:
+    label: To Reproduce
+    description: "Steps to reproduce the behavior"
+    render: markdown
+    placeholder: |
+      1. Go to '...'
+      2. Click on '....'
+      3. Scroll down to '....'
+      4. See error
+  validations:
+    required: true
+- type: textarea
+  id: actual-behavior
+  attributes:
+    label: Describe the bug
+    description: Also tell us, what did happen?
+    placeholder: A clear and concise description of what happened.
+  validations:
+    required: true
+- type: textarea
+  id: expected-behavior
+  attributes:
+    label: Describe the expected behavior
+    description: Also tell us, what did you expect to happen?
+    placeholder: A clear and concise description of what the expected behavior is.
+  validations:
+    required: true
+- type: textarea
+  id: controller-logs
+  attributes:
+    label: Controller Logs
+    description: "NEVER EVER OMIT THIS! Include logs from `actions-runner-controller`'s controller-manager pod"
+    render: shell
+    placeholder: |
+      PROVIDE THE LOGS VIA A GIST LINK (https://gist.github.com/), NOT DIRECTLY IN THIS TEXT AREA
+      
+      To grab controller logs:
+
+      # Set NS according to your setup
+      NS=actions-runner-system
+
+      # Grab the pod name and set it to $POD_NAME
+      kubectl -n $NS get po
+
+      kubectl -n $NS logs $POD_NAME > arc.log
+  validations:
+    required: true
+- type: textarea
+  id: runner-pod-logs
+  attributes:
+    label: Runner Pod Logs
+    description: "Include logs from runner pod(s)"
+    render: shell
+    placeholder: |
+      PROVIDE THE LOGS VIA A GIST LINK (https://gist.github.com/), NOT DIRECTLY IN THIS TEXT AREA
+      
+      To grab the runner pod logs:
+
+      # Set NS according to your setup. It should match your RunnerDeployment's metadata.namespace.
+      NS=default
+
+      # Grab the name of the problematic runner pod and set it to $POD_NAME
+      kubectl -n $NS get po
+
+      kubectl -n $NS logs $POD_NAME -c runner > runnerpod_runner.log
+      kubectl -n $NS logs $POD_NAME -c docker > runnerpod_docker.log
+  validations:
+    required: true
+- type: textarea
+  id: additional-context
+  attributes:
+    label: Additional Context
+    description: |
+      Add any other context about the problem here.
+
+      Tip: You can attach images or log files by clicking this area to highlight it and then dragging files in.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,15 @@
+# Blank issues are mainly for maintainers who are known to write complete issue descriptions without need to following a form
+blank_issues_enabled: true
+contact_links:
+- name: Sponsor ARC Maintainers
+  about: If your business relies on the continued maintainance of actions-runner-controller, please consider sponsoring the project and the maintainers.
+  url: https://github.com/actions-runner-controller/actions-runner-controller/tree/master/CODEOWNERS
+- name: Ideas and Feature Requests
+  about: Wanna request a feature? Create a discussion and collect :+1:s first.
+  url: https://github.com/actions-runner-controller/actions-runner-controller/discussions/new?category=ideas
+- name: Questions and User Support
+  about: Need support using ARC? We use Discussions as the place to provide community support.
+  url: https://github.com/actions-runner-controller/actions-runner-controller/discussions/new?category=questions
+- name: Need Paid Support?
+  about: Consider contracting with any of the actions-runner-controller maintainers and contributors.
+  url: https://github.com/actions-runner-controller/actions-runner-controller/tree/master/CODEOWNERS

.github/actions/setup-docker-environment/action.yaml

@@ -0,0 +1,52 @@
+name: "Setup Docker"
+
+inputs:
+  username:
+    description: "Username"
+    required: true
+  password:
+    description: "Password"
+    required: true
+  ghcr_username:
+    description: "GHCR username. Usually set from the github.actor variable"
+    required: true
+  ghcr_password:
+    description: "GHCR password. Usually set from the secrets.GITHUB_TOKEN variable"
+    required: true
+
+outputs:
+  sha_short:
+    description: "The short SHA used for image builds"
+    value: ${{ steps.vars.outputs.sha_short }}
+
+runs:
+  using: "composite"
+  steps:
+    - name: Get Short SHA
+      id: vars
+      run: |
+        echo ::set-output name=sha_short::${GITHUB_SHA::7}
+      shell: bash
+
+    - name: Set up QEMU
+      uses: docker/setup-qemu-action@v2
+
+    - name: Set up Docker Buildx
+      uses: docker/setup-buildx-action@v2
+      with:
+        version: latest
+
+    - name: Login to DockerHub
+      if: ${{ github.event_name == 'release' || github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+      uses: docker/login-action@v2
+      with:
+        username: ${{ inputs.username }}
+        password: ${{ inputs.password }}
+
+    - name: Login to GitHub Container Registry
+      if: ${{ github.event_name == 'release' || github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+      uses: docker/login-action@v2
+      with:
+        registry: ghcr.io
+        username: ${{ inputs.ghcr_username }}
+        password: ${{ inputs.ghcr_password }}

.github/lock.yml

@@ -1,25 +0,0 @@
-# Configuration for Lock Threads
-# Repo: https://github.com/dessant/lock-threads-app
-# App: https://github.com/apps/lock
-
-# Number of days of inactivity before a closed issue or pull request is locked
-daysUntilLock: 7
-
-# Skip issues and pull requests created before a given timestamp. Timestamp must
-# follow ISO 8601 (`YYYY-MM-DD`). Set to `false` to disable
-skipCreatedBefore: false
-
-# Issues and pull requests with these labels will be ignored. Set to `[]` to disable
-exemptLabels: []
-
-# Label to add before locking, such as `outdated`. Set to `false` to disable
-lockLabel: false
-
-# Comment to post before locking. Set to `false` to disable
-lockComment: >
-  This thread has been automatically locked since there has not been
-  any recent activity after it was closed. Please open a new issue for
-  related bugs.
-
-# Assign `resolved` as the reason for locking. Set to `false` to disable
-setLockReason: true

.github/renovate.json5

@@ -1,5 +1,6 @@
 {
   "extends": ["config:base"],
+  "labels": ["dependencies"],
   "packageRules": [
     {
       // automatically merge an update of runner
@@ -11,10 +12,30 @@
   "regexManagers": [
     {
       // use https://github.com/actions/runner/releases
-      "fileMatch": [".github/workflows/build-and-release-runners.yml"],
+      "fileMatch": [
+        ".github/workflows/runners.yaml"
+      ],
       "matchStrings": ["RUNNER_VERSION: +(?<currentValue>.*?)\\n"],
       "depNameTemplate": "actions/runner",
       "datasourceTemplate": "github-releases"
+    },
+    {
+      "fileMatch": [
+        "runner/Makefile",
+        "Makefile"
+      ],
+      "matchStrings": ["RUNNER_VERSION \\?= +(?<currentValue>.*?)\\n"],
+      "depNameTemplate": "actions/runner",
+      "datasourceTemplate": "github-releases"
+    },
+    {
+      "fileMatch": [
+        "runner/actions-runner.dockerfile",
+        "runner/actions-runner-dind.dockerfile"
+      ],
+      "matchStrings": ["RUNNER_VERSION=+(?<currentValue>.*?)\\n"],
+      "depNameTemplate": "actions/runner",
+      "datasourceTemplate": "github-releases"
     }
   ]
-}
+}

.github/stale.yml

@@ -1,66 +0,0 @@
-# Configuration for probot-stale - https://github.com/probot/stale
-
-# Number of days of inactivity before an Issue or Pull Request becomes stale
-daysUntilStale: 30
-
-# Number of days of inactivity before an Issue or Pull Request with the stale label is closed.
-# Set to false to disable. If disabled, issues still need to be closed manually, but will remain marked as stale.
-daysUntilClose: 14
-
-# Only issues or pull requests with all of these labels are check if stale. Defaults to `[]` (disabled)
-onlyLabels: []
-
-# Issues or Pull Requests with these labels will never be considered stale. Set to `[]` to disable
-exemptLabels:
-  - pinned
-  - security
-  - enhancement
-  - refactor
-  - documentation
-  - chore
-  - needs-investigation
-  - bug
-
-# Set to true to ignore issues in a project (defaults to false)
-exemptProjects: false
-
-# Set to true to ignore issues in a milestone (defaults to false)
-exemptMilestones: false
-
-# Set to true to ignore issues with an assignee (defaults to false)
-exemptAssignees: false
-
-# Label to use when marking as stale
-staleLabel: stale
-
-# Comment to post when marking as stale. Set to `false` to disable
-markComment: >
-  This issue has been automatically marked as stale because it has not had
-  recent activity. It will be closed if no further activity occurs. Thank you
-  for your contributions.
-
-# Comment to post when removing the stale label.
-# unmarkComment: >
-#   Your comment here.
-
-# Comment to post when closing a stale Issue or Pull Request.
-# closeComment: >
-#   Your comment here.
-
-# Limit the number of actions per hour, from 1-30. Default is 30
-limitPerRun: 30
-
-# Limit to only `issues` or `pulls`
-# only: issues
-
-# Optionally, specify configuration settings that are specific to just 'issues' or 'pulls':
-# pulls:
-#   daysUntilStale: 30
-#   markComment: >
-#     This pull request has been automatically marked as stale because it has not had
-#     recent activity. It will be closed if no further activity occurs. Thank you
-#     for your contributions.
-
-# issues:
-#   exemptLabels:
-#     - confirmed

.github/workflows/build-and-release-runners.yml

@@ -1,121 +0,0 @@
-name: Build and Release Runners
-
-on:
-  pull_request:
-    branches:
-      - '**'
-    paths:
-      - 'runner/**'
-      - .github/workflows/build-and-release-runners.yml
-  push:
-    branches:
-      - master
-    paths:
-      - runner/patched/*
-      - runner/Dockerfile
-      - runner/Dockerfile.ubuntu.1804
-      - runner/Dockerfile.dindrunner
-      - runner/entrypoint.sh
-      - .github/workflows/build-and-release-runners.yml
-
-env:
-  RUNNER_VERSION: 2.283.1
-  DOCKER_VERSION: 20.10.8
-  DOCKERHUB_USERNAME: summerwind
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    name: Build ${{ matrix.name }}-ubuntu-${{ matrix.os-version }}
-    strategy:
-      matrix:
-        include:
-          - name: actions-runner
-            os-version: 20.04
-            dockerfile: Dockerfile
-          - name: actions-runner
-            os-version: 18.04
-            dockerfile: Dockerfile.ubuntu.1804
-          - name: actions-runner-dind
-            os-version: 20.04
-            dockerfile: Dockerfile.dindrunner
-
-    steps:
-      - name: Set outputs
-        id: vars
-        run: echo ::set-output name=sha_short::${GITHUB_SHA::7}
-
-      - name: Checkout
-        uses: actions/checkout@v2
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
-        with:
-          version: latest
-
-      - name: Login to DockerHub
-        uses: docker/login-action@v1
-        if: ${{ github.event_name == 'push' || github.event_name == 'release' }}
-        with:
-          username: ${{ secrets.DOCKER_USER }}
-          password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
-
-      - name: Build and Push Versioned Tags
-        uses: docker/build-push-action@v2
-        with:
-          context: ./runner
-          file: ./runner/${{ matrix.dockerfile }}
-          platforms: linux/amd64,linux/arm64
-          push: ${{ github.event_name != 'pull_request' }}
-          build-args: |
-            RUNNER_VERSION=${{ env.RUNNER_VERSION }}
-            DOCKER_VERSION=${{ env.DOCKER_VERSION }}
-          tags: |
-            ${{ env.DOCKERHUB_USERNAME }}/${{ matrix.name }}:v${{ env.RUNNER_VERSION }}-ubuntu-${{ matrix.os-version }}
-            ${{ env.DOCKERHUB_USERNAME }}/${{ matrix.name }}:v${{ env.RUNNER_VERSION }}-ubuntu-${{ matrix.os-version }}-${{ steps.vars.outputs.sha_short }}
-
-  latest-tags:
-    if: ${{ github.event_name == 'push' || github.event_name == 'release' }}
-    runs-on: ubuntu-latest
-    name: Build ${{ matrix.name }}-latest
-    strategy:
-      matrix:
-        include:
-          - name: actions-runner
-            dockerfile: Dockerfile
-          - name: actions-runner-dind
-            dockerfile: Dockerfile.dindrunner
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v1
-        with:
-          version: latest
-
-      - name: Login to DockerHub
-        uses: docker/login-action@v1
-        with:
-          username: ${{ secrets.DOCKER_USER }}
-          password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
-
-      - name: Build and Push Latest Tag
-        uses: docker/build-push-action@v2
-        with:
-          context: ./runner
-          file: ./runner/${{ matrix.dockerfile }}
-          platforms: linux/amd64,linux/arm64
-          push: true
-          build-args: |
-            RUNNER_VERSION=${{ env.RUNNER_VERSION }}
-            DOCKER_VERSION=${{ env.DOCKER_VERSION }}
-          tags: |
-            ${{ env.DOCKERHUB_USERNAME }}/${{ matrix.name }}:latest

.github/workflows/publish-arc.yaml

@@ -1,20 +1,28 @@
+name: Publish ARC
+
 on:
   release:
-    types: [published]
+    types:
+      - published
+
+# https://docs.github.com/en/rest/overview/permissions-required-for-github-apps
+permissions:
+ contents: write 
+ packages: write
 
 jobs:
-  build:
-    runs-on: ubuntu-latest
+  release-controller:
     name: Release
+    runs-on: ubuntu-latest
     env:
       DOCKERHUB_USERNAME: ${{ secrets.DOCKER_USER }}
     steps:
-      - name: Set outputs
-        id: vars
-        run: echo ::set-output name=sha_short::${GITHUB_SHA::7}
-
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
+
+      - uses: actions/setup-go@v3
+        with:
+          go-version: '1.18.2'
 
       - name: Install tools
         run: |
@@ -33,25 +41,20 @@ jobs:
       - name: Upload artifacts
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        run: make github-release
+        run: |
+          make github-release
 
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v1
+      - name: Setup Docker Environment
+        id: vars
+        uses: ./.github/actions/setup-docker-environment
         with:
-          version: latest
-
-      - name: Login to DockerHub
-        uses: docker/login-action@v1
-        with:
-          username: ${{ secrets.DOCKER_USER }}
+          username: ${{ env.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
+          ghcr_username: ${{ github.actor }}
+          ghcr_password: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build and Push
-        uses: docker/build-push-action@v2
+        uses: docker/build-push-action@v3
         with:
           file: Dockerfile
           platforms: linux/amd64,linux/arm64
@@ -60,4 +63,8 @@ jobs:
             ${{ env.DOCKERHUB_USERNAME }}/actions-runner-controller:latest
             ${{ env.DOCKERHUB_USERNAME }}/actions-runner-controller:${{ env.VERSION }}
             ${{ env.DOCKERHUB_USERNAME }}/actions-runner-controller:${{ env.VERSION }}-${{ steps.vars.outputs.sha_short }}
-
+            ghcr.io/actions-runner-controller/actions-runner-controller:latest
+            ghcr.io/actions-runner-controller/actions-runner-controller:${{ env.VERSION }}
+            ghcr.io/actions-runner-controller/actions-runner-controller:${{ env.VERSION }}-${{ steps.vars.outputs.sha_short }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.github/workflows/publish-canary.yaml

@@ -0,0 +1,58 @@
+name: Publish Canary Image
+
+on:
+  push:
+    branches:
+      - master
+    paths-ignore:
+      - '**.md'
+      - '.github/ISSUE_TEMPLATE/**'
+      - '.github/workflows/validate-chart.yaml'
+      - '.github/workflows/publish-chart.yaml'
+      - '.github/workflows/publish-arc.yaml'
+      - '.github/workflows/runners.yaml'
+      - '.github/workflows/validate-entrypoint.yaml'
+      - '.github/renovate.*'
+      - 'runner/**'
+      - '.gitignore'
+      - 'PROJECT'
+      - 'LICENSE'
+      - 'Makefile'
+
+# https://docs.github.com/en/rest/overview/permissions-required-for-github-apps
+permissions:
+  contents: read
+  packages: write  
+
+jobs:
+  canary-build:
+    name: Build and Publish Canary Image  
+    runs-on: ubuntu-latest
+    env:
+      DOCKERHUB_USERNAME: ${{ secrets.DOCKER_USER }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Docker Environment
+        id: vars
+        uses: ./.github/actions/setup-docker-environment
+        with:
+          username: ${{ env.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
+          ghcr_username: ${{ github.actor }}
+          ghcr_password: ${{ secrets.GITHUB_TOKEN }}
+
+      # Considered unstable builds
+      # See Issue #285, PR #286, and PR #323 for more information
+      - name: Build and Push
+        uses: docker/build-push-action@v3
+        with:
+          file: Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: |
+            ${{ env.DOCKERHUB_USERNAME }}/actions-runner-controller:canary
+            ghcr.io/actions-runner-controller/actions-runner-controller:canary
+          cache-from: type=gha,scope=arc-canary
+          cache-to: type=gha,mode=max,scope=arc-canary

.github/workflows/publish-chart.yaml

@@ -1,4 +1,4 @@
-name: Publish helm chart
+name: Publish Helm Chart
 
 on:
   push:
@@ -6,26 +6,32 @@ on:
       - master
     paths:
       - 'charts/**'
-      - '.github/workflows/on-push-master-publish-chart.yml'
+      - '.github/workflows/publish-chart.yaml'
       - '!charts/actions-runner-controller/docs/**'
       - '!**.md'
   workflow_dispatch:
 
 env:
   KUBE_SCORE_VERSION: 1.10.0
-  HELM_VERSION: v3.4.1
+  HELM_VERSION: v3.8.0
+
+permissions:
+  contents: read
 
 jobs:
   lint-chart:
+    name: Lint Chart
     runs-on: ubuntu-latest
+    outputs:
+      publish-chart: ${{ steps.publish-chart-step.outputs.publish }}
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
 
       - name: Set up Helm
-        uses: azure/setup-helm@v1
+        uses: azure/setup-helm@v3.0
         with:
           version: ${{ env.HELM_VERSION }}
 
@@ -46,12 +52,12 @@ jobs:
               --enable-optional-test container-security-context-readonlyrootfilesystem
 
       # python is a requirement for the chart-testing action below (supports yamllint among other tests)
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         with:
-          python-version: 3.7
+          python-version: '3.7'
 
       - name: Set up chart-testing
-        uses: helm/chart-testing-action@v2.1.0
+        uses: helm/chart-testing-action@v2.2.1
 
       - name: Run chart-testing (list-changed)
         id: list-changed
@@ -62,31 +68,50 @@ jobs:
           fi
 
       - name: Run chart-testing (lint)
-        run: ct lint --config charts/.ci/ct-config.yaml
+        run: |
+          ct lint --config charts/.ci/ct-config.yaml
 
       - name: Create kind cluster
-        uses: helm/kind-action@v1.2.0
         if: steps.list-changed.outputs.changed == 'true'
+        uses: helm/kind-action@v1.3.0
 
       # We need cert-manager already installed in the cluster because we assume the CRDs exist
       - name: Install cert-manager
+        if: steps.list-changed.outputs.changed == 'true'      
         run: |
           helm repo add jetstack https://charts.jetstack.io --force-update
           helm install cert-manager jetstack/cert-manager --set installCRDs=true --wait
-        if: steps.list-changed.outputs.changed == 'true'
 
       - name: Run chart-testing (install)
-        run: ct install --config charts/.ci/ct-config.yaml
         if: steps.list-changed.outputs.changed == 'true'
+        run: ct install --config charts/.ci/ct-config.yaml
+
+      # WARNING: This relies on the latest release being inat the top of the JSON from GitHub and a clean chart.yaml
+      - name: Check if Chart Publish is Needed
+        id: publish-chart-step
+        run: |
+          CHART_TEXT=$(curl -fs https://raw.githubusercontent.com/actions-runner-controller/actions-runner-controller/master/charts/actions-runner-controller/Chart.yaml)
+          NEW_CHART_VERSION=$(echo "$CHART_TEXT" | grep version: | cut -d ' ' -f 2)
+          RELEASE_LIST=$(curl -fs https://api.github.com/repos/actions-runner-controller/actions-runner-controller/releases  | jq .[].tag_name | grep actions-runner-controller | cut -d '"' -f 2 | cut -d '-' -f 4)
+          LATEST_RELEASED_CHART_VERSION=$(echo $RELEASE_LIST | cut -d ' ' -f 1)
+          echo "Chart version in master : $NEW_CHART_VERSION"
+          echo "Latest release chart version : $LATEST_RELEASED_CHART_VERSION"
+          if [[ $NEW_CHART_VERSION != $LATEST_RELEASED_CHART_VERSION ]]; then
+            echo "::set-output name=publish::true"
+          fi
 
   publish-chart:
-
-    runs-on: ubuntu-latest
+    if: needs.lint-chart.outputs.publish-chart == 'true'
     needs: lint-chart
+    name: Publish Chart
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write  # for helm/chart-releaser-action to push chart release and create a release
+    
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
 
@@ -96,7 +121,7 @@ jobs:
           git config user.email "$GITHUB_ACTOR@users.noreply.github.com"
 
       - name: Run chart-releaser
-        uses: helm/chart-releaser-action@v1.2.1
+        uses: helm/chart-releaser-action@v1.4.0
         env:
           CR_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
 

.github/workflows/run-codeql.yaml

@@ -0,0 +1,32 @@
+name: Run CodeQL
+
+on:
+  push:
+    branches: 
+      - master
+  pull_request:
+    branches:
+      - master
+  schedule:
+    - cron: '30 1 * * 0'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      security-events: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@v2
+        with:
+          languages: go
+
+      - name: Autobuild
+        uses: github/codeql-action/autobuild@v2
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@v2

.github/workflows/run-stale.yaml

@@ -0,0 +1,25 @@
+name: Run Stale Bot
+on:
+  schedule:
+    - cron: '30 1 * * *'
+
+permissions:
+  contents: read
+
+jobs:
+  stale:
+    name: Run Stale
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write         # for actions/stale to close stale issues
+      pull-requests: write  # for actions/stale to close stale PRs
+    steps:
+      - uses: actions/stale@v5
+        with:
+          stale-issue-message: 'This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.'
+          # turn off stale for both issues and PRs
+          days-before-stale: -1
+          # turn stale back on for issues only
+          days-before-issue-stale: 30
+          days-before-issue-close: 14
+          exempt-issue-labels: 'pinned,security,enhancement,refactor,documentation,chore,bug,dependencies,needs-investigation'

.github/workflows/runners.yaml

@@ -0,0 +1,83 @@
+name: Runners
+
+on:
+  pull_request:
+    types:
+      - opened
+      - synchronize
+      - reopened
+    branches:
+      - 'master'
+    paths:
+      - 'runner/**'
+      - '!runner/Makefile'
+      - '.github/workflows/runners.yaml'
+      - '!**.md'
+  # We must do a trigger on a push: instead of a types: closed so GitHub Secrets 
+  # are available to the workflow run
+  push:
+    branches:
+      - 'master'
+    paths:
+      - 'runner/**'
+      - '!runner/Makefile'
+      - '.github/workflows/runners.yaml'
+      - '!**.md'
+
+env:
+  RUNNER_VERSION: 2.294.0
+  DOCKER_VERSION: 20.10.12
+  RUNNER_CONTAINER_HOOKS_VERSION: 0.1.2
+  DOCKERHUB_USERNAME: summerwind
+
+jobs:
+  build-runners:
+    name: Build ${{ matrix.name }}-${{ matrix.os-name }}-${{ matrix.os-version }}
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - name: actions-runner
+            os-name: ubuntu
+            os-version: 20.04
+          - name: actions-runner-dind
+            os-name: ubuntu
+            os-version: 20.04
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+
+      - name: Setup Docker Environment
+        id: vars
+        uses: ./.github/actions/setup-docker-environment
+        with:
+          username: ${{ env.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
+          ghcr_username: ${{ github.actor }}
+          ghcr_password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and Push Versioned Tags
+        uses: docker/build-push-action@v3
+        with:
+          context: ./runner
+          file: ./runner/${{ matrix.name }}.dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
+          build-args: |
+            RUNNER_VERSION=${{ env.RUNNER_VERSION }}
+            DOCKER_VERSION=${{ env.DOCKER_VERSION }}
+            RUNNER_CONTAINER_HOOKS_VERSION=${{ env.RUNNER_CONTAINER_HOOKS_VERSION }}
+          tags: |
+            ${{ env.DOCKERHUB_USERNAME }}/${{ matrix.name }}:v${{ env.RUNNER_VERSION }}-${{ matrix.os-name }}-${{ matrix.os-version }}
+            ${{ env.DOCKERHUB_USERNAME }}/${{ matrix.name }}:v${{ env.RUNNER_VERSION }}-${{ matrix.os-name }}-${{ matrix.os-version }}-${{ steps.vars.outputs.sha_short }}
+            ${{ env.DOCKERHUB_USERNAME }}/${{ matrix.name }}:latest
+            ghcr.io/${{ github.repository }}/${{ matrix.name }}:latest
+            ghcr.io/${{ github.repository }}/${{ matrix.name }}:v${{ env.RUNNER_VERSION }}-${{ matrix.os-name }}-${{ matrix.os-version }}
+            ghcr.io/${{ github.repository }}/${{ matrix.name }}:v${{ env.RUNNER_VERSION }}-${{ matrix.os-name }}-${{ matrix.os-version }}-${{ steps.vars.outputs.sha_short }}
+          cache-from: type=gha,scope=build-${{ matrix.name }}
+          cache-to: type=gha,mode=max,scope=build-${{ matrix.name }}

.github/workflows/test.yaml

@@ -1,34 +0,0 @@
-name: CI
-
-on:
-  pull_request:
-    branches:
-      - master
-    paths-ignore:
-    - 'runner/**'
-    - .github/workflows/build-and-release-runners.yml
-    - '*.md'
-    - '.gitignore'
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    name: Test
-    steps:
-    - name: Checkout
-      uses: actions/checkout@v2
-    - uses: actions/setup-go@v2
-      with:
-        go-version: '^1.16.5'
-    - run: go version
-    - name: Install kubebuilder
-      run: |
-        curl -L -O https://github.com/kubernetes-sigs/kubebuilder/releases/download/v2.3.2/kubebuilder_2.3.2_linux_amd64.tar.gz
-        tar zxvf kubebuilder_2.3.2_linux_amd64.tar.gz
-        sudo mv kubebuilder_2.3.2_linux_amd64 /usr/local/kubebuilder
-    - name: Run tests
-      run: make test
-    - name: Verify manifests are up-to-date
-      run: |
-        make manifests
-        git diff --exit-code

.github/workflows/validate-arc.yaml

@@ -0,0 +1,60 @@
+name: Validate ARC
+
+on:
+  pull_request:
+    branches:
+      - master
+    paths-ignore:
+      - '**.md'
+      - '.github/ISSUE_TEMPLATE/**'
+      - '.github/workflows/publish-canary.yaml'
+      - '.github/workflows/validate-chart.yaml'
+      - '.github/workflows/publish-chart.yaml'
+      - '.github/workflows/runners.yaml'
+      - '.github/workflows/publish-arc.yaml'
+      - '.github/workflows/validate-entrypoint.yaml'
+      - '.github/renovate.*'
+      - 'runner/**'
+      - '.gitignore'
+      - 'PROJECT'
+      - 'LICENSE'
+      - 'Makefile'
+
+permissions:
+  contents: read
+
+jobs:
+  test-controller:
+    name: Test ARC
+    runs-on: ubuntu-latest
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v3
+
+    - name: Set-up Go
+      uses: actions/setup-go@v3
+      with:
+        go-version: '1.18.2'
+        check-latest: false
+    
+    - uses: actions/cache@v3
+      with:
+        path: ~/go/pkg/mod
+        key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
+        restore-keys: |
+          ${{ runner.os }}-go-
+
+    - name: Install kubebuilder
+      run: |
+        curl -L -O https://github.com/kubernetes-sigs/kubebuilder/releases/download/v2.3.2/kubebuilder_2.3.2_linux_amd64.tar.gz
+        tar zxvf kubebuilder_2.3.2_linux_amd64.tar.gz
+        sudo mv kubebuilder_2.3.2_linux_amd64 /usr/local/kubebuilder
+
+    - name: Run tests
+      run: |
+        make test
+
+    - name: Verify manifests are up-to-date
+      run: |
+        make manifests
+        git diff --exit-code

.github/workflows/validate-chart.yaml

@@ -1,28 +1,32 @@
-name: Lint and Test Charts
+name: Validate Helm Chart
 
 on:
   push:
     paths:
       - 'charts/**'
-      - '.github/workflows/on-push-lint-charts.yml'
+      - '.github/workflows/validate-chart.yaml'
       - '!charts/actions-runner-controller/docs/**'
       - '!**.md'
   workflow_dispatch:
 env:
   KUBE_SCORE_VERSION: 1.10.0
-  HELM_VERSION: v3.4.1
+  HELM_VERSION: v3.8.0
+
+permissions:
+  contents: read
 
 jobs:
-  lint-test:
+  validate-chart:
+    name: Lint Chart
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@v3
         with:
           fetch-depth: 0
 
       - name: Set up Helm
-        uses: azure/setup-helm@v1
+        uses: azure/setup-helm@v3.0
         with:
           version: ${{ env.HELM_VERSION }}
 
@@ -43,12 +47,12 @@ jobs:
               --enable-optional-test container-security-context-readonlyrootfilesystem
 
       # python is a requirement for the chart-testing action below (supports yamllint among other tests)
-      - uses: actions/setup-python@v2
+      - uses: actions/setup-python@v4
         with:
-          python-version: 3.7
+          python-version: '3.7'
 
       - name: Set up chart-testing
-        uses: helm/chart-testing-action@v2.1.0
+        uses: helm/chart-testing-action@v2.2.1
 
       - name: Run chart-testing (list-changed)
         id: list-changed
@@ -59,18 +63,20 @@ jobs:
           fi
 
       - name: Run chart-testing (lint)
-        run: ct lint --config charts/.ci/ct-config.yaml
+        run: |
+          ct lint --config charts/.ci/ct-config.yaml
 
       - name: Create kind cluster
-        uses: helm/kind-action@v1.2.0
+        uses: helm/kind-action@v1.3.0
         if: steps.list-changed.outputs.changed == 'true'
 
       # We need cert-manager already installed in the cluster because we assume the CRDs exist
       - name: Install cert-manager
+        if: steps.list-changed.outputs.changed == 'true'
         run: |
           helm repo add jetstack https://charts.jetstack.io --force-update
           helm install cert-manager jetstack/cert-manager --set installCRDs=true --wait
-        if: steps.list-changed.outputs.changed == 'true'
 
       - name: Run chart-testing (install)
-        run: ct install --config charts/.ci/ct-config.yaml
+        run: |
+          ct install --config charts/.ci/ct-config.yaml

.github/workflows/validate-runners.yaml

@@ -1,4 +1,4 @@
-name: Unit tests for entrypoint
+name: Validate Runners
 
 on:
   pull_request:
@@ -7,15 +7,19 @@ on:
     paths:
       - 'runner/**'
       - 'test/entrypoint/**'
+      - '!**.md'
+
+permissions:
+  contents: read
 
 jobs:
-  test:
-    runs-on: ubuntu-latest
+  test-runner-entrypoint:
     name: Test entrypoint
+    runs-on: ubuntu-latest
     steps:
     - name: Checkout
-      uses: actions/checkout@v2
-    - name: Run unit tests for entrypoint.sh
+      uses: actions/checkout@v3
+
+    - name: Run tests
       run: |
-        cd test/entrypoint
-        bash entrypoint_unittest.sh
+        make acceptance/runner/entrypoint

.github/workflows/wip.yml

@@ -1,44 +0,0 @@
-on:
-  push:
-    branches:
-      - master
-    paths-ignore:
-      - "runner/**"
-      - "**.md"
-      - ".gitignore"
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    name: release-latest
-    env:
-      DOCKERHUB_USERNAME: ${{ secrets.DOCKER_USER }}
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@v1
-
-      - name: Set up Docker Buildx
-        id: buildx
-        uses: docker/setup-buildx-action@v1
-        with:
-          version: latest
-
-      - name: Login to DockerHub
-        uses: docker/login-action@v1
-        with:
-          username: ${{ secrets.DOCKER_USER }}
-          password: ${{ secrets.DOCKER_ACCESS_TOKEN }}
-
-      # Considered unstable builds
-      # See Issue #285, PR #286, and PR #323 for more information
-      - name: Build and Push
-        uses: docker/build-push-action@v2
-        with:
-          file: Dockerfile
-          platforms: linux/amd64,linux/arm64
-          push: true
-          tags: |
-            ${{ env.DOCKERHUB_USERNAME }}/actions-runner-controller:canary

CODEOWNERS

@@ -0,0 +1,2 @@
+# actions-runner-controller maintainers
+* @mumoshu @toast-gear

CONTRIBUTING.md

@@ -1,10 +1,25 @@
 ## Contributing
 
+### Testing Controller Built from a Pull Request
+
+We always appreciate your help in testing open pull requests by deploying custom builds of actions-runner-controller onto your own environment, so that we are extra sure we didn't break anything.
+
+It is especially true when the pull request is about GitHub Enterprise, both GHEC and GHES, as [maintainers don't have GitHub Enterprise environments for testing](/README.md#github-enterprise-support).
+
+The process would look like the below:
+
+- Clone this repository locally
+- Checkout the branch. If you use the `gh` command, run `gh pr checkout $PR_NUMBER`
+- Run `NAME=$DOCKER_USER/actions-runner-controller VERSION=canary make docker-build docker-push` for a custom container image build
+- Update your actions-runner-controller's controller-manager deployment to use the new image, `$DOCKER_USER/actions-runner-controller:canary`
+
+Please also note that you need to replace `$DOCKER_USER` with your own DockerHub account name.
+
 ### How to Contribute a Patch
 
 Depending on what you are patching depends on how you should go about it. Below are some guides on how to test patches locally as well as develop the controller and runners.
 
-When sumitting a PR for a change please provide evidence that your change works as we still need to work on improving the CI of the project. Some resources are provided for helping achieve this, see this guide for details.
+When submitting a PR for a change please provide evidence that your change works as we still need to work on improving the CI of the project. Some resources are provided for helping achieve this, see this guide for details.
 
 #### Running an End to End Test
 
@@ -80,6 +95,7 @@ To make your development cycle faster, use the below command to update deploy an
 # you either need to bump VERSION and RUNNER_TAG on each run,
 # or manually run `kubectl delete pod $POD` on respective pods for changes to actually take effect.
 
+# Makefile
 VERSION=controller1 \
   RUNNER_TAG=runner1 \
   make acceptance/pull acceptance/kind docker-build acceptance/load acceptance/deploy
@@ -88,14 +104,16 @@ VERSION=controller1 \
 If you've already deployed actions-runner-controller and only want to recreate pods to use the newer image, you can run:
 
 ```shell
+# Makefile
 NAME=$DOCKER_USER/actions-runner-controller \
   make docker-build acceptance/load && \
   kubectl -n actions-runner-system delete po $(kubectl -n actions-runner-system get po -ojsonpath={.items[*].metadata.name})
 ```
 
-Similarly, if you'd like to recreate runner pods with the newer runner image,
+Similarly, if you'd like to recreate runner pods with the newer runner image you can use the runner specific [Makefile](runner/Makefile) to build and / or push new runner images
 
 ```shell
+# runner/Makefile
 NAME=$DOCKER_USER/actions-runner make \
   -C runner docker-{build,push}-ubuntu && \
   (kubectl get po -ojsonpath={.items[*].metadata.name} | xargs -n1 kubectl delete po)
@@ -136,7 +154,4 @@ GINKGO_FOCUS='[It] should create a new Runner resource from the specified templa
 
 #### Helm Version Bumps
 
-**Chart Version :** When bumping the chart version follow semantic versioning https://semver.org/<br />
-**App Version :** When bumping the app version you will also need to bump the chart version too. Again, follow semantic versioning when bumping the chart.
-
-To determine if you need to bump the MAJOR, MINOR or PATCH versions you will need to review the changes between the previous app version and the new app version and / or ask for a maintainer to advise.
+In general we ask you not to bump the version in your PR, the maintainers in general manage the publishing of a new chart.

Dockerfile

@@ -1,29 +1,44 @@
 # Build the manager binary
-FROM golang:1.17 as builder
-
-ARG TARGETPLATFORM
+FROM --platform=$BUILDPLATFORM golang:1.18.3 as builder
 
 WORKDIR /workspace
 
-ENV GO111MODULE=on \
-  CGO_ENABLED=0
+# Make it runnable on a distroless image/without libc
+ENV CGO_ENABLED=0
 
 # Copy the Go Modules manifests
 COPY go.mod go.sum ./
 
 # cache deps before building and copying source so that we don't need to re-download as much
-# and so that source changes don't invalidate our downloaded layer
+# and so that source changes don't invalidate our downloaded layer.
+#
+# Also, we need to do this before setting TARGETPLATFORM/TARGETOS/TARGETARCH/TARGETVARIANT
+# so that go mod cache is shared across platforms.
 RUN go mod download
 
 # Copy the go source
-COPY . .
+# COPY . .
+
+# Usage:
+#   docker buildx build --tag repo/img:tag -f ./Dockerfile . --platform linux/amd64,linux/arm64,linux/arm/v7
+#
+# With the above commmand,
+# TARGETOS can be "linux", TARGETARCH can be "amd64", "arm64", and "arm", TARGETVARIANT can be "v7".
+
+ARG TARGETPLATFORM TARGETOS TARGETARCH TARGETVARIANT
+
+# We intentionally avoid `--mount=type=cache,mode=0777,target=/go/pkg/mod` in the `go mod download` and the `go build` runs
+# to avoid https://github.com/moby/buildkit/issues/2334
+# We can use docker layer cache so the build is fast enogh anyway
+# We also use per-platform GOCACHE for the same reason.
+env GOCACHE /build/${TARGETPLATFORM}/root/.cache/go-build
 
 # Build
-RUN export GOOS=$(echo ${TARGETPLATFORM} | cut -d / -f1) && \
-  export GOARCH=$(echo ${TARGETPLATFORM} | cut -d / -f2) && \
-  GOARM=$(echo ${TARGETPLATFORM} | cut -d / -f3 | cut -c2-) && \
-  go build -a -o manager main.go && \
-  go build -a -o github-webhook-server ./cmd/githubwebhookserver
+RUN --mount=target=. \
+  --mount=type=cache,mode=0777,target=${GOCACHE} \
+  export GOOS=${TARGETOS} GOARCH=${TARGETARCH} GOARM=${TARGETVARIANT#v} && \
+  go build -o /out/manager main.go && \
+  go build -o /out/github-webhook-server ./cmd/githubwebhookserver
 
 # Use distroless as minimal base image to package the manager binary
 # Refer to https://github.com/GoogleContainerTools/distroless for more details
@@ -31,8 +46,8 @@ FROM gcr.io/distroless/static:nonroot
 
 WORKDIR /
 
-COPY --from=builder /workspace/manager .
-COPY --from=builder /workspace/github-webhook-server .
+COPY --from=builder /out/manager .
+COPY --from=builder /out/github-webhook-server .
 
 USER nonroot:nonroot
 

Makefile

@@ -5,21 +5,23 @@ else
 endif
 DOCKER_USER ?= $(shell echo ${NAME} | cut -d / -f1)
 VERSION ?= latest
+RUNNER_VERSION ?= 2.294.0
+TARGETPLATFORM ?= $(shell arch)
 RUNNER_NAME ?= ${DOCKER_USER}/actions-runner
 RUNNER_TAG  ?= ${VERSION}
 TEST_REPO ?= ${DOCKER_USER}/actions-runner-controller
 TEST_ORG ?=
 TEST_ORG_REPO ?=
 TEST_EPHEMERAL ?= false
-SYNC_PERIOD ?= 5m
+SYNC_PERIOD ?= 1m
 USE_RUNNERSET ?=
-RUNNER_FEATURE_FLAG_EPHEMERAL ?=
 KUBECONTEXT ?= kind-acceptance
 CLUSTER ?= acceptance
 CERT_MANAGER_VERSION ?= v1.1.1
+KUBE_RBAC_PROXY_VERSION ?= v0.11.0
 
 # Produce CRDs that work back to Kubernetes 1.11 (no version conversion)
-CRD_OPTIONS ?= "crd:trivialVersions=true,generateEmbeddedObjectMeta=true"
+CRD_OPTIONS ?= "crd:generateEmbeddedObjectMeta=true"
 
 # Get the currently used golang install path (in GOPATH/bin, unless GOBIN is set)
 ifeq (,$(shell go env GOBIN))
@@ -54,6 +56,7 @@ GO_TEST_ARGS ?= -short
 # Run tests
 test: generate fmt vet manifests
 	go test $(GO_TEST_ARGS) ./... -coverprofile cover.out
+	go test -fuzz=Fuzz -fuzztime=10s -run=Fuzz* ./controllers
 
 test-with-deps: kube-apiserver etcd kubectl
 	# See https://pkg.go.dev/sigs.k8s.io/controller-runtime/pkg/envtest#pkg-constants
@@ -107,13 +110,9 @@ vet:
 generate: controller-gen
 	$(CONTROLLER_GEN) object:headerFile=./hack/boilerplate.go.txt paths="./..."
 
-# Build the docker image
-docker-build:
-	docker build -t ${NAME}:${VERSION} .
-	docker build -t ${RUNNER_NAME}:${RUNNER_TAG} --build-arg TARGETPLATFORM=$(shell arch) runner
-
 docker-buildx:
-	export DOCKER_CLI_EXPERIMENTAL=enabled
+	export DOCKER_CLI_EXPERIMENTAL=enabled ;\
+	export DOCKER_BUILDKIT=1
 	@if ! docker buildx ls | grep -q container-builder; then\
 		docker buildx create --platform ${PLATFORMS} --name container-builder --use;\
 	fi
@@ -156,7 +155,7 @@ acceptance/kind:
 # See https://kind.sigs.k8s.io/docs/user/known-issues/#docker-installed-with-snap
 acceptance/load:
 	kind load docker-image ${NAME}:${VERSION} --name ${CLUSTER}
-	kind load docker-image quay.io/brancz/kube-rbac-proxy:v0.10.0 --name ${CLUSTER}
+	kind load docker-image quay.io/brancz/kube-rbac-proxy:$(KUBE_RBAC_PROXY_VERSION) --name ${CLUSTER}
 	kind load docker-image ${RUNNER_NAME}:${RUNNER_TAG} --name ${CLUSTER}
 	kind load docker-image docker:dind --name ${CLUSTER}
 	kind load docker-image quay.io/jetstack/cert-manager-controller:$(CERT_MANAGER_VERSION) --name ${CLUSTER}
@@ -166,7 +165,7 @@ acceptance/load:
 
 # Pull the docker images for acceptance
 acceptance/pull:
-	docker pull quay.io/brancz/kube-rbac-proxy:v0.10.0
+	docker pull quay.io/brancz/kube-rbac-proxy:$(KUBE_RBAC_PROXY_VERSION)
 	docker pull docker:dind
 	docker pull quay.io/jetstack/cert-manager-controller:$(CERT_MANAGER_VERSION)
 	docker pull quay.io/jetstack/cert-manager-cainjector:$(CERT_MANAGER_VERSION)
@@ -189,12 +188,14 @@ acceptance/deploy:
 	TEST_ORG=${TEST_ORG} TEST_ORG_REPO=${TEST_ORG_REPO} SYNC_PERIOD=${SYNC_PERIOD} \
 	USE_RUNNERSET=${USE_RUNNERSET} \
 	TEST_EPHEMERAL=${TEST_EPHEMERAL} \
-	RUNNER_FEATURE_FLAG_EPHEMERAL=${RUNNER_FEATURE_FLAG_EPHEMERAL} \
 	acceptance/deploy.sh
 
 acceptance/tests:
 	acceptance/checks.sh
 
+acceptance/runner/entrypoint:
+	cd test/entrypoint/ && bash test.sh
+
 # We use -count=1 instead of `go clean -testcache`
 # See https://terratest.gruntwork.io/docs/testing-best-practices/avoid-test-caching/
 .PHONY: e2e
@@ -221,7 +222,7 @@ ifeq (, $(wildcard $(GOBIN)/controller-gen))
 	CONTROLLER_GEN_TMP_DIR=$$(mktemp -d) ;\
 	cd $$CONTROLLER_GEN_TMP_DIR ;\
 	go mod init tmp ;\
-	go get sigs.k8s.io/controller-tools/cmd/controller-gen@v0.6.0 ;\
+	go install sigs.k8s.io/controller-tools/cmd/controller-gen@v0.7.0 ;\
 	rm -rf $$CONTROLLER_GEN_TMP_DIR ;\
 	}
 endif
@@ -241,7 +242,7 @@ ifeq (, $(wildcard $(GOBIN)/yq))
 	YQ_TMP_DIR=$$(mktemp -d) ;\
 	cd $$YQ_TMP_DIR ;\
 	go mod init tmp ;\
-	go get github.com/mikefarah/yq/v3@3.4.0 ;\
+	go install github.com/mikefarah/yq/v3@3.4.0 ;\
 	rm -rf $$YQ_TMP_DIR ;\
 	}
 endif

SECURITY.md

@@ -0,0 +1,22 @@
+# Security Policy
+
+##  Sponsoring the project
+
+This project is maintained by a small team of two and therefore lacks the resource to provide security fixes in a timely manner.
+
+If you have important business(es) that relies on this project, please consider sponsoring the project so that the maintainer(s) can commit to providing such service.
+
+Please refer to https://github.com/sponsors/actions-runner-controller for available tiers.
+
+## Supported Versions
+
+| Version | Supported          |
+| ------- | ------------------ |
+| 0.23.0  | :white_check_mark: |
+| < 0.23.0| :x:                |
+
+## Reporting a Vulnerability
+
+To report a security issue, please email ykuoka+arcsecurity(at)gmail.com with a description of the issue, the steps you took to create the issue, affected versions, and, if known, mitigations for the issue.
+
+A maintainer will try to respond within 5 working days. If the issue is confirmed as a vulnerability, a Security Advisory will be opened. This project tries to follow a 90 day disclosure timeline.

TROUBLESHOOTING.md

@@ -0,0 +1,240 @@
+# Troubleshooting
+
+* [Tools](#tools)
+* [Installation](#installation)
+  * [InternalError when calling webhook: context deadline exceeded](#internalerror-when-calling-webhook-context-deadline-exceeded)
+  * [Invalid header field value](#invalid-header-field-value)
+* [Operations](#operations)
+  * [Stuck runner kind or backing pod](#stuck-runner-kind-or-backing-pod)
+  * [Delay in jobs being allocated to runners](#delay-in-jobs-being-allocated-to-runners)
+  * [Runner coming up before network available](#runner-coming-up-before-network-available)
+  * [Outgoing network action hangs indefinitely](#outgoing-network-action-hangs-indefinitely)
+  * [Unable to scale to zero with TotalNumberOfQueuedAndInProgressWorkflowRuns](#unable-to-scale-to-zero-with-totalnumberofqueuedandinprogressworkflowruns)
+
+## Tools
+
+A list of tools which are helpful for troubleshooting
+
+* https://github.com/rewanthtammana/kubectl-fields Kubernetes resources hierarchy parsing tool
+* https://github.com/stern/stern Multi pod and container log tailing for Kubernetes
+
+## Installation
+
+Troubeshooting runbooks that relate to ARC installation problems
+
+### InternalError when calling webhook: context deadline exceeded
+
+**Problem**
+
+This issue can come up for various reasons like leftovers from previous installations or not being able to access the K8s service's clusterIP associated with the admission webhook server (of ARC).
+
+```
+Internal error occurred: failed calling webhook "mutate.runnerdeployment.actions.summerwind.dev":
+Post "https://actions-runner-controller-webhook.actions-runner-system.svc:443/mutate-actions-summerwind-dev-v1alpha1-runnerdeployment?timeout=10s": context deadline exceeded
+```
+
+**Solution**
+
+First we will try the common solution of checking webhook leftovers from previous installations:
+
+1.  ```bash
+    kubectl get validatingwebhookconfiguration -A
+    kubectl get mutatingwebhookconfiguration -A
+    ```
+2.  If you see any webhooks related to actions-runner-controller, delete them:
+    ```bash
+    kubectl delete mutatingwebhookconfiguration actions-runner-controller-mutating-webhook-configuration
+    kubectl delete validatingwebhookconfiguration actions-runner-controller-validating-webhook-configuration
+    ```
+
+If that didn't work then probably your K8s control-plane is somehow unable to access the K8s service's clusterIP associated with the admission webhook server:
+1. You're running apiserver as a binary and you didn't make service cluster IPs available to the host network. 
+2. You're running the apiserver in the pod but your pod network (i.e. CNI plugin installation and config) is not good so your pods(like kube-apiserver) in the K8s control-plane nodes can't access ARC's admission webhook server pod(s) in probably data-plane nodes.
+
+
+Another reason could be due to GKEs firewall settings you may run into the following errors when trying to deploy runners on a private GKE cluster: 
+
+To fix this, you may either:
+
+1. Configure the webhook to use another port, such as 443 or 10250, [each of
+   which allow traffic by default](https://cloud.google.com/kubernetes-engine/docs/how-to/private-clusters#add_firewall_rules).
+
+   ```sh
+   # With helm, you'd set `webhookPort` to the port number of your choice
+   # See https://github.com/actions-runner-controller/actions-runner-controller/pull/1410/files for more information
+   helm upgrade --install --namespace actions-runner-system --create-namespace \
+                --wait actions-runner-controller actions-runner-controller/actions-runner-controller \
+                --set webhookPort=10250
+   ```
+
+2. Set up a firewall rule to allow the master node to connect to the default
+   webhook port. The exact way to do this may vary, but the following script
+   should point you in the right direction:
+
+   ```sh
+   # 1) Retrieve the network tag automatically given to the worker nodes
+   # NOTE: this only works if you have only one cluster in your GCP project. You will have to manually inspect the result of this command to find the tag for the cluster you want to target
+   WORKER_NODES_TAG=$(gcloud compute instances list --format='text(tags.items[0])' --filter='metadata.kubelet-config:*' | grep tags | awk '{print $2}' | sort | uniq)
+
+   # 2) Take note of the VPC network in which you deployed your cluster
+   # NOTE this only works if you have only one network in which you deploy your clusters
+   NETWORK=$(gcloud compute instances list --format='text(networkInterfaces[0].network)' --filter='metadata.kubelet-config:*' | grep networks | awk -F'/' '{print $NF}' | sort | uniq)
+
+   # 3) Get the master source ip block
+   SOURCE=$(gcloud container clusters describe <cluster-name> --region <region> | grep masterIpv4CidrBlock| cut -d ':' -f 2 | tr -d ' ')
+
+   gcloud compute firewall-rules create k8s-cert-manager --source-ranges $SOURCE --target-tags $WORKER_NODES_TAG  --allow TCP:9443 --network $NETWORK
+   ```
+
+### Invalid header field value
+
+**Problem**
+
+```json
+2020-11-12T22:17:30.693Z	ERROR	controller-runtime.controller	Reconciler error	
+{
+  "controller": "runner",
+  "request": "actions-runner-system/runner-deployment-dk7q8-dk5c9",
+  "error": "failed to create registration token: Post \"https://api.github.com/orgs/$YOUR_ORG_HERE/actions/runners/registration-token\": net/http: invalid header field value \"Bearer $YOUR_TOKEN_HERE\\n\" for key Authorization"
+}
+```
+
+**Solution**
+
+Your base64'ed PAT token has a new line at the end, it needs to be created without a `\n` added, either:
+* `echo -n $TOKEN | base64`
+* Create the secret as described in the docs using the shell and documented flags
+
+
+## Operations
+
+Troubeshooting runbooks that relate to ARC operational problems
+
+### Stuck runner kind or backing pod
+
+**Problem**
+
+Sometimes either the runner kind (`kubectl get runners`) or it's underlying pod can get stuck in a terminating state for various reasons. You can get the kind unstuck by removing its finaliser using something like this:
+
+**Solution**
+
+Remove the finaliser from the relevent runner kind or pod
+
+```
+# Get all kind runners and remove the finalizer
+$ kubectl get runners --no-headers | awk {'print $1'} | xargs kubectl patch runner --type merge -p '{"metadata":{"finalizers":null}}'
+
+# Get all pods that are stuck terminating and remove the finalizer
+$ kubectl -n get pods | grep Terminating | awk {'print $1'} | xargs kubectl patch pod -p '{"metadata":{"finalizers":null}}'
+```
+
+_Note the code assumes you have already selected the namespace your runners are in and that they 
+are in a namespace not shared with anything else_
+
+### Delay in jobs being allocated to runners
+
+**Problem**
+
+ARC isn't involved in jobs actually getting allocated to a runner. ARC is responsible for orchestrating runners and the runner lifecycle. Why some people see large delays in job allocation is not clear however it has been https://github.com/actions-runner-controller/actions-runner-controller/issues/1387#issuecomment-1122593984 that this is caused from the self-update process somehow.
+
+**Solution**
+
+Disable the self-update process in your runner manifests
+
+```yaml
+apiVersion: actions.summerwind.dev/v1alpha1
+kind: RunnerDeployment
+metadata:
+  name: example-runnerdeployment-with-sleep
+spec:
+  template:
+    spec:
+      ...
+      env:
+        - name: DISABLE_RUNNER_UPDATE
+          value: "true"
+```
+
+### Runner coming up before network available
+
+**Problem**
+
+If you're running your action runners on a service mesh like Istio, you might
+have problems with runner configuration accompanied by logs like:
+
+```
+....
+runner Starting Runner listener with startup type: service
+runner Started listener process
+runner An error occurred: Not configured
+runner Runner listener exited with error code 2
+runner Runner listener exit with retryable error, re-launch runner in 5 seconds.
+....
+```
+
+This is because the `istio-proxy` has not completed configuring itself when the
+configuration script tries to communicate with the network.
+
+More broadly, there are many other circumstances where the runner pod coming up first can cause issues.
+
+**Solution**<br />
+
+> Added originally to help users with older istio instances.
+> Newer Istio instances can use Istio's `holdApplicationUntilProxyStarts` attribute ([istio/istio#11130](https://github.com/istio/istio/issues/11130)) to avoid having to delay starting up the runner.
+> Please read the discussion in [#592](https://github.com/actions-runner-controller/actions-runner-controller/pull/592) for more information.
+
+You can add a delay to the runner's entrypoint script by setting the `STARTUP_DELAY_IN_SECONDS` environment variable for the runner pod. This will cause the script to sleep X seconds, this works with any runner kind.
+
+```yaml
+apiVersion: actions.summerwind.dev/v1alpha1
+kind: RunnerDeployment
+metadata:
+  name: example-runnerdeployment-with-sleep
+spec:
+  template:
+    spec:
+      ...
+      env:
+        - name: STARTUP_DELAY_IN_SECONDS
+          value: "5"
+```
+
+## Outgoing network action hangs indefinitely
+
+**Problem**
+
+Some random outgoing network actions hangs indefinitely. This could be because your cluster does not give Docker the standard MTU of 1500, you can check this out by running `ip link` in a pod that encounters the problem and reading the outgoing interface's MTU value. If it is smaller than 1500, then try the following.
+
+**Solution**
+
+Add a `dockerMTU` key in your runner's spec with the value you read on the outgoing interface. For instance:
+
+```yaml
+apiVersion: actions.summerwind.dev/v1alpha1
+kind: RunnerDeployment
+metadata:
+  name: github-runner
+  namespace: github-system
+spec:
+  replicas: 6
+  template:
+    spec:
+      dockerMTU: 1400
+      repository: $username/$repo
+      env: []
+```
+
+There may be more places you need to tweak for MTU.
+Please consult issues like #651 for more information.
+
+## Unable to scale to zero with TotalNumberOfQueuedAndInProgressWorkflowRuns
+
+**Problem**
+
+HRA doesn't scale the RunnerDeployment to zero, even though you did configure HRA correctly, to have a pull-based scaling metric `TotalNumberOfQueuedAndInProgressWorkflowRuns`, and set `minReplicas: 0`.
+
+**Solution**
+
+You very likely have some dangling workflow jobs stuck in `queued` or `in_progress` as seen in [#1057](https://github.com/actions-runner-controller/actions-runner-controller/issues/1057#issuecomment-1133439061).
+
+Manually call [the "list workflow runs" API](https://docs.github.com/en/rest/actions/workflow-runs#list-workflow-runs-for-a-repository), and [remove the dangling workflow job(s)](https://docs.github.com/en/rest/actions/workflow-runs#delete-a-workflow-run).

acceptance/deploy.sh

@@ -6,6 +6,8 @@ tpe=${ACCEPTANCE_TEST_SECRET_TYPE}
 
 VALUES_FILE=${VALUES_FILE:-$(dirname $0)/values.yaml}
 
+kubectl delete secret -n actions-runner-system controller-manager || :
+
 if [ "${tpe}" == "token" ]; then
   if ! kubectl get secret controller-manager -n actions-runner-system >/dev/null; then
     kubectl create secret generic controller-manager \
@@ -16,16 +18,29 @@ elif [ "${tpe}" == "app" ]; then
   kubectl create secret generic controller-manager \
     -n actions-runner-system \
     --from-literal=github_app_id=${APP_ID:?must not be empty} \
-    --from-literal=github_app_installation_id=${INSTALLATION_ID:?must not be empty} \
-    --from-file=github_app_private_key=${PRIVATE_KEY_FILE_PATH:?must not be empty}
+    --from-literal=github_app_installation_id=${APP_INSTALLATION_ID:?must not be empty} \
+    --from-file=github_app_private_key=${APP_PRIVATE_KEY_FILE:?must not be empty}
 else
   echo "ACCEPTANCE_TEST_SECRET_TYPE must be set to either \"token\" or \"app\"" 1>&2
   exit 1
 fi
 
+if [ -n "${WEBHOOK_GITHUB_TOKEN}" ]; then
+  kubectl -n actions-runner-system delete secret \
+      github-webhook-server || :
+  kubectl -n actions-runner-system create secret generic \
+      github-webhook-server \
+      --from-literal=github_token=${WEBHOOK_GITHUB_TOKEN:?WEBHOOK_GITHUB_TOKEN must not be empty}
+else
+  echo 'Skipped deploying secret "github-webhook-server". Set WEBHOOK_GITHUB_TOKEN to deploy.' 1>&2
+fi
+
 tool=${ACCEPTANCE_TEST_DEPLOYMENT_TOOL}
 
+TEST_ID=${TEST_ID:-default}
+
 if [ "${tool}" == "helm" ]; then
+  set -v
   helm upgrade --install actions-runner-controller \
     charts/actions-runner-controller \
     -n actions-runner-system \
@@ -34,42 +49,30 @@ if [ "${tool}" == "helm" ]; then
     --set authSecret.create=false \
     --set image.repository=${NAME} \
     --set image.tag=${VERSION} \
+    --set podAnnotations.test-id=${TEST_ID} \
+    --set githubWebhookServer.podAnnotations.test-id=${TEST_ID} \
     -f ${VALUES_FILE}
-  kubectl apply -f charts/actions-runner-controller/crds
-  kubectl -n actions-runner-system wait deploy/actions-runner-controller --for condition=available --timeout 60s
+  set +v
+  # To prevent `CustomResourceDefinition.apiextensions.k8s.io "runners.actions.summerwind.dev" is invalid: metadata.annotations: Too long: must have at most 262144 bytes`
+  # errors
+  kubectl create -f charts/actions-runner-controller/crds || kubectl replace -f charts/actions-runner-controller/crds
+  # This wait fails due to timeout when it's already in crashloopback and this update doesn't change the image tag.
+  # That's why we add `|| :`. With that we prevent stopping the script in case of timeout and
+  # proceed to delete (possibly in crashloopback and/or running with outdated image) pods so that they are recreated by K8s.
+  kubectl -n actions-runner-system wait deploy/actions-runner-controller --for condition=available --timeout 60s || :
 else
   kubectl apply \
     -n actions-runner-system \
     -f release/actions-runner-controller.yaml
-  kubectl -n actions-runner-system wait deploy/controller-manager --for condition=available --timeout 120s
+  kubectl -n actions-runner-system wait deploy/controller-manager --for condition=available --timeout 120s || :
 fi
 
+# Restart all ARC pods
+kubectl -n actions-runner-system delete po -l app.kubernetes.io/name=actions-runner-controller
+
+echo Waiting for all ARC pods to be up and running after restart
+
+kubectl -n actions-runner-system wait deploy/actions-runner-controller --for condition=available --timeout 120s
+
 # Adhocly wait for some time until actions-runner-controller's admission webhook gets ready
 sleep 20
-
-RUNNER_LABEL=${RUNNER_LABEL:-self-hosted}
-
-if [ -n "${TEST_REPO}" ]; then
-  if [ -n "USE_RUNNERSET" ]; then
-      cat acceptance/testdata/repo.runnerset.yaml | envsubst | kubectl apply -f -
-      cat acceptance/testdata/repo.runnerset.hra.yaml | envsubst | kubectl apply -f -
-  else
-    echo 'Deploying runnerdeployment and hra. Set USE_RUNNERSET if you want to deploy runnerset instead.'
-    cat acceptance/testdata/repo.runnerdeploy.yaml | envsubst | kubectl apply -f -
-    cat acceptance/testdata/repo.hra.yaml | envsubst | kubectl apply -f -
-  fi
-else
-  echo 'Skipped deploying runnerdeployment and hra. Set TEST_REPO to "yourorg/yourrepo" to deploy.'
-fi
-
-if [ -n "${TEST_ORG}" ]; then
-  cat acceptance/testdata/org.runnerdeploy.yaml | envsubst | kubectl apply -f -
-
-  if [ -n "${TEST_ORG_REPO}" ]; then
-    cat acceptance/testdata/org.hra.yaml | envsubst | kubectl apply -f -
-  else
-    echo 'Skipped deploying organizational hra. Set TEST_ORG_REPO to "yourorg/yourrepo" to deploy.'
-  fi
-else
-  echo 'Skipped deploying organizational runnerdeployment. Set TEST_ORG to deploy.'
-fi

acceptance/deploy_runners.sh

@@ -0,0 +1,58 @@
+#!/usr/bin/env bash
+
+set -e
+
+OP=${OP:-apply}
+
+RUNNER_LABEL=${RUNNER_LABEL:-self-hosted}
+
+if [ -n "${TEST_REPO}" ]; then
+  if [ "${USE_RUNNERSET}" != "false" ]; then
+    cat acceptance/testdata/runnerset.envsubst.yaml | TEST_ENTERPRISE= TEST_ORG= RUNNER_MIN_REPLICAS=${REPO_RUNNER_MIN_REPLICAS} NAME=repo-runnerset envsubst | kubectl ${OP} -f -
+  else
+    echo "Running ${OP} runnerdeployment and hra. Set USE_RUNNERSET if you want to deploy runnerset instead."
+    cat acceptance/testdata/runnerdeploy.envsubst.yaml | TEST_ENTERPRISE= TEST_ORG= RUNNER_MIN_REPLICAS=${REPO_RUNNER_MIN_REPLICAS} NAME=repo-runnerdeploy envsubst | kubectl ${OP} -f -
+  fi
+else
+  echo "Skipped ${OP} for runnerdeployment and hra. Set TEST_REPO to "yourorg/yourrepo" to deploy."
+fi
+
+if [ -n "${TEST_ORG}" ]; then
+  if [ "${USE_RUNNERSET}" != "false" ]; then
+    cat acceptance/testdata/runnerset.envsubst.yaml | TEST_ENTERPRISE= TEST_REPO= RUNNER_MIN_REPLICAS=${ORG_RUNNER_MIN_REPLICAS} NAME=org-runnerset envsubst | kubectl ${OP} -f -
+  else
+    cat acceptance/testdata/runnerdeploy.envsubst.yaml | TEST_ENTERPRISE= TEST_REPO= RUNNER_MIN_REPLICAS=${ORG_RUNNER_MIN_REPLICAS} NAME=org-runnerdeploy envsubst | kubectl ${OP} -f -
+  fi
+
+  if [ -n "${TEST_ORG_GROUP}" ]; then
+    if [ "${USE_RUNNERSET}" != "false" ]; then
+      cat acceptance/testdata/runnerset.envsubst.yaml | TEST_ENTERPRISE= TEST_REPO= RUNNER_MIN_REPLICAS=${ORG_RUNNER_MIN_REPLICAS} TEST_GROUP=${TEST_ORG_GROUP} NAME=orggroup-runnerset envsubst | kubectl ${OP} -f -
+    else
+      cat acceptance/testdata/runnerdeploy.envsubst.yaml | TEST_ENTERPRISE= TEST_REPO= RUNNER_MIN_REPLICAS=${ORG_RUNNER_MIN_REPLICAS} TEST_GROUP=${TEST_ORG_GROUP} NAME=orggroup-runnerdeploy envsubst | kubectl ${OP} -f -
+    fi
+  else
+    echo "Skipped ${OP} on enterprise runnerdeployment. Set TEST_ORG_GROUP to ${OP}."
+  fi
+else
+  echo "Skipped ${OP} on organizational runnerdeployment. Set TEST_ORG to ${OP}."
+fi
+
+if [ -n "${TEST_ENTERPRISE}" ]; then
+  if [ "${USE_RUNNERSET}" != "false" ]; then
+    cat acceptance/testdata/runnerset.envsubst.yaml | TEST_ORG= TEST_REPO= RUNNER_MIN_REPLICAS=${ENTERPRISE_RUNNER_MIN_REPLICAS} NAME=enterprise-runnerset envsubst | kubectl ${OP} -f -
+  else
+    cat acceptance/testdata/runnerdeploy.envsubst.yaml | TEST_ORG= TEST_REPO= RUNNER_MIN_REPLICAS=${ENTERPRISE_RUNNER_MIN_REPLICAS} NAME=enterprise-runnerdeploy envsubst | kubectl ${OP} -f -
+  fi
+
+  if [ -n "${TEST_ENTERPRISE_GROUP}" ]; then
+    if [ "${USE_RUNNERSET}" != "false" ]; then
+      cat acceptance/testdata/runnerset.envsubst.yaml | TEST_ORG= TEST_REPO= RUNNER_MIN_REPLICAS=${ENTERPRISE_RUNNER_MIN_REPLICAS} TEST_GROUP=${TEST_ENTERPRISE_GROUP} NAME=enterprisegroup-runnerset envsubst | kubectl ${OP} -f -
+    else
+      cat acceptance/testdata/runnerdeploy.envsubst.yaml | TEST_ORG= TEST_REPO= RUNNER_MIN_REPLICAS=${ENTERPRISE_RUNNER_MIN_REPLICAS} TEST_GROUP=${TEST_ENTERPRISE_GROUP} NAME=enterprisegroup-runnerdeploy envsubst | kubectl ${OP} -f -
+    fi
+  else
+    echo "Skipped ${OP} on enterprise runnerdeployment. Set TEST_ENTERPRISE_GROUP to ${OP}."
+  fi
+else
+  echo "Skipped ${OP} on enterprise runnerdeployment. Set TEST_ENTERPRISE to ${OP}."
+fi

acceptance/testdata/org.hra.yaml

@@ -1,36 +0,0 @@
-apiVersion: actions.summerwind.dev/v1alpha1
-kind: HorizontalRunnerAutoscaler
-metadata:
-  name: org
-spec:
-  scaleTargetRef:
-    name: org-runnerdeploy
-  scaleUpTriggers:
-  - githubEvent:
-      checkRun:
-        types: ["created"]
-        status: "queued"
-    amount: 1
-    duration: "1m"
-  scheduledOverrides:
-  - startTime: "2021-05-11T16:05:00+09:00"
-    endTime: "2021-05-11T16:40:00+09:00"
-    minReplicas: 2
-  - startTime: "2021-05-01T00:00:00+09:00"
-    endTime: "2021-05-03T00:00:00+09:00"
-    recurrenceRule:
-      frequency: Weekly
-      untilTime: "2022-05-01T00:00:00+09:00"
-    minReplicas: 0
-  minReplicas: 0
-  maxReplicas: 5
-  # Used to test that HRA is working for org runners
-  metrics:
-  - type: PercentageRunnersBusy
-    scaleUpThreshold: '0.75'
-    scaleDownThreshold: '0.3'
-    scaleUpFactor: '2'
-    scaleDownFactor: '0.5'
-  - type: TotalNumberOfQueuedAndInProgressWorkflowRuns
-    repositoryNames:
-    - ${TEST_ORG_REPO}

acceptance/testdata/repo.hra.yaml

@@ -1,25 +0,0 @@
-apiVersion: actions.summerwind.dev/v1alpha1
-kind: HorizontalRunnerAutoscaler
-metadata:
-  name: actions-runner-aos-autoscaler
-spec:
-  scaleTargetRef:
-    name: example-runnerdeploy
-  scaleUpTriggers:
-  - githubEvent:
-      checkRun:
-        types: ["created"]
-        status: "queued"
-    amount: 1
-    duration: "1m"
-  minReplicas: 0
-  maxReplicas: 5
-  metrics:
-  - type: PercentageRunnersBusy
-    scaleUpThreshold: '0.75'
-    scaleDownThreshold: '0.3'
-    scaleUpFactor: '2'
-    scaleDownFactor: '0.5'
-  - type: TotalNumberOfQueuedAndInProgressWorkflowRuns
-    repositoryNames:
-    - ${TEST_REPO}

acceptance/testdata/repo.runnerdeploy.yaml

@@ -1,37 +0,0 @@
-apiVersion: actions.summerwind.dev/v1alpha1
-kind: RunnerDeployment
-metadata:
-  name: example-runnerdeploy
-spec:
-#  replicas: 1
-  template:
-    spec:
-      repository: ${TEST_REPO}
-
-      #
-      # Custom runner image
-      #
-      image: ${RUNNER_NAME}:${RUNNER_TAG}
-      imagePullPolicy: IfNotPresent
-
-      #
-      # dockerd within runner container
-      #
-      ## Replace `mumoshu/actions-runner-dind:dev` with your dind image
-      #dockerdWithinRunnerContainer: true
-      #image: mumoshu/actions-runner-dind:dev
-
-      #
-      # Set the MTU used by dockerd-managed network interfaces (including docker-build-ubuntu)
-      #
-      #dockerMTU: 1450
-
-      #Runner group
-      # labels:
-      # - "mylabel 1"
-      # - "mylabel 2"
-
-      #
-      # Non-standard working directory
-      #
-      # workDir: "/"

acceptance/testdata/repo.runnerset.hra.yaml

@@ -1,29 +0,0 @@
-apiVersion: actions.summerwind.dev/v1alpha1
-kind: HorizontalRunnerAutoscaler
-metadata:
-  name: example-runnerset
-spec:
-  scaleTargetRef:
-    kind: RunnerSet
-    name: example-runnerset
-  scaleUpTriggers:
-  - githubEvent:
-      checkRun:
-        types: ["created"]
-        status: "queued"
-    amount: 1
-    duration: "1m"
-  # RunnerSet doesn't support scale from/to zero yet
-  minReplicas: 1
-  maxReplicas: 5
-  # This should be less than 600(seconds, the default) for faster testing
-  scaleDownDelaySecondsAfterScaleOut: 60
-  metrics:
-  - type: PercentageRunnersBusy
-    scaleUpThreshold: '0.75'
-    scaleDownThreshold: '0.3'
-    scaleUpFactor: '2'
-    scaleDownFactor: '0.5'
-  - type: TotalNumberOfQueuedAndInProgressWorkflowRuns
-    repositoryNames:
-    - ${TEST_REPO}

acceptance/testdata/repo.runnerset.yaml

@@ -1,59 +0,0 @@
-apiVersion: actions.summerwind.dev/v1alpha1
-kind: RunnerSet
-metadata:
-  name: example-runnerset
-spec:
-  # MANDATORY because it is based on StatefulSet: Results in a below error when omitted:
-  #   missing required field "selector" in dev.summerwind.actions.v1alpha1.RunnerSet.spec
-  selector:
-    matchLabels:
-      app: example-runnerset
-
-  # MANDATORY because it is based on StatefulSet: Results in a below error when omitted:
-  # missing required field "serviceName" in dev.summerwind.actions.v1alpha1.RunnerSet.spec]
-  serviceName: example-runnerset
-
-  #replicas: 1
-
-  # From my limited testing, `ephemeral: true` is more reliable.
-  # Seomtimes, updating already deployed runners from `ephemeral: false` to `ephemeral: true` seems to
-  # result in queued jobs hanging forever.
-  ephemeral: ${TEST_EPHEMERAL}
-
-  repository: ${TEST_REPO}
-  #
-  # Custom runner image
-  #
-  image: ${RUNNER_NAME}:${RUNNER_TAG}
-  #
-  # dockerd within runner container
-  #
-  ## Replace `mumoshu/actions-runner-dind:dev` with your dind image
-  #dockerdWithinRunnerContainer: true
-  #
-  # Set the MTU used by dockerd-managed network interfaces (including docker-build-ubuntu)
-  #
-  #dockerMTU: 1450
-  #Runner group
-  # labels:
-  # - "mylabel 1"
-  # - "mylabel 2"
-  labels:
-  - "${RUNNER_LABEL}"
-  #
-  # Non-standard working directory
-  #
-  # workDir: "/"
-  template:
-    metadata:
-      labels:
-        app: example-runnerset
-    spec:
-      containers:
-      - name: runner
-        imagePullPolicy: IfNotPresent
-        env:
-        - name: RUNNER_FEATURE_FLAG_EPHEMERAL
-          value: "${RUNNER_FEATURE_FLAG_EPHEMERAL}"
-      #- name: docker
-      #  #image: mumoshu/actions-runner-dind:dev

acceptance/testdata/runnerdeploy.envsubst.yaml

@@ -1,12 +1,15 @@
 apiVersion: actions.summerwind.dev/v1alpha1
 kind: RunnerDeployment
 metadata:
-  name: org-runnerdeploy
+  name: ${NAME}
 spec:
 #  replicas: 1
   template:
     spec:
+      enterprise: ${TEST_ENTERPRISE}
+      group: ${TEST_GROUP}
       organization: ${TEST_ORG}
+      repository: ${TEST_REPO}
 
       #
       # Custom runner image
@@ -14,12 +17,15 @@ spec:
       image: ${RUNNER_NAME}:${RUNNER_TAG}
       imagePullPolicy: IfNotPresent
 
+      ephemeral: ${TEST_EPHEMERAL}
+
       #
       # dockerd within runner container
       #
       ## Replace `mumoshu/actions-runner-dind:dev` with your dind image
       #dockerdWithinRunnerContainer: true
       #image: mumoshu/actions-runner-dind:dev
+      dockerdWithinRunnerContainer: ${RUNNER_DOCKERD_WITHIN_RUNNER_CONTAINER}
 
       #
       # Set the MTU used by dockerd-managed network interfaces (including docker-build-ubuntu)
@@ -30,8 +36,26 @@ spec:
       # labels:
       # - "mylabel 1"
       # - "mylabel 2"
+      labels:
+      - "${RUNNER_LABEL}"
 
       #
       # Non-standard working directory
       #
       # workDir: "/"
+---
+apiVersion: actions.summerwind.dev/v1alpha1
+kind: HorizontalRunnerAutoscaler
+metadata:
+  name: ${NAME}
+spec:
+  scaleTargetRef:
+    name: ${NAME}
+  scaleUpTriggers:
+  - githubEvent:
+      workflowJob: {}
+    amount: 1
+    duration: "10m"
+  minReplicas: ${RUNNER_MIN_REPLICAS}
+  maxReplicas: 10
+  scaleDownDelaySecondsAfterScaleOut: ${RUNNER_SCALE_DOWN_DELAY_SECONDS_AFTER_SCALE_OUT}

acceptance/testdata/runnerset.envsubst.yaml

@@ -0,0 +1,263 @@
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: ${NAME}-runner-work-dir
+  labels:
+    content: ${NAME}-runner-work-dir
+provisioner: rancher.io/local-path
+reclaimPolicy: Delete
+volumeBindingMode: WaitForFirstConsumer
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: ${NAME}
+# In kind environments, the provider writes:
+#   /var/lib/docker/volumes/KIND_NODE_CONTAINER_VOL_ID/_data/local-path-provisioner/PV_NAME
+# It can be hundreds of gigabytes depending on what you cache in the test workflow. Beware to not encounter `no space left on device` errors!
+# If you did encounter no space errorrs try:
+#   docker system prune
+#   docker buildx prune #=> frees up /var/lib/docker/volumes/buildx_buildkit_container-builder0_state
+#   sudo rm -rf /var/lib/docker/volumes/KIND_NODE_CONTAINER_VOL_ID/_data/local-path-provisioner #=> frees up local-path-provisioner's data
+provisioner: rancher.io/local-path
+reclaimPolicy: Retain
+volumeBindingMode: WaitForFirstConsumer
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: ${NAME}-var-lib-docker
+  labels:
+    content: ${NAME}-var-lib-docker
+provisioner: rancher.io/local-path
+reclaimPolicy: Retain
+volumeBindingMode: WaitForFirstConsumer
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: ${NAME}-cache
+  labels:
+    content: ${NAME}-cache
+provisioner: rancher.io/local-path
+reclaimPolicy: Retain
+volumeBindingMode: WaitForFirstConsumer
+---
+apiVersion: storage.k8s.io/v1
+kind: StorageClass
+metadata:
+  name: ${NAME}-runner-tool-cache
+  labels:
+    content: ${NAME}-runner-tool-cache
+provisioner: rancher.io/local-path
+reclaimPolicy: Retain
+volumeBindingMode: WaitForFirstConsumer
+---
+apiVersion: actions.summerwind.dev/v1alpha1
+kind: RunnerSet
+metadata:
+  name: ${NAME}
+spec:
+  # MANDATORY because it is based on StatefulSet: Results in a below error when omitted:
+  #   missing required field "selector" in dev.summerwind.actions.v1alpha1.RunnerSet.spec
+  selector:
+    matchLabels:
+      app: ${NAME}
+
+  # MANDATORY because it is based on StatefulSet: Results in a below error when omitted:
+  # missing required field "serviceName" in dev.summerwind.actions.v1alpha1.RunnerSet.spec]
+  serviceName: ${NAME}
+
+  #replicas: 1
+
+  # From my limited testing, `ephemeral: true` is more reliable.
+  # Seomtimes, updating already deployed runners from `ephemeral: false` to `ephemeral: true` seems to
+  # result in queued jobs hanging forever.
+  ephemeral: ${TEST_EPHEMERAL}
+
+  enterprise: ${TEST_ENTERPRISE}
+  group: ${TEST_GROUP}
+  organization: ${TEST_ORG}
+  repository: ${TEST_REPO}
+
+  #
+  # Custom runner image
+  #
+  image: ${RUNNER_NAME}:${RUNNER_TAG}
+
+  #
+  # dockerd within runner container
+  #
+  ## Replace `mumoshu/actions-runner-dind:dev` with your dind image
+  #dockerdWithinRunnerContainer: true
+  dockerdWithinRunnerContainer: ${RUNNER_DOCKERD_WITHIN_RUNNER_CONTAINER}
+
+  #
+  # Set the MTU used by dockerd-managed network interfaces (including docker-build-ubuntu)
+  #
+  #dockerMTU: 1450
+  #Runner group
+  # labels:
+  # - "mylabel 1"
+  # - "mylabel 2"
+  labels:
+  - "${RUNNER_LABEL}"
+  #
+  # Non-standard working directory
+  #
+  # workDir: "/"
+  template:
+    metadata:
+      labels:
+        app: ${NAME}
+    spec:
+      containers:
+      - name: runner
+        imagePullPolicy: IfNotPresent
+        env:
+        - name: RUNNER_FEATURE_FLAG_EPHEMERAL
+          value: "${RUNNER_FEATURE_FLAG_EPHEMERAL}"
+        - name: GOMODCACHE
+          value: "/home/runner/.cache/go-mod"
+        # PV-backed runner work dir
+        volumeMounts:
+        # Comment out the ephemeral work volume if you're going to test the kubernetes container mode
+        # The volume and mount with the same names will be created by workVolumeClaimTemplate and the kubernetes container mode support.
+        # - name: work
+        #   mountPath: /runner/_work
+        # Cache docker image layers, in case dockerdWithinRunnerContainer=true
+        - name: var-lib-docker
+          mountPath: /var/lib/docker
+        # Cache go modules and builds
+        # - name: gocache
+        #   # Run `goenv | grep GOCACHE` to verify the path is correct for your env
+        #   mountPath: /home/runner/.cache/go-build
+        # - name: gomodcache
+        #   # Run `goenv | grep GOMODCACHE` to verify the path is correct for your env
+        #   # mountPath: /home/runner/go/pkg/mod
+        - name: cache
+          # go: could not create module cache: stat /home/runner/.cache/go-mod: permission denied
+          mountPath: "/home/runner/.cache"
+        - name: runner-tool-cache
+          # This corresponds to our runner image's default setting of RUNNER_TOOL_CACHE=/opt/hostedtoolcache.
+          #
+          # In case you customize the envvar in both runner and docker containers of the runner pod spec,
+          # You'd need to change this mountPath accordingly.
+          #
+          # The tool cache directory is defined in actions/toolkit's tool-cache module:
+          # https://github.com/actions/toolkit/blob/2f164000dcd42fb08287824a3bc3030dbed33687/packages/tool-cache/src/tool-cache.ts#L621-L638
+          #
+          # Many setup-* actions like setup-go utilizes the tool-cache module to download and cache installed binaries:
+          # https://github.com/actions/setup-go/blob/56a61c9834b4a4950dbbf4740af0b8a98c73b768/src/installer.ts#L144
+          mountPath: "/opt/hostedtoolcache"
+      # Valid only when dockerdWithinRunnerContainer=false
+      - name: docker
+        # PV-backed runner work dir
+        volumeMounts:
+        - name: work
+          mountPath: /runner/_work
+        # Cache docker image layers, in case dockerdWithinRunnerContainer=false
+        - name: var-lib-docker
+          mountPath: /var/lib/docker
+        # image: mumoshu/actions-runner-dind:dev
+
+        # For buildx cache
+        - name: cache
+          mountPath: "/home/runner/.cache"
+        # Comment out the ephemeral work volume if you're going to test the kubernetes container mode
+      # volumes:
+      # - name: work
+      #   ephemeral:
+      #     volumeClaimTemplate:
+      #       spec:
+      #         accessModes:
+      #         - ReadWriteOnce
+      #         storageClassName: "${NAME}-runner-work-dir"
+      #         resources:
+      #           requests:
+      #             storage: 10Gi
+  volumeClaimTemplates:
+  - metadata:
+      name: vol1
+    spec:
+      accessModes:
+      - ReadWriteOnce
+      resources:
+        requests:
+          storage: 10Mi
+      storageClassName: ${NAME}
+      ## Dunno which provider supports auto-provisioning with selector.
+      ## At least the rancher local path provider stopped with:
+      ##  waiting for a volume to be created, either by external provisioner "rancher.io/local-path" or manually created by system administrator
+      # selector:
+      #    matchLabels:
+      #      runnerset-volume-id: ${NAME}-vol1
+  - metadata:
+      name: vol2
+    spec:
+      accessModes:
+      - ReadWriteOnce
+      resources:
+        requests:
+          storage: 10Mi
+      storageClassName: ${NAME}
+      # selector:
+      #    matchLabels:
+      #      runnerset-volume-id: ${NAME}-vol2
+  - metadata:
+      name: var-lib-docker
+    spec:
+      accessModes:
+      - ReadWriteOnce
+      resources:
+        requests:
+          storage: 10Mi
+      storageClassName: ${NAME}-var-lib-docker
+  - metadata:
+      name: cache
+    spec:
+      accessModes:
+      - ReadWriteOnce
+      resources:
+        requests:
+          storage: 10Mi
+      storageClassName: ${NAME}-cache
+  - metadata:
+      name: runner-tool-cache
+      # It turns out labels doesn't distinguish PVs across PVCs and the
+      # end result is PVs are reused by wrong PVCs.
+      # The correct way seems to be to differentiate storage class per pvc template.
+      # labels:
+      #   id: runner-tool-cache
+    spec:
+      accessModes:
+      - ReadWriteOnce
+      resources:
+        requests:
+          storage: 10Mi
+      storageClassName: ${NAME}-runner-tool-cache
+---
+apiVersion: actions.summerwind.dev/v1alpha1
+kind: HorizontalRunnerAutoscaler
+metadata:
+  name: ${NAME}
+spec:
+  scaleTargetRef:
+    kind: RunnerSet
+    name: ${NAME}
+  scaleUpTriggers:
+  - githubEvent:
+      workflowJob: {}
+    amount: 1
+    duration: "10m"
+  minReplicas: ${RUNNER_MIN_REPLICAS}
+  maxReplicas: 10
+  scaleDownDelaySecondsAfterScaleOut: ${RUNNER_SCALE_DOWN_DELAY_SECONDS_AFTER_SCALE_OUT}
+  # Comment out the whole metrics if you'd like to solely test webhook-based scaling
+  metrics:
+  - type: PercentageRunnersBusy
+    scaleUpThreshold: '0.75'
+    scaleDownThreshold: '0.25'
+    scaleUpFactor: '2'
+    scaleDownFactor: '0.5'

acceptance/values.yaml

@@ -1,12 +1,15 @@
 # Set actions-runner-controller settings for testing
-githubAPICacheDuration: 10s
+logLevel: "-4"
 githubWebhookServer:
+  logLevel: "-4"
   enabled: true
   labels: {}
   replicaCount: 1
   syncPeriod: 10m
+  useRunnerGroupsVisibility: true
   secret:
-    create: true
+    enabled: true
+    # create: true
     name: "github-webhook-server"
     ### GitHub Webhook Configuration
     #github_webhook_secret_token: ""

api/v1alpha1/horizontalrunnerautoscaler_types.go

@@ -29,7 +29,7 @@ type HorizontalRunnerAutoscalerSpec struct {
 	// +optional
 	MinReplicas *int `json:"minReplicas,omitempty"`
 
-	// MinReplicas is the maximum number of replicas the deployment is allowed to scale
+	// MaxReplicas is the maximum number of replicas the deployment is allowed to scale
 	// +optional
 	MaxReplicas *int `json:"maxReplicas,omitempty"`
 
@@ -72,10 +72,12 @@ type GitHubEventScaleUpTriggerSpec struct {
 	CheckRun    *CheckRunSpec    `json:"checkRun,omitempty"`
 	PullRequest *PullRequestSpec `json:"pullRequest,omitempty"`
 	Push        *PushSpec        `json:"push,omitempty"`
+	WorkflowJob *WorkflowJobSpec `json:"workflowJob,omitempty"`
 }
 
 // https://docs.github.com/en/actions/reference/events-that-trigger-workflows#check_run
 type CheckRunSpec struct {
+	// One of: created, rerequested, or completed
 	Types  []string `json:"types,omitempty"`
 	Status string   `json:"status,omitempty"`
 
@@ -90,6 +92,10 @@ type CheckRunSpec struct {
 	Repositories []string `json:"repositories,omitempty"`
 }
 
+// https://docs.github.com/en/developers/webhooks-and-events/webhooks/webhook-events-and-payloads#workflow_job
+type WorkflowJobSpec struct {
+}
+
 // https://docs.github.com/en/actions/reference/events-that-trigger-workflows#pull_request
 type PullRequestSpec struct {
 	Types    []string `json:"types,omitempty"`
@@ -107,6 +113,9 @@ type CapacityReservation struct {
 	Name           string      `json:"name,omitempty"`
 	ExpirationTime metav1.Time `json:"expirationTime,omitempty"`
 	Replicas       int         `json:"replicas,omitempty"`
+
+	// +optional
+	EffectiveTime metav1.Time `json:"effectiveTime,omitempty"`
 }
 
 type ScaleTargetRef struct {

api/v1alpha1/runner_types.go

@@ -18,8 +18,10 @@ package v1alpha1
 
 import (
 	"errors"
+	"fmt"
 
 	"k8s.io/apimachinery/pkg/api/resource"
+	"k8s.io/apimachinery/pkg/util/validation/field"
 
 	corev1 "k8s.io/api/core/v1"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
@@ -71,6 +73,9 @@ type RunnerConfig struct {
 	VolumeSizeLimit *resource.Quantity `json:"volumeSizeLimit,omitempty"`
 	// +optional
 	VolumeStorageMedium *string `json:"volumeStorageMedium,omitempty"`
+
+	// +optional
+	ContainerMode string `json:"containerMode,omitempty"`
 }
 
 // RunnerPodSpec defines the desired pod spec fields of the runner pod
@@ -81,6 +86,9 @@ type RunnerPodSpec struct {
 	// +optional
 	DockerVolumeMounts []corev1.VolumeMount `json:"dockerVolumeMounts,omitempty"`
 
+	// +optional
+	DockerEnv []corev1.EnvVar `json:"dockerEnv,omitempty"`
+
 	// +optional
 	Containers []corev1.Container `json:"containers,omitempty"`
 
@@ -132,6 +140,9 @@ type RunnerPodSpec struct {
 	// +optional
 	Tolerations []corev1.Toleration `json:"tolerations,omitempty"`
 
+	// +optional
+	PriorityClassName string `json:"priorityClassName,omitempty"`
+
 	// +optional
 	TerminationGracePeriodSeconds *int64 `json:"terminationGracePeriodSeconds,omitempty"`
 
@@ -141,17 +152,47 @@ type RunnerPodSpec struct {
 	// +optional
 	HostAliases []corev1.HostAlias `json:"hostAliases,omitempty"`
 
+	// +optional
+	TopologySpreadConstraints []corev1.TopologySpreadConstraint `json:"topologySpreadConstraints,omitempty"`
+
 	// RuntimeClassName is the container runtime configuration that containers should run under.
 	// More info: https://kubernetes.io/docs/concepts/containers/runtime-class
 	// +optional
 	RuntimeClassName *string `json:"runtimeClassName,omitempty"`
 
 	// +optional
-	DnsConfig []corev1.PodDNSConfig `json:"dnsConfig,omitempty"`
+	DnsConfig *corev1.PodDNSConfig `json:"dnsConfig,omitempty"`
+
+	// +optional
+	WorkVolumeClaimTemplate *WorkVolumeClaimTemplate `json:"workVolumeClaimTemplate,omitempty"`
+}
+
+func (rs *RunnerSpec) Validate(rootPath *field.Path) field.ErrorList {
+	var (
+		errList field.ErrorList
+		err     error
+	)
+
+	err = rs.validateRepository()
+	if err != nil {
+		errList = append(errList, field.Invalid(rootPath.Child("repository"), rs.Repository, err.Error()))
+	}
+
+	err = rs.validateWorkVolumeClaimTemplate()
+	if err != nil {
+		errList = append(errList, field.Invalid(rootPath.Child("workVolumeClaimTemplate"), rs.WorkVolumeClaimTemplate, err.Error()))
+	}
+
+	err = rs.validateIsServiceAccountNameSet()
+	if err != nil {
+		errList = append(errList, field.Invalid(rootPath.Child("serviceAccountName"), rs.ServiceAccountName, err.Error()))
+	}
+
+	return errList
 }
 
 // ValidateRepository validates repository field.
-func (rs *RunnerSpec) ValidateRepository() error {
+func (rs *RunnerSpec) validateRepository() error {
 	// Enterprise, Organization and repository are both exclusive.
 	foundCount := 0
 	if len(rs.Organization) > 0 {
@@ -173,8 +214,34 @@ func (rs *RunnerSpec) ValidateRepository() error {
 	return nil
 }
 
+func (rs *RunnerSpec) validateWorkVolumeClaimTemplate() error {
+	if rs.ContainerMode != "kubernetes" {
+		return nil
+	}
+
+	if rs.WorkVolumeClaimTemplate == nil {
+		return errors.New("Spec.ContainerMode: kubernetes must have workVolumeClaimTemplate field specified")
+	}
+
+	return rs.WorkVolumeClaimTemplate.validate()
+}
+
+func (rs *RunnerSpec) validateIsServiceAccountNameSet() error {
+	if rs.ContainerMode != "kubernetes" {
+		return nil
+	}
+
+	if rs.ServiceAccountName == "" {
+		return errors.New("service account name is required if container mode is kubernetes")
+	}
+	return nil
+}
+
 // RunnerStatus defines the observed state of Runner
 type RunnerStatus struct {
+	// Turns true only if the runner pod is ready.
+	// +optional
+	Ready bool `json:"ready"`
 	// +optional
 	Registration RunnerStatusRegistration `json:"registration"`
 	// +optional
@@ -198,6 +265,51 @@ type RunnerStatusRegistration struct {
 	ExpiresAt    metav1.Time `json:"expiresAt"`
 }
 
+type WorkVolumeClaimTemplate struct {
+	StorageClassName string                              `json:"storageClassName"`
+	AccessModes      []corev1.PersistentVolumeAccessMode `json:"accessModes"`
+	Resources        corev1.ResourceRequirements         `json:"resources"`
+}
+
+func (w *WorkVolumeClaimTemplate) validate() error {
+	if w.AccessModes == nil || len(w.AccessModes) == 0 {
+		return errors.New("Access mode should have at least one mode specified")
+	}
+
+	for _, accessMode := range w.AccessModes {
+		switch accessMode {
+		case corev1.ReadWriteOnce, corev1.ReadWriteMany:
+		default:
+			return fmt.Errorf("Access mode %v is not supported", accessMode)
+		}
+	}
+	return nil
+}
+
+func (w *WorkVolumeClaimTemplate) V1Volume() corev1.Volume {
+	return corev1.Volume{
+		Name: "work",
+		VolumeSource: corev1.VolumeSource{
+			Ephemeral: &corev1.EphemeralVolumeSource{
+				VolumeClaimTemplate: &corev1.PersistentVolumeClaimTemplate{
+					Spec: corev1.PersistentVolumeClaimSpec{
+						AccessModes:      w.AccessModes,
+						StorageClassName: &w.StorageClassName,
+						Resources:        w.Resources,
+					},
+				},
+			},
+		},
+	}
+}
+
+func (w *WorkVolumeClaimTemplate) V1VolumeMount(mountPath string) corev1.VolumeMount {
+	return corev1.VolumeMount{
+		MountPath: mountPath,
+		Name:      "work",
+	}
+}
+
 // +kubebuilder:object:root=true
 // +kubebuilder:subresource:status
 // +kubebuilder:printcolumn:JSONPath=".spec.enterprise",name=Enterprise,type=string

api/v1alpha1/runner_webhook.go

@@ -66,15 +66,7 @@ func (r *Runner) ValidateDelete() error {
 
 // Validate validates resource spec.
 func (r *Runner) Validate() error {
-	var (
-		errList field.ErrorList
-		err     error
-	)
-
-	err = r.Spec.ValidateRepository()
-	if err != nil {
-		errList = append(errList, field.Invalid(field.NewPath("spec", "repository"), r.Spec.Repository, err.Error()))
-	}
+	errList := r.Spec.Validate(field.NewPath("spec"))
 
 	if len(errList) > 0 {
 		return apierrors.NewInvalid(r.GroupVersionKind().GroupKind(), r.Name, errList)

api/v1alpha1/runnerdeployment_types.go

@@ -31,6 +31,14 @@ type RunnerDeploymentSpec struct {
 	// +nullable
 	Replicas *int `json:"replicas,omitempty"`
 
+	// EffectiveTime is the time the upstream controller requested to sync Replicas.
+	// It is usually populated by the webhook-based autoscaler via HRA.
+	// The value is inherited to RunnerRepicaSet(s) and used to prevent ephemeral runners from unnecessarily recreated.
+	//
+	// +optional
+	// +nullable
+	EffectiveTime *metav1.Time `json:"effectiveTime"`
+
 	// +optional
 	// +nullable
 	Selector *metav1.LabelSelector `json:"selector"`

api/v1alpha1/runnerdeployment_webhook.go

@@ -26,7 +26,7 @@ import (
 )
 
 // log is for logging in this package.
-var runenrDeploymentLog = logf.Log.WithName("runnerdeployment-resource")
+var runnerDeploymentLog = logf.Log.WithName("runnerdeployment-resource")
 
 func (r *RunnerDeployment) SetupWebhookWithManager(mgr ctrl.Manager) error {
 	return ctrl.NewWebhookManagedBy(mgr).
@@ -49,13 +49,13 @@ var _ webhook.Validator = &RunnerDeployment{}
 
 // ValidateCreate implements webhook.Validator so a webhook will be registered for the type
 func (r *RunnerDeployment) ValidateCreate() error {
-	runenrDeploymentLog.Info("validate resource to be created", "name", r.Name)
+	runnerDeploymentLog.Info("validate resource to be created", "name", r.Name)
 	return r.Validate()
 }
 
 // ValidateUpdate implements webhook.Validator so a webhook will be registered for the type
 func (r *RunnerDeployment) ValidateUpdate(old runtime.Object) error {
-	runenrDeploymentLog.Info("validate resource to be updated", "name", r.Name)
+	runnerDeploymentLog.Info("validate resource to be updated", "name", r.Name)
 	return r.Validate()
 }
 
@@ -66,15 +66,7 @@ func (r *RunnerDeployment) ValidateDelete() error {
 
 // Validate validates resource spec.
 func (r *RunnerDeployment) Validate() error {
-	var (
-		errList field.ErrorList
-		err     error
-	)
-
-	err = r.Spec.Template.Spec.ValidateRepository()
-	if err != nil {
-		errList = append(errList, field.Invalid(field.NewPath("spec", "template", "spec", "repository"), r.Spec.Template.Spec.Repository, err.Error()))
-	}
+	errList := r.Spec.Template.Spec.Validate(field.NewPath("spec", "template", "spec"))
 
 	if len(errList) > 0 {
 		return apierrors.NewInvalid(r.GroupVersionKind().GroupKind(), r.Name, errList)

api/v1alpha1/runnerreplicaset_types.go

@@ -26,6 +26,15 @@ type RunnerReplicaSetSpec struct {
 	// +nullable
 	Replicas *int `json:"replicas,omitempty"`
 
+	// EffectiveTime is the time the upstream controller requested to sync Replicas.
+	// It is usually populated by the webhook-based autoscaler via HRA and RunnerDeployment.
+	// The value is used to prevent runnerreplicaset controller from unnecessarily recreating ephemeral runners
+	// based on potentially outdated Replicas value.
+	//
+	// +optional
+	// +nullable
+	EffectiveTime *metav1.Time `json:"effectiveTime"`
+
 	// +optional
 	// +nullable
 	Selector *metav1.LabelSelector `json:"selector"`

api/v1alpha1/runnerreplicaset_webhook.go

@@ -66,15 +66,7 @@ func (r *RunnerReplicaSet) ValidateDelete() error {
 
 // Validate validates resource spec.
 func (r *RunnerReplicaSet) Validate() error {
-	var (
-		errList field.ErrorList
-		err     error
-	)
-
-	err = r.Spec.Template.Spec.ValidateRepository()
-	if err != nil {
-		errList = append(errList, field.Invalid(field.NewPath("spec", "template", "spec", "repository"), r.Spec.Template.Spec.Repository, err.Error()))
-	}
+	errList := r.Spec.Template.Spec.Validate(field.NewPath("spec", "template", "spec"))
 
 	if len(errList) > 0 {
 		return apierrors.NewInvalid(r.GroupVersionKind().GroupKind(), r.Name, errList)

api/v1alpha1/runnerset_types.go

@@ -25,6 +25,20 @@ import (
 type RunnerSetSpec struct {
 	RunnerConfig `json:",inline"`
 
+	// EffectiveTime is the time the upstream controller requested to sync Replicas.
+	// It is usually populated by the webhook-based autoscaler via HRA.
+	// It is used to prevent ephemeral runners from unnecessarily recreated.
+	//
+	// +optional
+	// +nullable
+	EffectiveTime *metav1.Time `json:"effectiveTime,omitempty"`
+
+	// +optional
+	ServiceAccountName string `json:"serviceAccountName,omitempty"`
+
+	// +optional
+	WorkVolumeClaimTemplate *WorkVolumeClaimTemplate `json:"workVolumeClaimTemplate,omitempty"`
+
 	appsv1.StatefulSetSpec `json:",inline"`
 }
 

api/v1alpha1/zz_generated.deepcopy.go

@@ -47,6 +47,7 @@ func (in *CacheEntry) DeepCopy() *CacheEntry {
 func (in *CapacityReservation) DeepCopyInto(out *CapacityReservation) {
 	*out = *in
 	in.ExpirationTime.DeepCopyInto(&out.ExpirationTime)
+	in.EffectiveTime.DeepCopyInto(&out.EffectiveTime)
 }
 
 // DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new CapacityReservation.
@@ -107,6 +108,11 @@ func (in *GitHubEventScaleUpTriggerSpec) DeepCopyInto(out *GitHubEventScaleUpTri
 		*out = new(PushSpec)
 		**out = **in
 	}
+	if in.WorkflowJob != nil {
+		in, out := &in.WorkflowJob, &out.WorkflowJob
+		*out = new(WorkflowJobSpec)
+		**out = **in
+	}
 }
 
 // DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new GitHubEventScaleUpTriggerSpec.
@@ -498,6 +504,10 @@ func (in *RunnerDeploymentSpec) DeepCopyInto(out *RunnerDeploymentSpec) {
 		*out = new(int)
 		**out = **in
 	}
+	if in.EffectiveTime != nil {
+		in, out := &in.EffectiveTime, &out.EffectiveTime
+		*out = (*in).DeepCopy()
+	}
 	if in.Selector != nil {
 		in, out := &in.Selector, &out.Selector
 		*out = new(metav1.LabelSelector)
@@ -599,6 +609,13 @@ func (in *RunnerPodSpec) DeepCopyInto(out *RunnerPodSpec) {
 			(*in)[i].DeepCopyInto(&(*out)[i])
 		}
 	}
+	if in.DockerEnv != nil {
+		in, out := &in.DockerEnv, &out.DockerEnv
+		*out = make([]v1.EnvVar, len(*in))
+		for i := range *in {
+			(*in)[i].DeepCopyInto(&(*out)[i])
+		}
+	}
 	if in.Containers != nil {
 		in, out := &in.Containers, &out.Containers
 		*out = make([]v1.Container, len(*in))
@@ -707,6 +724,13 @@ func (in *RunnerPodSpec) DeepCopyInto(out *RunnerPodSpec) {
 			(*in)[i].DeepCopyInto(&(*out)[i])
 		}
 	}
+	if in.TopologySpreadConstraints != nil {
+		in, out := &in.TopologySpreadConstraints, &out.TopologySpreadConstraints
+		*out = make([]v1.TopologySpreadConstraint, len(*in))
+		for i := range *in {
+			(*in)[i].DeepCopyInto(&(*out)[i])
+		}
+	}
 	if in.RuntimeClassName != nil {
 		in, out := &in.RuntimeClassName, &out.RuntimeClassName
 		*out = new(string)
@@ -714,10 +738,13 @@ func (in *RunnerPodSpec) DeepCopyInto(out *RunnerPodSpec) {
 	}
 	if in.DnsConfig != nil {
 		in, out := &in.DnsConfig, &out.DnsConfig
-		*out = make([]v1.PodDNSConfig, len(*in))
-		for i := range *in {
-			(*in)[i].DeepCopyInto(&(*out)[i])
-		}
+		*out = new(v1.PodDNSConfig)
+		(*in).DeepCopyInto(*out)
+	}
+	if in.WorkVolumeClaimTemplate != nil {
+		in, out := &in.WorkVolumeClaimTemplate, &out.WorkVolumeClaimTemplate
+		*out = new(WorkVolumeClaimTemplate)
+		(*in).DeepCopyInto(*out)
 	}
 }
 
@@ -798,6 +825,10 @@ func (in *RunnerReplicaSetSpec) DeepCopyInto(out *RunnerReplicaSetSpec) {
 		*out = new(int)
 		**out = **in
 	}
+	if in.EffectiveTime != nil {
+		in, out := &in.EffectiveTime, &out.EffectiveTime
+		*out = (*in).DeepCopy()
+	}
 	if in.Selector != nil {
 		in, out := &in.Selector, &out.Selector
 		*out = new(metav1.LabelSelector)
@@ -909,6 +940,15 @@ func (in *RunnerSetList) DeepCopyObject() runtime.Object {
 func (in *RunnerSetSpec) DeepCopyInto(out *RunnerSetSpec) {
 	*out = *in
 	in.RunnerConfig.DeepCopyInto(&out.RunnerConfig)
+	if in.EffectiveTime != nil {
+		in, out := &in.EffectiveTime, &out.EffectiveTime
+		*out = (*in).DeepCopy()
+	}
+	if in.WorkVolumeClaimTemplate != nil {
+		in, out := &in.WorkVolumeClaimTemplate, &out.WorkVolumeClaimTemplate
+		*out = new(WorkVolumeClaimTemplate)
+		(*in).DeepCopyInto(*out)
+	}
 	in.StatefulSetSpec.DeepCopyInto(&out.StatefulSetSpec)
 }
 
@@ -1095,3 +1135,39 @@ func (in *ScheduledOverride) DeepCopy() *ScheduledOverride {
 	in.DeepCopyInto(out)
 	return out
 }
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkVolumeClaimTemplate) DeepCopyInto(out *WorkVolumeClaimTemplate) {
+	*out = *in
+	if in.AccessModes != nil {
+		in, out := &in.AccessModes, &out.AccessModes
+		*out = make([]v1.PersistentVolumeAccessMode, len(*in))
+		copy(*out, *in)
+	}
+	in.Resources.DeepCopyInto(&out.Resources)
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkVolumeClaimTemplate.
+func (in *WorkVolumeClaimTemplate) DeepCopy() *WorkVolumeClaimTemplate {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkVolumeClaimTemplate)
+	in.DeepCopyInto(out)
+	return out
+}
+
+// DeepCopyInto is an autogenerated deepcopy function, copying the receiver, writing into out. in must be non-nil.
+func (in *WorkflowJobSpec) DeepCopyInto(out *WorkflowJobSpec) {
+	*out = *in
+}
+
+// DeepCopy is an autogenerated deepcopy function, copying the receiver, creating a new WorkflowJobSpec.
+func (in *WorkflowJobSpec) DeepCopy() *WorkflowJobSpec {
+	if in == nil {
+		return nil
+	}
+	out := new(WorkflowJobSpec)
+	in.DeepCopyInto(out)
+	return out
+}

charts/.ci/ct-config.yaml

@@ -2,3 +2,4 @@
 lint-conf: charts/.ci/lint-config.yaml
 chart-repos:
   - jetstack=https://charts.jetstack.io
+check-version-increment: false # Disable checking that the chart version has been bumped

charts/actions-runner-controller/Chart.yaml

@@ -15,10 +15,10 @@ type: application
 # This is the chart version. This version number should be incremented each time you make changes
 # to the chart and its templates, including the app version.
 # Versions are expected to follow Semantic Versioning (https://semver.org/)
-version: 0.13.0
+version: 0.20.0
 
 # Used as the default manager tag value when no tag property is provided in the values.yaml
-appVersion: 0.20.0
+appVersion: 0.25.0
 
 home: https://github.com/actions-runner-controller/actions-runner-controller
 

charts/actions-runner-controller/README.md

@@ -4,69 +4,88 @@ All additional docs are kept in the `docs/` folder, this README is solely for do
 
 ## Values
 
-**_The values are documented as of HEAD, to review the configuration options for your chart version ensure you view this file at the relevent [tag](https://github.com/actions-runner-controller/actions-runner-controller/tags)_**
+**_The values are documented as of HEAD, to review the configuration options for your chart version ensure you view this file at the relevant [tag](https://github.com/actions-runner-controller/actions-runner-controller/tags)_**
 
-> _Default values are the defaults set in the charts values.yaml, some properties have default configurations in the code for when the property is omitted or invalid_
+> _Default values are the defaults set in the charts `values.yaml`, some properties have default configurations in the code for when the property is omitted or invalid_
 
 | Key                                                      | Description                                                                                                                | Default                                                              |
 |----------------------------------------------------------|----------------------------------------------------------------------------------------------------------------------------|----------------------------------------------------------------------|
 | `labels`                                                 | Set labels to apply to all resources in the chart                                                                          |                                                                      |
 | `replicaCount`                                           | Set the number of controller pods                                                                                          | 1                                                                    |
+| `webhookPort`                                            | Set the containerPort for the webhook Pod                                                                                  | 9443                                                                 |
 | `syncPeriod`                                             | Set the period in which the controler reconciles the desired runners count                                                 | 10m                                                                  |
 | `enableLeaderElection`                                   | Enable election configuration                                                                                              | true                                                                 |
 | `leaderElectionId`                                       | Set the election ID for the controller group                                                                               |                                                                      |
-| `githubAPICacheDuration`                                 | Set the cache period for API calls                                                                                         |                                                                      |
 | `githubEnterpriseServerURL`                              | Set the URL for a self-hosted GitHub Enterprise Server                                                                     |                                                                      |
+| `githubURL`                                              | Override GitHub URL to be used for GitHub API calls                                                                        |                                                                      |
+| `githubUploadURL`                                        | Override GitHub Upload URL to be used for GitHub API calls                                                                 |                                                                      |
+| `runnerGithubURL`                                        | Override GitHub URL to be used by runners during registration                                                              |                                                                      |
 | `logLevel`                                               | Set the log level of the controller container                                                                              |                                                                      |
+| `additionalVolumes`                                      | Set additional volumes to add to the manager container                                                                     |                                                                      |
+| `additionalVolumeMounts`                                 | Set additional volume mounts to add to the manager container                                                               |                                                                      |
 | `authSecret.create`                                      | Deploy the controller auth secret                                                                                          | false                                                                |
 | `authSecret.name`                                        | Set the name of the auth secret                                                                                            | controller-manager                                                   |
+| `authSecret.annotations`                                 | Set annotations for the auth Secret                                                                                        |                                                                      |
 | `authSecret.github_app_id`                               | The ID of your GitHub App. **This can't be set at the same time as `authSecret.github_token`**                             |                                                                      |
 | `authSecret.github_app_installation_id`                  | The ID of your GitHub App installation. **This can't be set at the same time as `authSecret.github_token`**                |                                                                      |
 | `authSecret.github_app_private_key`                      | The multiline string of your GitHub App's private key. **This can't be set at the same time as `authSecret.github_token`** |                                                                      |
 | `authSecret.github_token`                                | Your chosen GitHub PAT token. **This can't be set at the same time as the `authSecret.github_app_*`**                      |                                                                      |
+| `authSecret.github_basicauth_username`                     | Username for GitHub basic auth to use instead of PAT or GitHub APP in case it's running behind a proxy API                 |                                                                      |
+| `authSecret.github_basicauth_password`                     | Password for GitHub basic auth to use instead of PAT or GitHub APP in case it's running behind a proxy API                 |                                                                      |
 | `dockerRegistryMirror`                                   | The default Docker Registry Mirror used by runners.                                                                        |                                                                      |
+| `hostNetwork`                                            | The "hostNetwork" of the controller container                                                                              | false                                                                |
 | `image.repository`                                       | The "repository/image" of the controller container                                                                         | summerwind/actions-runner-controller                                 |
 | `image.tag`                                              | The tag of the controller container                                                                                        |                                                                      |
 | `image.actionsRunnerRepositoryAndTag`                    | The "repository/image" of the actions runner container                                                                     | summerwind/actions-runner:latest                                     |
+| `image.actionsRunnerImagePullSecrets`                    | Optional image pull secrets to be included in the runner pod's ImagePullSecrets                                            |                                                                      |
 | `image.dindSidecarRepositoryAndTag`                      | The "repository/image" of the dind sidecar container                                                                       | docker:dind                                                          |
 | `image.pullPolicy`                                       | The pull policy of the controller image                                                                                    | IfNotPresent                                                         |
 | `metrics.serviceMonitor`                                 | Deploy serviceMonitor kind for for use with prometheus-operator CRDs                                                       | false                                                                |
+| `metrics.serviceAnnotations`                             | Set annotations for the provisioned metrics service resource                                                               |                                                                      |
 | `metrics.port`                                           | Set port of metrics service                                                                                                | 8443                                                                 |
 | `metrics.proxy.enabled`                                  | Deploy kube-rbac-proxy container in controller pod                                                                         | true                                                                 |
 | `metrics.proxy.image.repository`                         | The "repository/image" of the kube-proxy container                                                                         | quay.io/brancz/kube-rbac-proxy                                       |
 | `metrics.proxy.image.tag`                                | The tag of the kube-proxy image to use when pulling the container                                                          | v0.10.0                                                              |
 | `metrics.serviceMonitorLabels`                           | Set labels to apply to ServiceMonitor resources                                                                            |                                                                      |
 | `imagePullSecrets`                                       | Specifies the secret to be used when pulling the controller pod containers                                                 |                                                                      |
-| `fullNameOverride`                                       | Override the full resource names	                                                                                        |                                                                      |
+| `fullnameOverride`                                       | Override the full resource names	                                                                                        |                                                                      |
 | `nameOverride`                                           | Override the resource name prefix	                                                                                        |                                                                      |
-| `serviceAccont.annotations`                              | Set annotations to the service account                                                                                     |                                                                      |
+| `serviceAccount.annotations`                              | Set annotations to the service account                                                                                     |                                                                      |
 | `serviceAccount.create`                                  | Deploy the controller pod under a service account                                                                          | true                                                                 |
 | `podAnnotations`                                         | Set annotations for the controller pod                                                                                     |                                                                      |
 | `podLabels`                                              | Set labels for the controller pod                                                                                          |                                                                      |
 | `serviceAccount.name`                                    | Set the name of the service account                                                                                        |                                                                      |
 | `securityContext`                                        | Set the security context for each container in the controller pod                                                          |                                                                      |
 | `podSecurityContext`                                     | Set the security context to controller pod                                                                                 |                                                                      |
-| `service.port`                                           | Set controller service type                                                                                                |                                                                      |
-| `service.type`                                           | Set controller service ports                                                                                               |                                                                      |
+| `service.annotations`                                    | Set annotations for the provisioned webhook service resource                                                               |                                                                      |
+| `service.port`                                           | Set controller service ports                                                                                                |                                                                      |
+| `service.type`                                           | Set controller service type                                                                                               |                                                                      |
 | `topologySpreadConstraints`                              | Set the controller pod topologySpreadConstraints                                                                           |                                                                      |
 | `nodeSelector`                                           | Set the controller pod nodeSelector                                                                                        |                                                                      |
 | `resources`                                              | Set the controller pod resources                                                                                           |                                                                      |
 | `affinity`                                               | Set the controller pod affinity rules                                                                                      |                                                                      |
+| `podDisruptionBudget.enabled`                            | Enables a PDB to ensure HA of controller pods                                                                              |      false                                                           |
+| `podDisruptionBudget.minAvailable`                       | Minimum number of pods that must be available after eviction                                                               |                                                                      |
+| `podDisruptionBudget.maxUnavailable`                     | Maximum number of pods that can be unavailable after eviction. Kubernetes 1.7+ required.                                   |                                                                      |
 | `tolerations`                                            | Set the controller pod tolerations                                                                                         |                                                                      |
 | `env`                                                    | Set environment variables for the controller container                                                                     |                                                                      |
 | `priorityClassName`                                      | Set the controller pod priorityClassName                                                                                   |                                                                      |
-| `scope.watchNamespace`                                   | Tells the controller which namespace to watch if `scope.singleNamespace` is true                                           |                                                                      |
+| `scope.watchNamespace`                                   | Tells the controller and the github webhook server which namespace to watch if `scope.singleNamespace` is true             | `Release.Namespace` (the default namespace of the helm chart).       |
 | `scope.singleNamespace`                                  | Limit the controller to watch a single namespace                                                                           | false                                                                |
+| `certManagerEnabled`                                     | Enable cert-manager. If disabled you must set admissionWebHooks.caBundle and create TLS secrets manually                   | true                                                                 |
+| `admissionWebHooks.caBundle`                             | Base64-encoded PEM bundle containing the CA that signed the webhook's serving certificate                                  |                                                                      |
 | `githubWebhookServer.logLevel`                           | Set the log level of the githubWebhookServer container                                                                     |                                                                      |
 | `githubWebhookServer.replicaCount`                       | Set the number of webhook server pods                                                                                      | 1                                                                    |
+| `githubWebhookServer.useRunnerGroupsVisibility`          | Enable supporting runner groups with custom visibility. This will incur in extra API calls and may blow up your budget. Currently, you also need to set `githubWebhookServer.secret.enabled` to enable this feature. | false                                                                |
 | `githubWebhookServer.syncPeriod`                         | Set the period in which the controller reconciles the resources                                                            | 10m                                                                  |
 | `githubWebhookServer.enabled`                            | Deploy the webhook server pod                                                                                              | false                                                                |
+| `githubWebhookServer.secret.enabled`                      | Passes the webhook hook secret to the github-webhook-server                                                                             | false                                                                |
 | `githubWebhookServer.secret.create`                      | Deploy the webhook hook secret                                                                                             | false                                                                |
 | `githubWebhookServer.secret.name`                        | Set the name of the webhook hook secret                                                                                    | github-webhook-server                                                |
 | `githubWebhookServer.secret.github_webhook_secret_token` | Set the webhook secret token value                                                                                         |                                                                      |
 | `githubWebhookServer.imagePullSecrets`                   | Specifies the secret to be used when pulling the githubWebhookServer pod containers                                        |                                                                      |
-| `githubWebhookServer.nameOveride`                        | Override the resource name prefix	                                                                                        |                                                                      |
-| `githubWebhookServer.fullNameOveride`                    | Override the full resource names	                                                                                        |                                                                      |
+| `githubWebhookServer.nameOverride`                        | Override the resource name prefix	                                                                                        |                                                                      |
+| `githubWebhookServer.fullnameOverride`                    | Override the full resource names	                                                                                        |                                                                      |
 | `githubWebhookServer.serviceAccount.create`              | Deploy the githubWebhookServer under a service account                                                                     | true                                                                 |
 | `githubWebhookServer.serviceAccount.annotations`         | Set annotations for the service account                                                                                    |                                                                      |
 | `githubWebhookServer.serviceAccount.name`                | Set the service account name                                                                                               |                                                                      |
@@ -86,3 +105,7 @@ All additional docs are kept in the `docs/` folder, this README is solely for do
 | `githubWebhookServer.ingress.annotations`                | Set annotations for the ingress kind                                                                                       |                                                                      |
 | `githubWebhookServer.ingress.hosts`                      | Set hosts configuration for ingress                                                                                        | `[{"host": "chart-example.local", "paths": []}]`                     |
 | `githubWebhookServer.ingress.tls`                        | Set tls configuration for ingress                                                                                          |                                                                      |
+| `githubWebhookServer.ingress.ingressClassName`           | Set ingress class name                                                                                                     |                                                                      |
+| `githubWebhookServer.podDisruptionBudget.enabled`        | Enables a PDB to ensure HA of githubwebhook pods                                                                           |      false                                                           |
+| `githubWebhookServer.podDisruptionBudget.minAvailable`   | Minimum number of pods that must be available after eviction                                                               |                                                                      |
+| `githubWebhookServer.podDisruptionBudget.maxUnavailable` | Maximum number of pods that can be unavailable after eviction. Kubernetes 1.7+ required.                                   |                                                                      |

charts/actions-runner-controller/crds/actions.summerwind.dev_horizontalrunnerautoscalers.yaml

@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.6.0
+    controller-gen.kubebuilder.io/version: v0.7.0
   creationTimestamp: null
   name: horizontalrunnerautoscalers.actions.summerwind.dev
 spec:
@@ -49,6 +49,9 @@ spec:
                   items:
                     description: CapacityReservation specifies the number of replicas temporarily added to the scale target until ExpirationTime.
                     properties:
+                      effectiveTime:
+                        format: date-time
+                        type: string
                       expirationTime:
                         format: date-time
                         type: string
@@ -59,7 +62,7 @@ spec:
                     type: object
                   type: array
                 maxReplicas:
-                  description: MinReplicas is the maximum number of replicas the deployment is allowed to scale
+                  description: MaxReplicas is the maximum number of replicas the deployment is allowed to scale
                   type: integer
                 metrics:
                   description: Metrics is the collection of various metric targets to calculate desired number of runners
@@ -138,6 +141,7 @@ spec:
                               status:
                                 type: string
                               types:
+                                description: 'One of: created, rerequested, or completed'
                                 items:
                                   type: string
                                 type: array
@@ -157,6 +161,9 @@ spec:
                           push:
                             description: PushSpec is the condition for triggering scale-up on push event Also see https://docs.github.com/en/actions/reference/events-that-trigger-workflows#push
                             type: object
+                          workflowJob:
+                            description: https://docs.github.com/en/developers/webhooks-and-events/webhooks/webhook-events-and-payloads#workflow_job
+                            type: object
                         type: object
                     type: object
                   type: array

charts/actions-runner-controller/docs/UPGRADING.md

@@ -18,23 +18,27 @@ Due to the above you can't just do a `helm upgrade` to release the latest versio
 
 ## Steps
 
-1. Upgrade CRDs
+1. Upgrade CRDs, this isn't optional, the CRDs you are using must be those that correspond with the version of the controller you are installing
 
 ```shell
- # REMEMBER TO UPDATE THE CHART_VERSION TO RELEVANT CHART VERISON!!!!
-CHART_VERSION=0.11.0
+# REMEMBER TO UPDATE THE CHART_VERSION TO RELEVANT CHART VERISON!!!!
+CHART_VERSION=0.18.0
 
 curl -L https://github.com/actions-runner-controller/actions-runner-controller/releases/download/actions-runner-controller-${CHART_VERSION}/actions-runner-controller-${CHART_VERSION}.tgz | tar zxv --strip 1 actions-runner-controller/crds
 
-kubectl apply -f crds/
+kubectl replace -f crds/
 ```
 
 2. Upgrade the Helm release
 
 ```shell
-helm upgrade --install \
-  --namespace actions-runner-system \
-  --version ${CHART_VERSION} \
+# helm repo [command]
+helm repo update
+
+# helm upgrade [RELEASE] [CHART] [flags]
+helm upgrade actions-runner-controller \
   actions-runner-controller/actions-runner-controller \
-  actions-runner-controller
+  --install \
+  --namespace actions-runner-system \
+  --version ${CHART_VERSION}
 ```

charts/actions-runner-controller/templates/_github_webhook_server_helpers.tpl

@@ -58,3 +58,7 @@ Create the name of the service account to use
 {{- define "actions-runner-controller-github-webhook-server.serviceMonitorName" -}}
 {{- include "actions-runner-controller-github-webhook-server.fullname" . | trunc 47 }}-service-monitor
 {{- end }}
+
+{{- define "actions-runner-controller-github-webhook-server.pdbName" -}}
+{{- include "actions-runner-controller-github-webhook-server.fullname" . | trunc 59 }}-pdb
+{{- end }}

charts/actions-runner-controller/templates/_helpers.tpl

@@ -68,6 +68,10 @@ Create the name of the service account to use
 {{- default (include "actions-runner-controller.fullname" .) .Values.authSecret.name -}}
 {{- end }}
 
+{{- define "actions-runner-controller.githubWebhookServerSecretName" -}}
+{{- default (include "actions-runner-controller.fullname" .) .Values.githubWebhookServer.secret.name -}}
+{{- end }}
+
 {{- define "actions-runner-controller.leaderElectionRoleName" -}}
 {{- include "actions-runner-controller.fullname" . }}-leader-election
 {{- end }}
@@ -107,3 +111,7 @@ Create the name of the service account to use
 {{- define "actions-runner-controller.servingCertName" -}}
 {{- include "actions-runner-controller.fullname" . }}-serving-cert
 {{- end }}
+
+{{- define "actions-runner-controller.pdbName" -}}
+{{- include "actions-runner-controller.fullname" . | trunc 59 }}-pdb
+{{- end }}

charts/actions-runner-controller/templates/certificate.yaml

@@ -1,3 +1,4 @@
+{{- if .Values.certManagerEnabled }}
 # The following manifests contain a self-signed issuer CR and a certificate CR.
 # More document can be found at https://docs.cert-manager.io
 # WARNING: Targets CertManager 0.11 check https://docs.cert-manager.io/en/latest/tasks/upgrading/index.html for breaking changes
@@ -22,3 +23,4 @@ spec:
     kind: Issuer
     name: {{ include "actions-runner-controller.selfsignedIssuerName" . }}
   secretName: {{ include "actions-runner-controller.servingCertName" . }}
+{{- end }}

charts/actions-runner-controller/templates/ci-secret.yaml

@@ -7,4 +7,8 @@ data:
 kind: Secret
 metadata:
   name: controller-manager
+  {{- if .Values.authSecret.annotations }}
+  annotations:
+    {{ toYaml .Values.authSecret.annotations | nindent 4 }}
+  {{- end }}
 {{- end }}

charts/actions-runner-controller/templates/controller.metrics.service.yaml

@@ -5,6 +5,10 @@ metadata:
     {{- include "actions-runner-controller.labels" . | nindent 4 }}
   name: {{ include "actions-runner-controller.metricsServiceName" . }}
   namespace: {{ .Release.Namespace }}
+  {{- with .Values.metrics.serviceAnnotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
 spec:
   ports:
   - name: metrics-port

charts/actions-runner-controller/templates/controller.pdb.yaml

@@ -0,0 +1,19 @@
+{{- if .Values.podDisruptionBudget.enabled }}
+apiVersion: policy/v1beta1
+kind: PodDisruptionBudget
+metadata:
+  labels:
+    {{- include "actions-runner-controller.labels" . | nindent 4 }}
+  name: {{ include "actions-runner-controller.pdbName" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  {{- if .Values.podDisruptionBudget.minAvailable }}
+  minAvailable: {{ .Values.podDisruptionBudget.minAvailable }}
+  {{- end  }}
+  {{- if .Values.podDisruptionBudget.maxUnavailable }}
+  maxUnavailable: {{ .Values.podDisruptionBudget.maxUnavailable }}
+  {{- end  }}
+  selector:
+    matchLabels:
+      {{- include "actions-runner-controller.selectorLabels" . | nindent 6 }}
+{{- end -}}

charts/actions-runner-controller/templates/deployment.yaml

@@ -14,6 +14,7 @@ spec:
     metadata:
       {{- with .Values.podAnnotations }}
       annotations:
+        kubectl.kubernetes.io/default-logs-container: "manager"
         {{- toYaml . | nindent 8 }}
       {{- end }}
       labels:
@@ -43,9 +44,14 @@ spec:
         {{- if .Values.leaderElectionId }}
         - "--leader-election-id={{ .Values.leaderElectionId }}"
         {{- end }}
+        - "--port={{ .Values.webhookPort }}"
         - "--sync-period={{ .Values.syncPeriod }}"
+        - "--default-scale-down-delay={{ .Values.defaultScaleDownDelay }}"
         - "--docker-image={{ .Values.image.dindSidecarRepositoryAndTag }}"
         - "--runner-image={{ .Values.image.actionsRunnerRepositoryAndTag }}"
+        {{- range .Values.image.actionsRunnerImagePullSecrets }}
+        - "--runner-image-pull-secret={{ . }}"
+        {{- end }}
         {{- if .Values.dockerRegistryMirror }}
         - "--docker-registry-mirror={{ .Values.dockerRegistryMirror }}"
         {{- end }}
@@ -58,6 +64,9 @@ spec:
         {{- if .Values.logLevel }}
         - "--log-level={{ .Values.logLevel }}"
         {{- end }}
+        {{- if .Values.runnerGithubURL  }}
+        - "--runner-github-url={{ .Values.runnerGithubURL }}"
+        {{- end }}
         command:
         - "/manager"
         env:
@@ -65,6 +74,15 @@ spec:
         - name: GITHUB_ENTERPRISE_URL
           value: {{ .Values.githubEnterpriseServerURL }}
         {{- end }}
+        {{- if .Values.githubURL  }}
+        - name: GITHUB_URL
+          value: {{ .Values.githubURL }}
+        {{- end }}
+        {{- if .Values.githubUploadURL  }}
+        - name: GITHUB_UPLOAD_URL
+          value: {{ .Values.githubUploadURL }}
+        {{- end }}
+        {{- if .Values.authSecret.enabled }}
         - name: GITHUB_TOKEN
           valueFrom:
             secretKeyRef:
@@ -84,7 +102,22 @@ spec:
               name: {{ include "actions-runner-controller.secretName" . }}
               optional: true
         - name: GITHUB_APP_PRIVATE_KEY
-          value: /etc/actions-runner-controller/github_app_private_key
+          valueFrom:
+            secretKeyRef:
+              key: github_app_private_key
+              name: {{ include "actions-runner-controller.secretName" . }}
+              optional: true
+        {{- if .Values.authSecret.github_basicauth_username }}
+        - name: GITHUB_BASICAUTH_USERNAME
+          value: {{ .Values.authSecret.github_basicauth_username }}
+        {{- end }}
+        - name: GITHUB_BASICAUTH_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              key: github_basicauth_password
+              name: {{ include "actions-runner-controller.secretName" . }}
+              optional: true
+        {{- end }}
         {{- range $key, $val := .Values.env }}
         - name: {{ $key }}
           value: {{ $val | quote }}
@@ -93,7 +126,7 @@ spec:
         name: manager
         imagePullPolicy: {{ .Values.image.pullPolicy }}
         ports:
-        - containerPort: 9443
+        - containerPort: {{ .Values.webhookPort }}
           name: webhook-server
           protocol: TCP
         {{- if not .Values.metrics.proxy.enabled }}
@@ -106,14 +139,19 @@ spec:
         securityContext:
           {{- toYaml .Values.securityContext | nindent 12 }}
         volumeMounts:
+        {{- if .Values.authSecret.enabled }}
         - mountPath: "/etc/actions-runner-controller"
           name: secret
           readOnly: true
+        {{- end }}
         - mountPath: /tmp
           name: tmp
         - mountPath: /tmp/k8s-webhook-server/serving-certs
           name: cert
           readOnly: true
+        {{- if .Values.additionalVolumeMounts }}
+          {{- toYaml .Values.additionalVolumeMounts | nindent 8 }} 
+        {{- end }}
       {{- if .Values.metrics.proxy.enabled }}
       - args:
         - "--secure-listen-address=0.0.0.0:{{ .Values.metrics.port }}"
@@ -133,15 +171,20 @@ spec:
       {{- end }}
       terminationGracePeriodSeconds: 10
       volumes:
+      {{- if .Values.authSecret.enabled }}
       - name: secret
         secret:
           secretName: {{ include "actions-runner-controller.secretName" . }}
+      {{- end }}
       - name: cert
         secret:
           defaultMode: 420
           secretName: {{ include "actions-runner-controller.servingCertName" . }}
       - name: tmp
         emptyDir: {}
+      {{- if .Values.additionalVolumes }}
+        {{- toYaml .Values.additionalVolumes | nindent 6}}
+      {{- end }}
       {{- with .Values.nodeSelector }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}
@@ -158,3 +201,6 @@ spec:
       topologySpreadConstraints:
         {{- toYaml . | nindent 8 }}
       {{- end }}
+      {{- if .Values.hostNetwork }}
+      hostNetwork: {{ .Values.hostNetwork }}
+      {{- end }}

charts/actions-runner-controller/templates/githubwebhook.deployment.yaml

@@ -15,6 +15,7 @@ spec:
     metadata:
       {{- with .Values.githubWebhookServer.podAnnotations }}
       annotations:
+        kubectl.kubernetes.io/default-logs-container: "github-webhook-server"
         {{- toYaml . | nindent 8 }}
       {{- end }}
       labels:
@@ -42,6 +43,12 @@ spec:
         {{- if .Values.githubWebhookServer.logLevel }}
         - "--log-level={{ .Values.githubWebhookServer.logLevel }}"
         {{- end }}
+        {{- if .Values.scope.singleNamespace }}
+        - "--watch-namespace={{ default .Release.Namespace .Values.scope.watchNamespace }}"
+        {{- end }}
+        {{- if .Values.runnerGithubURL  }}
+        - "--runner-github-url={{ .Values.runnerGithubURL }}"
+        {{- end }}
         command:
         - "/github-webhook-server"
         env:
@@ -51,6 +58,54 @@ spec:
               key: github_webhook_secret_token
               name: {{ include "actions-runner-controller-github-webhook-server.secretName" . }}
               optional: true
+        {{- if .Values.githubEnterpriseServerURL  }}
+        - name: GITHUB_ENTERPRISE_URL
+          value: {{ .Values.githubEnterpriseServerURL }}
+        {{- end }}
+        {{- if .Values.githubURL  }}
+        - name: GITHUB_URL
+          value: {{ .Values.githubURL }}
+        {{- end }}
+        {{- if .Values.githubUploadURL  }}
+        - name: GITHUB_UPLOAD_URL
+          value: {{ .Values.githubUploadURL }}
+        {{- end }}
+        {{- if and .Values.githubWebhookServer.useRunnerGroupsVisibility .Values.githubWebhookServer.secret.enabled }}
+        - name: GITHUB_TOKEN
+          valueFrom:
+            secretKeyRef:
+              key: github_token
+              name: {{ include "actions-runner-controller.githubWebhookServerSecretName" . }}
+              optional: true
+        - name: GITHUB_APP_ID
+          valueFrom:
+            secretKeyRef:
+              key: github_app_id
+              name: {{ include "actions-runner-controller.githubWebhookServerSecretName" . }}
+              optional: true
+        - name: GITHUB_APP_INSTALLATION_ID
+          valueFrom:
+            secretKeyRef:
+              key: github_app_installation_id
+              name: {{ include "actions-runner-controller.githubWebhookServerSecretName" . }}
+              optional: true
+        - name: GITHUB_APP_PRIVATE_KEY
+          valueFrom:
+            secretKeyRef:
+              key: github_app_private_key
+              name: {{ include "actions-runner-controller.githubWebhookServerSecretName" . }}
+              optional: true
+        {{- if .Values.authSecret.github_basicauth_username }}
+        - name: GITHUB_BASICAUTH_USERNAME
+          value: {{ .Values.authSecret.github_basicauth_username }}
+        {{- end }}
+        - name: GITHUB_BASICAUTH_PASSWORD
+          valueFrom:
+            secretKeyRef:
+              key: github_basicauth_password
+              name: {{ include "actions-runner-controller.secretName" . }}
+              optional: true
+        {{- end }}
         {{- range $key, $val := .Values.githubWebhookServer.env }}
         - name: {{ $key }}
           value: {{ $val | quote }}

charts/actions-runner-controller/templates/githubwebhook.ingress.yaml

@@ -1,14 +1,17 @@
 {{- if .Values.githubWebhookServer.ingress.enabled -}}
 {{- $fullName := include "actions-runner-controller-github-webhook-server.fullname" . -}}
 {{- $svcPort := (index .Values.githubWebhookServer.service.ports 0).port -}}
-{{- if semverCompare ">=1.14-0" .Capabilities.KubeVersion.GitVersion -}}
+{{- if .Capabilities.APIVersions.Has "networking.k8s.io/v1/Ingress" }}
+apiVersion: networking.k8s.io/v1
+{{- else if .Capabilities.APIVersions.Has "networking.k8s.io/v1beta1/Ingress" }}
 apiVersion: networking.k8s.io/v1beta1
-{{- else -}}
+{{- else if .Capabilities.APIVersions.Has "extensions/v1beta1/Ingress" }}
 apiVersion: extensions/v1beta1
 {{- end }}
 kind: Ingress
 metadata:
   name: {{ $fullName }}
+  namespace: {{ .Release.Namespace }}
   labels:
     {{- include "actions-runner-controller.labels" . | nindent 4 }}
   {{- with .Values.githubWebhookServer.ingress.annotations }}
@@ -26,16 +29,32 @@ spec:
       secretName: {{ .secretName }}
     {{- end }}
   {{- end }}
+  {{- with .Values.githubWebhookServer.ingress.ingressClassName }}
+  ingressClassName: {{ . }}
+  {{- end }}
   rules:
     {{- range .Values.githubWebhookServer.ingress.hosts }}
     - host: {{ .host | quote }}
       http:
         paths:
+          {{- if .extraPaths }}
+          {{- toYaml .extraPaths | nindent 10 }}
+          {{- end }}
           {{- range .paths }}
           - path: {{ .path }}
+            {{- if $.Capabilities.APIVersions.Has "networking.k8s.io/v1/Ingress" }}
+            pathType: {{ .pathType }}
+            {{- end }}
             backend:
+              {{- if $.Capabilities.APIVersions.Has "networking.k8s.io/v1/Ingress" }}
+              service:
+               name: {{ $fullName }}
+               port:
+                 number: {{ $svcPort }}
+              {{- else }}
               serviceName: {{ $fullName }}
               servicePort: {{ $svcPort }}
+              {{- end }}
           {{- end }}
     {{- end }}
   {{- end }}

charts/actions-runner-controller/templates/githubwebhook.pdb.yaml

@@ -0,0 +1,19 @@
+{{- if .Values.githubWebhookServer.podDisruptionBudget.enabled }}
+apiVersion: policy/v1beta1
+kind: PodDisruptionBudget
+metadata:
+  labels:
+    {{- include "actions-runner-controller.labels" . | nindent 4 }}
+  name: {{ include "actions-runner-controller-github-webhook-server.pdbName" . }}
+  namespace: {{ .Release.Namespace }}
+spec:
+  {{- if .Values.githubWebhookServer.podDisruptionBudget.minAvailable }}
+  minAvailable: {{ .Values.githubWebhookServer.podDisruptionBudget.minAvailable }}
+  {{- end  }}
+  {{- if .Values.githubWebhookServer.podDisruptionBudget.maxUnavailable }}
+  maxUnavailable: {{ .Values.githubWebhookServer.podDisruptionBudget.maxUnavailable }}
+  {{- end  }}
+  selector:
+    matchLabels:
+      {{- include "actions-runner-controller-github-webhook-server.selectorLabels" . | nindent 6 }}
+{{- end -}}

charts/actions-runner-controller/templates/githubwebhook.secrets.yaml

@@ -12,5 +12,17 @@ data:
 {{- if .Values.githubWebhookServer.secret.github_webhook_secret_token }}
   github_webhook_secret_token: {{ .Values.githubWebhookServer.secret.github_webhook_secret_token | toString | b64enc }}
 {{- end }}
+{{- if .Values.githubWebhookServer.secret.github_app_id }}
+  github_app_id: {{ .Values.githubWebhookServer.secret.github_app_id | toString | b64enc }}
+{{- end }}
+{{- if .Values.githubWebhookServer.secret.github_app_installation_id }}
+  github_app_installation_id: {{ .Values.githubWebhookServer.secret.github_app_installation_id | toString | b64enc }}
+{{- end }}
+{{- if .Values.githubWebhookServer.secret.github_app_private_key }}
+  github_app_private_key: {{ .Values.githubWebhookServer.secret.github_app_private_key | toString | b64enc }}
+{{- end }}
+{{- if .Values.githubWebhookServer.secret.github_token }}
+  github_token: {{ .Values.githubWebhookServer.secret.github_token | toString | b64enc }}
+{{- end }}
 {{- end }}
 {{- end }}

charts/actions-runner-controller/templates/manager_role.yaml

@@ -195,6 +195,28 @@ rules:
   verbs:
   - create
   - patch
+- apiGroups:
+  - ""
+  resources:
+  - persistentvolumeclaims
+  verbs:
+  - delete
+  - get
+  - list
+  - patch
+  - update
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - persistentvolumes
+  verbs:
+  - delete
+  - get
+  - list
+  - patch
+  - update
+  - watch
 - apiGroups:
   - coordination.k8s.io
   resources:
@@ -228,3 +250,11 @@ rules:
   - patch
   - update
   - watch
+- apiGroups:
+  - ""
+  resources:
+  - secrets
+  verbs:
+  - get
+  - list
+  - watch

charts/actions-runner-controller/templates/manager_secrets.yaml

@@ -4,14 +4,20 @@ kind: Secret
 metadata:
   name: {{ include "actions-runner-controller.secretName" . }}
   namespace: {{ .Release.Namespace }}
+  {{- if .Values.authSecret.annotations }}
+  annotations:
+    {{ toYaml .Values.authSecret.annotations | nindent 4 }}
+  {{- end }}
   labels:
     {{- include "actions-runner-controller.labels" . | nindent 4 }}
 type: Opaque
 data:
 {{- if .Values.authSecret.github_app_id }}
+  # Keep this as a string as strings integrate better with things like AWS Parameter Store, see PR #882 for an example
   github_app_id: {{ .Values.authSecret.github_app_id | toString | b64enc }}
 {{- end }}
 {{- if .Values.authSecret.github_app_installation_id }}
+  # Keep this as a string as strings integrate better with things like AWS Parameter Store, see PR #882 for an example
   github_app_installation_id: {{ .Values.authSecret.github_app_installation_id | toString | b64enc }}
 {{- end }}
 {{- if .Values.authSecret.github_app_private_key }}
@@ -20,4 +26,7 @@ data:
 {{- if .Values.authSecret.github_token }}
   github_token: {{ .Values.authSecret.github_token | toString | b64enc }}
 {{- end }}
+{{- if .Values.authSecret.github_basicauth_password }}
+  github_basicauth_password: {{ .Values.authSecret.github_basicauth_password | toString | b64enc }}
+{{- end }}
 {{- end }}

charts/actions-runner-controller/templates/webhook_configs.yaml

@@ -5,12 +5,22 @@ kind: MutatingWebhookConfiguration
 metadata:
   creationTimestamp: null
   name: {{ include "actions-runner-controller.fullname" . }}-mutating-webhook-configuration
+  {{- if .Values.certManagerEnabled }}
   annotations:
     cert-manager.io/inject-ca-from: {{ .Release.Namespace }}/{{ include "actions-runner-controller.servingCertName" . }}
+  {{- end }}
 webhooks:
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ quote .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}
@@ -30,7 +40,15 @@ webhooks:
   sideEffects: None
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}
@@ -50,7 +68,15 @@ webhooks:
   sideEffects: None
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}
@@ -70,7 +96,15 @@ webhooks:
   sideEffects: None
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}
@@ -96,12 +130,22 @@ kind: ValidatingWebhookConfiguration
 metadata:
   creationTimestamp: null
   name: {{ include "actions-runner-controller.fullname" . }}-validating-webhook-configuration
+  {{- if .Values.certManagerEnabled }}
   annotations:
     cert-manager.io/inject-ca-from: {{ .Release.Namespace }}/{{ include "actions-runner-controller.servingCertName" . }}
+  {{- end }}
 webhooks:
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}
@@ -121,7 +165,15 @@ webhooks:
   sideEffects: None
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}
@@ -141,7 +193,15 @@ webhooks:
   sideEffects: None
 - admissionReviewVersions:
   - v1beta1
+  {{- if .Values.scope.singleNamespace }}
+  namespaceSelector:
+    matchLabels:
+      name: {{ default .Release.Namespace .Values.scope.watchNamespace }}
+  {{- end }}
   clientConfig:
+    {{- if .Values.admissionWebHooks.caBundle }}
+    caBundle: {{ .Values.admissionWebHooks.caBundle }}
+    {{- end }}
     service:
       name: {{ include "actions-runner-controller.webhookServiceName" . }}
       namespace: {{ .Release.Namespace }}

charts/actions-runner-controller/templates/webhook_service.yaml

@@ -5,11 +5,15 @@ metadata:
   namespace: {{ .Release.Namespace }}
   labels:
     {{- include "actions-runner-controller.labels" . | nindent 4 }}
+  {{- with .Values.service.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
 spec:
   type: {{ .Values.service.type }}
   ports:
     - port: 443
-      targetPort: 9443
+      targetPort: {{ .Values.webhookPort }}
       protocol: TCP
       name: https
   selector:

charts/actions-runner-controller/values.yaml

@@ -6,13 +6,16 @@ labels: {}
 
 replicaCount: 1
 
-syncPeriod: 10m
+webhookPort: 9443
+syncPeriod: 1m
+defaultScaleDownDelay: 10m
 
 enableLeaderElection: true
 # Specifies the controller id for leader election.
 # Must be unique if more than one controller installed onto the same namespace.
 #leaderElectionId: "actions-runner-controller"
 
+# DEPRECATED: This has been removed as unnecessary in #1192
 # The controller tries its best not to repeat the duplicate GitHub API call
 # within this duration.
 # Defaults to syncPeriod - 10s.
@@ -21,17 +24,34 @@ enableLeaderElection: true
 # The URL of your GitHub Enterprise server, if you're using one.
 #githubEnterpriseServerURL: https://github.example.com
 
+# Override GitHub URLs in case of using proxy APIs
+#githubURL: ""
+#githubUploadURL: ""
+#runnerGithubURL: ""
+
 # Only 1 authentication method can be deployed at a time
 # Uncomment the configuration you are applying and fill in the details
+#
+# If authSecret.enabled=true these values are inherited to actions-runner-controller's controller-manager container's env.
+#
+# Do set authSecret.enabled=false and set env if you want full control over
+# the GitHub authn related envvars of the container.
+# See https://github.com/actions-runner-controller/actions-runner-controller/pull/937 for more details.
 authSecret:
+  enabled: true
   create: false
   name: "controller-manager"
+  annotations: {}
   ### GitHub Apps Configuration
+  ## NOTE: IDs MUST be strings, use quotes
   #github_app_id: ""
   #github_app_installation_id: ""
   #github_app_private_key: |
   ### GitHub PAT Configuration
   #github_token: ""
+  ### Basic auth for github API proxy
+  #github_basicauth_username: ""
+  #github_basicauth_password: ""
 
 dockerRegistryMirror: ""
 image:
@@ -39,6 +59,9 @@ image:
   actionsRunnerRepositoryAndTag: "summerwind/actions-runner:latest"
   dindSidecarRepositoryAndTag: "docker:dind"
   pullPolicy: IfNotPresent
+  # The default image-pull secrets name for self-hosted runner container.
+  # It's added to spec.ImagePullSecrets of self-hosted runner pods.
+  actionsRunnerImagePullSecrets: []
 
 imagePullSecrets: []
 nameOverride: ""
@@ -70,11 +93,15 @@ securityContext:
   # runAsNonRoot: true
   # runAsUser: 1000
 
+# Webhook service resource
 service:
   type: ClusterIP
   port: 443
+  annotations: {}
 
+# Metrics service resource
 metrics:
+  serviceAnnotations: {}
   serviceMonitor: false
   serviceMonitorLabels: {}
   port: 8443
@@ -82,7 +109,7 @@ metrics:
     enabled: true
     image:
       repository: quay.io/brancz/kube-rbac-proxy
-      tag: v0.10.0
+      tag: v0.13.0
 
 resources:
   {}
@@ -103,6 +130,12 @@ tolerations: []
 
 affinity: {}
 
+# Only one of minAvailable or maxUnavailable can be set
+podDisruptionBudget:
+  enabled: false
+  # minAvailable: 1
+  # maxUnavailable: 3
+
 # Leverage a PriorityClass to ensure your pods survive resource shortages
 # ref: https://kubernetes.io/docs/concepts/configuration/pod-priority-preemption/
 # PriorityClass: system-cluster-critical
@@ -114,6 +147,14 @@ env:
   # https_proxy: "proxy.com:8080"
   # no_proxy: ""
 
+## specify additional volumes to mount in the manager container, this can be used
+## to specify additional storage of material or to inject files from ConfigMaps
+## into the running container
+additionalVolumes: []
+
+## specify where the additional volumes are mounted in the manager container
+additionalVolumeMounts: []
+
 scope:
   # If true, the controller will only watch custom resources in a single namespace
   singleNamespace: false
@@ -121,15 +162,34 @@ scope:
   # The default value is "", which means the namespace of the controller
   watchNamespace: ""
 
+certManagerEnabled: true
+
+admissionWebHooks:
+  {}
+  #caBundle: "Ci0tLS0tQk...<base64-encoded PEM bundle containing the CA that signed the webhook's serving certificate>...tLS0K"
+
+# There may be alternatives to setting `hostNetwork: true`, see
+# https://github.com/actions-runner-controller/actions-runner-controller/issues/1005#issuecomment-993097155
+#hostNetwork: true
+
 githubWebhookServer:
   enabled: false
   replicaCount: 1
   syncPeriod: 10m
+  useRunnerGroupsVisibility: false
   secret:
+    enabled: false
     create: false
     name: "github-webhook-server"
     ### GitHub Webhook Configuration
     github_webhook_secret_token: ""
+    ### GitHub Apps Configuration
+    ## NOTE: IDs MUST be strings, use quotes
+    #github_app_id: ""
+    #github_app_installation_id: ""
+    #github_app_private_key: |
+    ### GitHub PAT Configuration
+    #github_token: ""
   imagePullSecrets: []
   nameOverride: ""
   fullnameOverride: ""
@@ -162,14 +222,36 @@ githubWebhookServer:
         #nodePort: someFixedPortForUseWithTerraformCdkCfnEtc
   ingress:
     enabled: false
-    annotations:
-      {}
+    ingressClassName: ""
+    annotations: {}
       # kubernetes.io/ingress.class: nginx
       # kubernetes.io/tls-acme: "true"
     hosts:
       - host: chart-example.local
         paths: []
+        #  - path: /*
+        #    pathType: ImplementationSpecific
+        # Extra paths that are not automatically connected to the server. This is useful when working with annotation based services.
+        extraPaths: []
+        # - path: /*
+        #   backend:
+        #     serviceName: ssl-redirect
+        #     servicePort: use-annotation
+        ## for Kubernetes >=1.19 (when "networking.k8s.io/v1" is used)
+        # - path: /*
+        #   pathType: Prefix
+        #   backend:
+        #     service:
+        #       name: ssl-redirect
+        #       port:
+        #         name: use-annotation
     tls: []
     #  - secretName: chart-example-tls
     #    hosts:
     #      - chart-example.local
+
+  # Only one of minAvailable or maxUnavailable can be set
+  podDisruptionBudget:
+    enabled: false
+    # minAvailable: 1
+    # maxUnavailable: 3

cmd/githubwebhookserver/main.go

@@ -20,6 +20,7 @@ import (
 	"context"
 	"errors"
 	"flag"
+	"fmt"
 	"net/http"
 	"os"
 	"sync"
@@ -27,14 +28,15 @@ import (
 
 	actionsv1alpha1 "github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
 	"github.com/actions-runner-controller/actions-runner-controller/controllers"
-	zaplib "go.uber.org/zap"
+	"github.com/actions-runner-controller/actions-runner-controller/github"
+	"github.com/actions-runner-controller/actions-runner-controller/logging"
+	"github.com/kelseyhightower/envconfig"
 	"k8s.io/apimachinery/pkg/runtime"
 	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
 	_ "k8s.io/client-go/plugin/pkg/client/auth/exec"
 	_ "k8s.io/client-go/plugin/pkg/client/auth/gcp"
 	_ "k8s.io/client-go/plugin/pkg/client/auth/oidc"
 	ctrl "sigs.k8s.io/controller-runtime"
-	"sigs.k8s.io/controller-runtime/pkg/log/zap"
 	// +kubebuilder:scaffold:imports
 )
 
@@ -44,10 +46,7 @@ var (
 )
 
 const (
-	logLevelDebug = "debug"
-	logLevelInfo  = "info"
-	logLevelWarn  = "warn"
-	logLevelError = "error"
+	webhookSecretTokenEnvName = "GITHUB_WEBHOOK_SECRET_TOKEN"
 )
 
 func init() {
@@ -65,16 +64,27 @@ func main() {
 		metricsAddr string
 
 		// The secret token of the GitHub Webhook. See https://docs.github.com/en/developers/webhooks-and-events/securing-your-webhooks
-		webhookSecretToken string
+		webhookSecretToken    string
+		webhookSecretTokenEnv string
 
 		watchNamespace string
 
 		enableLeaderElection bool
 		syncPeriod           time.Duration
 		logLevel             string
+		queueLimit           int
+
+		ghClient *github.Client
 	)
 
-	webhookSecretToken = os.Getenv("GITHUB_WEBHOOK_SECRET_TOKEN")
+	var c github.Config
+	err = envconfig.Process("github", &c)
+	if err != nil {
+		fmt.Fprintf(os.Stderr, "Error: processing environment variables: %v\n", err)
+		os.Exit(1)
+	}
+
+	webhookSecretTokenEnv = os.Getenv(webhookSecretTokenEnvName)
 
 	flag.StringVar(&webhookAddr, "webhook-addr", ":8000", "The address the metric endpoint binds to.")
 	flag.StringVar(&metricsAddr, "metrics-addr", ":8080", "The address the metric endpoint binds to.")
@@ -82,11 +92,28 @@ func main() {
 	flag.BoolVar(&enableLeaderElection, "enable-leader-election", false,
 		"Enable leader election for controller manager. Enabling this will ensure there is only one active controller manager.")
 	flag.DurationVar(&syncPeriod, "sync-period", 10*time.Minute, "Determines the minimum frequency at which K8s resources managed by this controller are reconciled. When you use autoscaling, set to a lower value like 10 minute, because this corresponds to the minimum time to react on demand change")
-	flag.StringVar(&logLevel, "log-level", logLevelDebug, `The verbosity of the logging. Valid values are "debug", "info", "warn", "error". Defaults to "debug".`)
+	flag.StringVar(&logLevel, "log-level", logging.LogLevelDebug, `The verbosity of the logging. Valid values are "debug", "info", "warn", "error". Defaults to "debug".`)
+	flag.IntVar(&queueLimit, "queue-limit", controllers.DefaultQueueLimit, `The maximum length of the scale operation queue. The scale opration is enqueued per every matching webhook event, and the server returns a 500 HTTP status when the queue was already full on enqueue attempt.`)
+	flag.StringVar(&webhookSecretToken, "github-webhook-secret-token", "", "The personal access token of GitHub.")
+	flag.StringVar(&c.Token, "github-token", c.Token, "The personal access token of GitHub.")
+	flag.Int64Var(&c.AppID, "github-app-id", c.AppID, "The application ID of GitHub App.")
+	flag.Int64Var(&c.AppInstallationID, "github-app-installation-id", c.AppInstallationID, "The installation ID of GitHub App.")
+	flag.StringVar(&c.AppPrivateKey, "github-app-private-key", c.AppPrivateKey, "The path of a private key file to authenticate as a GitHub App")
+	flag.StringVar(&c.URL, "github-url", c.URL, "GitHub URL to be used for GitHub API calls")
+	flag.StringVar(&c.UploadURL, "github-upload-url", c.UploadURL, "GitHub Upload URL to be used for GitHub API calls")
+	flag.StringVar(&c.BasicauthUsername, "github-basicauth-username", c.BasicauthUsername, "Username for GitHub basic auth to use instead of PAT or GitHub APP in case it's running behind a proxy API")
+	flag.StringVar(&c.BasicauthPassword, "github-basicauth-password", c.BasicauthPassword, "Password for GitHub basic auth to use instead of PAT or GitHub APP in case it's running behind a proxy API")
+	flag.StringVar(&c.RunnerGitHubURL, "runner-github-url", c.RunnerGitHubURL, "GitHub URL to be used by runners during registration")
+
 	flag.Parse()
 
+	if webhookSecretToken == "" && webhookSecretTokenEnv != "" {
+		setupLog.Info(fmt.Sprintf("Using the value from %s for -github-webhook-secret-token", webhookSecretTokenEnvName))
+		webhookSecretToken = webhookSecretTokenEnv
+	}
+
 	if webhookSecretToken == "" {
-		setupLog.Info("-webhook-secret-token is missing or empty. Create one following https://docs.github.com/en/developers/webhooks-and-events/securing-your-webhooks")
+		setupLog.Info(fmt.Sprintf("-github-webhook-secret-token and %s are missing or empty. Create one following https://docs.github.com/en/developers/webhooks-and-events/securing-your-webhooks and specify it via the flag or the envvar", webhookSecretTokenEnvName))
 	}
 
 	if watchNamespace == "" {
@@ -95,24 +122,28 @@ func main() {
 		setupLog.Info("-watch-namespace is %q. Only HorizontalRunnerAutoscalers in %q are watched, cached, and considered as scale targets.")
 	}
 
-	logger := zap.New(func(o *zap.Options) {
-		switch logLevel {
-		case logLevelDebug:
-			o.Development = true
-		case logLevelInfo:
-			lvl := zaplib.NewAtomicLevelAt(zaplib.InfoLevel)
-			o.Level = &lvl
-		case logLevelWarn:
-			lvl := zaplib.NewAtomicLevelAt(zaplib.WarnLevel)
-			o.Level = &lvl
-		case logLevelError:
-			lvl := zaplib.NewAtomicLevelAt(zaplib.ErrorLevel)
-			o.Level = &lvl
-		}
-	})
+	logger := logging.NewLogger(logLevel)
 
 	ctrl.SetLogger(logger)
 
+	// In order to support runner groups with custom visibility (selected repositories), we need to perform some GitHub API calls.
+	// Let the user define if they want to opt-in supporting this option by providing the proper GitHub authentication parameters
+	// Without an opt-in, runner groups with custom visibility won't be supported to save API calls
+	// That is, all runner groups managed by ARC are assumed to be visible to any repositories,
+	// which is wrong when you have one or more non-default runner groups in your organization or enterprise.
+	if len(c.Token) > 0 || (c.AppID > 0 && c.AppInstallationID > 0 && c.AppPrivateKey != "") || (len(c.BasicauthUsername) > 0 && len(c.BasicauthPassword) > 0) {
+		c.Log = &logger
+
+		ghClient, err = c.NewClient()
+		if err != nil {
+			fmt.Fprintln(os.Stderr, "Error: Client creation failed.", err)
+			setupLog.Error(err, "unable to create controller", "controller", "Runner")
+			os.Exit(1)
+		}
+	} else {
+		setupLog.Info("GitHub client is not initialized. Runner groups with custom visibility are not supported. If needed, please provide GitHub authentication. This will incur in extra GitHub API calls")
+	}
+
 	mgr, err := ctrl.NewManager(ctrl.GetConfigOrDie(), ctrl.Options{
 		Scheme:             scheme,
 		SyncPeriod:         &syncPeriod,
@@ -127,16 +158,19 @@ func main() {
 	}
 
 	hraGitHubWebhook := &controllers.HorizontalRunnerAutoscalerGitHubWebhook{
+		Name:           "webhookbasedautoscaler",
 		Client:         mgr.GetClient(),
-		Log:            ctrl.Log.WithName("controllers").WithName("Runner"),
+		Log:            ctrl.Log.WithName("controllers").WithName("webhookbasedautoscaler"),
 		Recorder:       nil,
 		Scheme:         mgr.GetScheme(),
 		SecretKeyBytes: []byte(webhookSecretToken),
 		Namespace:      watchNamespace,
+		GitHubClient:   ghClient,
+		QueueLimit:     queueLimit,
 	}
 
 	if err = hraGitHubWebhook.SetupWithManager(mgr); err != nil {
-		setupLog.Error(err, "unable to create controller", "controller", "Runner")
+		setupLog.Error(err, "unable to create controller", "controller", "webhookbasedautoscaler")
 		os.Exit(1)
 	}
 

config/crd/bases/actions.summerwind.dev_horizontalrunnerautoscalers.yaml

@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.6.0
+    controller-gen.kubebuilder.io/version: v0.7.0
   creationTimestamp: null
   name: horizontalrunnerautoscalers.actions.summerwind.dev
 spec:
@@ -49,6 +49,9 @@ spec:
                   items:
                     description: CapacityReservation specifies the number of replicas temporarily added to the scale target until ExpirationTime.
                     properties:
+                      effectiveTime:
+                        format: date-time
+                        type: string
                       expirationTime:
                         format: date-time
                         type: string
@@ -59,7 +62,7 @@ spec:
                     type: object
                   type: array
                 maxReplicas:
-                  description: MinReplicas is the maximum number of replicas the deployment is allowed to scale
+                  description: MaxReplicas is the maximum number of replicas the deployment is allowed to scale
                   type: integer
                 metrics:
                   description: Metrics is the collection of various metric targets to calculate desired number of runners
@@ -138,6 +141,7 @@ spec:
                               status:
                                 type: string
                               types:
+                                description: 'One of: created, rerequested, or completed'
                                 items:
                                   type: string
                                 type: array
@@ -157,6 +161,9 @@ spec:
                           push:
                             description: PushSpec is the condition for triggering scale-up on push event Also see https://docs.github.com/en/actions/reference/events-that-trigger-workflows#push
                             type: object
+                          workflowJob:
+                            description: https://docs.github.com/en/developers/webhooks-and-events/webhooks/webhook-events-and-payloads#workflow_job
+                            type: object
                         type: object
                     type: object
                   type: array

config/crd/patches/webhook_in_runners.yaml

@@ -8,6 +8,7 @@ spec:
   conversion:
     strategy: Webhook
     webhook:
+      conversionReviewVersions: ["v1","v1beta1"]
       clientConfig:
         # this is "\n" used as a placeholder, otherwise it will be rejected by the apiserver for being blank,
         # but we're going to set it later using the cert-manager (or potentially a patch if not using cert-manager)

config/default/kustomization.yaml

@@ -20,19 +20,20 @@ bases:
 - ../webhook
 # [CERTMANAGER] To enable cert-manager, uncomment all sections with 'CERTMANAGER'. 'WEBHOOK' components are required.
 - ../certmanager
-# [PROMETHEUS] To enable prometheus monitor, uncomment all sections with 'PROMETHEUS'. 
+# [PROMETHEUS] To enable prometheus monitor, uncomment all sections with 'PROMETHEUS'.
 #- ../prometheus
 
 patchesStrategicMerge:
-  # Protect the /metrics endpoint by putting it behind auth.
-  # Only one of manager_auth_proxy_patch.yaml and
-  # manager_prometheus_metrics_patch.yaml should be enabled.
+# Protect the /metrics endpoint by putting it behind auth.
+# Only one of manager_auth_proxy_patch.yaml and
+# manager_prometheus_metrics_patch.yaml should be enabled.
 - manager_auth_proxy_patch.yaml
-  # If you want your controller-manager to expose the /metrics
-  # endpoint w/o any authn/z, uncomment the following line and
-  # comment manager_auth_proxy_patch.yaml.
-  # Only one of manager_auth_proxy_patch.yaml and
-  # manager_prometheus_metrics_patch.yaml should be enabled.
+
+# If you want your controller-manager to expose the /metrics
+# endpoint w/o any authn/z, uncomment the following line and
+# comment manager_auth_proxy_patch.yaml.
+# Only one of manager_auth_proxy_patch.yaml and
+# manager_prometheus_metrics_patch.yaml should be enabled.
 #- manager_prometheus_metrics_patch.yaml
 
 # [WEBHOOK] To enable webhook, uncomment all the sections with [WEBHOOK] prefix including the one in crd/kustomization.yaml

config/default/manager_auth_proxy_patch.yaml

@@ -23,4 +23,3 @@ spec:
         args:
         - "--metrics-addr=127.0.0.1:8080"
         - "--enable-leader-election"
-        - "--sync-period=10m"

config/github-webhook-server/deployment.yaml

@@ -0,0 +1,37 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app.kubernetes.io/component: github-webhook-server
+    app.kubernetes.io/part-of: actions-runner-controller
+  name: github-webhook-server
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/component: github-webhook-server
+      app.kubernetes.io/part-of: actions-runner-controller
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/component: github-webhook-server
+        app.kubernetes.io/part-of: actions-runner-controller
+    spec:
+      containers:
+        - name: github-webhook-server
+          image: controller:latest
+          command:
+            - '/github-webhook-server'
+          env:
+            - name: GITHUB_WEBHOOK_SECRET_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  key: github_webhook_secret_token
+                  name: github-webhook-server
+                  optional: true
+          ports:
+            - containerPort: 8000
+              name: http
+              protocol: TCP
+      serviceAccountName: github-webhook-server
+      terminationGracePeriodSeconds: 10

config/github-webhook-server/gh-webhook-server-auth-proxy-patch.yaml

@@ -0,0 +1,23 @@
+# This patch injects an HTTP proxy sidecar container that performs RBAC
+# authorization against the Kubernetes API using SubjectAccessReviews.
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: github-webhook-server
+spec:
+  template:
+    spec:
+      containers:
+        - name: kube-rbac-proxy
+          image: quay.io/brancz/kube-rbac-proxy:v0.10.0
+          args:
+            - '--secure-listen-address=0.0.0.0:8443'
+            - '--upstream=http://127.0.0.1:8080/'
+            - '--logtostderr=true'
+            - '--v=10'
+          ports:
+            - containerPort: 8443
+              name: https
+        - name: github-webhook-server
+          args:
+            - '--metrics-addr=127.0.0.1:8080'

config/github-webhook-server/kustomization.yaml

@@ -0,0 +1,15 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+images:
+- name: controller
+  newName: summerwind/actions-runner-controller
+  newTag: latest
+
+resources:
+- deployment.yaml
+- rbac.yaml
+- service.yaml
+
+patchesStrategicMerge:
+- gh-webhook-server-auth-proxy-patch.yaml

config/github-webhook-server/rbac.yaml

@@ -0,0 +1,113 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  labels:
+    app.kubernetes.io/component: github-webhook-server
+    app.kubernetes.io/part-of: actions-runner-controller
+  name: github-webhook-server
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  labels:
+    app.kubernetes.io/component: github-webhook-server
+    app.kubernetes.io/part-of: actions-runner-controller
+  name: github-webhook-server
+rules:
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - horizontalrunnerautoscalers
+    verbs:
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - horizontalrunnerautoscalers/finalizers
+    verbs:
+      - create
+      - delete
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - horizontalrunnerautoscalers/status
+    verbs:
+      - get
+      - patch
+      - update
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - runnersets
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - runnerdeployments
+    verbs:
+      - create
+      - delete
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - runnerdeployments/finalizers
+    verbs:
+      - create
+      - delete
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - actions.summerwind.dev
+    resources:
+      - runnerdeployments/status
+    verbs:
+      - get
+      - patch
+      - update
+  - apiGroups:
+      - authentication.k8s.io
+    resources:
+      - tokenreviews
+    verbs:
+      - create
+  - apiGroups:
+      - authorization.k8s.io
+    resources:
+      - subjectaccessreviews
+    verbs:
+      - create
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  labels:
+    app.kubernetes.io/component: github-webhook-server
+    app.kubernetes.io/part-of: actions-runner-controller
+  name: github-webhook-server
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: github-webhook-server
+subjects:
+  - kind: ServiceAccount
+    name: github-webhook-server

config/github-webhook-server/service.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Service
+metadata:
+  labels:
+    app.kubernetes.io/component: github-webhook-server
+    app.kubernetes.io/part-of: actions-runner-controller
+  name: github-webhook-server
+spec:
+  ports:
+    - port: 80
+      targetPort: http
+      protocol: TCP
+      name: http
+  selector:
+    app.kubernetes.io/component: github-webhook-server
+    app.kubernetes.io/part-of: actions-runner-controller

config/rbac/role.yaml

@@ -202,6 +202,29 @@ rules:
   verbs:
   - create
   - patch
+- apiGroups:
+  - ""
+  resources:
+  - persistentvolumeclaims
+  verbs:
+  - create
+  - delete
+  - get
+  - list
+  - patch
+  - update
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - persistentvolumes
+  verbs:
+  - delete
+  - get
+  - list
+  - patch
+  - update
+  - watch
 - apiGroups:
   - ""
   resources:
@@ -226,3 +249,12 @@ rules:
   - patch
   - update
   - watch
+- apiGroups:
+  - ""
+  resources:
+  - secrets
+  verbs:
+  - delete
+  - get
+  - list
+  - watch

controllers/autoscaling.go

@@ -7,9 +7,11 @@ import (
 	"math"
 	"strconv"
 	"strings"
-	"time"
 
 	"github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
+	"github.com/google/go-github/v45/github"
+	corev1 "k8s.io/api/core/v1"
+	"sigs.k8s.io/controller-runtime/pkg/client"
 )
 
 const (
@@ -19,47 +21,6 @@ const (
 	defaultScaleDownFactor    = 0.7
 )
 
-func getValueAvailableAt(now time.Time, from, to *time.Time, reservedValue int) *int {
-	if to != nil && now.After(*to) {
-		return nil
-	}
-
-	if from != nil && now.Before(*from) {
-		return nil
-	}
-
-	return &reservedValue
-}
-
-func (r *HorizontalRunnerAutoscalerReconciler) fetchSuggestedReplicasFromCache(hra v1alpha1.HorizontalRunnerAutoscaler) *int {
-	var entry *v1alpha1.CacheEntry
-
-	for i := range hra.Status.CacheEntries {
-		ent := hra.Status.CacheEntries[i]
-
-		if ent.Key != v1alpha1.CacheEntryKeyDesiredReplicas {
-			continue
-		}
-
-		if !time.Now().Before(ent.ExpirationTime.Time) {
-			continue
-		}
-
-		entry = &ent
-
-		break
-	}
-
-	if entry != nil {
-		v := getValueAvailableAt(time.Now(), nil, &entry.ExpirationTime.Time, entry.Value)
-		if v != nil {
-			return v
-		}
-	}
-
-	return nil
-}
-
 func (r *HorizontalRunnerAutoscalerReconciler) suggestDesiredReplicas(st scaleTarget, hra v1alpha1.HorizontalRunnerAutoscaler) (*int, error) {
 	if hra.Spec.MinReplicas == nil {
 		return nil, fmt.Errorf("horizontalrunnerautoscaler %s/%s is missing minReplicas", hra.Namespace, hra.Name)
@@ -70,13 +31,11 @@ func (r *HorizontalRunnerAutoscalerReconciler) suggestDesiredReplicas(st scaleTa
 	metrics := hra.Spec.Metrics
 	numMetrics := len(metrics)
 	if numMetrics == 0 {
-		if len(hra.Spec.ScaleUpTriggers) == 0 {
-			return r.suggestReplicasByQueuedAndInProgressWorkflowRuns(st, hra, nil)
-		}
-
+		// We don't default to anything since ARC 0.23.0
+		// See https://github.com/actions-runner-controller/actions-runner-controller/issues/728
 		return nil, nil
 	} else if numMetrics > 2 {
-		return nil, fmt.Errorf("Too many autoscaling metrics configured: It must be 0 to 2, but got %d", numMetrics)
+		return nil, fmt.Errorf("too many autoscaling metrics configured: It must be 0 to 2, but got %d", numMetrics)
 	}
 
 	primaryMetric := metrics[0]
@@ -93,7 +52,7 @@ func (r *HorizontalRunnerAutoscalerReconciler) suggestDesiredReplicas(st scaleTa
 	case v1alpha1.AutoscalingMetricTypePercentageRunnersBusy:
 		suggested, err = r.suggestReplicasByPercentageRunnersBusy(st, hra, primaryMetric)
 	default:
-		return nil, fmt.Errorf("validting autoscaling metrics: unsupported metric type %q", primaryMetric)
+		return nil, fmt.Errorf("validating autoscaling metrics: unsupported metric type %q", primaryMetric)
 	}
 
 	if err != nil {
@@ -164,14 +123,46 @@ func (r *HorizontalRunnerAutoscalerReconciler) suggestReplicasByQueuedAndInProgr
 			fallback_cb()
 			return
 		}
-		jobs, _, err := r.GitHubClient.Actions.ListWorkflowJobs(context.TODO(), user, repoName, runID, nil)
-		if err != nil {
-			r.Log.Error(err, "Error listing workflow jobs")
-			fallback_cb()
-		} else if len(jobs.Jobs) == 0 {
+		opt := github.ListWorkflowJobsOptions{ListOptions: github.ListOptions{PerPage: 50}}
+		var allJobs []*github.WorkflowJob
+		for {
+			jobs, resp, err := r.GitHubClient.Actions.ListWorkflowJobs(context.TODO(), user, repoName, runID, &opt)
+			if err != nil {
+				r.Log.Error(err, "Error listing workflow jobs")
+				return //err
+			}
+			allJobs = append(allJobs, jobs.Jobs...)
+			if resp.NextPage == 0 {
+				break
+			}
+			opt.Page = resp.NextPage
+		}
+		if len(allJobs) == 0 {
 			fallback_cb()
 		} else {
-			for _, job := range jobs.Jobs {
+		JOB:
+			for _, job := range allJobs {
+				runnerLabels := make(map[string]struct{}, len(st.labels))
+				for _, l := range st.labels {
+					runnerLabels[l] = struct{}{}
+				}
+
+				if len(job.Labels) == 0 {
+					// This shouldn't usually happen
+					r.Log.Info("Detected job with no labels, which is not supported by ARC. Skipping anyway.", "labels", job.Labels, "run_id", job.GetRunID(), "job_id", job.GetID())
+					continue JOB
+				}
+
+				for _, l := range job.Labels {
+					if l == "self-hosted" {
+						continue
+					}
+
+					if _, ok := runnerLabels[l]; !ok {
+						continue JOB
+					}
+				}
+
 				switch job.GetStatus() {
 				case "completed":
 					// We add a case for `completed` so it is not counted in `unknown`.
@@ -325,22 +316,52 @@ func (r *HorizontalRunnerAutoscalerReconciler) suggestReplicasByPercentageRunner
 		numRunners           int
 		numRunnersRegistered int
 		numRunnersBusy       int
+		numTerminatingBusy   int
 	)
 
 	numRunners = len(runnerMap)
 
+	busyTerminatingRunnerPods := map[string]struct{}{}
+
+	kindLabel := LabelKeyRunnerDeploymentName
+	if hra.Spec.ScaleTargetRef.Kind == "RunnerSet" {
+		kindLabel = LabelKeyRunnerSetName
+	}
+
+	var runnerPodList corev1.PodList
+	if err := r.Client.List(ctx, &runnerPodList, client.InNamespace(hra.Namespace), client.MatchingLabels(map[string]string{
+		kindLabel: hra.Spec.ScaleTargetRef.Name,
+	})); err != nil {
+		return nil, err
+	}
+
+	for _, p := range runnerPodList.Items {
+		if p.Annotations[AnnotationKeyUnregistrationFailureMessage] != "" {
+			busyTerminatingRunnerPods[p.Name] = struct{}{}
+		}
+	}
+
 	for _, runner := range runners {
 		if _, ok := runnerMap[*runner.Name]; ok {
 			numRunnersRegistered++
 
 			if runner.GetBusy() {
 				numRunnersBusy++
+			} else if _, ok := busyTerminatingRunnerPods[*runner.Name]; ok {
+				numTerminatingBusy++
 			}
+
+			delete(busyTerminatingRunnerPods, *runner.Name)
 		}
 	}
 
+	// Remaining busyTerminatingRunnerPods are runners that were not on the ListRunners API response yet
+	for range busyTerminatingRunnerPods {
+		numTerminatingBusy++
+	}
+
 	var desiredReplicas int
-	fractionBusy := float64(numRunnersBusy) / float64(desiredReplicasBefore)
+	fractionBusy := float64(numRunnersBusy+numTerminatingBusy) / float64(desiredReplicasBefore)
 	if fractionBusy >= scaleUpThreshold {
 		if scaleUpAdjustment > 0 {
 			desiredReplicas = desiredReplicasBefore + scaleUpAdjustment
@@ -369,6 +390,7 @@ func (r *HorizontalRunnerAutoscalerReconciler) suggestReplicasByPercentageRunner
 		"num_runners", numRunners,
 		"num_runners_registered", numRunnersRegistered,
 		"num_runners_busy", numRunnersBusy,
+		"num_terminating_busy", numTerminatingBusy,
 		"namespace", hra.Namespace,
 		"kind", st.kind,
 		"name", st.st,

controllers/autoscaling_test.go

@@ -41,8 +41,12 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 
 	metav1Now := metav1.Now()
 	testcases := []struct {
-		repo      string
-		org       string
+		description string
+
+		repo   string
+		org    string
+		labels []string
+
 		fixed     *int
 		max       *int
 		min       *int
@@ -68,6 +72,19 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"status":"in_progress"}, {"status":"in_progress"}]}"`,
 			want:                     3,
 		},
+		// Explicitly speified the default `self-hosted` label which is ignored by the simulator,
+		// as we assume that GitHub Actions automatically associates the `self-hosted` label to every self-hosted runner.
+		// 3 demanded, max at 3
+		{
+			repo:                     "test/valid",
+			labels:                   []string{"self-hosted"},
+			min:                      intPtr(2),
+			max:                      intPtr(3),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"status":"queued"}, {"status":"in_progress"}, {"status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"status":"in_progress"}, {"status":"in_progress"}]}"`,
+			want:                     3,
+		},
 		// 2 demanded, max at 3, currently 3, delay scaling down due to grace period
 		{
 			repo:                     "test/valid",
@@ -152,9 +169,40 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 			want:                     3,
 		},
 
-		// Job-level autoscaling
-		// 5 requested from 3 workflows
 		{
+			description:              "Job-level autoscaling with no explicit runner label (runners have implicit self-hosted, requested self-hosted, 5 jobs from 3 workflows)",
+			repo:                     "test/valid",
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted"]}, {"status":"queued", "labels":["self-hosted"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted"]}, {"status":"completed", "labels":["self-hosted"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted"]}, {"status":"queued", "labels":["self-hosted"]}]}`,
+			},
+			want: 5,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling with no explicit runner label (runners have implicit self-hosted, requested self-hosted+custom, 0 jobs from 3 workflows)",
+			repo:                     "test/valid",
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 2,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling with no label (runners have implicit self-hosted, jobs had no labels, 0 jobs from 3 workflows)",
 			repo:                     "test/valid",
 			min:                      intPtr(2),
 			max:                      intPtr(10),
@@ -166,6 +214,91 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 				2: `{"jobs": [{"status": "in_progress"}, {"status":"completed"}]}`,
 				3: `{"jobs": [{"status": "in_progress"}, {"status":"queued"}]}`,
 			},
+			want: 2,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling with default runner label (runners have self-hosted only, requested self-hosted+custom, 0 jobs from 3 workflows)",
+			repo:                     "test/valid",
+			labels:                   []string{"self-hosted"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 2,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling with custom runner label (runners have custom2, requested self-hosted+custom, 0 jobs from 5 workflows",
+			repo:                     "test/valid",
+			labels:                   []string{"custom2"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 2,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling with default runner label (runners have self-hosted, requested managed-runner-label, 0 jobs from 3 runs)",
+			repo:                     "test/valid",
+			labels:                   []string{"self-hosted"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["managed-runner-label"]}, {"status":"queued", "labels":["managed-runner-label"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["managed-runner-label"]}, {"status":"completed", "labels":["managed-runner-label"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["managed-runner-label"]}, {"status":"queued", "labels":["managed-runner-label"]}]}`,
+			},
+			want: 2,
+		},
+
+		{
+			description:              "Job-level autoscaling with default + custom runner label (runners have self-hosted+custom, requested self-hosted+custom, 5 jobs from 3 workflows)",
+			repo:                     "test/valid",
+			labels:                   []string{"self-hosted", "custom"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 5,
+		},
+
+		{
+			description:              "Job-level autoscaling with custom runner label (runners have custom, requested self-hosted+custom, 5 jobs from 3 workflows)",
+			repo:                     "test/valid",
+			labels:                   []string{"custom"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
 			want: 5,
 		},
 	}
@@ -181,7 +314,12 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 		_ = clientgoscheme.AddToScheme(scheme)
 		_ = v1alpha1.AddToScheme(scheme)
 
-		t.Run(fmt.Sprintf("case %d", i), func(t *testing.T) {
+		testName := fmt.Sprintf("case %d", i)
+		if tc.description != "" {
+			testName = tc.description
+		}
+
+		t.Run(testName, func(t *testing.T) {
 			server := fake.NewServer(
 				fake.WithListRepositoryWorkflowRunsResponse(200, tc.workflowRuns, tc.workflowRuns_queued, tc.workflowRuns_in_progress),
 				fake.WithListWorkflowJobsResponse(200, tc.workflowJobs),
@@ -191,9 +329,10 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 			client := newGithubClient(server)
 
 			h := &HorizontalRunnerAutoscalerReconciler{
-				Log:          log,
-				GitHubClient: client,
-				Scheme:       scheme,
+				Log:                   log,
+				GitHubClient:          client,
+				Scheme:                scheme,
+				DefaultScaleDownDelay: DefaultScaleDownDelay,
 			}
 
 			rd := v1alpha1.RunnerDeployment{
@@ -206,6 +345,7 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 						Spec: v1alpha1.RunnerSpec{
 							RunnerConfig: v1alpha1.RunnerConfig{
 								Repository: tc.repo,
+								Labels:     tc.labels,
 							},
 						},
 					},
@@ -220,6 +360,11 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 				Spec: v1alpha1.HorizontalRunnerAutoscalerSpec{
 					MaxReplicas: tc.max,
 					MinReplicas: tc.min,
+					Metrics: []v1alpha1.MetricSpec{
+						{
+							Type: "TotalNumberOfQueuedAndInProgressWorkflowRuns",
+						},
+					},
 				},
 				Status: v1alpha1.HorizontalRunnerAutoscalerStatus{
 					DesiredReplicas:            tc.sReplicas,
@@ -234,7 +379,7 @@ func TestDetermineDesiredReplicas_RepositoryRunner(t *testing.T) {
 
 			st := h.scaleTargetFromRD(context.Background(), rd)
 
-			got, _, _, err := h.computeReplicasWithCache(log, metav1Now.Time, st, hra, minReplicas)
+			got, err := h.computeReplicasWithCache(log, metav1Now.Time, st, hra, minReplicas)
 			if err != nil {
 				if tc.err == "" {
 					t.Fatalf("unexpected error: expected none, got %v", err)
@@ -258,8 +403,12 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 
 	metav1Now := metav1.Now()
 	testcases := []struct {
-		repos     []string
-		org       string
+		description string
+
+		repos  []string
+		org    string
+		labels []string
+
 		fixed     *int
 		max       *int
 		min       *int
@@ -399,9 +548,43 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 			err:                      "validating autoscaling metrics: spec.autoscaling.metrics[].repositoryNames is required and must have one more more entries for organizational runner deployment",
 		},
 
-		// Job-level autoscaling
-		// 5 requested from 3 workflows
 		{
+			description:              "Job-level autoscaling (runners have implicit self-hosted, requested self-hosted, 5 jobs from 3 runs)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted"]}, {"status":"queued", "labels":["self-hosted"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted"]}, {"status":"completed", "labels":["self-hosted"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted"]}, {"status":"queued", "labels":["self-hosted"]}]}`,
+			},
+			want: 5,
+		},
+
+		{
+			description:              "Job-level autoscaling (runners have explicit self-hosted, requested self-hosted, 5 jobs from 3 runs)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			labels:                   []string{"self-hosted"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted"]}, {"status":"queued", "labels":["self-hosted"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted"]}, {"status":"completed", "labels":["self-hosted"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted"]}, {"status":"queued", "labels":["self-hosted"]}]}`,
+			},
+			want: 5,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling (jobs lack labels, 0 requested from 3 workflows)",
 			org:                      "test",
 			repos:                    []string{"valid"},
 			min:                      intPtr(2),
@@ -414,8 +597,97 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 				2: `{"jobs": [{"status": "in_progress"}, {"status":"completed"}]}`,
 				3: `{"jobs": [{"status": "in_progress"}, {"status":"queued"}]}`,
 			},
+			want: 2,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling (runners have valid and implicit self-hosted, requested self-hosted+custom, 0 jobs from 3 runs)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 2,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling (runners have self-hosted, requested self-hosted+custom, 0 jobs from 3 workflows)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			labels:                   []string{"self-hosted"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 2,
+		},
+
+		{
+			description:              "Job-level autoscaling (runners have custom, requested self-hosted+custom, 5 requested from 3 workflows)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			labels:                   []string{"custom"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
 			want: 5,
 		},
+
+		{
+			description:              "Job-level autoscaling (runners have custom, requested custom, 5 requested from 3 workflows)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			labels:                   []string{"custom"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["custom"]}, {"status":"queued", "labels":["custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["custom"]}, {"status":"completed", "labels":["custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["custom"]}, {"status":"queued", "labels":["custom"]}]}`,
+			},
+			want: 5,
+		},
+
+		{
+			description:              "Skipped job-level autoscaling (specified custom2, 0 requested from 3 workflows)",
+			org:                      "test",
+			repos:                    []string{"valid"},
+			labels:                   []string{"custom2"},
+			min:                      intPtr(2),
+			max:                      intPtr(10),
+			workflowRuns:             `{"total_count": 4, "workflow_runs":[{"id": 1, "status":"queued"}, {"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowRuns_queued:      `{"total_count": 1, "workflow_runs":[{"id": 1, "status":"queued"}]}"`,
+			workflowRuns_in_progress: `{"total_count": 2, "workflow_runs":[{"id": 2, "status":"in_progress"}, {"id": 3, "status":"in_progress"}, {"status":"completed"}]}"`,
+			workflowJobs: map[int]string{
+				1: `{"jobs": [{"status":"queued", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+				2: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"completed", "labels":["self-hosted", "custom"]}]}`,
+				3: `{"jobs": [{"status": "in_progress", "labels":["self-hosted", "custom"]}, {"status":"queued", "labels":["self-hosted", "custom"]}]}`,
+			},
+			want: 2,
+		},
 	}
 
 	for i := range testcases {
@@ -429,7 +701,12 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 		_ = clientgoscheme.AddToScheme(scheme)
 		_ = v1alpha1.AddToScheme(scheme)
 
-		t.Run(fmt.Sprintf("case %d", i), func(t *testing.T) {
+		testName := fmt.Sprintf("case %d", i)
+		if tc.description != "" {
+			testName = tc.description
+		}
+
+		t.Run(testName, func(t *testing.T) {
 			t.Helper()
 
 			server := fake.NewServer(
@@ -441,9 +718,10 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 			client := newGithubClient(server)
 
 			h := &HorizontalRunnerAutoscalerReconciler{
-				Log:          log,
-				Scheme:       scheme,
-				GitHubClient: client,
+				Log:                   log,
+				Scheme:                scheme,
+				GitHubClient:          client,
+				DefaultScaleDownDelay: DefaultScaleDownDelay,
 			}
 
 			rd := v1alpha1.RunnerDeployment{
@@ -465,6 +743,7 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 						Spec: v1alpha1.RunnerSpec{
 							RunnerConfig: v1alpha1.RunnerConfig{
 								Organization: tc.org,
+								Labels:       tc.labels,
 							},
 						},
 					},
@@ -502,7 +781,7 @@ func TestDetermineDesiredReplicas_OrganizationalRunner(t *testing.T) {
 
 			st := h.scaleTargetFromRD(context.Background(), rd)
 
-			got, _, _, err := h.computeReplicasWithCache(log, metav1Now.Time, st, hra, minReplicas)
+			got, err := h.computeReplicasWithCache(log, metav1Now.Time, st, hra, minReplicas)
 			if err != nil {
 				if tc.err == "" {
 					t.Fatalf("unexpected error: expected none, got %v", err)

controllers/constants.go

@@ -0,0 +1,72 @@
+package controllers
+
+import "time"
+
+const (
+	LabelKeyRunnerSetName = "runnerset-name"
+	LabelKeyRunner        = "actions-runner"
+)
+
+const (
+	// This names requires at least one slash to work.
+	// See https://github.com/google/knative-gcp/issues/378
+	runnerPodFinalizerName             = "actions.summerwind.dev/runner-pod"
+	runnerLinkedResourcesFinalizerName = "actions.summerwind.dev/linked-resources"
+
+	annotationKeyPrefix = "actions-runner/"
+
+	AnnotationKeyLastRegistrationCheckTime = "actions-runner-controller/last-registration-check-time"
+
+	// AnnotationKeyUnregistrationFailureMessage is the annotation that is added onto the pod once it failed to be unregistered from GitHub due to e.g. 422 error
+	AnnotationKeyUnregistrationFailureMessage = annotationKeyPrefix + "unregistration-failure-message"
+
+	// AnnotationKeyUnregistrationCompleteTimestamp is the annotation that is added onto the pod once the previously started unregistration process has been completed.
+	AnnotationKeyUnregistrationCompleteTimestamp = annotationKeyPrefix + "unregistration-complete-timestamp"
+
+	// AnnotationKeyRunnerCompletionWaitStartTimestamp is the annotation that is added onto the pod when
+	// ARC decided to wait until the pod to complete by itself, without the need for ARC to unregister the corresponding runner.
+	AnnotationKeyRunnerCompletionWaitStartTimestamp = annotationKeyPrefix + "runner-completion-wait-start-timestamp"
+
+	// unregistarionStartTimestamp is the annotation that contains the time that the requested unregistration process has been started
+	AnnotationKeyUnregistrationStartTimestamp = annotationKeyPrefix + "unregistration-start-timestamp"
+
+	// AnnotationKeyUnregistrationRequestTimestamp is the annotation that contains the time that the unregistration has been requested.
+	// This doesn't immediately start the unregistration. Instead, ARC will first check if the runner has already been registered.
+	// If not, ARC will hold on until the registration to complete first, and only after that it starts the unregistration process.
+	// This is crucial to avoid a race between ARC marking the runner pod for deletion while the actions-runner registers itself to GitHub, leaving the assigned job
+	// hang like forever.
+	AnnotationKeyUnregistrationRequestTimestamp = annotationKeyPrefix + "unregistration-request-timestamp"
+
+	AnnotationKeyRunnerID = annotationKeyPrefix + "id"
+
+	// This can be any value but a larger value can make an unregistration timeout longer than configured in practice.
+	DefaultUnregistrationRetryDelay = time.Minute
+
+	// RetryDelayOnCreateRegistrationError is the delay between retry attempts for runner registration token creation.
+	// Usually, a retry in this case happens when e.g. your PAT has no access to certain scope of runners, like you're using repository admin's token
+	// for creating a broader scoped runner token, like organizationa or enterprise runner token.
+	// Such permission issue will never fixed automatically, so we don't need to retry so often, hence this value.
+	RetryDelayOnCreateRegistrationError = 3 * time.Minute
+
+	// registrationTimeout is the duration until a pod times out after it becomes Ready and Running.
+	// A pod that is timed out can be terminated if needed.
+	registrationTimeout = 10 * time.Minute
+
+	// DefaultRunnerPodRecreationDelayAfterWebhookScale is the delay until syncing the runners with the desired replicas
+	// after a webhook-based scale up.
+	// This is used to prevent ARC from recreating completed runner pods that are deleted soon without being used at all.
+	// In other words, this is used as a timer to wait for the completed runner to emit the next `workflow_job` webhook event to decrease the desired replicas.
+	// So if we set 30 seconds for this, you are basically saying that you would assume GitHub and your installation of ARC to
+	// emit and propagate a workflow_job completion event down to the RunnerSet or RunnerReplicaSet, vha ARC's github webhook server and HRA, in approximately 30 seconds.
+	// In case it actually took more than DefaultRunnerPodRecreationDelayAfterWebhookScale for the workflow_job completion event to arrive,
+	// ARC will recreate the completed runner(s), assuming something went wrong in either GitHub, your K8s cluster, or ARC, so ARC needs to resync anyway.
+	//
+	// See https://github.com/actions-runner-controller/actions-runner-controller/pull/1180
+	DefaultRunnerPodRecreationDelayAfterWebhookScale = 10 * time.Minute
+
+	EnvVarRunnerName  = "RUNNER_NAME"
+	EnvVarRunnerToken = "RUNNER_TOKEN"
+
+	// defaultHookPath is path to the hook script used when the "containerMode: kubernetes" is specified
+	defaultRunnerHookPath = "/runner/k8s/index.js"
+)

controllers/horizontal_runner_autoscaler_batch_scale.go

@@ -0,0 +1,207 @@
+package controllers
+
+import (
+	"context"
+	"fmt"
+	"sync"
+	"time"
+
+	"github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
+	"github.com/go-logr/logr"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/apimachinery/pkg/types"
+	"sigs.k8s.io/controller-runtime/pkg/client"
+)
+
+type batchScaler struct {
+	Ctx      context.Context
+	Client   client.Client
+	Log      logr.Logger
+	interval time.Duration
+
+	queue       chan *ScaleTarget
+	workerStart sync.Once
+}
+
+func newBatchScaler(ctx context.Context, client client.Client, log logr.Logger) *batchScaler {
+	return &batchScaler{
+		Ctx:      ctx,
+		Client:   client,
+		Log:      log,
+		interval: 3 * time.Second,
+	}
+}
+
+type batchScaleOperation struct {
+	namespacedName types.NamespacedName
+	scaleOps       []scaleOperation
+}
+
+type scaleOperation struct {
+	trigger v1alpha1.ScaleUpTrigger
+	log     logr.Logger
+}
+
+// Add the scale target to the unbounded queue, blocking until the target is successfully added to the queue.
+// All the targets in the queue are dequeued every 3 seconds, grouped by the HRA, and applied.
+// In a happy path, batchScaler update each HRA only once, even though the HRA had two or more associated webhook events in the 3 seconds interval,
+// which results in less K8s API calls and less HRA update conflicts in case your ARC installation receives a lot of webhook events
+func (s *batchScaler) Add(st *ScaleTarget) {
+	if st == nil {
+		return
+	}
+
+	s.workerStart.Do(func() {
+		var expBackoff = []time.Duration{time.Second, 2 * time.Second, 4 * time.Second, 8 * time.Second, 16 * time.Second}
+
+		s.queue = make(chan *ScaleTarget)
+
+		log := s.Log
+
+		go func() {
+			log.Info("Starting batch worker")
+			defer log.Info("Stopped batch worker")
+
+			for {
+				select {
+				case <-s.Ctx.Done():
+					return
+				default:
+				}
+
+				log.V(2).Info("Batch worker is dequeueing operations")
+
+				batches := map[types.NamespacedName]batchScaleOperation{}
+				after := time.After(s.interval)
+				var ops uint
+
+			batch:
+				for {
+					select {
+					case <-after:
+						after = nil
+						break batch
+					case st := <-s.queue:
+						nsName := types.NamespacedName{
+							Namespace: st.HorizontalRunnerAutoscaler.Namespace,
+							Name:      st.HorizontalRunnerAutoscaler.Name,
+						}
+						b, ok := batches[nsName]
+						if !ok {
+							b = batchScaleOperation{
+								namespacedName: nsName,
+							}
+						}
+						b.scaleOps = append(b.scaleOps, scaleOperation{
+							log:     *st.log,
+							trigger: st.ScaleUpTrigger,
+						})
+						batches[nsName] = b
+						ops++
+					}
+				}
+
+				log.V(2).Info("Batch worker dequeued operations", "ops", ops, "batches", len(batches))
+
+			retry:
+				for i := 0; ; i++ {
+					failed := map[types.NamespacedName]batchScaleOperation{}
+
+					for nsName, b := range batches {
+						b := b
+						if err := s.batchScale(context.Background(), b); err != nil {
+							log.V(2).Info("Failed to scale due to error", "error", err)
+							failed[nsName] = b
+						} else {
+							log.V(2).Info("Successfully ran batch scale", "hra", b.namespacedName)
+						}
+					}
+
+					if len(failed) == 0 {
+						break retry
+					}
+
+					batches = failed
+
+					delay := 16 * time.Second
+					if i < len(expBackoff) {
+						delay = expBackoff[i]
+					}
+					time.Sleep(delay)
+				}
+			}
+		}()
+	})
+
+	s.queue <- st
+}
+
+func (s *batchScaler) batchScale(ctx context.Context, batch batchScaleOperation) error {
+	var hra v1alpha1.HorizontalRunnerAutoscaler
+
+	if err := s.Client.Get(ctx, batch.namespacedName, &hra); err != nil {
+		return err
+	}
+
+	copy := hra.DeepCopy()
+
+	copy.Spec.CapacityReservations = getValidCapacityReservations(copy)
+
+	var added, completed int
+
+	for _, scale := range batch.scaleOps {
+		amount := 1
+
+		if scale.trigger.Amount != 0 {
+			amount = scale.trigger.Amount
+		}
+
+		scale.log.V(2).Info("Adding capacity reservation", "amount", amount)
+
+		if amount > 0 {
+			now := time.Now()
+			copy.Spec.CapacityReservations = append(copy.Spec.CapacityReservations, v1alpha1.CapacityReservation{
+				EffectiveTime:  metav1.Time{Time: now},
+				ExpirationTime: metav1.Time{Time: now.Add(scale.trigger.Duration.Duration)},
+				Replicas:       amount,
+			})
+
+			added += amount
+		} else if amount < 0 {
+			var reservations []v1alpha1.CapacityReservation
+
+			var found bool
+
+			for _, r := range copy.Spec.CapacityReservations {
+				if !found && r.Replicas+amount == 0 {
+					found = true
+				} else {
+					reservations = append(reservations, r)
+				}
+			}
+
+			copy.Spec.CapacityReservations = reservations
+
+			completed += amount
+		}
+	}
+
+	before := len(hra.Spec.CapacityReservations)
+	expired := before - len(copy.Spec.CapacityReservations)
+	after := len(copy.Spec.CapacityReservations)
+
+	s.Log.V(1).Info(
+		fmt.Sprintf("Updating hra %s for capacityReservations update", hra.Name),
+		"before", before,
+		"expired", expired,
+		"added", added,
+		"completed", completed,
+		"after", after,
+	)
+
+	if err := s.Client.Update(ctx, copy); err != nil {
+		return fmt.Errorf("updating horizontalrunnerautoscaler to add capacity reservation: %w", err)
+	}
+
+	return nil
+}

controllers/horizontal_runner_autoscaler_webhook.go

@@ -18,28 +18,36 @@ package controllers
 
 import (
 	"context"
+	"encoding/json"
 	"fmt"
 	"io/ioutil"
 	"net/http"
 	"strings"
+	"sync"
 	"time"
 
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/types"
 	"sigs.k8s.io/controller-runtime/pkg/reconcile"
 
 	"github.com/go-logr/logr"
-	gogithub "github.com/google/go-github/v37/github"
+	gogithub "github.com/google/go-github/v45/github"
 	"k8s.io/apimachinery/pkg/runtime"
 	"k8s.io/client-go/tools/record"
 	ctrl "sigs.k8s.io/controller-runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 
 	"github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
+	"github.com/actions-runner-controller/actions-runner-controller/github"
+	"github.com/actions-runner-controller/actions-runner-controller/simulator"
 )
 
 const (
 	scaleTargetKey = "scaleTarget"
+
+	keyPrefixEnterprise = "enterprises/"
+	keyRunnerGroup      = "/group/"
+
+	DefaultQueueLimit = 100
 )
 
 // HorizontalRunnerAutoscalerGitHubWebhook autoscales a HorizontalRunnerAutoscaler and the RunnerDeployment on each
@@ -54,11 +62,23 @@ type HorizontalRunnerAutoscalerGitHubWebhook struct {
 	// the administrator is generated and specified in GitHub Web UI.
 	SecretKeyBytes []byte
 
+	// GitHub Client to discover runner groups assigned to a repository
+	GitHubClient *github.Client
+
 	// Namespace is the namespace to watch for HorizontalRunnerAutoscaler's to be
 	// scaled on Webhook.
 	// Set to empty for letting it watch for all namespaces.
 	Namespace string
 	Name      string
+
+	// QueueLimit is the maximum length of the bounded queue of scale targets and their associated operations
+	// A scale target is enqueued on each retrieval of each eligible webhook event, so that it is processed asynchronously.
+	QueueLimit int
+
+	worker      *worker
+	workerInit  sync.Once
+	workerStart sync.Once
+	batchCh     chan *ScaleTarget
 }
 
 func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Reconcile(_ context.Context, request reconcile.Request) (reconcile.Result, error) {
@@ -84,7 +104,7 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 			if err != nil {
 				msg := err.Error()
 				if written, err := w.Write([]byte(msg)); err != nil {
-					autoscaler.Log.Error(err, "failed writing http error response", "msg", msg, "written", written)
+					autoscaler.Log.V(1).Error(err, "failed writing http error response", "msg", msg, "written", written)
 				}
 			}
 		}
@@ -98,6 +118,7 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 
 	// respond ok to GET / e.g. for health check
 	if r.Method == http.MethodGet {
+		ok = true
 		fmt.Fprintln(w, "webhook server is running")
 		return
 	}
@@ -141,6 +162,20 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 		"delivery", r.Header.Get("X-GitHub-Delivery"),
 	)
 
+	var enterpriseEvent struct {
+		Enterprise struct {
+			Slug string `json:"slug,omitempty"`
+		} `json:"enterprise,omitempty"`
+	}
+	if err := json.Unmarshal(payload, &enterpriseEvent); err != nil {
+		var s string
+		if payload != nil {
+			s = string(payload)
+		}
+		autoscaler.Log.Error(err, "could not parse webhook payload for extracting enterprise slug", "webhookType", webhookType, "payload", s)
+	}
+	enterpriseSlug := enterpriseEvent.Enterprise.Slug
+
 	switch e := event.(type) {
 	case *gogithub.PushEvent:
 		target, err = autoscaler.getScaleUpTarget(
@@ -149,6 +184,9 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 			e.Repo.GetName(),
 			e.Repo.Owner.GetLogin(),
 			e.Repo.Owner.GetType(),
+			// Most go-github Event types don't seem to contain Enteprirse(.Slug) fields
+			// we need, so we parse it by ourselves.
+			enterpriseSlug,
 			autoscaler.MatchPushEvent(e),
 		)
 	case *gogithub.PullRequestEvent:
@@ -158,6 +196,9 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 			e.Repo.GetName(),
 			e.Repo.Owner.GetLogin(),
 			e.Repo.Owner.GetType(),
+			// Most go-github Event types don't seem to contain Enteprirse(.Slug) fields
+			// we need, so we parse it by ourselves.
+			enterpriseSlug,
 			autoscaler.MatchPullRequestEvent(e),
 		)
 
@@ -174,6 +215,9 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 			e.Repo.GetName(),
 			e.Repo.Owner.GetLogin(),
 			e.Repo.Owner.GetType(),
+			// Most go-github Event types don't seem to contain Enteprirse(.Slug) fields
+			// we need, so we parse it by ourselves.
+			enterpriseSlug,
 			autoscaler.MatchCheckRunEvent(e),
 		)
 
@@ -191,13 +235,14 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 				"repository.name", e.Repo.GetName(),
 				"repository.owner.login", e.Repo.Owner.GetLogin(),
 				"repository.owner.type", e.Repo.Owner.GetType(),
+				"enterprise.slug", enterpriseSlug,
 				"action", e.GetAction(),
 			)
 		}
 
 		labels := e.WorkflowJob.Labels
 
-		switch e.GetAction() {
+		switch action := e.GetAction(); action {
 		case "queued", "completed":
 			target, err = autoscaler.getJobScaleUpTargetForRepoOrOrg(
 				context.TODO(),
@@ -205,22 +250,34 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 				e.Repo.GetName(),
 				e.Repo.Owner.GetLogin(),
 				e.Repo.Owner.GetType(),
+				enterpriseSlug,
 				labels,
 			)
-
-			if target != nil {
-				if e.GetAction() == "queued" {
-					target.Amount = 1
-				} else if e.GetAction() == "completed" {
-					// A nagative amount is processed in the tryScale func as a scale-down request,
-					// that erasese the oldest CapacityReservation with the same amount.
-					// If the first CapacityReservation was with Replicas=1, this negative scale target erases that,
-					// so that the resulting desired replicas decreases by 1.
-					target.Amount = -1
-				}
+			if target == nil {
+				break
 			}
-		default:
 
+			if e.GetAction() == "queued" {
+				target.Amount = 1
+				break
+			} else if e.GetAction() == "completed" && e.GetWorkflowJob().GetConclusion() != "skipped" {
+				// A nagative amount is processed in the tryScale func as a scale-down request,
+				// that erasese the oldest CapacityReservation with the same amount.
+				// If the first CapacityReservation was with Replicas=1, this negative scale target erases that,
+				// so that the resulting desired replicas decreases by 1.
+				target.Amount = -1
+				break
+			}
+			// If the conclusion is "skipped", we will ignore it and fallthrough to the default case.
+			fallthrough
+		default:
+			ok = true
+
+			w.WriteHeader(http.StatusOK)
+
+			log.V(2).Info("Received and ignored a workflow_job event as it triggers neither scale-up nor scale-down", "action", action)
+
+			return
 		}
 	case *gogithub.PingEvent:
 		ok = true
@@ -249,7 +306,7 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 	}
 
 	if target == nil {
-		log.Info(
+		log.V(1).Info(
 			"Scale target not found. If this is unexpected, ensure that there is exactly one repository-wide or organizational runner deployment that matches this webhook event",
 		)
 
@@ -266,9 +323,19 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) Handle(w http.Respons
 		return
 	}
 
-	if err := autoscaler.tryScale(context.TODO(), target); err != nil {
-		log.Error(err, "could not scale up")
+	autoscaler.workerInit.Do(func() {
+		batchScaler := newBatchScaler(context.Background(), autoscaler.Client, autoscaler.Log)
 
+		queueLimit := autoscaler.QueueLimit
+		if queueLimit == 0 {
+			queueLimit = DefaultQueueLimit
+		}
+		autoscaler.worker = newWorker(context.Background(), queueLimit, batchScaler.Add)
+	})
+
+	target.log = &log
+	if ok := autoscaler.worker.Add(target); !ok {
+		log.Error(err, "Could not scale up due to queue full")
 		return
 	}
 
@@ -310,9 +377,7 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) findHRAsByKey(ctx con
 			return nil, err
 		}
 
-		for _, d := range hraList.Items {
-			hras = append(hras, d)
-		}
+		hras = append(hras, hraList.Items...)
 	}
 
 	return hras, nil
@@ -339,6 +404,8 @@ func matchTriggerConditionAgainstEvent(types []string, eventAction *string) bool
 type ScaleTarget struct {
 	v1alpha1.HorizontalRunnerAutoscaler
 	v1alpha1.ScaleUpTrigger
+
+	log *logr.Logger
 }
 
 func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) searchScaleTargets(hras []v1alpha1.HorizontalRunnerAutoscaler, f func(v1alpha1.ScaleUpTrigger) bool) []ScaleTarget {
@@ -391,7 +458,7 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getScaleTarget(ctx co
 			"Found too many scale targets: "+
 				"It must be exactly one to avoid ambiguity. "+
 				"Either set Namespace for the webhook-based autoscaler to let it only find HRAs in the namespace, "+
-				"or update Repository or Organization fields in your RunnerDeployment resources to fix the ambiguity.",
+				"or update Repository, Organization, or Enterprise fields in your RunnerDeployment resources to fix the ambiguity.",
 			"scaleTargets", strings.Join(scaleTargetIDs, ","))
 
 		return nil, nil
@@ -400,44 +467,31 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getScaleTarget(ctx co
 	return &targets[0], nil
 }
 
-func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getScaleUpTarget(ctx context.Context, log logr.Logger, repo, owner, ownerType string, f func(v1alpha1.ScaleUpTrigger) bool) (*ScaleTarget, error) {
-	repositoryRunnerKey := owner + "/" + repo
-
-	if target, err := autoscaler.getScaleTarget(ctx, repositoryRunnerKey, f); err != nil {
-		log.Info("finding repository-wide runner", "repository", repositoryRunnerKey)
-		return nil, err
-	} else if target != nil {
-		log.Info("scale up target is repository-wide runners", "repository", repo)
-		return target, nil
+func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getScaleUpTarget(ctx context.Context, log logr.Logger, repo, owner, ownerType, enterprise string, f func(v1alpha1.ScaleUpTrigger) bool) (*ScaleTarget, error) {
+	scaleTarget := func(value string) (*ScaleTarget, error) {
+		return autoscaler.getScaleTarget(ctx, value, f)
 	}
-
-	if ownerType == "User" {
-		log.V(1).Info("no repository runner found", "organization", owner)
-
-		return nil, nil
-	}
-
-	if target, err := autoscaler.getScaleTarget(ctx, owner, f); err != nil {
-		log.Info("finding organizational runner", "organization", owner)
-		return nil, err
-	} else if target != nil {
-		log.Info("scale up target is organizational runners", "organization", owner)
-		return target, nil
-	} else {
-		log.V(1).Info("no repository runner or organizational runner found",
-			"repository", repositoryRunnerKey,
-			"organization", owner,
-		)
-	}
-
-	return nil, nil
+	return autoscaler.getScaleUpTargetWithFunction(ctx, log, repo, owner, ownerType, enterprise, scaleTarget)
 }
 
-func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getJobScaleUpTargetForRepoOrOrg(ctx context.Context, log logr.Logger, repo, owner, ownerType string, labels []string) (*ScaleTarget, error) {
+func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getJobScaleUpTargetForRepoOrOrg(
+	ctx context.Context, log logr.Logger, repo, owner, ownerType, enterprise string, labels []string,
+) (*ScaleTarget, error) {
+
+	scaleTarget := func(value string) (*ScaleTarget, error) {
+		return autoscaler.getJobScaleTarget(ctx, value, labels)
+	}
+	return autoscaler.getScaleUpTargetWithFunction(ctx, log, repo, owner, ownerType, enterprise, scaleTarget)
+}
+
+func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getScaleUpTargetWithFunction(
+	ctx context.Context, log logr.Logger, repo, owner, ownerType, enterprise string, scaleTarget func(value string) (*ScaleTarget, error)) (*ScaleTarget, error) {
+
 	repositoryRunnerKey := owner + "/" + repo
 
-	if target, err := autoscaler.getJobScaleTarget(ctx, repositoryRunnerKey, labels); err != nil {
-		log.Info("finding repository-wide runner", "repository", repositoryRunnerKey)
+	// Search for repository HRAs
+	if target, err := scaleTarget(repositoryRunnerKey); err != nil {
+		log.Error(err, "finding repository-wide runner", "repository", repositoryRunnerKey)
 		return nil, err
 	} else if target != nil {
 		log.Info("job scale up target is repository-wide runners", "repository", repo)
@@ -445,25 +499,181 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getJobScaleUpTargetFo
 	}
 
 	if ownerType == "User" {
-		log.V(1).Info("no repository runner found", "organization", owner)
-
+		log.V(1).Info("user repositories not supported", "owner", owner)
 		return nil, nil
 	}
 
-	if target, err := autoscaler.getJobScaleTarget(ctx, owner, labels); err != nil {
-		log.Info("finding organizational runner", "organization", owner)
+	// Find the potential runner groups first to avoid spending API queries needless. Once/if GitHub improves an
+	// API to find related/linked runner groups from a specific repository this logic could be removed
+	managedRunnerGroups, err := autoscaler.getManagedRunnerGroupsFromHRAs(ctx, enterprise, owner)
+	if err != nil {
+		log.Error(err, "finding potential organization/enterprise runner groups from HRAs", "organization", owner)
 		return nil, err
-	} else if target != nil {
-		log.Info("job scale up target is organizational runners", "organization", owner)
-		return target, nil
-	} else {
-		log.V(1).Info("no repository runner or organizational runner found",
+	}
+	if managedRunnerGroups.IsEmpty() {
+		log.V(1).Info("no repository/organizational/enterprise runner found",
 			"repository", repositoryRunnerKey,
 			"organization", owner,
+			"enterprises", enterprise,
+		)
+	} else {
+		log.V(1).Info("Found some runner groups are managed by ARC", "groups", managedRunnerGroups)
+	}
+
+	var visibleGroups *simulator.VisibleRunnerGroups
+	if autoscaler.GitHubClient != nil {
+		simu := &simulator.Simulator{
+			Client: autoscaler.GitHubClient,
+			Log:    log,
+		}
+		// Get available organization runner groups and enterprise runner groups for a repository
+		// These are the sum of runner groups with repository access = All repositories and runner groups
+		// where owner/repo has access to as well. The list will include default runner group also if it has access to
+		visibleGroups, err = simu.GetRunnerGroupsVisibleToRepository(ctx, owner, repositoryRunnerKey, managedRunnerGroups)
+		log.V(1).Info("Searching in runner groups", "groups", visibleGroups)
+		if err != nil {
+			log.Error(err, "Unable to find runner groups from repository", "organization", owner, "repository", repo)
+			return nil, fmt.Errorf("error while finding visible runner groups: %v", err)
+		}
+	} else {
+		// For backwards compatibility if GitHub authentication is not configured, we assume all runner groups have
+		// visibility=all to honor the previous implementation, therefore any available enterprise/organization runner
+		// is a potential target for scaling. This will also avoid doing extra API calls caused by
+		// GitHubClient.GetRunnerGroupsVisibleToRepository in case users are not using custom visibility on their runner
+		// groups or they are using only default runner groups
+		visibleGroups = managedRunnerGroups
+	}
+
+	scaleTargetKey := func(rg simulator.RunnerGroup) string {
+		switch rg.Kind {
+		case simulator.Default:
+			switch rg.Scope {
+			case simulator.Organization:
+				return owner
+			case simulator.Enterprise:
+				return enterpriseKey(enterprise)
+			}
+		case simulator.Custom:
+			switch rg.Scope {
+			case simulator.Organization:
+				return organizationalRunnerGroupKey(owner, rg.Name)
+			case simulator.Enterprise:
+				return enterpriseRunnerGroupKey(enterprise, rg.Name)
+			}
+		}
+		return ""
+	}
+
+	log.V(1).Info("groups", "groups", visibleGroups)
+
+	var t *ScaleTarget
+
+	traverseErr := visibleGroups.Traverse(func(rg simulator.RunnerGroup) (bool, error) {
+		key := scaleTargetKey(rg)
+
+		target, err := scaleTarget(key)
+
+		if err != nil {
+			log.Error(err, "finding runner group", "enterprise", enterprise, "organization", owner, "repository", repo, "key", key)
+			return false, err
+		} else if target == nil {
+			return false, nil
+		}
+
+		t = target
+		log.V(1).Info("job scale up target found", "enterprise", enterprise, "organization", owner, "repository", repo, "key", key)
+
+		return true, nil
+	})
+
+	if traverseErr != nil {
+		return nil, err
+	}
+
+	if t == nil {
+		log.V(1).Info("no repository/organizational/enterprise runner found",
+			"repository", repositoryRunnerKey,
+			"organization", owner,
+			"enterprise", enterprise,
 		)
 	}
 
-	return nil, nil
+	return t, nil
+}
+
+func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getManagedRunnerGroupsFromHRAs(ctx context.Context, enterprise, org string) (*simulator.VisibleRunnerGroups, error) {
+	groups := simulator.NewVisibleRunnerGroups()
+	ns := autoscaler.Namespace
+
+	var defaultListOpts []client.ListOption
+	if ns != "" {
+		defaultListOpts = append(defaultListOpts, client.InNamespace(ns))
+	}
+
+	opts := append([]client.ListOption{}, defaultListOpts...)
+	if autoscaler.Namespace != "" {
+		opts = append(opts, client.InNamespace(autoscaler.Namespace))
+	}
+
+	var hraList v1alpha1.HorizontalRunnerAutoscalerList
+	if err := autoscaler.List(ctx, &hraList, opts...); err != nil {
+		return groups, err
+	}
+
+	for _, hra := range hraList.Items {
+		var o, e, g string
+
+		kind := hra.Spec.ScaleTargetRef.Kind
+		switch kind {
+		case "RunnerSet":
+			var rs v1alpha1.RunnerSet
+			if err := autoscaler.Client.Get(context.Background(), types.NamespacedName{Namespace: hra.Namespace, Name: hra.Spec.ScaleTargetRef.Name}, &rs); err != nil {
+				return groups, err
+			}
+			o, e, g = rs.Spec.Organization, rs.Spec.Enterprise, rs.Spec.Group
+		case "RunnerDeployment", "":
+			var rd v1alpha1.RunnerDeployment
+			if err := autoscaler.Client.Get(context.Background(), types.NamespacedName{Namespace: hra.Namespace, Name: hra.Spec.ScaleTargetRef.Name}, &rd); err != nil {
+				return groups, err
+			}
+			o, e, g = rd.Spec.Template.Spec.Organization, rd.Spec.Template.Spec.Enterprise, rd.Spec.Template.Spec.Group
+		default:
+			return nil, fmt.Errorf("unsupported scale target kind: %v", kind)
+		}
+
+		if g != "" && e == "" && o == "" {
+			autoscaler.Log.V(1).Info(
+				"invalid runner group config in scale target: spec.group must be set along with either spec.enterprise or spec.organization",
+				"scaleTargetKind", kind,
+				"group", g,
+				"enterprise", e,
+				"organization", o,
+			)
+
+			continue
+		}
+
+		if e != enterprise && o != org {
+			autoscaler.Log.V(1).Info(
+				"Skipped scale target irrelevant to event",
+				"eventOrganization", org,
+				"eventEnterprise", enterprise,
+				"scaleTargetKind", kind,
+				"scaleTargetGroup", g,
+				"scaleTargetEnterprise", e,
+				"scaleTargetOrganization", o,
+			)
+
+			continue
+		}
+
+		rg := simulator.NewRunnerGroupFromProperties(e, o, g)
+
+		if err := groups.Add(rg); err != nil {
+			return groups, fmt.Errorf("failed adding visible group from HRA %s/%s: %w", hra.Namespace, hra.Name, err)
+		}
+	}
+	return groups, nil
 }
 
 func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) getJobScaleTarget(ctx context.Context, name string, labels []string) (*ScaleTarget, error) {
@@ -482,16 +692,29 @@ HRA:
 
 		if len(hra.Spec.ScaleUpTriggers) > 1 {
 			autoscaler.Log.V(1).Info("Skipping this HRA as it has too many ScaleUpTriggers to be used in workflow_job based scaling", "hra", hra.Name)
+			continue
+		}
+
+		if len(hra.Spec.ScaleUpTriggers) == 0 {
+			autoscaler.Log.V(1).Info("Skipping this HRA as it has no ScaleUpTriggers configured", "hra", hra.Name)
+			continue
+		}
+
+		scaleUpTrigger := hra.Spec.ScaleUpTriggers[0]
+
+		if scaleUpTrigger.GitHubEvent == nil {
+			autoscaler.Log.V(1).Info("Skipping this HRA as it has no `githubEvent` scale trigger configured", "hra", hra.Name)
 
 			continue
 		}
 
-		var duration metav1.Duration
+		if scaleUpTrigger.GitHubEvent.WorkflowJob == nil {
+			autoscaler.Log.V(1).Info("Skipping this HRA as it has no `githubEvent.workflowJob` scale trigger configured", "hra", hra.Name)
 
-		if len(hra.Spec.ScaleUpTriggers) > 0 {
-			duration = hra.Spec.ScaleUpTriggers[0].Duration
+			continue
 		}
 
+		duration := scaleUpTrigger.Duration
 		if duration.Duration <= 0 {
 			// Try to release the reserved capacity after at least 10 minutes by default,
 			// we won't end up in the reserved capacity remained forever in case GitHub somehow stopped sending us "completed" workflow_job events.
@@ -508,13 +731,17 @@ HRA:
 				return nil, err
 			}
 
-			if len(labels) == 1 && labels[0] == "self-hosted" {
-				return &ScaleTarget{HorizontalRunnerAutoscaler: hra, ScaleUpTrigger: v1alpha1.ScaleUpTrigger{Duration: duration}}, nil
-			}
-
 			// Ensure that the RunnerSet-managed runners have all the labels requested by the workflow_job.
 			for _, l := range labels {
 				var matched bool
+
+				// ignore "self-hosted" label as all instance here are self-hosted
+				if l == "self-hosted" {
+					continue
+				}
+
+				// TODO labels related to OS and architecture needs to be explicitly declared or the current implementation will not be able to find them.
+
 				for _, l2 := range rs.Spec.Labels {
 					if l == l2 {
 						matched = true
@@ -535,14 +762,18 @@ HRA:
 				return nil, err
 			}
 
-			if len(labels) == 1 && labels[0] == "self-hosted" {
-				return &ScaleTarget{HorizontalRunnerAutoscaler: hra, ScaleUpTrigger: v1alpha1.ScaleUpTrigger{Duration: duration}}, nil
-			}
-
 			// Ensure that the RunnerDeployment-managed runners have all the labels requested by the workflow_job.
 			for _, l := range labels {
 				var matched bool
-				for _, l2 := range rd.Spec.Template.Labels {
+
+				// ignore "self-hosted" label as all instance here are self-hosted
+				if l == "self-hosted" {
+					continue
+				}
+
+				// TODO labels related to OS and architecture needs to be explicitly declared or the current implementation will not be able to find them.
+
+				for _, l2 := range rd.Spec.Template.Spec.Labels {
 					if l == l2 {
 						matched = true
 						break
@@ -563,55 +794,6 @@ HRA:
 	return nil, nil
 }
 
-func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) tryScale(ctx context.Context, target *ScaleTarget) error {
-	if target == nil {
-		return nil
-	}
-
-	copy := target.HorizontalRunnerAutoscaler.DeepCopy()
-
-	amount := 1
-
-	if target.ScaleUpTrigger.Amount != 0 {
-		amount = target.ScaleUpTrigger.Amount
-	}
-
-	capacityReservations := getValidCapacityReservations(copy)
-
-	if amount > 0 {
-		copy.Spec.CapacityReservations = append(capacityReservations, v1alpha1.CapacityReservation{
-			ExpirationTime: metav1.Time{Time: time.Now().Add(target.ScaleUpTrigger.Duration.Duration)},
-			Replicas:       amount,
-		})
-	} else if amount < 0 {
-		var reservations []v1alpha1.CapacityReservation
-
-		var found bool
-
-		for _, r := range capacityReservations {
-			if !found && r.Replicas+amount == 0 {
-				found = true
-			} else {
-				reservations = append(reservations, r)
-			}
-		}
-
-		copy.Spec.CapacityReservations = reservations
-	}
-
-	autoscaler.Log.Info(
-		"Patching hra for capacityReservations update",
-		"before", target.HorizontalRunnerAutoscaler.Spec.CapacityReservations,
-		"after", copy.Spec.CapacityReservations,
-	)
-
-	if err := autoscaler.Client.Patch(ctx, copy, client.MergeFrom(&target.HorizontalRunnerAutoscaler)); err != nil {
-		return fmt.Errorf("patching horizontalrunnerautoscaler to add capacity reservation: %w", err)
-	}
-
-	return nil
-}
-
 func getValidCapacityReservations(autoscaler *v1alpha1.HorizontalRunnerAutoscaler) []v1alpha1.CapacityReservation {
 	var capacityReservations []v1alpha1.CapacityReservation
 
@@ -638,26 +820,63 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) SetupWithManager(mgr
 		hra := rawObj.(*v1alpha1.HorizontalRunnerAutoscaler)
 
 		if hra.Spec.ScaleTargetRef.Name == "" {
+			autoscaler.Log.V(1).Info(fmt.Sprintf("scale target ref name not set for hra %s", hra.Name))
 			return nil
 		}
 
 		switch hra.Spec.ScaleTargetRef.Kind {
 		case "", "RunnerDeployment":
 			var rd v1alpha1.RunnerDeployment
-
 			if err := autoscaler.Client.Get(context.Background(), types.NamespacedName{Namespace: hra.Namespace, Name: hra.Spec.ScaleTargetRef.Name}, &rd); err != nil {
+				autoscaler.Log.V(1).Info(fmt.Sprintf("RunnerDeployment not found with scale target ref name %s for hra %s", hra.Spec.ScaleTargetRef.Name, hra.Name))
 				return nil
 			}
 
-			return []string{rd.Spec.Template.Spec.Repository, rd.Spec.Template.Spec.Organization}
+			keys := []string{}
+			if rd.Spec.Template.Spec.Repository != "" {
+				keys = append(keys, rd.Spec.Template.Spec.Repository) // Repository runners
+			}
+			if rd.Spec.Template.Spec.Organization != "" {
+				if group := rd.Spec.Template.Spec.Group; group != "" {
+					keys = append(keys, organizationalRunnerGroupKey(rd.Spec.Template.Spec.Organization, rd.Spec.Template.Spec.Group)) // Organization runner groups
+				} else {
+					keys = append(keys, rd.Spec.Template.Spec.Organization) // Organization runners
+				}
+			}
+			if enterprise := rd.Spec.Template.Spec.Enterprise; enterprise != "" {
+				if group := rd.Spec.Template.Spec.Group; group != "" {
+					keys = append(keys, enterpriseRunnerGroupKey(enterprise, rd.Spec.Template.Spec.Group)) // Enterprise runner groups
+				} else {
+					keys = append(keys, enterpriseKey(enterprise)) // Enterprise runners
+				}
+			}
+			autoscaler.Log.V(2).Info(fmt.Sprintf("HRA keys indexed for HRA %s: %v", hra.Name, keys))
+			return keys
 		case "RunnerSet":
 			var rs v1alpha1.RunnerSet
-
 			if err := autoscaler.Client.Get(context.Background(), types.NamespacedName{Namespace: hra.Namespace, Name: hra.Spec.ScaleTargetRef.Name}, &rs); err != nil {
+				autoscaler.Log.V(1).Info(fmt.Sprintf("RunnerSet not found with scale target ref name %s for hra %s", hra.Spec.ScaleTargetRef.Name, hra.Name))
 				return nil
 			}
 
-			return []string{rs.Spec.Repository, rs.Spec.Organization}
+			keys := []string{}
+			if rs.Spec.Repository != "" {
+				keys = append(keys, rs.Spec.Repository) // Repository runners
+			}
+			if rs.Spec.Organization != "" {
+				keys = append(keys, rs.Spec.Organization) // Organization runners
+				if group := rs.Spec.Group; group != "" {
+					keys = append(keys, organizationalRunnerGroupKey(rs.Spec.Organization, rs.Spec.Group)) // Organization runner groups
+				}
+			}
+			if enterprise := rs.Spec.Enterprise; enterprise != "" {
+				keys = append(keys, enterpriseKey(enterprise)) // Enterprise runners
+				if group := rs.Spec.Group; group != "" {
+					keys = append(keys, enterpriseRunnerGroupKey(enterprise, rs.Spec.Group)) // Enterprise runner groups
+				}
+			}
+			autoscaler.Log.V(2).Info(fmt.Sprintf("HRA keys indexed for HRA %s: %v", hra.Name, keys))
+			return keys
 		}
 
 		return nil
@@ -670,3 +889,15 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) SetupWithManager(mgr
 		Named(name).
 		Complete(autoscaler)
 }
+
+func enterpriseKey(name string) string {
+	return keyPrefixEnterprise + name
+}
+
+func organizationalRunnerGroupKey(owner, group string) string {
+	return owner + keyRunnerGroup + group
+}
+
+func enterpriseRunnerGroupKey(enterprise, group string) string {
+	return keyPrefixEnterprise + enterprise + keyRunnerGroup + group
+}

controllers/horizontal_runner_autoscaler_webhook_on_check_run.go

@@ -3,7 +3,7 @@ package controllers
 import (
 	"github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
 	"github.com/actions-runner-controller/actions-runner-controller/pkg/actionsglob"
-	"github.com/google/go-github/v37/github"
+	"github.com/google/go-github/v45/github"
 )
 
 func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) MatchCheckRunEvent(event *github.CheckRunEvent) func(scaleUpTrigger v1alpha1.ScaleUpTrigger) bool {

controllers/horizontal_runner_autoscaler_webhook_on_pull_request.go

@@ -2,7 +2,7 @@ package controllers
 
 import (
 	"github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
-	"github.com/google/go-github/v37/github"
+	"github.com/google/go-github/v45/github"
 )
 
 func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) MatchPullRequestEvent(event *github.PullRequestEvent) func(scaleUpTrigger v1alpha1.ScaleUpTrigger) bool {

controllers/horizontal_runner_autoscaler_webhook_on_push.go

@@ -2,7 +2,7 @@ package controllers
 
 import (
 	"github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
-	"github.com/google/go-github/v37/github"
+	"github.com/google/go-github/v45/github"
 )
 
 func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) MatchPushEvent(event *github.PushEvent) func(scaleUpTrigger v1alpha1.ScaleUpTrigger) bool {
@@ -15,10 +15,6 @@ func (autoscaler *HorizontalRunnerAutoscalerGitHubWebhook) MatchPushEvent(event
 
 		push := g.Push
 
-		if push == nil {
-			return false
-		}
-
-		return true
+		return push != nil
 	}
 }

controllers/horizontal_runner_autoscaler_webhook_test.go

@@ -15,7 +15,7 @@ import (
 
 	actionsv1alpha1 "github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
 	"github.com/go-logr/logr"
-	"github.com/google/go-github/v37/github"
+	"github.com/google/go-github/v45/github"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/runtime"
 	clientgoscheme "k8s.io/client-go/kubernetes/scheme"
@@ -114,6 +114,326 @@ func TestWebhookPing(t *testing.T) {
 	)
 }
 
+func TestWebhookWorkflowJob(t *testing.T) {
+	setupTest := func() github.WorkflowJobEvent {
+		f, err := os.Open("testdata/org_webhook_workflow_job_payload.json")
+		if err != nil {
+			t.Fatalf("could not open the fixture: %s", err)
+		}
+		defer f.Close()
+		var e github.WorkflowJobEvent
+		if err := json.NewDecoder(f).Decode(&e); err != nil {
+			t.Fatalf("invalid json: %s", err)
+		}
+
+		return e
+	}
+	t.Run("Successful", func(t *testing.T) {
+		e := setupTest()
+		hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+				ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+					Name: "test-name",
+				},
+				ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+					{
+						GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+							WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+						},
+					},
+				},
+			},
+		}
+
+		rd := &actionsv1alpha1.RunnerDeployment{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.RunnerDeploymentSpec{
+				Template: actionsv1alpha1.RunnerTemplate{
+					Spec: actionsv1alpha1.RunnerSpec{
+						RunnerConfig: actionsv1alpha1.RunnerConfig{
+							Organization: "MYORG",
+							Labels:       []string{"label1"},
+						},
+					},
+				},
+			},
+		}
+
+		initObjs := []runtime.Object{hra, rd}
+
+		testServerWithInitObjs(t,
+			"workflow_job",
+			&e,
+			200,
+			"scaled test-name by 1",
+			initObjs,
+		)
+	})
+	t.Run("WrongLabels", func(t *testing.T) {
+		e := setupTest()
+		hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+				ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+					Name: "test-name",
+				},
+				ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+					{
+						GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+							WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+						},
+					},
+				},
+			},
+		}
+
+		rd := &actionsv1alpha1.RunnerDeployment{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.RunnerDeploymentSpec{
+				Template: actionsv1alpha1.RunnerTemplate{
+					Spec: actionsv1alpha1.RunnerSpec{
+						RunnerConfig: actionsv1alpha1.RunnerConfig{
+							Organization: "MYORG",
+							Labels:       []string{"bad-label"},
+						},
+					},
+				},
+			},
+		}
+
+		initObjs := []runtime.Object{hra, rd}
+
+		testServerWithInitObjs(t,
+			"workflow_job",
+			&e,
+			200,
+			"no horizontalrunnerautoscaler to scale for this github event",
+			initObjs,
+		)
+	})
+	// This test verifies that the old way of matching labels doesn't work anymore
+	t.Run("OldLabels", func(t *testing.T) {
+		e := setupTest()
+		hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+				ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+					Name: "test-name",
+				},
+				ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+					{
+						GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+							WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+						},
+					},
+				},
+			},
+		}
+
+		rd := &actionsv1alpha1.RunnerDeployment{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.RunnerDeploymentSpec{
+				Template: actionsv1alpha1.RunnerTemplate{
+					ObjectMeta: metav1.ObjectMeta{
+						Labels: map[string]string{
+							"label1": "label1",
+						},
+					},
+					Spec: actionsv1alpha1.RunnerSpec{
+						RunnerConfig: actionsv1alpha1.RunnerConfig{
+							Organization: "MYORG",
+							Labels:       []string{"bad-label"},
+						},
+					},
+				},
+			},
+		}
+
+		initObjs := []runtime.Object{hra, rd}
+
+		testServerWithInitObjs(t,
+			"workflow_job",
+			&e,
+			200,
+			"no horizontalrunnerautoscaler to scale for this github event",
+			initObjs,
+		)
+	})
+}
+
+func TestWebhookWorkflowJobWithSelfHostedLabel(t *testing.T) {
+	setupTest := func() github.WorkflowJobEvent {
+		f, err := os.Open("testdata/org_webhook_workflow_job_with_self_hosted_label_payload.json")
+		if err != nil {
+			t.Fatalf("could not open the fixture: %s", err)
+		}
+		defer f.Close()
+		var e github.WorkflowJobEvent
+		if err := json.NewDecoder(f).Decode(&e); err != nil {
+			t.Fatalf("invalid json: %s", err)
+		}
+
+		return e
+	}
+	t.Run("Successful", func(t *testing.T) {
+		e := setupTest()
+		hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+				ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+					Name: "test-name",
+				},
+				ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+					{
+						GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+							WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+						},
+					},
+				},
+			},
+		}
+
+		rd := &actionsv1alpha1.RunnerDeployment{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.RunnerDeploymentSpec{
+				Template: actionsv1alpha1.RunnerTemplate{
+					Spec: actionsv1alpha1.RunnerSpec{
+						RunnerConfig: actionsv1alpha1.RunnerConfig{
+							Organization: "MYORG",
+							Labels:       []string{"label1"},
+						},
+					},
+				},
+			},
+		}
+
+		initObjs := []runtime.Object{hra, rd}
+
+		testServerWithInitObjs(t,
+			"workflow_job",
+			&e,
+			200,
+			"scaled test-name by 1",
+			initObjs,
+		)
+	})
+	t.Run("WrongLabels", func(t *testing.T) {
+		e := setupTest()
+		hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+				ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+					Name: "test-name",
+				},
+				ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+					{
+						GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+							WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+						},
+					},
+				},
+			},
+		}
+
+		rd := &actionsv1alpha1.RunnerDeployment{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.RunnerDeploymentSpec{
+				Template: actionsv1alpha1.RunnerTemplate{
+					Spec: actionsv1alpha1.RunnerSpec{
+						RunnerConfig: actionsv1alpha1.RunnerConfig{
+							Organization: "MYORG",
+							Labels:       []string{"bad-label"},
+						},
+					},
+				},
+			},
+		}
+
+		initObjs := []runtime.Object{hra, rd}
+
+		testServerWithInitObjs(t,
+			"workflow_job",
+			&e,
+			200,
+			"no horizontalrunnerautoscaler to scale for this github event",
+			initObjs,
+		)
+	})
+	// This test verifies that the old way of matching labels doesn't work anymore
+	t.Run("OldLabels", func(t *testing.T) {
+		e := setupTest()
+		hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+				ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+					Name: "test-name",
+				},
+				ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+					{
+						GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+							WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+						},
+					},
+				},
+			},
+		}
+
+		rd := &actionsv1alpha1.RunnerDeployment{
+			ObjectMeta: metav1.ObjectMeta{
+				Name: "test-name",
+			},
+			Spec: actionsv1alpha1.RunnerDeploymentSpec{
+				Template: actionsv1alpha1.RunnerTemplate{
+					ObjectMeta: metav1.ObjectMeta{
+						Labels: map[string]string{
+							"label1": "label1",
+						},
+					},
+					Spec: actionsv1alpha1.RunnerSpec{
+						RunnerConfig: actionsv1alpha1.RunnerConfig{
+							Organization: "MYORG",
+							Labels:       []string{"bad-label"},
+						},
+					},
+				},
+			},
+		}
+
+		initObjs := []runtime.Object{hra, rd}
+
+		testServerWithInitObjs(t,
+			"workflow_job",
+			&e,
+			200,
+			"no horizontalrunnerautoscaler to scale for this github event",
+			initObjs,
+		)
+	})
+}
+
 func TestGetRequest(t *testing.T) {
 	hra := HorizontalRunnerAutoscalerGitHubWebhook{}
 	request, _ := http.NewRequest(http.MethodGet, "/", nil)
@@ -167,23 +487,23 @@ func TestGetValidCapacityReservations(t *testing.T) {
 func installTestLogger(webhook *HorizontalRunnerAutoscalerGitHubWebhook) *bytes.Buffer {
 	logs := &bytes.Buffer{}
 
-	log := testLogger{
+	sink := &testLogSink{
 		name:   "testlog",
 		writer: logs,
 	}
 
-	webhook.Log = &log
+	log := logr.New(sink)
+
+	webhook.Log = log
 
 	return logs
 }
 
-func testServer(t *testing.T, eventType string, event interface{}, wantCode int, wantBody string) {
+func testServerWithInitObjs(t *testing.T, eventType string, event interface{}, wantCode int, wantBody string, initObjs []runtime.Object) {
 	t.Helper()
 
 	hraWebhook := &HorizontalRunnerAutoscalerGitHubWebhook{}
 
-	var initObjs []runtime.Object
-
 	client := fake.NewFakeClientWithScheme(sc, initObjs...)
 
 	logs := installTestLogger(hraWebhook)
@@ -227,6 +547,11 @@ func testServer(t *testing.T, eventType string, event interface{}, wantCode int,
 	}
 }
 
+func testServer(t *testing.T, eventType string, event interface{}, wantCode int, wantBody string) {
+	var initObjs []runtime.Object
+	testServerWithInitObjs(t, eventType, event, wantCode, wantBody, initObjs)
+}
+
 func sendWebhook(server *httptest.Server, eventType string, event interface{}) (*http.Response, error) {
 	jsonBuf := &bytes.Buffer{}
 	enc := json.NewEncoder(jsonBuf)
@@ -256,18 +581,22 @@ func sendWebhook(server *httptest.Server, eventType string, event interface{}) (
 	return http.DefaultClient.Do(req)
 }
 
-// testLogger is a sample logr.Logger that logs in-memory.
+// testLogSink is a sample logr.Logger that logs in-memory.
 // It's only for testing log outputs.
-type testLogger struct {
+type testLogSink struct {
 	name      string
 	keyValues map[string]interface{}
 
 	writer io.Writer
 }
 
-var _ logr.Logger = &testLogger{}
+var _ logr.LogSink = &testLogSink{}
 
-func (l *testLogger) Info(msg string, kvs ...interface{}) {
+func (l *testLogSink) Init(_ logr.RuntimeInfo) {
+
+}
+
+func (l *testLogSink) Info(_ int, msg string, kvs ...interface{}) {
 	fmt.Fprintf(l.writer, "%s] %s\t", l.name, msg)
 	for k, v := range l.keyValues {
 		fmt.Fprintf(l.writer, "%s=%+v ", k, v)
@@ -278,28 +607,24 @@ func (l *testLogger) Info(msg string, kvs ...interface{}) {
 	fmt.Fprintf(l.writer, "\n")
 }
 
-func (_ *testLogger) Enabled() bool {
+func (_ *testLogSink) Enabled(level int) bool {
 	return true
 }
 
-func (l *testLogger) Error(err error, msg string, kvs ...interface{}) {
+func (l *testLogSink) Error(err error, msg string, kvs ...interface{}) {
 	kvs = append(kvs, "error", err)
-	l.Info(msg, kvs...)
+	l.Info(0, msg, kvs...)
 }
 
-func (l *testLogger) V(_ int) logr.InfoLogger {
-	return l
-}
-
-func (l *testLogger) WithName(name string) logr.Logger {
-	return &testLogger{
+func (l *testLogSink) WithName(name string) logr.LogSink {
+	return &testLogSink{
 		name:      l.name + "." + name,
 		keyValues: l.keyValues,
 		writer:    l.writer,
 	}
 }
 
-func (l *testLogger) WithValues(kvs ...interface{}) logr.Logger {
+func (l *testLogSink) WithValues(kvs ...interface{}) logr.LogSink {
 	newMap := make(map[string]interface{}, len(l.keyValues)+len(kvs)/2)
 	for k, v := range l.keyValues {
 		newMap[k] = v
@@ -307,7 +632,7 @@ func (l *testLogger) WithValues(kvs ...interface{}) logr.Logger {
 	for i := 0; i < len(kvs); i += 2 {
 		newMap[kvs[i].(string)] = kvs[i+1]
 	}
-	return &testLogger{
+	return &testLogSink{
 		name:      l.name,
 		keyValues: newMap,
 		writer:    l.writer,

controllers/horizontal_runner_autoscaler_webhook_worker.go

@@ -0,0 +1,55 @@
+package controllers
+
+import (
+	"context"
+)
+
+// worker is a worker that has a non-blocking bounded queue of scale targets, dequeues scale target and executes the scale operation one by one.
+type worker struct {
+	scaleTargetQueue chan *ScaleTarget
+	work             func(*ScaleTarget)
+	done             chan struct{}
+}
+
+func newWorker(ctx context.Context, queueLimit int, work func(*ScaleTarget)) *worker {
+	w := &worker{
+		scaleTargetQueue: make(chan *ScaleTarget, queueLimit),
+		work:             work,
+		done:             make(chan struct{}),
+	}
+
+	go func() {
+		defer close(w.done)
+
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case t := <-w.scaleTargetQueue:
+				work(t)
+			}
+		}
+	}()
+
+	return w
+}
+
+// Add the scale target to the bounded queue, returning the result as a bool value. It returns true on successful enqueue, and returns false otherwise.
+// When returned false, the queue is already full so the enqueue operation must be retried later.
+// If the enqueue was triggered by an external source and there's no intermediate queue that we can use,
+// you must instruct the source to resend the original request later.
+// In case you're building a webhook server around this worker, this means that you must return a http error to the webhook server,
+// so that (hopefully) the sender can resend the webhook event later, or at least the human operator can notice or be notified about the
+// webhook develiery failure so that a manual retry can be done later.
+func (w *worker) Add(st *ScaleTarget) bool {
+	select {
+	case w.scaleTargetQueue <- st:
+		return true
+	default:
+		return false
+	}
+}
+
+func (w *worker) Done() chan struct{} {
+	return w.done
+}

controllers/horizontal_runner_autoscaler_webhook_worker_test.go

@@ -0,0 +1,36 @@
+package controllers
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestWorker_Add(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	w := newWorker(ctx, 2, func(st *ScaleTarget) {})
+	require.True(t, w.Add(&ScaleTarget{}))
+	require.True(t, w.Add(&ScaleTarget{}))
+	require.False(t, w.Add(&ScaleTarget{}))
+}
+
+func TestWorker_Work(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	var count int
+
+	w := newWorker(ctx, 1, func(st *ScaleTarget) {
+		count++
+		cancel()
+	})
+	require.True(t, w.Add(&ScaleTarget{}))
+	require.False(t, w.Add(&ScaleTarget{}))
+
+	<-w.Done()
+
+	require.Equal(t, count, 1)
+}

controllers/horizontalrunnerautoscaler_controller.go

@@ -25,10 +25,10 @@ import (
 	corev1 "k8s.io/api/core/v1"
 
 	"github.com/actions-runner-controller/actions-runner-controller/github"
+	"github.com/go-logr/logr"
 	kerrors "k8s.io/apimachinery/pkg/api/errors"
 	"k8s.io/apimachinery/pkg/types"
 
-	"github.com/go-logr/logr"
 	"k8s.io/apimachinery/pkg/runtime"
 	"k8s.io/client-go/tools/record"
 	ctrl "sigs.k8s.io/controller-runtime"
@@ -47,13 +47,13 @@ const (
 // HorizontalRunnerAutoscalerReconciler reconciles a HorizontalRunnerAutoscaler object
 type HorizontalRunnerAutoscalerReconciler struct {
 	client.Client
-	GitHubClient *github.Client
-	Log          logr.Logger
-	Recorder     record.EventRecorder
-	Scheme       *runtime.Scheme
-
-	CacheDuration time.Duration
-	Name          string
+	GitHubClient          *github.Client
+	Log                   logr.Logger
+	Recorder              record.EventRecorder
+	Scheme                *runtime.Scheme
+	CacheDuration         time.Duration
+	DefaultScaleDownDelay time.Duration
+	Name                  string
 }
 
 const defaultReplicas = 1
@@ -99,11 +99,33 @@ func (r *HorizontalRunnerAutoscalerReconciler) Reconcile(ctx context.Context, re
 		return r.reconcile(ctx, req, log, hra, st, func(newDesiredReplicas int) error {
 			currentDesiredReplicas := getIntOrDefault(rd.Spec.Replicas, defaultReplicas)
 
+			ephemeral := rd.Spec.Template.Spec.Ephemeral == nil || *rd.Spec.Template.Spec.Ephemeral
+
+			var effectiveTime *time.Time
+
+			for _, r := range hra.Spec.CapacityReservations {
+				t := r.EffectiveTime
+				if effectiveTime == nil || effectiveTime.Before(t.Time) {
+					effectiveTime = &t.Time
+				}
+			}
+
 			// Please add more conditions that we can in-place update the newest runnerreplicaset without disruption
 			if currentDesiredReplicas != newDesiredReplicas {
 				copy := rd.DeepCopy()
 				copy.Spec.Replicas = &newDesiredReplicas
 
+				if ephemeral && effectiveTime != nil {
+					copy.Spec.EffectiveTime = &metav1.Time{Time: *effectiveTime}
+				}
+
+				if err := r.Client.Patch(ctx, copy, client.MergeFrom(&rd)); err != nil {
+					return fmt.Errorf("patching runnerdeployment to have %d replicas: %w", newDesiredReplicas, err)
+				}
+			} else if ephemeral && effectiveTime != nil {
+				copy := rd.DeepCopy()
+				copy.Spec.EffectiveTime = &metav1.Time{Time: *effectiveTime}
+
 				if err := r.Client.Patch(ctx, copy, client.MergeFrom(&rd)); err != nil {
 					return fmt.Errorf("patching runnerdeployment to have %d replicas: %w", newDesiredReplicas, err)
 				}
@@ -137,6 +159,7 @@ func (r *HorizontalRunnerAutoscalerReconciler) Reconcile(ctx context.Context, re
 			org:        rs.Spec.Organization,
 			repo:       rs.Spec.Repository,
 			replicas:   replicas,
+			labels:     rs.Spec.RunnerConfig.Labels,
 			getRunnerMap: func() (map[string]struct{}, error) {
 				// return the list of runners in namespace. Horizontal Runner Autoscaler should only be responsible for scaling resources in its own ns.
 				var runnerPodList corev1.PodList
@@ -180,15 +203,38 @@ func (r *HorizontalRunnerAutoscalerReconciler) Reconcile(ctx context.Context, re
 			}
 			currentDesiredReplicas := getIntOrDefault(replicas, defaultReplicas)
 
+			ephemeral := rs.Spec.Ephemeral == nil || *rs.Spec.Ephemeral
+
+			var effectiveTime *time.Time
+
+			for _, r := range hra.Spec.CapacityReservations {
+				t := r.EffectiveTime
+				if effectiveTime == nil || effectiveTime.Before(t.Time) {
+					effectiveTime = &t.Time
+				}
+			}
+
 			if currentDesiredReplicas != newDesiredReplicas {
 				copy := rs.DeepCopy()
 				v := int32(newDesiredReplicas)
 				copy.Spec.Replicas = &v
 
+				if ephemeral && effectiveTime != nil {
+					copy.Spec.EffectiveTime = &metav1.Time{Time: *effectiveTime}
+				}
+
+				if err := r.Client.Patch(ctx, copy, client.MergeFrom(&rs)); err != nil {
+					return fmt.Errorf("patching runnerset to have %d replicas: %w", newDesiredReplicas, err)
+				}
+			} else if ephemeral && effectiveTime != nil {
+				copy := rs.DeepCopy()
+				copy.Spec.EffectiveTime = &metav1.Time{Time: *effectiveTime}
+
 				if err := r.Client.Patch(ctx, copy, client.MergeFrom(&rs)); err != nil {
 					return fmt.Errorf("patching runnerset to have %d replicas: %w", newDesiredReplicas, err)
 				}
 			}
+
 			return nil
 		})
 	}
@@ -206,6 +252,7 @@ func (r *HorizontalRunnerAutoscalerReconciler) scaleTargetFromRD(ctx context.Con
 		org:        rd.Spec.Template.Spec.Organization,
 		repo:       rd.Spec.Template.Spec.Repository,
 		replicas:   rd.Spec.Replicas,
+		labels:     rd.Spec.Template.Spec.RunnerConfig.Labels,
 		getRunnerMap: func() (map[string]struct{}, error) {
 			// return the list of runners in namespace. Horizontal Runner Autoscaler should only be responsible for scaling resources in its own ns.
 			var runnerList v1alpha1.RunnerList
@@ -248,6 +295,7 @@ type scaleTarget struct {
 	st, kind              string
 	enterprise, repo, org string
 	replicas              *int
+	labels                []string
 
 	getRunnerMap func() (map[string]struct{}, error)
 }
@@ -262,7 +310,7 @@ func (r *HorizontalRunnerAutoscalerReconciler) reconcile(ctx context.Context, re
 		return ctrl.Result{}, err
 	}
 
-	newDesiredReplicas, computedReplicas, computedReplicasFromCache, err := r.computeReplicasWithCache(log, now, st, hra, minReplicas)
+	newDesiredReplicas, err := r.computeReplicasWithCache(log, now, st, hra, minReplicas)
 	if err != nil {
 		r.Recorder.Event(&hra, corev1.EventTypeNormal, "RunnerAutoscalingFailure", err.Error())
 
@@ -287,24 +335,6 @@ func (r *HorizontalRunnerAutoscalerReconciler) reconcile(ctx context.Context, re
 		updated.Status.DesiredReplicas = &newDesiredReplicas
 	}
 
-	if computedReplicasFromCache == nil {
-		cacheEntries := getValidCacheEntries(updated, now)
-
-		var cacheDuration time.Duration
-
-		if r.CacheDuration > 0 {
-			cacheDuration = r.CacheDuration
-		} else {
-			cacheDuration = 10 * time.Minute
-		}
-
-		updated.Status.CacheEntries = append(cacheEntries, v1alpha1.CacheEntry{
-			Key:            v1alpha1.CacheEntryKeyDesiredReplicas,
-			Value:          computedReplicas,
-			ExpirationTime: metav1.Time{Time: time.Now().Add(cacheDuration)},
-		})
-	}
-
 	var overridesSummary string
 
 	if (active != nil && upcoming == nil) || (active != nil && upcoming != nil && active.Period.EndTime.Before(upcoming.Period.StartTime)) {
@@ -339,18 +369,6 @@ func (r *HorizontalRunnerAutoscalerReconciler) reconcile(ctx context.Context, re
 	return ctrl.Result{}, nil
 }
 
-func getValidCacheEntries(hra *v1alpha1.HorizontalRunnerAutoscaler, now time.Time) []v1alpha1.CacheEntry {
-	var cacheEntries []v1alpha1.CacheEntry
-
-	for _, ent := range hra.Status.CacheEntries {
-		if ent.ExpirationTime.After(now) {
-			cacheEntries = append(cacheEntries, ent)
-		}
-	}
-
-	return cacheEntries
-}
-
 func (r *HorizontalRunnerAutoscalerReconciler) SetupWithManager(mgr ctrl.Manager) error {
 	name := "horizontalrunnerautoscaler-controller"
 	if r.Name != "" {
@@ -443,32 +461,18 @@ func (r *HorizontalRunnerAutoscalerReconciler) getMinReplicas(log logr.Logger, n
 	return minReplicas, active, upcoming, nil
 }
 
-func (r *HorizontalRunnerAutoscalerReconciler) computeReplicasWithCache(log logr.Logger, now time.Time, st scaleTarget, hra v1alpha1.HorizontalRunnerAutoscaler, minReplicas int) (int, int, *int, error) {
+func (r *HorizontalRunnerAutoscalerReconciler) computeReplicasWithCache(log logr.Logger, now time.Time, st scaleTarget, hra v1alpha1.HorizontalRunnerAutoscaler, minReplicas int) (int, error) {
 	var suggestedReplicas int
 
-	suggestedReplicasFromCache := r.fetchSuggestedReplicasFromCache(hra)
+	v, err := r.suggestDesiredReplicas(st, hra)
+	if err != nil {
+		return 0, err
+	}
 
-	var cached *int
-
-	if suggestedReplicasFromCache != nil {
-		cached = suggestedReplicasFromCache
-
-		if cached == nil {
-			suggestedReplicas = minReplicas
-		} else {
-			suggestedReplicas = *cached
-		}
+	if v == nil {
+		suggestedReplicas = minReplicas
 	} else {
-		v, err := r.suggestDesiredReplicas(st, hra)
-		if err != nil {
-			return 0, 0, nil, err
-		}
-
-		if v == nil {
-			suggestedReplicas = minReplicas
-		} else {
-			suggestedReplicas = *v
-		}
+		suggestedReplicas = *v
 	}
 
 	var reserved int
@@ -496,7 +500,7 @@ func (r *HorizontalRunnerAutoscalerReconciler) computeReplicasWithCache(log logr
 	if hra.Spec.ScaleDownDelaySecondsAfterScaleUp != nil {
 		scaleDownDelay = time.Duration(*hra.Spec.ScaleDownDelaySecondsAfterScaleUp) * time.Second
 	} else {
-		scaleDownDelay = DefaultScaleDownDelay
+		scaleDownDelay = r.DefaultScaleDownDelay
 	}
 
 	var scaleDownDelayUntil *time.Time
@@ -527,8 +531,8 @@ func (r *HorizontalRunnerAutoscalerReconciler) computeReplicasWithCache(log logr
 		"min", minReplicas,
 	}
 
-	if cached != nil {
-		kvs = append(kvs, "cached", *cached)
+	if maxReplicas := hra.Spec.MaxReplicas; maxReplicas != nil {
+		kvs = append(kvs, "max", *maxReplicas)
 	}
 
 	if scaleDownDelayUntil != nil {
@@ -536,13 +540,9 @@ func (r *HorizontalRunnerAutoscalerReconciler) computeReplicasWithCache(log logr
 		kvs = append(kvs, "scale_down_delay_until", scaleDownDelayUntil)
 	}
 
-	if maxReplicas := hra.Spec.MaxReplicas; maxReplicas != nil {
-		kvs = append(kvs, "max", *maxReplicas)
-	}
-
 	log.V(1).Info(fmt.Sprintf("Calculated desired replicas of %d", newDesiredReplicas),
 		kvs...,
 	)
 
-	return newDesiredReplicas, suggestedReplicas, suggestedReplicasFromCache, nil
+	return newDesiredReplicas, nil
 }

controllers/horizontalrunnerautoscaler_controller_test.go

@@ -1,50 +0,0 @@
-package controllers
-
-import (
-	"testing"
-	"time"
-
-	actionsv1alpha1 "github.com/actions-runner-controller/actions-runner-controller/api/v1alpha1"
-	"github.com/google/go-cmp/cmp"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
-)
-
-func TestGetValidCacheEntries(t *testing.T) {
-	now := time.Now()
-
-	hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
-		Status: actionsv1alpha1.HorizontalRunnerAutoscalerStatus{
-			CacheEntries: []actionsv1alpha1.CacheEntry{
-				{
-					Key:            "foo",
-					Value:          1,
-					ExpirationTime: metav1.Time{Time: now.Add(-time.Second)},
-				},
-				{
-					Key:            "foo",
-					Value:          2,
-					ExpirationTime: metav1.Time{Time: now},
-				},
-				{
-					Key:            "foo",
-					Value:          3,
-					ExpirationTime: metav1.Time{Time: now.Add(time.Second)},
-				},
-			},
-		},
-	}
-
-	revs := getValidCacheEntries(hra, now)
-
-	counts := map[string]int{}
-
-	for _, r := range revs {
-		counts[r.Key] += r.Value
-	}
-
-	want := map[string]int{"foo": 3}
-
-	if d := cmp.Diff(want, counts); d != "" {
-		t.Errorf("%s", d)
-	}
-}

controllers/integration_test.go

@@ -8,7 +8,7 @@ import (
 	"time"
 
 	github2 "github.com/actions-runner-controller/actions-runner-controller/github"
-	"github.com/google/go-github/v37/github"
+	"github.com/google/go-github/v45/github"
 
 	"github.com/actions-runner-controller/actions-runner-controller/github/fake"
 
@@ -108,8 +108,9 @@ func SetupIntegrationTest(ctx2 context.Context) *testEnvironment {
 			RunnerImage:                 "example/runner:test",
 			DockerImage:                 "example/docker:test",
 			Name:                        controllerName("runner"),
-			RegistrationRecheckInterval: time.Millisecond,
-			RegistrationRecheckJitter:   time.Millisecond,
+			RegistrationRecheckInterval: time.Millisecond * 100,
+			RegistrationRecheckJitter:   time.Millisecond * 10,
+			UnregistrationRetryDelay:    1 * time.Second,
 		}
 		err = runnerController.SetupWithManager(mgr)
 		Expect(err).NotTo(HaveOccurred(), "failed to setup runner controller")
@@ -268,7 +269,6 @@ var _ = Context("INTEGRATION: Inside of a new namespace", func() {
 
 				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1)
 				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 2)
-				ExpectHRAStatusCacheEntryLengthEventuallyEquals(ctx, ns.Name, name, 1)
 			}
 
 			{
@@ -371,7 +371,6 @@ var _ = Context("INTEGRATION: Inside of a new namespace", func() {
 
 				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1)
 				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 3)
-				ExpectHRAStatusCacheEntryLengthEventuallyEquals(ctx, ns.Name, name, 1)
 			}
 
 			{
@@ -538,6 +537,106 @@ var _ = Context("INTEGRATION: Inside of a new namespace", func() {
 			}
 		})
 
+		It("should create and scale organization's repository runners on workflow_job event", func() {
+			name := "example-runnerdeploy"
+
+			{
+				rd := &actionsv1alpha1.RunnerDeployment{
+					ObjectMeta: metav1.ObjectMeta{
+						Name:      name,
+						Namespace: ns.Name,
+					},
+					Spec: actionsv1alpha1.RunnerDeploymentSpec{
+						Replicas: intPtr(1),
+						Selector: &metav1.LabelSelector{
+							MatchLabels: map[string]string{
+								"foo": "bar",
+							},
+						},
+						Template: actionsv1alpha1.RunnerTemplate{
+							ObjectMeta: metav1.ObjectMeta{
+								Labels: map[string]string{
+									"foo": "bar",
+								},
+							},
+							Spec: actionsv1alpha1.RunnerSpec{
+								RunnerConfig: actionsv1alpha1.RunnerConfig{
+									Repository: "test/valid",
+									Image:      "bar",
+									Group:      "baz",
+								},
+								RunnerPodSpec: actionsv1alpha1.RunnerPodSpec{
+									Env: []corev1.EnvVar{
+										{Name: "FOO", Value: "FOOVALUE"},
+									},
+								},
+							},
+						},
+					},
+				}
+
+				ExpectCreate(ctx, rd, "test RunnerDeployment")
+				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1)
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 1)
+				env.ExpectRegisteredNumberCountEventuallyEquals(1, "count of fake list runners")
+			}
+
+			// Scale-up to 1 replica via ScaleUpTriggers.GitHubEvent.WorkflowJob based scaling
+			{
+				hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+					ObjectMeta: metav1.ObjectMeta{
+						Name:      name,
+						Namespace: ns.Name,
+					},
+					Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+						ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+							Name: name,
+						},
+						MinReplicas:                       intPtr(1),
+						MaxReplicas:                       intPtr(5),
+						ScaleDownDelaySecondsAfterScaleUp: intPtr(1),
+						ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+							{
+								GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+									WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+								},
+								Amount:   1,
+								Duration: metav1.Duration{Duration: time.Minute},
+							},
+						},
+					},
+				}
+
+				ExpectCreate(ctx, hra, "test HorizontalRunnerAutoscaler")
+
+				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1)
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 1)
+				env.ExpectRegisteredNumberCountEventuallyEquals(1, "count of fake list runners")
+			}
+
+			// Scale-up to 2 replicas on first workflow_job.queued webhook event
+			{
+				env.SendWorkflowJobEvent("test", "valid", "queued", []string{"self-hosted"})
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 2, "runners after first webhook event")
+				env.ExpectRegisteredNumberCountEventuallyEquals(2, "count of fake list runners")
+			}
+
+			// Scale-up to 3 replicas on second workflow_job.queued webhook event
+			{
+				env.SendWorkflowJobEvent("test", "valid", "queued", []string{"self-hosted"})
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 3, "runners after second webhook event")
+				env.ExpectRegisteredNumberCountEventuallyEquals(3, "count of fake list runners")
+			}
+
+			// Do not scale-up on third workflow_job.queued webhook event
+			// repo "example" doesn't match our Spec
+			{
+				env.SendWorkflowJobEvent("test", "example", "queued", []string{"self-hosted"})
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 3, "runners after third webhook event")
+				env.ExpectRegisteredNumberCountEventuallyEquals(3, "count of fake list runners")
+			}
+		})
+
 		It("should create and scale organization's repository runners only on check_run event", func() {
 			name := "example-runnerdeploy"
 
@@ -582,9 +681,7 @@ var _ = Context("INTEGRATION: Inside of a new namespace", func() {
 				env.ExpectRegisteredNumberCountEventuallyEquals(1, "count of fake list runners")
 			}
 
-			// Scale-up to 3 replicas by the default TotalNumberOfQueuedAndInProgressWorkflowRuns-based scaling
-			// See workflowRunsFor3Replicas_queued and workflowRunsFor3Replicas_in_progress for GitHub List-Runners API responses
-			// used while testing.
+			// Scale-up to 1 replica via ScaleUpTriggers.GitHubEvent.CheckRun based scaling
 			{
 				hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
 					ObjectMeta: metav1.ObjectMeta{
@@ -1077,24 +1174,176 @@ var _ = Context("INTEGRATION: Inside of a new namespace", func() {
 			}
 		})
 
+		It("should be able to scale visible organization runner group with default labels", func() {
+			name := "example-runnerdeploy"
+
+			{
+				rd := &actionsv1alpha1.RunnerDeployment{
+					ObjectMeta: metav1.ObjectMeta{
+						Name:      name,
+						Namespace: ns.Name,
+					},
+					Spec: actionsv1alpha1.RunnerDeploymentSpec{
+						Replicas: intPtr(1),
+						Selector: &metav1.LabelSelector{
+							MatchLabels: map[string]string{
+								"foo": "bar",
+							},
+						},
+						Template: actionsv1alpha1.RunnerTemplate{
+							ObjectMeta: metav1.ObjectMeta{
+								Labels: map[string]string{
+									"foo": "bar",
+								},
+							},
+							Spec: actionsv1alpha1.RunnerSpec{
+								RunnerConfig: actionsv1alpha1.RunnerConfig{
+									Repository: "test/valid",
+									Image:      "bar",
+									Group:      "baz",
+								},
+								RunnerPodSpec: actionsv1alpha1.RunnerPodSpec{
+									Env: []corev1.EnvVar{
+										{Name: "FOO", Value: "FOOVALUE"},
+									},
+								},
+							},
+						},
+					},
+				}
+
+				ExpectCreate(ctx, rd, "test RunnerDeployment")
+
+				hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+					ObjectMeta: metav1.ObjectMeta{
+						Name:      name,
+						Namespace: ns.Name,
+					},
+					Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+						ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+							Name: name,
+						},
+						MinReplicas:                       intPtr(1),
+						MaxReplicas:                       intPtr(5),
+						ScaleDownDelaySecondsAfterScaleUp: intPtr(1),
+						ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+							{
+								GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+									WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+								},
+								Amount:   1,
+								Duration: metav1.Duration{Duration: time.Minute},
+							},
+						},
+					},
+				}
+
+				ExpectCreate(ctx, hra, "test HorizontalRunnerAutoscaler")
+
+				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1)
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 1)
+			}
+
+			{
+				env.ExpectRegisteredNumberCountEventuallyEquals(1, "count of fake list runners")
+			}
+
+			// Scale-up to 2 replicas on first workflow_job webhook event
+			{
+				env.SendWorkflowJobEvent("test", "valid", "queued", []string{"self-hosted"})
+				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1, "runner sets after webhook")
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 2, "runners after first webhook event")
+				env.ExpectRegisteredNumberCountEventuallyEquals(2, "count of fake list runners")
+			}
+		})
+
+		It("should be able to scale visible organization runner group with custom labels", func() {
+			name := "example-runnerdeploy"
+
+			{
+				rd := &actionsv1alpha1.RunnerDeployment{
+					ObjectMeta: metav1.ObjectMeta{
+						Name:      name,
+						Namespace: ns.Name,
+					},
+					Spec: actionsv1alpha1.RunnerDeploymentSpec{
+						Replicas: intPtr(1),
+						Selector: &metav1.LabelSelector{
+							MatchLabels: map[string]string{
+								"foo": "bar",
+							},
+						},
+						Template: actionsv1alpha1.RunnerTemplate{
+							ObjectMeta: metav1.ObjectMeta{
+								Labels: map[string]string{
+									"foo": "bar",
+								},
+							},
+							Spec: actionsv1alpha1.RunnerSpec{
+								RunnerConfig: actionsv1alpha1.RunnerConfig{
+									Repository: "test/valid",
+									Image:      "bar",
+									Group:      "baz",
+									Labels:     []string{"custom-label"},
+								},
+								RunnerPodSpec: actionsv1alpha1.RunnerPodSpec{
+									Env: []corev1.EnvVar{
+										{Name: "FOO", Value: "FOOVALUE"},
+									},
+								},
+							},
+						},
+					},
+				}
+
+				ExpectCreate(ctx, rd, "test RunnerDeployment")
+
+				hra := &actionsv1alpha1.HorizontalRunnerAutoscaler{
+					ObjectMeta: metav1.ObjectMeta{
+						Name:      name,
+						Namespace: ns.Name,
+					},
+					Spec: actionsv1alpha1.HorizontalRunnerAutoscalerSpec{
+						ScaleTargetRef: actionsv1alpha1.ScaleTargetRef{
+							Name: name,
+						},
+						MinReplicas:                       intPtr(1),
+						MaxReplicas:                       intPtr(5),
+						ScaleDownDelaySecondsAfterScaleUp: intPtr(1),
+						ScaleUpTriggers: []actionsv1alpha1.ScaleUpTrigger{
+							{
+								GitHubEvent: &actionsv1alpha1.GitHubEventScaleUpTriggerSpec{
+									WorkflowJob: &actionsv1alpha1.WorkflowJobSpec{},
+								},
+								Amount:   1,
+								Duration: metav1.Duration{Duration: time.Minute},
+							},
+						},
+					},
+				}
+
+				ExpectCreate(ctx, hra, "test HorizontalRunnerAutoscaler")
+
+				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1)
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 1)
+			}
+
+			{
+				env.ExpectRegisteredNumberCountEventuallyEquals(1, "count of fake list runners")
+			}
+
+			// Scale-up to 2 replicas on first workflow_job webhook event
+			{
+				env.SendWorkflowJobEvent("test", "valid", "queued", []string{"custom-label"})
+				ExpectRunnerSetsCountEventuallyEquals(ctx, ns.Name, 1, "runner sets after webhook")
+				ExpectRunnerSetsManagedReplicasCountEventuallyEquals(ctx, ns.Name, 2, "runners after first webhook event")
+				env.ExpectRegisteredNumberCountEventuallyEquals(2, "count of fake list runners")
+			}
+		})
+
 	})
 })
 
-func ExpectHRAStatusCacheEntryLengthEventuallyEquals(ctx context.Context, ns string, name string, value int, optionalDescriptions ...interface{}) {
-	EventuallyWithOffset(
-		1,
-		func() int {
-			var hra actionsv1alpha1.HorizontalRunnerAutoscaler
-
-			err := k8sClient.Get(ctx, types.NamespacedName{Namespace: ns, Name: name}, &hra)
-
-			ExpectWithOffset(1, err).NotTo(HaveOccurred(), "failed to get test HRA resource")
-
-			return len(hra.Status.CacheEntries)
-		},
-		time.Second*5, time.Millisecond*500).Should(Equal(value), optionalDescriptions...)
-}
-
 func ExpectHRADesiredReplicasEquals(ctx context.Context, ns, name string, desired int, optionalDescriptions ...interface{}) {
 	var rd actionsv1alpha1.HorizontalRunnerAutoscaler
 
@@ -1118,7 +1367,7 @@ func (env *testEnvironment) ExpectRegisteredNumberCountEventuallyEquals(want int
 
 			return len(rs)
 		},
-		time.Second*5, time.Millisecond*500).Should(Equal(want), optionalDescriptions...)
+		time.Second*10, time.Millisecond*500).Should(Equal(want), optionalDescriptions...)
 }
 
 func (env *testEnvironment) SendOrgPullRequestEvent(org, repo, branch, action string) {
@@ -1166,6 +1415,30 @@ func (env *testEnvironment) SendOrgCheckRunEvent(org, repo, status, action strin
 	ExpectWithOffset(1, resp.StatusCode).To(Equal(200))
 }
 
+func (env *testEnvironment) SendWorkflowJobEvent(org, repo, statusAndAction string, labels []string) {
+	resp, err := sendWebhook(env.webhookServer, "workflow_job", &github.WorkflowJobEvent{
+		WorkflowJob: &github.WorkflowJob{
+			Status: &statusAndAction,
+			Labels: labels,
+		},
+		Org: &github.Organization{
+			Login: github.String(org),
+		},
+		Repo: &github.Repository{
+			Name: github.String(repo),
+			Owner: &github.User{
+				Login: github.String(org),
+				Type:  github.String("Organization"),
+			},
+		},
+		Action: github.String(statusAndAction),
+	})
+
+	ExpectWithOffset(1, err).NotTo(HaveOccurred(), "failed to send workflow_job event")
+
+	ExpectWithOffset(1, resp.StatusCode).To(Equal(200))
+}
+
 func (env *testEnvironment) SendUserPullRequestEvent(owner, repo, branch, action string) {
 	resp, err := sendWebhook(env.webhookServer, "pull_request", &github.PullRequestEvent{
 		PullRequest: &github.PullRequest{