Merge pull request #1248 from kubereboot/dependabot/github_actions/jdx/mise-action-3.4.0

Bumps alpine from 3.22.2 to 3.23.3.

---
updated-dependencies:
- dependency-name: alpine
  dependency-version: 3.23.3
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

.clomonitor.yml

@@ -0,0 +1,3 @@
+exemptions:
+  - check: analytics
+    reason: "We don't track people"

.github/ct.yaml

@@ -1,7 +0,0 @@
-# See https://github.com/helm/chart-testing#configuration
-remote: origin
-target-branch: main
-chart-dirs:
-  - charts
-chart-repos: []
-helm-extra-args: --timeout 600s

.github/dependabot.yml

@@ -16,6 +16,6 @@ updates:
       - dependency-name: "k8s.io/client-go"
       - dependency-name: "k8s.io/kubectl"
   - package-ecosystem: "docker"
-    directory: "cmd/kured"
+    directory: "/"
     schedule:
       interval: "daily"

.github/kind-cluster-1.21.yaml

@@ -1,13 +0,0 @@
-kind: Cluster
-apiVersion: kind.x-k8s.io/v1alpha4
-nodes:
-- role: control-plane
-  image: kindest/node:v1.21.2
-- role: control-plane
-  image: kindest/node:v1.21.2
-- role: control-plane
-  image: kindest/node:v1.21.2
-- role: worker
-  image: kindest/node:v1.21.2
-- role: worker
-  image: kindest/node:v1.21.2

.github/kind-cluster-1.22.yaml

@@ -1,13 +0,0 @@
-kind: Cluster
-apiVersion: kind.x-k8s.io/v1alpha4
-nodes:
-- role: control-plane
-  image: kindest/node:v1.22.4
-- role: control-plane
-  image: kindest/node:v1.22.4
-- role: control-plane
-  image: kindest/node:v1.22.4
-- role: worker
-  image: kindest/node:v1.22.4
-- role: worker
-  image: kindest/node:v1.22.4

.github/kind-cluster-1.23.yaml

@@ -1,13 +0,0 @@
-kind: Cluster
-apiVersion: kind.x-k8s.io/v1alpha4
-nodes:
-- role: control-plane
-  image: "kindest/node:v1.23.0"
-- role: control-plane
-  image: "kindest/node:v1.23.0"
-- role: control-plane
-  image: "kindest/node:v1.23.0"
-- role: worker
-  image: "kindest/node:v1.23.0"
-- role: worker
-  image: "kindest/node:v1.23.0"

.github/kind-cluster-current.yaml

@@ -0,0 +1,9 @@
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+nodes:
+- role: control-plane
+  image: "kindest/node:v1.34.0"
+- role: worker
+  image: "kindest/node:v1.34.0"
+- role: worker
+  image: "kindest/node:v1.34.0"

.github/kind-cluster-next.yaml

@@ -0,0 +1,9 @@
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+nodes:
+- role: control-plane
+  image: "kindest/node:v1.35.0"
+- role: worker
+  image: "kindest/node:v1.35.0"
+- role: worker
+  image: "kindest/node:v1.35.0"

.github/kind-cluster-previous.yaml

@@ -0,0 +1,9 @@
+kind: Cluster
+apiVersion: kind.x-k8s.io/v1alpha4
+nodes:
+- role: control-plane
+  image: "kindest/node:v1.33.4"
+- role: worker
+  image: "kindest/node:v1.33.4"
+- role: worker
+  image: "kindest/node:v1.33.4"

.github/workflows/codeql.yml

@@ -0,0 +1,83 @@
+# For most projects, this workflow file will not need changing; you simply need
+# to commit it to your repository.
+#
+# You may wish to alter this file to override the set of languages analyzed,
+# or to provide custom queries or build logic.
+#
+# ******** NOTE ********
+# We have attempted to detect the languages in your repository. Please check
+# the `language` matrix defined below to confirm you have the correct set of
+# supported CodeQL languages.
+#
+name: "CodeQL"
+
+on:
+  workflow_dispatch:
+  push:
+    branches: [ "main" ]
+  pull_request:
+    # The branches below must be a subset of the branches above
+    branches: [ "main" ]
+  schedule:
+    - cron: '24 13 * * 6'
+
+permissions:
+  contents: read
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-latest
+    permissions:
+      actions: read
+      contents: read
+      security-events: write
+
+    strategy:
+      fail-fast: false
+      matrix:
+        language: [ 'go' ]
+        # CodeQL supports [ 'cpp', 'csharp', 'go', 'java', 'javascript', 'python', 'ruby' ]
+        # Learn more about CodeQL language support at https://aka.ms/codeql-docs/language-support
+
+    steps:
+    - name: Harden Runner
+      uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+      with:
+        egress-policy: audit
+
+    - name: Checkout repository
+      uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+    # Initializes the CodeQL tools for scanning.
+    - name: Initialize CodeQL
+      uses: github/codeql-action/init@64d10c13136e1c5bce3e5fbde8d4906eeaafc885 # v3.30.6
+      with:
+        languages: ${{ matrix.language }}
+        # If you wish to specify custom queries, you can do so here or in a config file.
+        # By default, queries listed here will override any specified in a config file.
+        # Prefix the list here with "+" to use these queries and those in the config file.
+        
+        # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
+        # queries: security-extended,security-and-quality
+
+        
+    # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
+    # If this step fails, then you should remove it and run the build manually (see below)
+    - name: Autobuild
+      uses: github/codeql-action/autobuild@64d10c13136e1c5bce3e5fbde8d4906eeaafc885 # v3.30.6
+
+    # ℹ️ Command-line programs to run using the OS shell.
+    # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
+
+    #   If the Autobuild fails above, remove it and uncomment the following three lines. 
+    #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
+
+    # - run: |
+    #   echo "Run, Build Application using script"
+    #   ./location_of_script_within_repo/buildscript.sh
+
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@64d10c13136e1c5bce3e5fbde8d4906eeaafc885 # v3.30.6
+      with:
+        category: "/language:${{matrix.language}}"

.github/workflows/dependency-review.yml

@@ -0,0 +1,28 @@
+# Dependency Review Action
+#
+# This Action will scan dependency manifest files that change as part of a Pull Request,
+# surfacing known-vulnerable versions of the packages declared or updated in the PR.
+# Once installed, if the workflow run is marked as required,
+# PRs introducing known-vulnerable packages will be blocked from merging.
+#
+# Source repository: https://github.com/actions/dependency-review-action
+name: 'Dependency Review'
+on: [pull_request]
+
+permissions:
+  contents: read
+
+jobs:
+  dependency-review:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+      - name: 'Checkout Repository'
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+      - name: 'Dependency Review'
+        uses: actions/dependency-review-action@40c09b7dc99638e5ddb0bfd91c1673effc064d8a # v4.8.1

.github/workflows/on-main-push-charts.yaml

@@ -1,19 +0,0 @@
-name: Publish helm chart
-on:
-  push:
-    branches:
-      - "main"
-    paths:
-      - "charts/**"
-
-jobs:
-  publish-helm-chart:
-    name: Publish latest chart
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Publish Helm chart
-        uses: stefanprodan/helm-gh-pages@master
-        with:
-          token: ${{ secrets.GITHUB_TOKEN }}
-          charts_dir: charts

.github/workflows/on-main-push.yaml

@@ -5,41 +5,85 @@ on:
   push:
     branches:
       - main
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+permissions:
+  contents: read
+
 jobs:
   tag-scan-and-push-final-image:
     name: "Build, scan, and publish tagged image"
     runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      contents: write
+      packages: write
     steps:
-      - uses: actions/checkout@v2
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
 
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
 
       - name: Ensure go version
-        uses: actions/setup-go@v2
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
         with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
+          go-version-file: 'go.mod'
+          check-latest: true
 
-      - name: Login to DockerHub
-        uses: docker/login-action@v1
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
         with:
-          username: ${{ secrets.DOCKERHUB_USERNAME_WEAVEWORKSKUREDCI }}
-          password: ${{ secrets.DOCKERHUB_TOKEN_WEAVEWORKSKUREDCI }}
+          version: 2025.10.5
 
       - name: Login to ghcr.io
-        uses: docker/login-action@v1
+        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
         with:
-          registry: ghcr.io
-          username: weave-ghcr-bot
-          password: ${{ secrets.KURED_WEAVE_GHCR_BOT_TOKEN }}
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+
+      - name: Find current tag version
+        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+        id: tags
+
+      - name: Build binaries
+        run: make kured-release-snapshot
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
       - name: Build image
-        run: |
-          make DH_ORG="${{ github.repository_owner }}" image
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
+        with:
+          context: .
+          platforms: linux/arm64, linux/amd64, linux/arm/v7, linux/arm/v6, linux/386
+          push: true
+          labels: ${{ steps.meta.outputs.labels }}
+          tags: |
+            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.sha_short }}
 
-      - name: Publish image
+      - name: Generate SBOM
         run: |
-          make DH_ORG="${{ github.repository_owner }}" publish-image
+          syft ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.sha_short }} -o spdx > kured.sbom
+
+      - name: Sign and attest artifacts
+        run: |
+          cosign sign -y -r ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.sha_short }}
+          cosign sign-blob -y --output-signature kured.sbom.sig --output-certificate kured.sbom.pem kured.sbom
+          cosign attest -y --type spdx --predicate kured.sbom ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.sha_short }}
+          cosign attach sbom --type spdx --sbom kured.sbom ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.sha_short }}

.github/workflows/on-pr-charts.yaml

@@ -1,78 +0,0 @@
-#This is just extra testing, for lint check, and basic installation
-#Those can fail earlier than functional tests (shorter tests)
-# and give developer feedback soon if they didn't test themselves
-name: PR - charts
-on:
-  pull_request:
-    paths:
-      - "charts/**"
-jobs:
-  # We create two jobs (with a matrix) instead of one to make those parallel.
-  # We don't need to conditionally check if something has changed, due to github actions
-  # tackling that for us.
-  # Fail-fast ensures that if one of those matrix job fail, the other one gets cancelled.
-  test-chart:
-    name: Test helm chart changes
-    runs-on: ubuntu-latest
-    strategy:
-      fail-fast: true
-      matrix:
-        test-action:
-          - lint
-          - install
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-        with:
-          fetch-depth: "0"
-
-      - uses: actions/setup-python@v2
-        with:
-          python-version: 3.7
-
-      # Helm is already present in github actions, so do not re-install it
-      - name: Setup chart testing
-        uses: helm/chart-testing-action@v2.1.0
-
-      - name: Create default kind cluster
-        uses: helm/kind-action@v1.2.0
-        with:
-          version: v0.11.0
-        if: ${{ matrix.test-action == 'install' }}
-
-      - name: Run chart tests
-        run: ct ${{ matrix.test-action }} --config .github/ct.yaml
-
-  # This doesn't re-use the ct actions, due to many limitations (auto tear down, no real testing)
-  deploy-chart:
-    name: Functional test of helm chart in its current state (needs published image of the helm chart)
-    runs-on: ubuntu-latest
-    needs: test-chart
-    steps:
-      - uses: actions/checkout@v2
-      
-      # Default name for helm/kind-action kind clusters is "chart-testing"
-      - name: Create 1 node kind cluster
-        uses: helm/kind-action@v1.2.0
-        with:
-          version: v0.11.0
-
-      - name: Deploy kured on default namespace with its helm chart
-        run: |
-          # Documented in official helm doc to live on the edge
-          curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          # Refresh bins
-          hash -r
-          helm install kured ./charts/kured/ --set configuration.period=1m --wait
-          kubectl config set-context kind-chart-testing
-          kubectl get ds --all-namespaces
-          kubectl describe ds kured
-
-      - name: Test if successful deploy
-        uses: nick-invision/retry@v2.6.0
-        with:
-          timeout_minutes: 10
-          max_attempts: 10
-          retry_wait_seconds: 10
-          # DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE should all be = to cluster_size
-          command: "kubectl get ds kured | grep -E 'kured.*1.*1.*1.*1.*1'"

.github/workflows/on-pr-docs.yaml

@@ -0,0 +1,26 @@
+name: Verify Docs Links
+on:
+  pull_request:
+  push:
+    paths:
+      - '**.md'
+
+jobs:
+  pr-check-docs-links:
+    name: Check docs for incorrect links
+    runs-on: ubuntu-latest
+    steps:
+    - name: Harden Runner
+      uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+      with:
+        egress-policy: audit
+
+    - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+    - name: Link Checker
+      uses: lycheeverse/lychee-action@a8c4c7cb88f0c7386610c35eb25108e448569cb0 # v2.7.0
+      env:
+        GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+      with:
+        args: --verbose --no-progress '*.md' '*.yaml' '*/*/*.go' --exclude-link-local
+        fail: true

.github/workflows/on-pr.yaml

@@ -4,94 +4,83 @@ on:
   push:
 
 jobs:
-  pr-gotest:
-    name: Run go tests
-    runs-on: ubuntu-18.04
+  pr-short-tests:
+    name: Run short go tests
+    runs-on: ubuntu-latest
     steps:
-      - name: checkout
-        uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
-      - name: Ensure go version
-        uses: actions/setup-go@v2
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
         with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
+          egress-policy: audit
+
+      - name: checkout
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+      - name: Ensure go version
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
+        with:
+          go-version-file: 'go.mod'
+          check-latest: true
+
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
+        with:
+          version: 2025.10.5
+
       - name: run tests
-        run: go test -json ./... > test.json
+        run: make test
+
       - name: Annotate tests
         if: always()
-        uses: guyarb/golang-test-annoations@v0.5.0
+        uses: guyarb/golang-test-annoations@2941118d7ef622b1b3771d1ff6eae9e90659eb26 # v0.8.0
         with:
           test-results: test.json
 
-  pr-shellcheck:
-    name: Lint bash code with shellcheck
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - name: Run ShellCheck
-      uses: bewuethr/shellcheck-action@v2
-
-  pr-lint-code:
-    name: Lint golang code
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - name: Find go version
-      run: |
-        GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-        echo "::set-output name=version::${GO_VERSION}"
-      id: awk_gomod
-    - name: Ensure go version
-      uses: actions/setup-go@v2
-      with:
-        go-version: "${{ steps.awk_gomod.outputs.version }}"
-    - name: Lint cmd folder
-      uses: Jerome1337/golint-action@v1.0.2
-      with:
-        golint-path: './cmd/...'
-    - name: Lint pkg folder
-      uses: Jerome1337/golint-action@v1.0.2
-      with:
-        golint-path: './pkg/...'
-
-  pr-check-docs-links:
-    name: Check docs for incorrect links
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - name: Link Checker
-      id: lc
-      uses: peter-evans/link-checker@v1
-      with:
-        args: -r *.md *.yaml */*/*.go -x .cluster.local
-    - name: Fail if there were link errors
-      run: exit ${{ steps.lc.outputs.exit_code }}
-
   # This should not be made a mandatory test
-  # It is only used to make us aware of any potential security failure, that
+  # It is only used to make us aware of any potential security failure that
   # should trigger a bump of the image in build/.
   pr-vuln-scan:
     name: Build image and scan it against known vulnerabilities
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
       - name: Ensure go version
-        uses: actions/setup-go@v2
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
         with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
-      - run: make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" image
-      - uses: Azure/container-scan@v0
+          go-version-file: 'go.mod'
+          check-latest: true
+
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
         with:
-          image-name: docker.io/${{ github.repository_owner }}/kured:${{ github.sha }}
+          version: 2025.10.5
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+
+      - name: Find current tag version
+        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+        id: tags
+
+      - name: Build image
+        run: VERSION="${{ steps.tags.outputs.sha_short }}" DH_ORG="${{ github.repository_owner }}" make image
+
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8
+        with:
+          image-ref: 'ghcr.io/${{ github.repository }}:${{ steps.tags.outputs.sha_short }}'
+          format: 'table'
+          exit-code: '1'
+          ignore-unfixed: true
+          vuln-type: 'os,library'
+          severity: 'CRITICAL,HIGH'
 
   # This ensures the latest code works with the manifests built from tree.
   # It is useful for two things:
@@ -99,238 +88,91 @@ jobs:
   # - Ensure manifests work with the latest versions even with no manifest change
   #     (compared to helm charts, manifests cannot easily template changes based on versions)
   # Helm charts are _trailing_ releases, while manifests are done during development.
+  # This test uses the "command" reboot-method.
   e2e-manifests:
     name: End-to-End test with kured with code and manifests from HEAD
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
-        kubernetes:
-          - "1.21"
-          - "1.22"
-          - "1.23"
+        testname:
+          - "TestE2EWithCommand"
+          - "TestE2EWithSignal"
+          - "TestE2EConcurrentWithCommand"
+          - "TestE2EConcurrentWithSignal"
+        kubernetes_version:
+          - "previous"
+          - "current"
+          - "next"
     steps:
-      - uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
       - name: Ensure go version
-        uses: actions/setup-go@v2
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
         with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
-      - name: Build artifacts
-        run: |
-          make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" image
-          make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" manifest
+          go-version-file: 'go.mod'
+          check-latest: true
 
-      - name: Workaround "Failed to attach 1 to compat systemd cgroup /actions_job/..." on gh actions
-        run: |
-          sudo bash << EOF
-              cp /etc/docker/daemon.json /etc/docker/daemon.json.old
-              echo '{}' > /etc/docker/daemon.json
-              systemctl restart docker || journalctl --no-pager -n 500
-              systemctl status docker
-          EOF
-
-      # Default name for helm/kind-action kind clusters is "chart-testing"
-      - name: Create kind cluster with 5 nodes
-        uses: helm/kind-action@v1.2.0
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
         with:
-          config: .github/kind-cluster-${{ matrix.kubernetes }}.yaml
-          version: v0.11.0
+          version: 2025.10.5
 
-      - name: Preload previously built images onto kind cluster
-        run: kind load docker-image docker.io/${{ github.repository_owner }}/kured:${{ github.sha }} --name chart-testing
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
 
-      - name: Do not wait for an hour before detecting the rebootSentinel
-        run: |
-          sed -i 's/#\(.*\)--period=1h/\1--period=30s/g' kured-ds.yaml
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
-      - name: Install kured with kubectl
-        run: |
-          kubectl apply -f kured-rbac.yaml && kubectl apply -f kured-ds.yaml
+      - name: Find current tag version
+        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+        id: tags
 
-      - name: Ensure kured is ready
-        uses: nick-invision/retry@v2.6.0
-        with:
-          timeout_minutes: 10
-          max_attempts: 10
-          retry_wait_seconds: 60
-          # DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE should all be = to cluster_size
-          command: "kubectl get ds -n kube-system kured | grep -E 'kured.*5.*5.*5.*5.*5'"
+      - name: Run specific e2e tests
+        run: make e2e-test ARGS="-run ^${{ matrix.testname }}/${{ matrix.kubernetes_version }}"
 
-      - name: Create reboot sentinel files
-        run: |
-          ./tests/kind/create-reboot-sentinels.sh
 
-      - name: Follow reboot until success
-        env:
-          DEBUG: true
-        run: |
-          ./tests/kind/follow-coordinated-reboot.sh
-
-  scenario-prom-helm:
-    name: Test prometheus with latest code from HEAD (=overrides image of the helm chart)
+  e2e-tests-singleversion:
+    name: End-to-End test targetting a single version of kubernetes
     runs-on: ubuntu-latest
-    # only build with oldest and newest supported, it should be good enough.
     strategy:
       fail-fast: false
       matrix:
-        kubernetes:
-          - "1.21"
+        testname:
+          - "TestCordonningIsKept/concurrency1"
+          - "TestCordonningIsKept/concurrency2"
+          - "TestE2EBlocker/podblocker"
     steps:
-      - uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
       - name: Ensure go version
-        uses: actions/setup-go@v2
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
         with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
-      - name: Build artifacts
-        run: |
-          make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" image
-          make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" helm-chart
+          go-version-file: 'go.mod'
+          check-latest: true
 
-      - name: Workaround 'Failed to attach 1 to compat systemd cgroup /actions_job/...' on gh actions
-        run: |
-          sudo bash << EOF
-              cp /etc/docker/daemon.json /etc/docker/daemon.json.old
-              echo '{}' > /etc/docker/daemon.json
-              systemctl restart docker || journalctl --no-pager -n 500
-              systemctl status docker
-          EOF
-
-      # Default name for helm/kind-action kind clusters is "chart-testing"
-      - name: Create 1 node kind cluster
-        uses: helm/kind-action@v1.2.0
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
         with:
-          version: v0.11.0
+          version: 2025.10.5
 
-      - name: Preload previously built images onto kind cluster
-        run: kind load docker-image docker.io/${{ github.repository_owner }}/kured:${{ github.sha }} --name chart-testing
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
 
-      - name: Deploy kured on default namespace with its helm chart
-        run: |
-          # Documented in official helm doc to live on the edge
-          curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          # Refresh bins
-          hash -r
-          helm install kured ./charts/kured/ --wait --values ./charts/kured/ci/prometheus-values.yaml
-          kubectl config set-context kind-chart-testing
-          kubectl get ds --all-namespaces
-          kubectl describe ds kured
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
 
-      - name: Ensure kured is ready
-        uses: nick-invision/retry@v2.6.0
-        with:
-          timeout_minutes: 10
-          max_attempts: 10
-          retry_wait_seconds: 60
-          # DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE
-          command: "kubectl get ds kured | grep -E 'kured.*1.*1.*1.*1.*1' "
+      - name: Find current tag version
+        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+        id: tags
 
-      - name: Get metrics (healthy)
-        uses: nick-invision/retry@v2.6.0
-        with:
-          timeout_minutes: 2
-          max_attempts: 12
-          retry_wait_seconds: 5
-          command: "./tests/kind/test-metrics.sh 0"
-
-      - name: Create reboot sentinel files
-        run: |
-          ./tests/kind/create-reboot-sentinels.sh
-
-      - name: Get metrics (need reboot)
-        uses: nick-invision/retry@v2.6.0
-        with:
-          timeout_minutes: 15
-          max_attempts: 10
-          retry_wait_seconds: 60
-          command: "./tests/kind/test-metrics.sh 1"
-
-
-  # TEMPLATE Scenario testing.
-  # Note: keep in mind that the helm chart's appVersion is overriden to test your HEAD of the branch,
-  # if you `make helm-chart`.
-  # This will allow you to test properly your scenario and not use an existing image which will not
-  # contain your feature.
-
-  # scenario-<REPLACETHIS>-helm:
-  #   #example: Testing <REPLACETHIS> with helm chart and code from HEAD"
-  #   name: "<REPLACETHIS>"
-  #   runs-on: ubuntu-latest
-  #   strategy:
-  #     fail-fast: false
-  #     # You can define your own kubernetes versions. For example if your helm chart change should behave differently with different kubernetes versions.
-  #     matrix:
-  #       kubernetes:
-  #         - "1.20"
-  #   steps:
-  #     - uses: actions/checkout@v2
-  #     - name: Find go version
-  #       run: |
-  #         GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-  #         echo "::set-output name=version::${GO_VERSION}"
-  #       id: awk_gomod
-  #     - name: Ensure go version
-  #       uses: actions/setup-go@v2
-  #       with:
-  #         go-version: "${{ steps.awk_gomod.outputs.version }}"
-  #     - name: Build artifacts
-  #       run: |
-  #         make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" image
-  #         make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" helm-chart
-  #
-  #     - name: "Workaround 'Failed to attach 1 to compat systemd cgroup /actions_job/...' on gh actions"
-  #       run: |
-  #         sudo bash << EOF
-  #             cp /etc/docker/daemon.json /etc/docker/daemon.json.old
-  #             echo '{}' > /etc/docker/daemon.json
-  #             systemctl restart docker || journalctl --no-pager -n 500
-  #             systemctl status docker
-  #         EOF
-  #
-  #     # Default name for helm/kind-action kind clusters is "chart-testing"
-  #     - name: Create 5 node kind cluster
-  #       uses: helm/kind-action@master
-  #       with:
-  #         config: .github/kind-cluster-${{ matrix.kubernetes }}.yaml
-  #
-  #     - name: Preload previously built images onto kind cluster
-  #       run: kind load docker-image docker.io/${{ github.repository_owner }}/kured:${{ github.sha }} --name chart-testing
-  #
-  #     - name: Deploy kured on default namespace with its helm chart
-  #       run: |
-  #         # Documented in official helm doc to live on the edge
-  #         curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-  #         # Refresh bins
-  #         hash -r
-  #         helm install kured ./charts/kured/ --wait --values ./charts/kured/ci/<REPLACETHIS>-values.yaml
-  #         kubectl config set-context kind-chart-testing
-  #         kubectl get ds --all-namespaces
-  #         kubectl describe ds kured
-  #
-  #     - name: Ensure kured is ready
-  #       uses: nick-invision/retry@v2.6.0
-  #       with:
-  #         timeout_minutes: 10
-  #         max_attempts: 10
-  #         retry_wait_seconds: 60
-  #         # DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE should all be = 5
-  #         command: "kubectl get ds kured | grep -E 'kured.*5.*5.*5.*5.*5' "
-  #
-  #     - name: Create reboot sentinel files
-  #       run: |
-  #         ./tests/kind/create-reboot-sentinels.sh
-  #
-  #     - name: Test <REPLACETHIS>
-  #       env:
-  #         DEBUG: true
-  #       run: |
-  #         <TODO>
+      - name: Run specific e2e tests
+        run: make e2e-test ARGS="-run ^${{ matrix.testname }}"

.github/workflows/on-tag.yaml

@@ -7,43 +7,104 @@ on:
   push:
     tags:
       - "*"
+
+env:
+  REGISTRY: ghcr.io
+  IMAGE_NAME: ${{ github.repository }}
+
+permissions:
+  contents: read
+
 jobs:
   tag-scan-and-push-final-image:
     name: "Build, scan, and publish tagged image"
     runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      contents: write
+      packages: write
     steps:
-      - uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
-      - name: Ensure go version
-        uses: actions/setup-go@v2
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
         with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
-      - name: Find current tag version
-        run: echo "::set-output name=version::${GITHUB_REF#refs/tags/}"
-        id: tags
-      - run: |
-          make DH_ORG="${{ github.repository_owner }}" VERSION="${{ steps.tags.outputs.version }}" image
-      - uses: Azure/container-scan@v0
-        with:
-          image-name: docker.io/${{ github.repository_owner }}/kured:${{ steps.tags.outputs.version }}
+          egress-policy: audit
 
-      - name: Login to DockerHub
-        uses: docker/login-action@v1
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+      - name: Ensure go version
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
         with:
-          username: ${{ secrets.DOCKERHUB_USERNAME_WEAVEWORKSKUREDCI }}
-          password: ${{ secrets.DOCKERHUB_TOKEN_WEAVEWORKSKUREDCI }}
+          go-version-file: 'go.mod'
+          check-latest: true
+
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
+        with:
+          version: 2025.10.5
+
+      - name: Find current tag version
+        run: echo "version=${GITHUB_REF#refs/tags/}" >> $GITHUB_OUTPUT
+        id: tags
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+
+      - name: Build binaries
+        run: make kured-release-tag
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build single image for scan
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
+        with:
+          context: .
+          push: false
+          load: true
+          tags: |
+            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }}
+
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8
+        with:
+          image-ref: '${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }}'
+          format: 'table'
+          exit-code: '1'
+          ignore-unfixed: true
+          vuln-type: 'os,library'
+          severity: 'CRITICAL,HIGH'
 
       - name: Login to ghcr.io
-        uses: docker/login-action@v1
+        uses: docker/login-action@5e57cd118135c172c3672efd75eb46360885c0ef # v3.6.0
         with:
-          registry: ghcr.io
-          username: weave-ghcr-bot
-          password: ${{ secrets.KURED_WEAVE_GHCR_BOT_TOKEN }}
+          registry: ${{ env.REGISTRY }}
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
 
-      - name: Publish image
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@c1e51972afc2121e065aed6d45c65596fe445f3f
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+
+      - name: Build release images
+        uses: docker/build-push-action@263435318d21b8e681c14492fe198d362a7d2c83 # v6.18.0
+        with:
+          context: .
+          platforms: linux/arm64, linux/amd64, linux/arm/v7, linux/arm/v6, linux/386
+          push: true
+          labels: ${{ steps.meta.outputs.labels }}
+          tags: |
+            ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }}
+
+      - name: Generate SBOM
         run: |
-          make DH_ORG="${{ github.repository_owner }}" VERSION="${{ steps.tags.outputs.version }}" publish-image
+          syft ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }} -o spdx > kured.sbom
+
+      - name: Sign and attest artifacts
+        run: |
+          cosign sign -y -r ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }}
+          cosign sign-blob -y --output-signature kured.sbom.sig kured.sbom
+          cosign attest -y --type spdx --predicate kured.sbom ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }}
+          cosign attach sbom --type spdx --sbom kured.sbom ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}:${{ steps.tags.outputs.version }}

.github/workflows/periodics-daily.yaml

@@ -1,136 +0,0 @@
-name: Daily jobs
-
-on:
-  schedule:
-  - cron: "30 1 * * *"
-
-jobs:
-  periodics-gotest:
-    name: Run go tests
-    runs-on: ubuntu-18.04
-    steps:
-      - name: checkout
-        uses: actions/checkout@v2
-      - name: run tests
-        run: go test -json ./... > test.json
-      - name: Annotate tests
-        if: always()
-        uses: guyarb/golang-test-annoations@v0.5.0
-        with:
-          test-results: test.json
-
-  periodics-mark-stale:
-    name: Mark stale issues and PRs
-    runs-on: ubuntu-latest
-    steps:
-    # Stale by default waits for 60 days before marking PR/issues as stale, and closes them after 21 days.
-    # Do not expire the first issues that would allow the community to grow.
-    - uses: actions/stale@v4
-      with:
-        repo-token: ${{ secrets.GITHUB_TOKEN }}
-        stale-issue-message: 'This issue was automatically considered stale due to lack of activity. Please update it and/or join our slack channels to promote it, before it automatically closes (in 7 days).'
-        stale-pr-message: 'This PR was automatically considered stale due to lack of activity. Please refresh it and/or join our slack channels to highlight it, before it automatically closes (in 7 days).'
-        stale-issue-label: 'no-issue-activity'
-        stale-pr-label: 'no-pr-activity'
-        exempt-issue-labels: 'good first issue,keep'
-        days-before-close: 21
-
-  check-docs-links:
-    name: Check docs for incorrect links
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - name: Link Checker
-      id: lc
-      uses: peter-evans/link-checker@v1
-      with:
-        args: -r *.md *.yaml */*/*.go -x .cluster.local
-    - name: Fail if there were link errors
-      run: exit ${{ steps.lc.outputs.exit_code }}
-
-  vuln-scan:
-    name: Build image and scan it against known vulnerabilities
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
-      - name: Ensure go version
-        uses: actions/setup-go@v2
-        with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
-      - run: make DH_ORG="${{ github.repository_owner }}" VERSION="${{ github.sha }}" image
-      - uses: Azure/container-scan@v0
-        with:
-          image-name: docker.io/${{ github.repository_owner }}/kured:${{ github.sha }}
-
-  deploy-helm:
-    name: Ensure our currently released helm chart works on all kubernetes versions
-    runs-on: ubuntu-latest
-    # only build with oldest and newest supported, it should be good enough.
-    strategy:
-      matrix:
-        kubernetes:
-          - "1.21"
-          - "1.22"
-          - "1.23"
-    steps:
-      - uses: actions/checkout@v2
-      - name: Find go version
-        run: |
-          GO_VERSION=$(awk '/^go/ {print $2};' go.mod)
-          echo "::set-output name=version::${GO_VERSION}"
-        id: awk_gomod
-      - name: Ensure go version
-        uses: actions/setup-go@v2
-        with:
-          go-version: "${{ steps.awk_gomod.outputs.version }}"
-
-      - name: "Workaround 'Failed to attach 1 to compat systemd cgroup /actions_job/...' on gh actions"
-        run: |
-          sudo bash << EOF
-              cp /etc/docker/daemon.json /etc/docker/daemon.json.old
-              echo '{}' > /etc/docker/daemon.json
-              systemctl restart docker || journalctl --no-pager -n 500
-              systemctl status docker
-          EOF
-
-      # Default name for helm/kind-action kind clusters is "chart-testing"
-      - name: Create 5 node kind cluster
-        uses: helm/kind-action@v1.2.0
-        with:
-          config: .github/kind-cluster-${{ matrix.kubernetes }}.yaml
-          version: v0.11.0
-
-      - name: Deploy kured on default namespace with its helm chart
-        run: |
-          # Documented in official helm doc to live on the edge
-          curl https://raw.githubusercontent.com/helm/helm/main/scripts/get-helm-3 | bash
-          # Refresh bins
-          hash -r
-          helm install kured ./charts/kured/ --set configuration.period=1m
-          kubectl config set-context kind-chart-testing
-          kubectl get ds --all-namespaces
-          kubectl describe ds kured
-
-      - name: Ensure kured is ready
-        uses: nick-invision/retry@v2.6.0
-        with:
-          timeout_minutes: 10
-          max_attempts: 10
-          retry_wait_seconds: 60
-          # DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE should all be = 5
-          command: "kubectl get ds kured | grep -E 'kured.*5.*5.*5.*5.*5' "
-
-      - name: Create reboot sentinel files
-        run: |
-          ./tests/kind/create-reboot-sentinels.sh
-
-      - name: Follow reboot until success
-        env:
-          DEBUG: true
-        run: |
-          ./tests/kind/follow-coordinated-reboot.sh

.github/workflows/periodics-weekly.yaml

@@ -0,0 +1,116 @@
+name: Daily jobs
+
+on:
+  schedule:
+  - cron: "30 1 * * 6"
+
+jobs:
+  periodics-gotest:
+    name: Run go tests
+    runs-on: ubuntu-latest
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+
+      - name: checkout
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
+        with:
+          version: 2025.10.5
+
+      - name: run tests
+        run: make test
+
+      - name: Annotate tests
+        if: always()
+        uses: guyarb/golang-test-annoations@2941118d7ef622b1b3771d1ff6eae9e90659eb26 # v0.8.0
+        with:
+          test-results: test.json
+
+  periodics-mark-stale:
+    name: Mark stale issues and PRs
+    runs-on: ubuntu-latest
+    steps:
+    # Stale, by default, waits for 60 days before marking PR/issues as stale and closes them after 21 days.
+    # Do not expire the first issues that would allow the community to grow.
+    - name: Harden Runner
+      uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+      with:
+        egress-policy: audit
+
+    - uses: actions/stale@5f858e3efba33a5ca4407a664cc011ad407f2008 # v10.1.0
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: 'This issue was automatically considered stale due to lack of activity. Please update it and/or join our slack channels to promote it, before it automatically closes (in 7 days).'
+        stale-pr-message: 'This PR was automatically considered stale due to lack of activity. Please refresh it and/or join our slack channels to highlight it, before it automatically closes (in 7 days).'
+        stale-issue-label: 'no-issue-activity'
+        stale-pr-label: 'no-pr-activity'
+        exempt-issue-labels: 'good first issue,keep'
+        exempt-pr-labels: 'keep'
+        days-before-close: 21
+
+  check-docs-links:
+    name: Check docs for incorrect links
+    runs-on: ubuntu-latest
+    steps:
+    - name: Harden Runner
+      uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+      with:
+        egress-policy: audit
+
+    - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+    - name: Link Checker
+      uses: lycheeverse/lychee-action@a8c4c7cb88f0c7386610c35eb25108e448569cb0
+      env:
+        GITHUB_TOKEN: ${{secrets.GITHUB_TOKEN}}
+      with:
+        args: --verbose --no-progress '*.md' '*.yaml' '*/*/*.go' --exclude-link-local
+        fail: true
+
+  vuln-scan:
+    name: Build image and scan it against known vulnerabilities
+    runs-on: ubuntu-latest
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+
+      - name: Ensure go version
+        uses: actions/setup-go@44694675825211faa026b3c33043df3e48a5fa00 # v6.0.0
+        with:
+          go-version-file: 'go.mod'
+          check-latest: true
+
+      - uses: jdx/mise-action@146a28175021df8ca24f8ee1828cc2a60f980bd5 # v3.5.1
+        with:
+          version: 2025.10.5
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@c7c53464625b32c7a7e944ae62b3e17d2b600130 # v3.7.0
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@e468171a9de216ec08956ac3ada2f0791b6bd435 # v3.11.1
+
+      - name: Find current tag version
+        run: echo "sha_short=$(git rev-parse --short HEAD)" >> $GITHUB_OUTPUT
+        id: tags
+
+      - name: Build artifacts
+        run: VERSION="${{ steps.tags.outputs.sha_short }}" DH_ORG="${{ github.repository_owner }}" make image
+      - name: Run Trivy vulnerability scanner
+        uses: aquasecurity/trivy-action@b6643a29fecd7f34b3597bc6acb0a98b03d33ff8
+        with:
+          image-ref: 'ghcr.io/${{ github.repository }}:${{ steps.tags.outputs.sha_short }}'
+          format: 'table'
+          exit-code: '1'
+          ignore-unfixed: true
+          vuln-type: 'os,library'
+          severity: 'CRITICAL,HIGH'

.github/workflows/scorecard.yml

@@ -0,0 +1,78 @@
+# This workflow uses actions that are not certified by GitHub. They are provided
+# by a third-party and are governed by separate terms of service, privacy
+# policy, and support documentation.
+
+name: Scorecard supply-chain security
+on:
+  # For Branch-Protection check. Only the default branch is supported. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#branch-protection
+  branch_protection_rule:
+  # To guarantee Maintained check is occasionally updated. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#maintained
+  schedule:
+    - cron: '34 3 * * 6'
+  push:
+    branches: [ "main" ]
+
+# Declare default permissions as read only.
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecard analysis
+    runs-on: ubuntu-latest
+    permissions:
+      # Needed to upload the results to code-scanning dashboard.
+      security-events: write
+      # Needed to publish results and get a badge (see publish_results below).
+      id-token: write
+      # Uncomment the permissions below if installing in a private repository.
+      # contents: read
+      # actions: read
+
+    steps:
+      - name: Harden Runner
+        uses: step-security/harden-runner@95d9a5deda9de15063e7595e9719c11c38c90ae2 # v2.13.2
+        with:
+          egress-policy: audit
+
+      - name: "Checkout code"
+        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        with:
+          persist-credentials: false
+
+      - name: "Run analysis"
+        uses: ossf/scorecard-action@4eaacf0543bb3f2c246792bd56e8cdeffafb205a # v2.4.3
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          # (Optional) "write" PAT token. Uncomment the `repo_token` line below if:
+          # - you want to enable the Branch-Protection check on a *public* repository, or
+          # - you are installing Scorecard on a *private* repository
+          # To create the PAT, follow the steps in https://github.com/ossf/scorecard-action?tab=readme-ov-file#authentication-with-fine-grained-pat-optional.
+          # repo_token: ${{ secrets.SCORECARD_TOKEN }}
+
+          # Public repositories:
+          #   - Publish results to OpenSSF REST API for easy access by consumers
+          #   - Allows the repository to include the Scorecard badge.
+          #   - See https://github.com/ossf/scorecard-action#publishing-results.
+          # For private repositories:
+          #   - `publish_results` will always be set to `false`, regardless
+          #     of the value entered here.
+          publish_results: true
+
+      # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
+      # format to the repository Actions tab.
+      - name: "Upload artifact"
+        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v3.pre.node20
+        with:
+          name: SARIF file
+          path: results.sarif
+          retention-days: 5
+
+      # Upload the results to GitHub's code scanning dashboard (optional).
+      # Commenting out will disable upload of results to your repo's Code Scanning dashboard
+      - name: "Upload to code-scanning"
+        uses: github/codeql-action/upload-sarif@64d10c13136e1c5bce3e5fbde8d4906eeaafc885 # v3.30.6
+        with:
+          sarif_file: results.sarif

.gitignore

@@ -1,3 +1,6 @@
 cmd/kured/kured
 vendor
 build
+dist
+test.json
+tests/kind/testfiles/*.yaml

.golangci.yml

@@ -0,0 +1,37 @@
+version: "2"
+#timeout : 5m we can add this if needed 
+modules-download-mode: readonly
+run:
+  tests: false
+linters:
+  enable:
+    - govet
+    - staticcheck
+    - unused
+    - contextcheck
+    - goconst
+    - gosec
+    - testifylint
+    - errcheck
+    - revive
+
+linters-settings:
+  errcheck:
+    check-type-assertions: true
+    check-blank: true
+  revive:
+    severity: warning
+    confidence: 0.8
+    rules:
+      - name: indent-error-flow
+      - name: var-naming
+      - name: import-shadowing
+      # https://github.com/mgechev/revive/blob/HEAD/RULES_DESCRIPTIONS.md#package-comments
+      - name: package-comments # This is not working!
+        disabled: true
+output:
+  format: colored-line-number
+  print-issued-lines: true
+  print-linter-name: true
+  uniq-by-line: false
+  sort-results: true

.goreleaser.yml

@@ -0,0 +1,32 @@
+project_name: kured
+before:
+  hooks:
+    - go mod tidy
+builds:
+  - main: ./cmd/kured
+    env:
+      - CGO_ENABLED=0
+    goos:
+      - linux
+    goarch:
+      - amd64
+      - arm64
+      - arm
+      - "386"
+    goarm:
+      - "6"
+      - "7"
+    ldflags:
+      - -s -w -X main.version={{ if .IsSnapshot }}{{ .ShortCommit }}{{ else }}{{ .Version }}{{ end }}
+    mod_timestamp: "{{ .CommitTimestamp }}"
+    flags:
+      - -trimpath
+
+snapshot:
+  name_template: "{{ .ShortCommit }}"
+
+release:
+  disable: true
+
+changelog:
+  skip: true

.lycheeignore

@@ -0,0 +1,6 @@
+app.fossa.com
+cluster.local
+hooks.slack.com
+localhost
+slack://
+teams://

.mise/config.toml

@@ -0,0 +1,8 @@
+[tools]
+cosign = "2.2.3"
+golangci-lint = "2.1.6"
+goreleaser = "1.24.0"
+kind = "0.31.0"
+kubectl = "1.35.0"
+shellcheck = "0.11.0"
+syft = "1.0.1"

CODE_OF_CONDUCT.md

@@ -0,0 +1,3 @@
+# Kured Community Code of Conduct
+
+Kured follows the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/main/code-of-conduct.md).

CONTRIBUTING.md

@@ -0,0 +1,357 @@
+# Developing `kured`
+
+We love contributions to `kured`, no matter if you are [helping out on
+Slack][slack], reporting or triaging [issues][issues] or contributing code
+to `kured`.
+
+In any case, it will make sense to familiarise yourself with the main
+[documentation][documentation] to understand the different features and
+options, which is helpful for testing. The "building" section in
+particular makes sense if you are planning to contribute code.
+
+[slack]: https://github.com/kubereboot/kured/blob/main/README.md#getting-help
+[issues]: https://github.com/kubereboot/kured/issues
+[documentation]: https://kured.dev/docs
+
+## Prepare your environment
+
+### Your IDE
+
+![JetBrains logo](https://resources.jetbrains.com/storage/products/company/brand/logos/jetbrains.png)
+
+The core team has access to Goland from [JetBrains][JetBrains]. Huge thanks to them for their sponsorship!
+
+You can use the IDE you prefer. Don't include anything from your IDE in the .gitignore. Please do so in your global .gitignore.
+
+[JetBrains]: https://www.jetbrains.com/
+
+### Basic binaries required
+
+Your system needs at least the following binaries installed:
+
+- make
+- sed
+- find
+- bash (command, echo)
+- docker (for docker buildx)
+- go (see the required version in go.mod)
+- mise (to manage developer tools. See [mise installation instructions](https://mise.jdx.dev/installing-mise.html).)
+
+### Fetch the additional binaries required
+
+Please run `make install-tools` once on a fresh repository clone to download necessary developer tools.
+Installed tools are listed in [.mise directory](.mise/config.toml).
+
+### Configure your git for the "Certificate of Origin"
+
+By contributing to this project, you agree to the Developer Certificate of
+Origin (DCO). This document was created by the Linux Kernel community and is a
+simple statement that you, as a contributor, have the legal right to make the
+contribution.
+
+We require all commits to be signed. By signing off with your signature, you
+certify that you wrote the patch or otherwise have the right to contribute the
+material by the rules of the [DCO](DCO):
+
+`Signed-off-by: Jane Doe <jane.doe@example.com>`
+
+The signature must contain your real name
+(sorry, no pseudonyms or anonymous contributions)
+If your `user.name` and `user.email` are configured in your Git config,
+you can sign your commit automatically with `git commit -s`.
+
+## Get to know Kured repositories
+
+All Kured repositories are kept under <https://github.com/kubereboot>. To find the code and work on the individual pieces that make Kured, here is our overview:
+
+| Repositories                            | Contents                  |
+|-----------------------------------------|---------------------------|
+| <https://github.com/kubereboot/kured>   | Kured operator itself     |
+| <https://github.com/kubereboot/charts>  | Helm chart                |
+| <https://github.com/kubereboot/website> | website and documentation |
+
+We use GitHub Actions in all our repositories.
+
+### Charts repo structure highlights
+
+- We use GitHub Actions to do the chart testing. Only linting/installation happens, no e2e test is done.
+- [charts/kured](https://github.com/kubereboot/charts/tree/main/charts/kured) is the place to contribute changes to the chart. Please bump [Chart.yaml](https://github.com/kubereboot/charts/blob/main/charts/kured/Chart.yaml) at each change according to semver.
+
+### Kured repo structure highlights
+
+Kured's main code can be found in the [`cmd`](cmd) and [`pkg`](pkg) directories
+
+Keep in mind we always want to guarantee that `kured` works for the previous, current, and next
+minor version of kubernetes according to `client-go` and `kubectl` dependencies in use.
+
+Our e2e tests are in the [`tests`](tests) directory. These are deep tests using our manifests with different params, on all supported k8s versions of a release.
+They are expensive but allow us to catch many issues quickly. If you want to ensure your scenario works, add an e2e test for it! Those e2e tests are encouraged by the maintainer team (See below).
+
+We also have other tests:
+
+- golangci-lint , shellcheck
+- a security check against our base image (alpine)
+
+All these tests are run on every PR/tagged release. See [.github/workflows](.github/workflows) for more details.
+
+We use [GoReleaser to build](.goreleaser.yml).
+
+## Regular development activities / maintenance
+
+### Updating k8s support
+
+At each new major release of kubernetes, we update our dependencies.
+
+Beware that whenever we want to update e.g. the `kubectl` or `client-go` dependencies, some other impactful changes might be necessary too.
+(RBAC, drain behaviour changes, ...)
+
+A few examples of what it took to support:
+
+- Kubernetes 1.10 <https://github.com/kubereboot/kured/commit/b3f9ddf> + <https://github.com/kubereboot/kured/commit/bc3f28d> + <https://github.com/kubereboot/kured/commit/908998a> + <https://github.com/kubereboot/kured/commit/efbb0c3> + <https://github.com/kubereboot/kured/commit/5731b98>
+- Kubernetes 1.14 <https://github.com/kubereboot/kured/pull/75>
+- Kubernetes 1.34 <https://github.com/kubereboot/kured/commit/6ab853dd711ee264663184976ae492a20b657b0a>
+
+Search the git log for inspiration for your cases.
+
+In general, the following activities have to happen:
+
+- Bump kind and its images (see below)
+- `go get k8s.io/kubectl@v0.{version}`
+
+### bump kind images support
+
+Go to `.github/workflows` and update the new k8s images. For that:
+
+- `cp .github/kind-cluster-current.yaml .github/kind-cluster-previous.yaml`
+- `cp .github/kind-cluster-next.yaml .github/kind-cluster-current.yaml`
+- Then edit `.github/kind-cluster-next.yaml` to point to the new version.
+
+This will make the full test matrix updated (the CI and the test code).
+
+Once your code passes all tests, update the support matrix in
+the [installation docs](https://kured.dev/docs/installation/).
+
+Beware that sometimes you also need to update the Kind version. grep in the [.github/workflows](.github/workflows) for the kind version.
+
+### Updating other dependencies
+
+Dependabot proposes changes in our `go.mod`/`go.sum`.
+CI testing covers some of those changes, but not all.
+
+Please make sure to test those not covered by CI (mostly the integration
+with other tools) manually before merging.
+
+In all cases, review dependabot changes: Imagine all changes as a possible supply chain
+attack vector. You then need to review the proposed changes by dependabot and evaluate the trust/risks.
+
+### Review periodic jobs
+
+We run periodic jobs (see also Automated testing section of this documentation).
+Those should be monitored for failures.
+
+If a failure happens in periodic testing, something terribly wrong must have happened
+(or GitHub is failing at the creation of a kind cluster). Please monitor those
+failures carefully.
+
+## Testing kured
+
+If you have developed anything (or just want to take kured for a spin!), run the following tests.
+As they will run in CI, we will quickly catch if you did not test before submitting your PR.
+
+### Linting
+
+We use [`golangci-lint`](https://golangci-lint.run/) for Go code linting.
+
+To run lint checks locally:
+
+```bash
+make lint
+```
+
+### Quick Golang code testing
+
+Please run `make test` to run only the basic tests. It gives a good
+idea of the code behaviour.
+
+### Functional testing 
+
+For functional testing, the maintainer team is using `minikube` or `kind` (explained below), but also encourages you to test kured on your own cluster(s).
+
+#### Testing on your own cluster
+
+This will allow the community to catch issues that might not have been tested in our CI, like integration with other tools, or your specific use case.
+
+To test kured on your own cluster, make sure you pass the right `image`, update the `period` and `reboot-days` (so you get immediate results), and update any other flags for your cases.
+Then login to a node and run:
+
+```console
+sudo touch /var/run/reboot-required
+```
+
+Then tell us about everything that went well or went wrong in Slack.
+
+#### Testing with `minikube`
+
+A test-run with `minikube` could look like this:
+
+```cli
+# start minikube
+minikube start --driver=kvm2 --kubernetes-version <k8s-release>
+
+# build kured image and publish to registry accessible by minikube
+make image minikube-publish
+
+# edit kured-ds.yaml to
+#   - point to new image
+#   - change e.g. period and reboot-days option for immediate results
+
+minikube kubectl -- apply -f kured-rbac.yaml
+minikube kubectl -- apply -f kured-ds.yaml
+minikube kubectl -- logs daemonset.apps/kured -n kube-system -f
+
+# In separate terminal
+minikube ssh
+ sudo touch /var/run/reboot-required
+minikube logs -f
+```
+
+Now check for the 'Commanding reboot' message and minikube going down.
+
+Unfortunately, as of today, you are going to run into
+<https://github.com/kubernetes/minikube/issues/2874>. This means that
+minikube won't come back easily. You will need to start minikube again.
+Then you can check for the lock release.
+
+#### Testing with `kind` "The hard way"
+
+A test-run with `kind` could look like this:
+
+```cli
+# create kind cluster
+kind create cluster --config .github/kind-cluster-<k8s-version>.yaml
+
+# create reboot required files on pre-defined kind nodes
+./tests/kind/create-reboot-sentinels.sh
+
+# check if reboot is working fine
+./tests/kind/follow-coordinated-reboot.sh
+
+```
+
+### Testing with `kind` "The easy way"
+
+You can automate the test with `kind` by using the same code as the CI.
+
+```cli
+# Build kured:dev image, build manifests, and run the "long" go tests
+make e2e-test
+```
+
+You can alter the test behaviour by passing arguments to this command.
+A few examples are given below:
+
+```shell
+# Run only TestE2EWithSignal test for the kubernetes version named "current" (see kind file)
+make e2e-test ARGS="-run ^TestE2EWithSignal/current"
+# Run all tests but make sure to extend the timeout, for slower machines.
+make e2e-test ARGS="-timeout 1200s'
+```
+
+## Introducing new features
+
+When you introduce a new feature, the kured team expects you to have tested (see above!)
+your change thoroughly. If possible, include all the necessary testing in your change.
+
+If your change involves a user facing change (change in flags of kured for example),
+please include expose your new feature in our default manifest (`kured-ds.yaml`),
+as a comment.
+
+Our release manifests and helm charts are our stable interfaces.
+Any user facing changes will therefore have to wait for a release before being
+exposed to our users.
+
+This also means that when you expose a new feature, you should create another PR
+for your changes in <https://github.com/kubereboot/charts> to make your feature
+available at the next kured version for helm users.
+
+In the charts PR, you can directly bump the `appVersion` to the next minor version
+(you are introducing a new feature, which requires a bump of the minor number.
+For example, if current `appVersion` is `1.6.x`, make sure you update your `appVersion`
+to `1.7.0`). It allows us to have an easy view of what we land each release.
+
+Do not hesitate to increase the test coverage for your feature, whether it's unit testing 
+to full functional testing (even using helm charts).
+
+The team of kured is small, so we will most likely refuse any feature adding maintenance burden.
+
+## Introducing changes in the helm chart
+
+When you change the helm chart, remember to bump its version according to semver.
+Changes to defaults are frowned upon unless absolutely necessary.
+
+## Introducing new tests / increasing test coverage
+
+On the opposite of features, we welcome ALL features increasing our stability and test coverage.
+See also our GitHub issues with the label [`testing`](https://github.com/kubereboot/kured/labels/testing).
+
+## Publishing a new kured release
+
+### Double-check the latest kubernetes patch version
+
+Ensure you have used the latest patch version in the tree. 
+Check the documentation "Updating k8s support" if the minor version was not yet applied.
+
+### Update the manifests with the new version
+
+```sh
+export VERSION=1.20.0
+make DH_ORG="kubereboot" VERSION="${VERSION}" manifest
+```
+Create a commit updating the manifest with future image [like this one](https://github.com/kubereboot/kured/commit/58091f6145771f426b4b9e012a43a9c847af2560).
+
+### Create the combined manifest for the new release
+
+Now create the `kured-<new version>-combined.yaml` for e.g. `1.20.0`:
+
+```sh
+export VERSION=1.20.0
+export MANIFEST="kured-$VERSION-combined.yaml"
+make DH_ORG="kubereboot" VERSION="${VERSION}" manifest # just to be safe
+cat kured-rbac.yaml > "$MANIFEST"
+cat kured-ds.yaml >> "$MANIFEST"
+```
+
+### Create the new version tag on the repo (optional, can also be done directly in GH web interface)
+
+Tag the previously created commit with the future release version.
+The GitHub Actions workflow will push the new image to the registry.
+
+### Publish new version release artifacts
+
+Now you can head to the GitHub UI for releases, drafting a new
+release. Chose, as tag, the new version number.
+
+Click to generate the release notes.
+
+Fill, as name, "Kured <new version>".
+
+Edit the generated text.
+
+Please describe what's new and noteworthy in the release notes, list the PRs
+that landed and give a shout-out to everyone who contributed.
+Please also note down on which releases the upcoming `kured` release was
+tested on or what it supports. (Check old release notes if you're unsure.)
+
+Before clicking on publishing release, upload the yaml manifest
+(`kured-<new version>-combined.yaml`) file.
+
+Click on publish the release and set as the latest release.
+
+### Prepare Helm chart
+
+Create a commit to [bump the chart and kured version like this one](https://github.com/kubereboot/charts/commit/e0191d91c21db8338be8cbe56f8991a557048110).
+
+### Prepare Documentation
+
+Ensure the [compatibility matrix](https://kured.dev/docs/installation/) is updated to the new version you want to release.
+

DCO

@@ -0,0 +1,36 @@
+Developer Certificate of Origin
+Version 1.1
+
+Copyright (C) 2004, 2006 The Linux Foundation and its contributors.
+660 York Street, Suite 102,
+San Francisco, CA 94110 USA
+
+Everyone is permitted to copy and distribute verbatim copies of this
+license document, but changing it is not allowed.
+
+
+Developer's Certificate of Origin 1.1
+
+By making a contribution to this project, I certify that:
+
+(a) The contribution was created in whole or in part by me and I
+    have the right to submit it under the open source license
+    indicated in the file; or
+
+(b) The contribution is based upon previous work that, to the best
+    of my knowledge, is covered under an appropriate open source
+    license and I have the right under that license to submit that
+    work with modifications, whether created in whole or in part
+    by me, under the same open source license (unless I am
+    permitted to submit under a different license), as indicated
+    in the file; or
+
+(c) The contribution was provided directly to me by some other
+    person who certified (a), (b) or (c) and I have not modified
+    it.
+
+(d) I understand and agree that this project and the contribution
+    are public and that a record of the contribution (including all
+    personal information I submit with it, including my sign-off) is
+    maintained indefinitely and may be redistributed consistent with
+    this project or the open source license(s) involved.

DEVELOPMENT.md

@@ -1,235 +1 @@
-# Developing `kured`
-
-We love contributions to `kured`, no matter if you are [helping out on
-Slack][slack], reporting or triaging [issues][issues] or contributing code
-to `kured`.
-
-In any case, it will make sense to familiarise yourself with the main
-[README][readme] to understand the different features and options, which is
-helpful for testing. The "building" section in particular makes sense if
-you are planning to contribute code.
-
-[slack]: README.md#getting-help
-[issues]: https://github.com/weaveworks/kured/issues
-[readme]: README.md
-
-## Regular development activities
-
-### Updating k8s support
-
-Whenever we want to update e.g. the `kubectl` or `client-go` dependencies,
-some RBAC changes might be necessary too.
-
-This is what it took to support Kubernetes 1.14:
-<https://github.com/weaveworks/kured/pull/75>
-
-That the process can be more involved that that can be seen in
-<https://github.com/weaveworks/kured/commits/support-k8s-1.10>
-
-Please update our .github/workflows with the new k8s images, starting by
-the creation of a .github/kind-cluster-<version>.yaml, then updating
-our workflows with the new versions.
-
-Once you updated everything, make sure you update the support matrix on
-the main [README][readme] as well.
-
-### Updating other dependencies
-
-Dependabot proposes changes in our go.mod/go.sum.
-Some of those changes are covered by CI testing, some are not.
-
-Please make sure to test those not covered by CI (mostly the integration
-with other tools) manually before merging.
-
-### Review periodic jobs
-
-We run periodic jobs (see also Automated testing section of this documentation).
-Those should be monitored for failures.
-
-If a failure happen in periodics, something terribly wrong must have happened
-(or github is failing at the creation of a kind cluster). Please monitor those
-failures carefully.
-
-### Introducing new features
-
-When you introduce a new feature, the kured team expects you to have tested
-your change thoroughly. If possible, include all the necessary testing in your change.
-
-If your change involves a user facing change (change in flags of kured for example),
-please include expose your new feature in our default manifest (`kured-ds.yaml`),
-as a comment.
-
-Do not update the helm chart directly.
-Helm charts and our release manifests (see below) are our stable interfaces.
-Any user facing changes will therefore have to wait for a while before being
-exposed to our users.
-
-This also means that when you expose a new feature, you should create another PR
-for your changes in `charts/` to make your feature available for our next kured version.
-In this change, you can directly bump the appVersion to the next minor version.
-(for example, if current appVersion is 1.6.x, make sure you update your appVersion
-to 1.7.0). It allows us to have an easy view of what we land each release.
-
-Do not hesitate to increase the test coverage for your feature, whether it's unit
-testing to full functional testing (even using helm charts)
-
-### Increasing test coverage
-
-We are welcoming any change to increase our test coverage.
-See also our github issues for the label `testing`.
-
-### Updating helm charts
-
-Helm charts are continuously published. Any change in `charts/` will be immediately
-pushed in production.
-
-## Automated testing
-
-Our CI is covered by github actions.
-You can see their contents in .github/workflows.
-
-We currently run:
-- go tests and lint
-- shellcheck
-- a check for dead links in our docs
-- a security check against our base image (alpine)
-- a deep functional test using our manifests on all supported k8s versions
-- basic deployment using our helm chart on any chart change
-
-Changes in helm charts are not functionally tested on PRs. We assume that
-the PRs to implement the feature are properly tested by our users and
-contributors before merge.
-
-To test your code manually, follow the section Manual testing.
-
-## Manual (release) testing
-
-Before `kured` is released, we want to make sure it still works fine on the
-previous, current and next minor version of Kubernetes (with respect to the
-`client-go` & `kubectl` dependencies in use). For local testing e.g.
-`minikube` or `kind` can be sufficient. This will allow you to catch issues
-that might not have been tested in our CI, like integration with other tools,
-or your specific use case.
-
-Deploy kured in your test scenario, make sure you pass the right `image`,
-update the e.g. `period` and `reboot-days` options, so you get immediate
-results, if you login to a node and run:
-
-```console
-sudo touch /var/run/reboot-required
-```
-
-### Example of golang testing
-
-Please run `make test`. You should have golint installed.
-
-### Example of testing with `minikube`
-
-A test-run with `minikube` could look like this:
-
-```console
-# start minikube
-minikube start --vm-driver kvm2 --kubernetes-version <k8s-release>
-
-# build kured image and publish to registry accessible by minikube
-make image minikube-publish
-
-# edit kured-ds.yaml to
-#   - point to new image
-#   - change e.g. period and reboot-days option for immediate results
-
-minikube kubectl -- apply -f kured-rbac.yaml
-minikube kubectl -- apply -f kured-ds.yaml
-minikube kubectl -- logs daemonset.apps/kured -n kube-system -f
-
-# Alternatively use helm to install the chart
-# edit values-local.yaml to change any chart parameters
-helm install kured ./charts/kured --namespace kube-system -f ./charts/kured/values.minikube.yaml
-
-# In separate terminal
-minikube ssh
- sudo touch /var/run/reboot-required
-minikube logs -f
-```
-
-Now check for the 'Commanding reboot' message and minikube going down.
-
-Unfortunately as of today, you are going to run into
-<https://github.com/kubernetes/minikube/issues/2874>. This means that
-minikube won't come back easily. You will need to start minikube again.
-Then you can check for the lock release.
-
-If all the tests ran well, kured maintainers can reach out to the Weaveworks
-team to get an upcoming `kured` release tested in the Dev environment for
-real life testing.
-
-### Example of testing with `kind`
-
-A test-run with `kind` could look like this:
-
-```console
-# create kind cluster
-kind create cluster --config .github/kind-cluster-<k8s-version>.yaml
-
-# create reboot required files on pre-defined kind nodes
-./tests/kind/create-reboot-sentinels.sh
-
-# check if reboot is working fine
-./tests/kind/follow-coordinated-reboot.sh
-
-```
-
-## Publishing a new kured release
-
-### Prepare Documentation
-
-Check that `README.md` has an updated compatibility matrix and that the
-url in the `kubectl` incantation (under "Installation") is updated to the
-new version you want to release.
-
-### Create a tag on the repo
-
-Before going further, we should freeze the code for a release, by
-tagging the code. The Github-Action should start a new job and push
-the new image to the registry.
-
-
-### Create the combined manifest
-
-Now create the `kured-<release>-dockerhub.yaml` for e.g. `1.3.0`:
-
-```sh
-VERSION=1.3.0
-MANIFEST="kured-$VERSION-dockerhub.yaml"
-make DH_ORG="weaveworks" VERSION="${VERSION}" manifest
-cat kured-rbac.yaml > "$MANIFEST"
-cat kured-ds.yaml >> "$MANIFEST"
-```
-
-### Publish release artifacts
-
-Now you can head to the Github UI, use the version number as tag and upload the
-`kured-<release>-dockerhub.yaml` file.
-
-Please describe what's new and noteworthy in the release notes, list the PRs
-that landed and give a shout-out to everyone who contributed.
-
-Please also note down on which releases the upcoming `kured` release was
-tested on. (Check old release notes if you're unsure.)
-
-### Update the Helm chart
-
-You can automatically bump the helm chart's application version
-with the latest image tag by running:
-
-```sh
-make DH_ORG="weaveworks" VERSION="1.3.0" helm-chart
-```
-
-A change in the helm chart requires a bump of the `version`
-in `charts/kured/Chart.yaml` (following the versioning rules).
-Update it, and issue a PR. Upon merge, that PR will automatically
-publish the chart to the gh-pages branch.
-
-When there are open helm-chart PRs which are on hold until the helm-chart has been updated
-with the new kured version, they can be merged now (unless a rebase is needed from the contributor).
+This file was moved to [CONTRIBUTING.md](CONTRIBUTING.md).

Dockerfile

@@ -0,0 +1,25 @@
+FROM alpine:3.23.3@sha256:25109184c71bdad752c8312a8623239686a9a2071e8825f20acb8f2198c3f659 AS bin
+
+ARG TARGETOS
+ARG TARGETARCH
+ARG TARGETVARIANT
+
+COPY dist/ /dist
+RUN set -ex \
+  && case "${TARGETARCH}" in \
+      amd64) \
+          SUFFIX="_v1" \
+          ;; \
+      arm) \
+          SUFFIX="_${TARGETVARIANT:1}" \
+          ;; \
+      *) \
+          SUFFIX="" \
+          ;; \
+    esac \
+  && cp /dist/kured_${TARGETOS}_${TARGETARCH}${SUFFIX}/kured /dist/kured;
+
+FROM alpine:3.23.3@sha256:25109184c71bdad752c8312a8623239686a9a2071e8825f20acb8f2198c3f659
+RUN apk update --no-cache && apk upgrade --no-cache && apk add --no-cache ca-certificates tzdata
+COPY --from=bin /dist/kured /usr/bin/kured
+ENTRYPOINT ["/usr/bin/kured"]

GOVERNANCE.md

@@ -0,0 +1,112 @@
+# Project Governance
+
+- [Values](#values)
+- [Maintainers](#maintainers)
+- [Becoming a Maintainer](#becoming-a-maintainer)
+- [Meetings](#meetings)
+- [Code of Conduct Enforcement](#code-of-conduct)
+- [Voting](#voting)
+
+## Values
+
+The Kured project and its leadership embrace the following values:
+
+- Openness: Communication and decision-making happens in the open and is discoverable for future
+  reference. As much as possible, all discussions and work take place in public
+  forums and open repositories.
+
+- Fairness: All stakeholders have the opportunity to provide feedback and submit
+  contributions, which will be considered on their merits.
+
+- Community over Product or Company: Sustaining and growing our community takes
+  priority over shipping code or sponsors' organizational goals.  Each
+  contributor participates in the project as an individual.
+
+- Inclusivity: We innovate through different perspectives and skill sets, which
+  can only be accomplished in a welcoming and respectful environment.
+
+- Participation: Responsibilities within the project are earned through
+  participation, and there is a clear path up the contributor ladder into leadership
+  positions.
+
+- Consensus: Whether or not wider input is required, the Kured community believes that
+  the best decisions are reached through Consensus
+  <https://en.wikipedia.org/wiki/Consensus_decision-making>.
+
+## Maintainers
+
+Kured Maintainers have write access to the [project GitHub
+organisation](https://github.com/kubereboot). They can merge their own patches or patches
+from others. The current maintainers can be found in [MAINTAINERS][maintainers-file].
+Maintainers collectively manage the project's resources and contributors.
+
+This privilege is granted with some expectation of responsibility: maintainers
+are people who care about the Kured project and want to help it grow and
+improve. A maintainer is not just someone who can make changes, but someone who
+has demonstrated their ability to collaborate with the team, get the most
+knowledgeable people to review code and docs, contribute high-quality code, and
+follow through to fix issues (in code or tests).
+
+A maintainer is a contributor to the project's success and a citizen helping
+the project succeed.
+
+## Becoming a Maintainer
+
+To become a Maintainer you need to demonstrate the following:
+
+- commitment to the project:
+  - participate in discussions, contributions, code and documentation reviews
+      for 3 months or more and participate in Slack discussions and meetings
+      if possible,
+  - perform reviews for 5 non-trivial pull requests,
+  - contribute 5 non-trivial pull requests and have them merged,
+- ability to write quality code and/or documentation,
+- ability to collaborate with the team,
+- understanding of how the team works (policies, processes for testing and code review, etc),
+- understanding of the project's code base and coding and documentation style.
+
+We realise that everybody brings different abilities and qualities to the team, that's
+why we are willing to change the rules somewhat depending on the circumstances.
+
+A new Maintainer can apply by proposing a PR to the [MAINTAINERS
+file][maintainers-file]. A simple majority vote of existing Maintainers
+approves the application.
+
+Maintainers who are selected will be granted the necessary GitHub rights,
+and invited to the [private maintainer mailing list][private-list].
+
+## Meetings
+
+Time zones permitting, Maintainers are expected to participate in the public
+developer meeting, details can be found [here][meeting-agenda].
+
+Maintainers will also have closed meetings in order to discuss security reports
+or Code of Conduct violations.  Such meetings should be scheduled by any
+Maintainer on receipt of a security issue or CoC report.  All current Maintainers
+must be invited to such closed meetings, except for any Maintainer who is
+accused of a CoC violation.
+
+## Code of Conduct
+
+[Code of Conduct](./CODE_OF_CONDUCT.md) violations by community members will
+be discussed and resolved on the [private Maintainer mailing list][private-list].
+If the reported CoC violator is a Maintainer, the Maintainers will instead
+designate two Maintainers to work with CNCF staff in resolving the report.
+
+## Voting
+
+While most business in Kured is conducted by "lazy consensus", periodically
+the Maintainers may need to vote on specific actions or changes.
+A vote can be taken in [kured issues labeled 'decision'][decision-issues] or
+[the private Maintainer mailing list][private-list] for security or conduct
+matters. Votes may also be taken at [the developer meeting][meeting-agenda].
+Any Maintainer may demand a vote be taken.
+
+Most votes require a simple majority of all Maintainers to succeed. Maintainers
+can be removed by a 2/3 majority vote of all Maintainers, and changes to this
+Governance require a 2/3 vote of all Maintainers.
+
+[maintainers-file]: ./MAINTAINERS
+[private-list]: cncf-kured-maintainers@lists.cncf.io
+[meeting-agenda]: https://docs.google.com/document/d/1AWT8YDdqZY-Se6Y1oAlwtujWLVpNVK2M_F_Vfqw06aI/edit
+[decision-issues]: https://github.com/kubereboot/kured/labels/decision

MAINTAINERS

@@ -1,5 +1,12 @@
-Christian Kotzbauer <christian.kotzbauer@gmail.com> (@ckotzbauer)
-Daniel Holbach <daniel@weave.works> (@dholbach)
-Hidde Beydals <hidde@weave.works> (@hiddeco)
-Jean-Phillipe Evrard <jean-philippe.evrard@suse.com> (@evrardjp)
+In alphabetical order:
+
+Dharsan Baskar <git@dharsanb.com> (@dharsanb)
 Jack Francis <jackfrancis@gmail.com> (@jackfrancis)
+Jean-Philippe Evrard <open-source@a.spamming.party> (@evrardjp)
+
+Retired maintainers:
+
+- Daniel Holbach
+- Christian Hopf
+
+Thank you for your involvement, and let us not say "farewell" ...

Makefile

@@ -1,55 +1,72 @@
 .DEFAULT: all
-.PHONY: all clean image publish-image minikube-publish manifest helm-chart test tests
+.PHONY: all clean image minikube-publish manifest test kured-all lint 
 
-DH_ORG=weaveworks
-VERSION=$(shell git symbolic-ref --short HEAD)-$(shell git rev-parse --short HEAD)
+DH_ORG ?= kubereboot
+VERSION=$(shell git rev-parse --short HEAD)
 SUDO=$(shell docker info >/dev/null 2>&1 || echo "sudo -E")
 
 all: image
 
+.PHONY: install-tools
+install-tools:
+	command -v  mise 2>&1 || { echo "please install mise to continue" >&2; exit 127; }
+	mise install
+
 clean:
-	rm -f cmd/kured/kured
-	rm -rf ./build
+	rm -rf ./dist
 
-godeps=$(shell go list -f '{{join .Deps "\n"}}' $1 | grep -v /vendor/ | xargs go list -f '{{if not .Standard}}{{ $$dep := . }}{{range .GoFiles}}{{$$dep.Dir}}/{{.}} {{end}}{{end}}')
+kured:
+	goreleaser build --clean --single-target --snapshot
 
-DEPS=$(call godeps,./cmd/kured)
+kured-all:
+	goreleaser build --clean --snapshot
 
-cmd/kured/kured: $(DEPS)
-cmd/kured/kured: cmd/kured/*.go
-	CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -ldflags "-X main.version=$(VERSION)" -o $@ cmd/kured/*.go
+kured-release-tag:
+	goreleaser release --clean
 
-build/.image.done: cmd/kured/Dockerfile cmd/kured/kured
-	mkdir -p build
-	cp $^ build
-	$(SUDO) docker build -t docker.io/$(DH_ORG)/kured -f build/Dockerfile ./build
-	$(SUDO) docker tag docker.io/$(DH_ORG)/kured docker.io/$(DH_ORG)/kured:$(VERSION)
-	$(SUDO) docker tag docker.io/$(DH_ORG)/kured ghcr.io/$(DH_ORG)/kured:$(VERSION)
-	touch $@
+kured-release-snapshot:
+	goreleaser release --clean --snapshot
 
-image: build/.image.done
+image: kured
+	$(SUDO) docker buildx build --no-cache --load -t ghcr.io/$(DH_ORG)/kured:$(VERSION) .
 
-publish-image: image
-	$(SUDO) docker push docker.io/$(DH_ORG)/kured:$(VERSION)
-	$(SUDO) docker push ghcr.io/$(DH_ORG)/kured:$(VERSION)
+dev-image: image
+	$(SUDO) docker tag ghcr.io/$(DH_ORG)/kured:$(VERSION) kured:dev
+
+dev-manifest:
+	# basic e2e scenario
+	sed -e "s#image: ghcr.io/.*kured.*#image: kured:dev#g" -e 's/#\(.*\)--period=1h/\1--period=20s/g' kured-ds.yaml > tests/kind/testfiles/kured-ds.yaml
+	# signal e2e scenario
+	sed -e "s#image: ghcr.io/.*kured.*#image: kured:dev#g" -e 's/#\(.*\)--period=1h/\1--period=20s/g' kured-ds-signal.yaml > tests/kind/testfiles/kured-ds-signal.yaml
+	# concurrency e2e command scenario
+	sed -e "s#image: ghcr.io/.*kured.*#image: kured:dev#g" -e 's/#\(.*\)--period=1h/\1--period=20s/g' -e 's/#\(.*\)--concurrency=1/\1--concurrency=2/g' kured-ds.yaml > tests/kind/testfiles/kured-ds-concurrent-command.yaml
+	# concurrency e2e signal scenario
+	sed -e "s#image: ghcr.io/.*kured.*#image: kured:dev#g" -e 's/#\(.*\)--period=1h/\1--period=20s/g' -e 's/#\(.*\)--concurrency=1/\1--concurrency=2/g' kured-ds-signal.yaml > tests/kind/testfiles/kured-ds-concurrent-signal.yaml
+	# pod blocker e2e signal scenario
+	sed -e "s#image: ghcr.io/.*kured.*#image: kured:dev#g" -e 's/#\(.*\)--period=1h/\1--period=20s/g' -e 's/#\(.*\)--blocking-pod-selector=name=temperamental/\1--blocking-pod-selector=app=blocker/g' kured-ds-signal.yaml > tests/kind/testfiles/kured-ds-podblocker.yaml
+
+e2e-test: dev-manifest dev-image
+	echo "Running ALL go tests"
+	go test -count=1 -v --parallel 4 ./... $(ARGS)
 
 minikube-publish: image
-	$(SUDO) docker save docker.io/$(DH_ORG)/kured | (eval $$(minikube docker-env) && docker load)
+	$(SUDO) docker save ghcr.io/$(DH_ORG)/kured | (eval $$(minikube docker-env) && docker load)
 
 manifest:
-	sed -i "s#image: docker.io/.*kured.*#image: docker.io/$(DH_ORG)/kured:$(VERSION)#g" kured-ds.yaml
+	sed -i "s#image: ghcr.io/.*kured.*#image: ghcr.io/$(DH_ORG)/kured:$(VERSION)#g" kured-ds.yaml
+	sed -i "s#image: ghcr.io/.*kured.*#image: ghcr.io/$(DH_ORG)/kured:$(VERSION)#g" kured-ds-signal.yaml
 	echo "Please generate combined manifest if necessary"
 
-helm-chart:
-	sed -i "s#repository:.*/kured#repository: $(DH_ORG)/kured#g" charts/kured/values.yaml
-	sed -i "s#appVersion:.*#appVersion: \"$(VERSION)\"#g" charts/kured/Chart.yaml
-	sed -i "s#\`[0-9]*\.[0-9]*\.[0-9]*\`#\`$(VERSION)\`#g" charts/kured/README.md
-	echo "Please bump version in charts/kured/Chart.yaml"
+test: lint
+	@echo "Running short go tests"
+	go test -test.short -json ./... > test.json
 
-test: tests
-	echo "Running go tests"
-	go test ./...
-	echo "Running golint on pkg"
-	golint ./pkg/...
-	echo "Running golint on cmd"
-	golint ./cmd/...
+lint:
+	@echo "Running shellcheck"
+	find . -name '*.sh' | xargs -n1 shellcheck
+	@echo "Running golangci-lint..."
+	golangci-lint run ./...
+
+lint-docs:
+	@echo "Running lychee"
+	mise x lychee@latest -- lychee --verbose --no-progress '*.md' '*.yaml' '*/*/*.go' --exclude-link-local

README.md

@@ -1,29 +1,18 @@
-
 # kured - Kubernetes Reboot Daemon
 
-<img src="https://github.com/weaveworks/kured/raw/main/img/logo.png" align="right"/>
+[![Artifact HUB](https://img.shields.io/endpoint?url=https://artifacthub.io/badge/repository/kured)](https://artifacthub.io/packages/helm/kured/kured)
+[![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2Fkubereboot%2Fkured.svg?type=shield)](https://app.fossa.com/projects/git%2Bgithub.com%2Fkubereboot%2Fkured?ref=badge_shield)
+[![CLOMonitor](https://img.shields.io/endpoint?url=https://clomonitor.io/api/projects/cncf/kured/badge)](https://clomonitor.io/projects/cncf/kured)
+[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/8867/badge)](https://www.bestpractices.dev/projects/8867)
 
-- [Introduction](#introduction)
-- [Kubernetes & OS Compatibility](#kubernetes--os-compatibility)
-- [Installation](#installation)
-- [Configuration](#configuration)
-  - [Reboot Sentinel File & Period](#reboot-sentinel-file--period)
-  - [Setting a schedule](#setting-a-schedule)
-  - [Blocking Reboots via Alerts](#blocking-reboots-via-alerts)
-  - [Blocking Reboots via Pods](#blocking-reboots-via-pods)
-  - [Prometheus Metrics](#prometheus-metrics)
-  - [Notifications](#notifications)
-  - [Overriding Lock Configuration](#overriding-lock-configuration)
-- [Operation](#operation)
-  - [Testing](#testing)
-  - [Disabling Reboots](#disabling-reboots)
-  - [Manual Unlock](#manual-unlock)
-  - [Automatic Unlock](#automatic-unlock)
-  - [Delaying Lock Release](#delaying-lock-release)
-- [Building](#building)
-- [Frequently Asked/Anticipated Questions](#frequently-askedanticipated-questions)
-  - [Why is there no `latest` tag on Docker Hub?](#why-is-there-no-latest-tag-on-docker-hub)
-- [Getting Help](#getting-help)
+<img src="https://github.com/kubereboot/website/raw/main/static/img/kured.png" alt="kured logo" width="200" align="right"/>
+
+- [kured - Kubernetes Reboot Daemon](#kured---kubernetes-reboot-daemon)
+  - [Introduction](#introduction)
+  - [Documentation](#documentation)
+  - [Getting Help](#getting-help)
+  - [Trademarks](#trademarks)
+  - [License](#license)
 
 ## Introduction
 
@@ -31,348 +20,48 @@ Kured (KUbernetes REboot Daemon) is a Kubernetes daemonset that
 performs safe automatic node reboots when the need to do so is
 indicated by the package management system of the underlying OS.
 
-* Watches for the presence of a reboot sentinel file e.g. `/var/run/reboot-required`
+- Watches for the presence of a reboot sentinel file e.g. `/var/run/reboot-required`
   or the successful run of a sentinel command.
-* Utilises a lock in the API server to ensure only one node reboots at
+- Utilises a lock in the API server to ensure only one node reboots at
   a time
-* Optionally defers reboots in the presence of active Prometheus alerts or selected pods
-* Cordons & drains worker nodes before reboot, uncordoning them after
+- Optionally defers reboots in the presence of active Prometheus alerts or selected pods
+- Cordons & drains worker nodes before reboot, uncordoning them after
 
-## Kubernetes & OS Compatibility
+## Documentation
 
-The daemon image contains versions of `k8s.io/client-go` and
-`k8s.io/kubectl` (the binary of `kubectl` in older releases) for the purposes of
-maintaining the lock and draining worker nodes. Kubernetes aims to provide
-forwards and backwards compatibility of one minor version between client and
-server:
+Find all our docs on <https://kured.dev>:
 
-| kured | kubectl | k8s.io/client-go | k8s.io/apimachinery | expected kubernetes compatibility |
-|-------|---------|------------------|---------------------|-----------------------------------|
-| main  | 1.22.4  | v0.22.4          | v0.22.4             | 1.21.x, 1.22.x, 1.23.x            |
-| 1.9.1 | 1.22.4  | v0.22.4          | v0.22.4             | 1.21.x, 1.22.x, 1.23.x            |
-| 1.8.1 | 1.21.4  | v0.21.4          | v0.21.4             | 1.20.x, 1.21.x, 1.22.x            |
-| 1.7.0 | 1.20.5  | v0.20.5          | v0.20.5             | 1.19.x, 1.20.x, 1.21.x            |
-| 1.6.1 | 1.19.4  | v0.19.4          | v0.19.4             | 1.18.x, 1.19.x, 1.20.x            |
-| 1.5.1 | 1.18.8  | v0.18.8          | v0.18.8             | 1.17.x, 1.18.x, 1.19.x            |
-| 1.4.4 | 1.17.7  | v0.17.0          | v0.17.0             | 1.16.x, 1.17.x, 1.18.x            |
-| 1.3.0 | 1.15.10 | v12.0.0          | release-1.15        | 1.15.x, 1.16.x, 1.17.x            |
-| 1.2.0 | 1.13.6  | v10.0.0          | release-1.13        | 1.12.x, 1.13.x, 1.14.x            |
-| 1.1.0 | 1.12.1  | v9.0.0           | release-1.12        | 1.11.x, 1.12.x, 1.13.x            |
-| 1.0.0 | 1.7.6   | v4.0.0           | release-1.7         | 1.6.x, 1.7.x, 1.8.x               |
+- [All Kured Documentation](https://kured.dev/docs/)
+- [Installing Kured](https://kured.dev/docs/installation/)
+- [Configuring Kured](https://kured.dev/docs/configuration/)
+- [Operating Kured](https://kured.dev/docs/operation/)
+- [Developing Kured](https://kured.dev/docs/development/)
 
-See the [release notes](https://github.com/weaveworks/kured/releases)
-for specific version compatibility information, including which
-combination have been formally tested.
-
-Versions >=1.1.0 enter the host mount namespace to invoke
-`systemctl reboot`, so should work on any systemd distribution.
-
-## Installation
-
-To obtain a default installation without Prometheus alerting interlock
-or Slack notifications:
-
-```console
-latest=$(curl -s https://api.github.com/repos/weaveworks/kured/releases | jq -r .[0].tag_name)
-kubectl apply -f "https://github.com/weaveworks/kured/releases/download/$latest/kured-$latest-dockerhub.yaml"
-```
-
-If you want to customise the installation, download the manifest and
-edit it in accordance with the following section before application.
-
-## Configuration
-
-The following arguments can be passed to kured via the daemonset pod template:
-
-```console
-Flags:
-      --alert-filter-regexp regexp.Regexp   alert names to ignore when checking for active alerts
-      --alert-firing-only bool              only consider firing alerts when checking for active alerts
-      --blocking-pod-selector stringArray   label selector identifying pods whose presence should prevent reboots
-      --drain-grace-period int              time in seconds given to each pod to terminate gracefully, if negative, the default value specified in the pod will be used (default: -1)
-      --skip-wait-for-delete-timeout int    when seconds is greater than zero, skip waiting for the pods whose deletion timestamp is older than N seconds while draining a node (default: 0)
-      --ds-name string                      name of daemonset on which to place lock (default "kured")
-      --ds-namespace string                 namespace containing daemonset on which to place lock (default "kube-system")
-      --end-time string                     schedule reboot only before this time of day (default "23:59:59")
-      --force-reboot bool                   force a reboot even if the drain is still running (default: false)
-      --drain-timeout duration              timeout after which the drain is aborted (default: 0, infinite time)
-  -h, --help                                help for kured
-      --lock-annotation string              annotation in which to record locking node (default "weave.works/kured-node-lock")
-      --lock-release-delay duration         hold lock after reboot by this duration (default: 0, disabled)
-      --lock-ttl duration                   expire lock annotation after this duration (default: 0, disabled)
-      --message-template-drain string       message template used to notify about a node being drained (default "Draining node %s")
-      --message-template-reboot string      message template used to notify about a node being rebooted (default "Rebooting node %s")
-      --notify-url                          url for reboot notifications (cannot use with --slack-hook-url flags)
-      --period duration                     reboot check period (default 1h0m0s)
-      --prefer-no-schedule-taint string     Taint name applied during pending node reboot (to prevent receiving additional pods from other rebooting nodes). Disabled by default. Set e.g. to "weave.works/kured-node-reboot" to enable tainting.
-      --prometheus-url string               Prometheus instance to probe for active alerts
-      --reboot-command string               command to run when a reboot is required by the sentinel (default "/sbin/systemctl reboot")
-      --reboot-days strings                 schedule reboot on these days (default [su,mo,tu,we,th,fr,sa])
-      --reboot-delay duration               add a delay after drain finishes but before the reboot command is issued (default 0, no time)
-      --reboot-sentinel string              path to file whose existence signals need to reboot (default "/var/run/reboot-required")
-      --reboot-sentinel-command string      command for which a successful run signals need to reboot (default ""). If non-empty, sentinel file will be ignored.
-      --slack-channel string                slack channel for reboot notfications
-      --slack-hook-url string               slack hook URL for reboot notfications [deprecated in favor of --notify-url]
-      --slack-username string               slack username for reboot notfications (default "kured")
-      --start-time string                   schedule reboot only after this time of day (default "0:00")
-      --time-zone string                    use this timezone for schedule inputs (default "UTC")
-      --log-format string                   log format specified as text or json, defaults to "text"
-```
-
-### Reboot Sentinel File & Period
-
-By default kured checks for the existence of
-`/var/run/reboot-required` every sixty minutes; you can override these
-values with `--reboot-sentinel` and `--period`. Each replica of the
-daemon uses a random offset derived from the period on startup so that
-nodes don't all contend for the lock simultaneously.
-
-Alternatively, a reboot sentinel command can be used. If a reboot
-sentinel command is used, the reboot sentinel file presence will be
-ignored.
-
-### Setting a schedule
-
-By default, kured will reboot any time it detects the sentinel, but this
-may cause reboots during odd hours.  While service disruption does not
-normally occur, anything is possible and operators may want to restrict
-reboots to predictable schedules.  Use `--reboot-days`, `--start-time`,
-`--end-time`, and `--time-zone` to set a schedule.  For example, business
-hours on the west coast USA can be specified with:
-
-```console
-  --reboot-days=mon,tue,wed,thu,fri
-  --start-time=9am
-  --end-time=5pm
-  --time-zone=America/Los_Angeles
-```
-
-Times can be formatted in numerous ways, including `5pm`, `5:00pm` `17:00`,
-and `17`.  `--time-zone` represents a Go `time.Location`, and can be `UTC`,
-`Local`, or any entry in the standard Linux tz database.
-
-Note that when using smaller time windows, you should consider shortening
-the sentinel check period (`--period`).
-
-### Blocking Reboots via Alerts
-
-You may find it desirable to block automatic node reboots when there
-are active alerts - you can do so by providing the URL of your
-Prometheus server:
-
-```console
---prometheus-url=http://prometheus.monitoring.svc.cluster.local
-```
-
-By default the presence of *any* active (pending or firing) alerts
-will block reboots, however you can ignore specific alerts:
-
-```console
---alert-filter-regexp=^(RebootRequired|AnotherBenignAlert|...$
-```
-
-You can also only block reboots for firing alerts:
-```console
---alert-firing-only=true
-```
-
-See the section on Prometheus metrics for an important application of this
-filter.
-
-### Blocking Reboots via Pods
-
-You can also block reboots of an _individual node_ when specific pods
-are scheduled on it:
-
-```console
---blocking-pod-selector=runtime=long,cost=expensive
-```
-
-Since label selector strings use commas to express logical 'and', you can
-specify this parameter multiple times for 'or':
-
-```console
---blocking-pod-selector=runtime=long,cost=expensive
---blocking-pod-selector=name=temperamental
-```
-
-In this case, the presence of either an (appropriately labelled) expensive long
-running job or a known temperamental pod on a node will stop it rebooting.
-
-> Try not to abuse this mechanism - it's better to strive for
-> restartability where possible. If you do use it, make sure you set
-> up a RebootRequired alert as described in the next section so that
-> you can intervene manually if reboots are blocked for too long.
-
-### Prometheus Metrics
-
-Each kured pod exposes a single gauge metric (`:8080/metrics`) that
-indicates the presence of the sentinel file:
-
-```console
-# HELP kured_reboot_required OS requires reboot due to software updates.
-# TYPE kured_reboot_required gauge
-kured_reboot_required{node="ip-xxx-xxx-xxx-xxx.ec2.internal"} 0
-```
-
-The purpose of this metric is to power an alert which will summon an
-operator if the cluster cannot reboot itself automatically for a
-prolonged period:
-
-```console
-# Alert if a reboot is required for any machines. Acts as a failsafe for the
-# reboot daemon, which will not reboot nodes if there are pending alerts save
-# this one.
-ALERT RebootRequired
-  IF          max(kured_reboot_required) != 0
-  FOR         24h
-  LABELS      { severity="warning" }
-  ANNOTATIONS {
-    summary = "Machine(s) require being rebooted, and the reboot daemon has failed to do so for 24 hours",
-    impact = "Cluster nodes more vulnerable to security exploits. Eventually, no disk space left.",
-    description = "Machine(s) require being rebooted, probably due to kernel update.",
-  }
-```
-
-If you choose to employ such an alert and have configured kured to
-probe for active alerts before rebooting, be sure to specify
-`--alert-filter-regexp=^RebootRequired$` to avoid deadlock!
-
-### Notifications
-
-When you specify a formatted URL using `--notify-url`, kured will notify
-about draining and rebooting nodes across a list of technologies.
-
-![Notification](img/slack-notification.png)
-
-Alternatively you can use the `--message-template-drain` and `--message-template-reboot` to customize the text of the message, e.g.
-
-```cli
---message-template-drain="Draining node %s part of *my-cluster* in region *xyz*"
-```
-
-Here is the syntax:
-
-- slack:           `slack://tokenA/tokenB/tokenC`
-(`--slack-hook-url` is deprecated but possible to use)
-
-- rocketchat:      `rocketchat://[username@]rocketchat-host/token[/channel|@recipient]`
-
-- teams:           `teams://tName/token-a/token-b/token-c`
-
-   > **Attention** as the [format of the url has changed](https://github.com/containrrr/shoutrrr/issues/138) you also have to specify a `tName`
-
-- Email:           `smtp://username:password@host:port/?fromAddress=fromAddress&toAddresses=recipient1[,recipient2,...]`
-
-More details here: [containrrr.dev/shoutrrr/v0.4/services/overview](https://containrrr.dev/shoutrrr/v0.4/services/overview)
-
-### Overriding Lock Configuration
-
-The `--ds-name` and `--ds-namespace` arguments should match the name and
-namespace of the daemonset used to deploy the reboot daemon - the locking is
-implemented by means of an annotation on this resource. The defaults match
-the daemonset YAML provided in the repository.
-
-Similarly `--lock-annotation` can be used to change the name of the
-annotation kured will use to store the lock, but the default is almost
-certainly safe.
-
-## Operation
-
-The example commands in this section assume that you have not
-overriden the default lock annotation, daemonset name or namespace;
-if you have, you will have to adjust the commands accordingly.
-
-### Testing
-
-You can test your configuration by provoking a reboot on a node:
-
-```console
-sudo touch /var/run/reboot-required
-```
-
-### Disabling Reboots
-
-If you need to temporarily stop kured from rebooting any nodes, you
-can take the lock manually:
-
-```console
-kubectl -n kube-system annotate ds kured weave.works/kured-node-lock='{"nodeID":"manual"}'
-```
-
-Don't forget to release it afterwards!
-
-### Manual Unlock
-
-In exceptional circumstances, such as a node experiencing a permanent
-failure whilst rebooting, manual intervention may be required to
-remove the cluster lock:
-
-```console
-kubectl -n kube-system annotate ds kured weave.works/kured-node-lock-
-```
-
-> NB the `-` at the end of the command is important - it instructs
-> `kubectl` to remove that annotation entirely.
-
-### Automatic Unlock
-
-In exceptional circumstances (especially when used with cluster-autoscaler) a node
-which holds lock might be killed thus annotation will stay there for ever.
-
-Using `--lock-ttl=30m` will allow other nodes to take over if TTL has expired (in this case 30min) and continue reboot process.
-
-### Delaying Lock Release
-
-
-Using `--lock-release-delay=30m` will cause nodes to hold the lock for the specified time frame (in this case 30min) before it is released and the reboot process continues. This can be used to throttle reboots across the cluster.
-
-## Building
-
-Kured now uses [Go
-Modules](https://github.com/golang/go/wiki/Modules), so build
-instructions vary depending on where you have checked out the
-repository:
-
-**Building outside $GOPATH:**
-
-```console
-make
-```
-
-**Building inside $GOPATH:**
-
-```console
-GO111MODULE=on make
-```
-
-You can find the current preferred version of Golang in the [go.mod file](go.mod).
-
-If you are interested in contributing code to kured, please take a look at
-our [development][development] docs.
-
-[development]: DEVELOPMENT.md
-
-## Frequently Asked/Anticipated Questions
-
-### Why is there no `latest` tag on Docker Hub?
-
-Use of `latest` for production deployments is bad practice - see
-[here](https://kubernetes.io/docs/concepts/configuration/overview) for
-details. The manifest on `main` refers to `latest` for local
-development testing with minikube only; for production use choose a
-versioned manifest from the [release page](https://github.com/weaveworks/kured/releases/).
+And there's much more!
 
 ## Getting Help
 
 If you have any questions about, feedback for or problems with `kured`:
 
-* Invite yourself to the <a href="https://slack.weave.works/" target="_blank">Weave Users Slack</a>.
-* Ask a question on the [#kured](https://weave-community.slack.com/messages/kured/) slack channel.
-* [File an issue](https://github.com/weaveworks/kured/issues/new).
-* Join us in [our monthly meeting](https://docs.google.com/document/d/1bsHTjHhqaaZ7yJnXF6W8c89UB_yn-OoSZEmDnIP34n8/edit#),
-  every fourth Wednesday of the month at 16:00 UTC.
+- Invite yourself to the <a href="https://slack.cncf.io/" target="_blank">CNCF Slack</a>.
+- Ask a question on the [#kured](https://cloud-native.slack.com/archives/kured) slack channel.
+- [File an issue](https://github.com/kubereboot/kured/issues/new).
+- Join us in [our monthly meeting](https://docs.google.com/document/d/1AWT8YDdqZY-Se6Y1oAlwtujWLVpNVK2M_F_Vfqw06aI/edit),
+  every first Wednesday of the month at 16:00 UTC.
+- You might want to [join the kured-dev mailing list](https://lists.cncf.io/g/cncf-kured-dev) as well.
 
-We follow the [CNCF Code of Conduct](https://github.com/cncf/foundation/blob/master/code-of-conduct.md).
+We follow the [CNCF Code of Conduct](CODE_OF_CONDUCT.md).
 
 Your feedback is always welcome!
+
+## Trademarks
+
+**Kured is a [Cloud Native Computing Foundation](https://cncf.io/) Sandbox project.**
+
+![Cloud Native Computing Foundation logo](img/cncf-color.png)
+
+The Linux Foundation® (TLF) has registered trademarks and uses trademarks. For a list of TLF trademarks, see [Trademark Usage](https://www.linuxfoundation.org/legal/trademark-usage).
+
+## License
+
+[![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2Fkubereboot%2Fkured.svg?type=large)](https://app.fossa.com/projects/git%2Bgithub.com%2Fkubereboot%2Fkured?ref=badge_large)

charts/kured/.helmignore

@@ -1,21 +0,0 @@
-# Patterns to ignore when building packages.
-# This supports shell glob matching, relative path matching, and
-# negation (prefixed with !). Only one pattern per line.
-.DS_Store
-# Common VCS dirs
-.git/
-.gitignore
-.bzr/
-.bzrignore
-.hg/
-.hgignore
-.svn/
-# Common backup files
-*.swp
-*.bak
-*.tmp
-*~
-# Various IDEs
-.project
-.idea/
-*.tmproj

charts/kured/Chart.yaml

@@ -1,14 +0,0 @@
-apiVersion: v1
-appVersion: "1.9.1"
-description: A Helm chart for kured
-name: kured
-version: 2.11.1
-home: https://github.com/weaveworks/kured
-maintainers:
-  - name: ckotzbauer
-    email: christian.kotzbauer@gmail.com
-  - name: davidkarlsen
-    email: david@davidkarlsen.com
-sources:
-  - https://github.com/weaveworks/kured
-icon: https://raw.githubusercontent.com/weaveworks/kured/main/img/logo.png

charts/kured/README.md

@@ -1,125 +0,0 @@
-# Kured (KUbernetes REboot Daemon)
-
-## Introduction
-This chart installs the "Kubernetes Reboot Daemon" using the Helm Package Manager.
-
-## Prerequisites
-- Kubernetes 1.9+
-
-## Installing the Chart
-To install the chart with the release name `my-release`:
-```bash
-$ helm repo add kured https://weaveworks.github.io/kured
-$ helm install my-release kured/kured
-```
-
-## Uninstalling the Chart
-To uninstall/delete the `my-release` deployment:
-```bash
-$ helm delete my-release
-```
-
-The command removes all the Kubernetes components associated with the chart and deletes the release.
-
-
-## Migrate from stable Helm-Chart
-The following changes have been made compared to the stable chart:
-- **[BREAKING CHANGE]** The `autolock` feature was removed. Use `configuration.startTime` and `configuration.endTime` instead.
-- Role inconsistencies have been fixed (allowed verbs for modifying the `DaemonSet`, apiGroup of `PodSecurityPolicy`)
-- Added support for affinities.
-- Configuration of cli-flags can be made through a `configuration` object.
-- Added optional `Service` and `ServiceMonitor` support for metrics endpoint.
-
-
-## Configuration
-
-| Config                  | Description                                                                 | Default                    |
-| ------                  | -----------                                                                 | -------                    |
-| `image.repository`      | Image repository                                                            | `weaveworks/kured` |
-| `image.tag`             | Image tag                                                                   | `1.9.1`                    |
-| `image.pullPolicy`      | Image pull policy                                                           | `IfNotPresent`             |
-| `image.pullSecrets`     | Image pull secrets                                                          | `[]`                       |
-| `updateStrategy`        | Daemonset update strategy                                                   | `RollingUpdate`            |
-| `maxUnavailable`        | The max pods unavailable during a rolling update                            | `1`                        |
-| `podAnnotations`        | Annotations to apply to pods (eg to add Prometheus annotations)             | `{}`                       |
-| `extraArgs`             | Extra arguments to pass to `/usr/bin/kured`. See below.                     | `{}`                       |
-| `extraEnvVars`          | Array of environment variables to pass to the daemonset.                    | `{}`                       |
-| `configuration.lockTtl` | cli-parameter `--lock-ttl`                                                  | `0`                       |
-| `configuration.lockReleaseDelay` | cli-parameter `--lock-release-delay`                               | `0`                       |
-| `configuration.alertFilterRegexp` | cli-parameter `--alert-filter-regexp`                             | `""`                       |
-| `configuration.alertFiringOnly` | cli-parameter `--alert-firing-only`                                 | `false`                   |
-| `configuration.blockingPodSelector` | Array of selectors for multiple cli-parameters `--blocking-pod-selector` | `[]`             |
-| `configuration.endTime` | cli-parameter `--end-time`                                                  | `""`                      |
-| `configuration.lockAnnotation` | cli-parameter `--lock-annotation`                                    | `""`                      |
-| `configuration.period` | cli-parameter `--period`                                                     | `""`                      |
-| `configuration.forceReboot` | cli-parameter `--force-reboot`                                          | `false`                   |
-| `configuration.drainGracePeriod` | cli-parameter `--drain-grace-period`                               | `""`                      |
-| `configuration.drainTimeout` | cli-parameter `--drain-timeout`                                        | `""`                      |
-| `configuration.skipWaitForDeleteTimeout` | cli-parameter `--skip-wait-for-delete-timeout`             | `""`                      |
-| `configuration.prometheusUrl` | cli-parameter `--prometheus-url`                                      | `""`                      |
-| `configuration.rebootDays` | Array of days for multiple cli-parameters `--reboot-days`                | `[]`                      |
-| `configuration.rebootSentinel` | cli-parameter `--reboot-sentinel`                                    | `""`                      |
-| `configuration.rebootSentinelCommand` | cli-parameter `--reboot-sentinel-command`                     | `""`                      |
-| `configuration.rebootCommand` | cli-parameter `--reboot-command`                                      | `""`                      |
-| `configuration.rebootDelay` | cli-parameter `--reboot-delay`                                          | `""`                      |
-| `configuration.slackChannel` | cli-parameter `--slack-channel`                                        | `""`                      |
-| `configuration.slackHookUrl` | cli-parameter `--slack-hook-url`                                       | `""`                      |
-| `configuration.slackUsername` | cli-parameter `--slack-username`                                      | `""`                      |
-| `configuration.notifyUrl` | cli-parameter `--notify-url`                                              | `""`                      |
-| `configuration.messageTemplateDrain` | cli-parameter `--message-template-drain`                       | `""`                      |
-| `configuration.messageTemplateReboot` | cli-parameter `--message-template-reboot`                     | `""`                      |
-| `configuration.startTime` | cli-parameter `--start-time`                                              | `""`                      |
-| `configuration.timeZone` | cli-parameter `--time-zone`                                                | `""`                      |
-| `configuration.annotateNodes` | cli-parameter `--annotate-nodes`                                      | `false`                   |
-| `configuration.logFormat` | cli-parameter `--log-format`                                              | `"text"`                  |
-| `configuration.preferNoScheduleTaint` | Taint name applied during pending node reboot                 | `""`                   |
-| `rbac.create`           | Create RBAC roles                                                           | `true`                     |
-| `serviceAccount.create` | Create a service account                                                    | `true`                     |
-| `serviceAccount.name`   | Service account name to create (or use if `serviceAccount.create` is false) | (chart fullname)           |
-| `podSecurityPolicy.create` | Create podSecurityPolicy                                                 | `false`                     |
-| `resources`             | Resources requests and limits.                                              | `{}`                       |
-| `metrics.create`        | Create a ServiceMonitor for prometheus-operator                             | `false`                    |
-| `metrics.namespace`     | The namespace to create the ServiceMonitor in                               | `""`                    |
-| `metrics.labels`        | Additional labels for the ServiceMonitor                                    | `{}`                    |
-| `metrics.interval`      | Interval prometheus should scrape the endpoint                              | `60s`                   |
-| `metrics.scrapeTimeout` | A custom scrapeTimeout for prometheus                                       | `""`                    |
-| `service.create`        | Create a Service for the metrics endpoint                                   | `false`                    |
-| `service.name  `        | Service name for the metrics endpoint                                       | `""`                       |
-| `service.port`          | Port of the service to expose                                               | `8080`                     |
-| `service.annotations`   | Annotations to apply to the service (eg to add Prometheus annotations)      | `{}`                       |
-| `podLabels`             | Additional labels for pods (e.g. CostCenter=IT)                             | `{}`                       |
-| `priorityClassName`     | Priority Class to be used by the pods                                       | `""`                       |
-| `tolerations`           | Tolerations to apply to the daemonset (eg to allow running on master)       | `[{"key": "node-role.kubernetes.io/master", "effect": "NoSchedule"}]`|
-| `affinity`              | Affinity for the daemonset (ie, restrict which nodes kured runs on)         | `{}`                       |
-| `nodeSelector`          | Node Selector for the daemonset (ie, restrict which nodes kured runs on)    | `{}`                       |
-| `volumeMounts`          | Maps of volumes mount to mount                                              | `{}`                       |
-| `volumes`               | Maps of volumes to mount                                                    | `{}`                       |
-See https://github.com/weaveworks/kured#configuration for values (not contained in the `configuration` object) for `extraArgs`. Note that
-```yaml
-extraArgs:
-  foo: 1
-  bar-baz: 2
-```
-becomes `/usr/bin/kured ... --foo=1 --bar-baz=2`.
-
-
-## Prometheus Metrics
-
-Kured exposes a single prometheus metric indicating whether a reboot is required or not (see [kured docs](https://github.com/weaveworks/kured#prometheus-metrics)) for details.
-
-#### Prometheus-Operator
-
-```yaml
-metrics:
-  create: true
-```
-
-#### Prometheus Annotations
-
-```yaml
-service:
-  annotations:
-    prometheus.io/scrape: "true"
-    prometheus.io/path: "/metrics"
-    prometheus.io/port: "8080"
-```

charts/kured/ci/prometheus-values.yaml

@@ -1,13 +0,0 @@
-# This is tested twice:
-# Basic install test with chart-testing (on charts PRs)
-# Functional testing in PRs (other PRs)
-
-service:
-  create: true
-  name: kured-prometheus-endpoint
-  port: 8080
-  type: NodePort
-  nodePort: 30000
-
-# Do not override the configuration: period in this, so that
-# We can test prometheus exposed metrics without rebooting.

charts/kured/templates/NOTES.txt

@@ -1,3 +0,0 @@
-Kured will check for /var/run/reboot-required, and reboot nodes when needed.
-
-See https://github.com/weaveworks/kured/ for details.

charts/kured/templates/_helpers.tpl

@@ -1,72 +0,0 @@
-{{/* vim: set filetype=mustache: */}}
-{{/*
-Expand the name of the chart.
-*/}}
-{{- define "kured.name" -}}
-{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-
-{{/*
-Create a default fully qualified app name.
-We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
-If release name contains chart name it will be used as a full name.
-*/}}
-{{- define "kured.fullname" -}}
-{{- if .Values.fullnameOverride -}}
-{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" -}}
-{{- else -}}
-{{- $name := default .Chart.Name .Values.nameOverride -}}
-{{- if contains $name .Release.Name -}}
-{{- .Release.Name | trunc 63 | trimSuffix "-" -}}
-{{- else -}}
-{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-{{- end -}}
-{{- end -}}
-
-{{/*
-Create chart name and version as used by the chart label.
-*/}}
-{{- define "kured.chart" -}}
-{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
-{{- end -}}
-
-{{/*
-Create the name of the service account to use
-*/}}
-{{- define "kured.serviceAccountName" -}}
-{{- if .Values.serviceAccount.create -}}
-    {{ default (include "kured.fullname" .) .Values.serviceAccount.name }}
-{{- else -}}
-    {{ default "default" .Values.serviceAccount.name }}
-{{- end -}}
-{{- end -}}
-
-{{/*
-Return the appropriate apiVersion for podsecuritypolicy.
-*/}}
-{{- define "kured.psp.apiVersion" -}}
-{{- if semverCompare "<1.10-0" .Capabilities.KubeVersion.GitVersion -}}
-{{- print "extensions/v1beta1" -}}
-{{- else -}}
-{{- print "policy/v1beta1" -}}
-{{- end -}}
-{{- end -}}
-
-{{/*
-Returns a set of labels applied to each resource.
-*/}}
-{{- define "kured.labels" -}}
-app: {{ template "kured.name" . }}
-chart: {{ template "kured.chart" . }}
-release: {{ .Release.Name }}
-heritage: {{ .Release.Service }}
-{{- end -}}
-
-{{/*
-Returns a set of matchLabels applied.
-*/}}
-{{- define "kured.matchLabels" -}}
-app: {{ template "kured.name" . }}
-release: {{ .Release.Name }}
-{{- end -}}

charts/kured/templates/clusterrole.yaml

@@ -1,30 +0,0 @@
-{{- if .Values.rbac.create -}}
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: {{ template "kured.fullname" . }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-rules:
-# Allow kured to read spec.unschedulable
-# Allow kubectl to drain/uncordon
-#
-# NB: These permissions are tightly coupled to the bundled version of kubectl; the ones below
-# match https://github.com/kubernetes/kubernetes/blob/v1.19.4/staging/src/k8s.io/kubectl/pkg/cmd/drain/drain.go
-#
-- apiGroups: [""]
-  resources: ["nodes"]
-  verbs:     ["get", "patch"]
-- apiGroups: [""]
-  resources: ["pods"]
-  verbs:     ["list","delete","get"]
-- apiGroups: ["extensions"]
-  resources: ["daemonsets"]
-  verbs:     ["get"]
-- apiGroups: ["apps"]
-  resources: ["daemonsets"]
-  verbs:     ["get"]
-- apiGroups: [""]
-  resources: ["pods/eviction"]
-  verbs:     ["create"]
-{{- end -}}

charts/kured/templates/clusterrolebinding.yaml

@@ -1,16 +0,0 @@
-{{- if .Values.rbac.create -}}
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: {{ template "kured.fullname" . }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: {{ template "kured.fullname" . }}
-subjects:
-- kind: ServiceAccount
-  name: {{ template "kured.serviceAccountName" . }}
-  namespace: {{ .Release.Namespace }}
-{{- end -}}

charts/kured/templates/daemonset.yaml

@@ -1,181 +0,0 @@
-apiVersion: apps/v1
-kind: DaemonSet
-metadata:
-  name: {{ template "kured.fullname" . }}
-  namespace: {{ .Release.Namespace }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-spec:
-  updateStrategy:
-    type: {{ .Values.updateStrategy }}
-{{- if eq .Values.updateStrategy "RollingUpdate"}}
-    rollingUpdate:
-      maxUnavailable: {{ .Values.maxUnavailable }}
-{{- end}}
-  selector:
-    matchLabels:
-      {{- include "kured.matchLabels" . | nindent 6 }}
-  template:
-    metadata:
-      labels:
-        {{- include "kured.labels" . | nindent 8 }}
-        {{- if .Values.podLabels }}
-        {{- toYaml .Values.podLabels | nindent 8 }}
-        {{- end }}
-      {{- if .Values.podAnnotations }}
-      annotations:
-      {{- range $key, $value := .Values.podAnnotations }}
-        {{ $key }}: {{ $value | quote }}
-      {{- end }}
-      {{- end }}
-    spec:
-      serviceAccountName: {{ template "kured.serviceAccountName" . }}
-      hostPID: true
-      restartPolicy: Always
-      {{- with .Values.image.pullSecrets }}
-      imagePullSecrets:
-{{ toYaml . | indent 8 }}
-      {{- end }}
-      {{- if .Values.priorityClassName }}
-      priorityClassName: {{ .Values.priorityClassName }}
-      {{- end }}
-      containers:
-        - name: {{ .Chart.Name }}
-          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.image.pullPolicy }}
-          securityContext:
-            privileged: true # Give permission to nsenter /proc/1/ns/mnt
-          resources:
-{{ toYaml .Values.resources | indent 12 }}
-          command:
-            - /usr/bin/kured
-          args:
-            - --ds-name={{ template "kured.fullname" . }}
-            - --ds-namespace={{ .Release.Namespace }}
-          {{- if .Values.configuration.lockTtl }}
-            - --lock-ttl={{ .Values.configuration.lockTtl }}
-          {{- end }}
-          {{- if .Values.configuration.lockReleaseDelay }}
-            - --lock-release-delay={{ .Values.configuration.lockReleaseDelay }}
-          {{- end }}
-          {{- if .Values.configuration.alertFilterRegexp }}
-            - --alert-filter-regexp={{ .Values.configuration.alertFilterRegexp }}
-          {{- end }}
-          {{- if .Values.configuration.alertFiringOnly }}
-            - --alert-firing-only={{ .Values.configuration.alertFiringOnly }}
-          {{- end }}
-          {{- range .Values.configuration.blockingPodSelector }}
-            - --blocking-pod-selector={{ . }}
-          {{- end }}
-          {{- if .Values.configuration.endTime }}
-            - --end-time={{ .Values.configuration.endTime }}
-          {{- end }}
-          {{- if .Values.configuration.lockAnnotation }}
-            - --lock-annotation={{ .Values.configuration.lockAnnotation }}
-          {{- end }}
-          {{- if .Values.configuration.period }}
-            - --period={{ .Values.configuration.period }}
-          {{- end }}
-          {{- if .Values.configuration.forceReboot }}
-            - --force-reboot
-          {{- end }}
-          {{- if .Values.configuration.drainGracePeriod }}
-            - --drain-grace-period={{ .Values.configuration.drainGracePeriod }}
-          {{- end }}
-          {{- if .Values.configuration.drainTimeout }}
-            - --drain-timeout={{ .Values.configuration.drainTimeout }}
-          {{- end }}
-          {{- if .Values.configuration.skipWaitForDeleteTimeout }}
-             - --skip-wait-for-delete-timeout={{ .Values.configuration.skipWaitForDeleteTimeout }}
-          {{- end }}
-          {{- if .Values.configuration.prometheusUrl }}
-            - --prometheus-url={{ .Values.configuration.prometheusUrl }}
-          {{- end }}
-          {{- range .Values.configuration.rebootDays }}
-            - --reboot-days={{ . }}
-          {{- end }}
-          {{- if .Values.configuration.rebootSentinel }}
-            - --reboot-sentinel={{ .Values.configuration.rebootSentinel }}
-          {{- end }}
-          {{- if .Values.configuration.rebootSentinelCommand }}
-            - --reboot-sentinel-command={{ .Values.configuration.rebootSentinelCommand }}
-          {{- end }}
-          {{- if .Values.configuration.rebootCommand }}
-            - --reboot-command={{ .Values.configuration.rebootCommand }}
-          {{- end }}
-          {{- if .Values.configuration.rebootDelay }}
-            - --reboot-delay={{ .Values.configuration.rebootDelay }}
-          {{- end }}
-          {{- if .Values.configuration.slackChannel }}
-            - --slack-channel={{ .Values.configuration.slackChannel }}
-          {{- end }}
-          {{- if .Values.configuration.slackHookUrl }}
-            - --slack-hook-url={{ .Values.configuration.slackHookUrl }}
-          {{- end }}
-          {{- if .Values.configuration.slackUsername }}
-            - --slack-username={{ .Values.configuration.slackUsername }}
-          {{- end }}
-          {{- if .Values.configuration.notifyUrl }}
-            - --notify-url={{ .Values.configuration.notifyUrl }}
-          {{- end }}
-          {{- if .Values.configuration.messageTemplateDrain }}
-            - --message-template-drain={{ .Values.configuration.messageTemplateDrain }}
-          {{- end }}
-          {{- if .Values.configuration.messageTemplateReboot }}
-            - --message-template-reboot={{ .Values.configuration.messageTemplateReboot }}
-          {{- end }}
-          {{- if .Values.configuration.startTime }}
-            - --start-time={{ .Values.configuration.startTime }}
-          {{- end }}
-          {{- if .Values.configuration.timeZone }}
-            - --time-zone={{ .Values.configuration.timeZone }}
-          {{- end }}
-          {{- if .Values.configuration.annotateNodes }}
-            - --annotate-nodes={{ .Values.configuration.annotateNodes }}
-          {{- end }}
-          {{- if .Values.configuration.preferNoScheduleTaint }}
-            - --prefer-no-schedule-taint={{ .Values.configuration.preferNoScheduleTaint }}
-          {{- end }}
-          {{- if .Values.configuration.logFormat }}
-            - --log-format={{ .Values.configuration.logFormat }}
-          {{- end }}
-          {{- range $key, $value := .Values.extraArgs }}
-            {{- if $value }}
-            - --{{ $key }}={{ $value }}
-            {{- else }}
-            - --{{ $key }}
-            {{- end }}
-          {{- end }}
-{{- if .Values.volumeMounts }}
-          volumeMounts:
-{{- toYaml .Values.volumeMounts  | nindent 12 }}
-{{- end }}
-          ports:
-            - containerPort: 8080
-              name: metrics
-          env:
-            # Pass in the name of the node on which this pod is scheduled
-            # for use with drain/uncordon operations and lock acquisition
-            - name: KURED_NODE_ID
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-            {{- if .Values.extraEnvVars }}
-              {{ toYaml .Values.extraEnvVars | nindent 12 }}
-            {{- end }}
-      {{- with .Values.tolerations }}
-      tolerations:
-{{ toYaml . | indent 8 }}
-      {{- end }}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-{{ toYaml . | indent 8 }}
-      {{- end }}
-      {{- with .Values.affinity }}
-      affinity:
-{{ toYaml . | indent 8 }}
-      {{- end }}
-{{- if .Values.volumes }}
-      volumes:
-{{- toYaml .Values.volumes  | nindent 8 }}
-{{- end }}

charts/kured/templates/podsecuritypolicy.yaml

@@ -1,21 +0,0 @@
-{{- if .Values.podSecurityPolicy.create}}
-apiVersion: {{ template "kured.psp.apiVersion" . }}
-kind: PodSecurityPolicy
-metadata:
-  name: {{ template "kured.fullname" . }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-spec:
-  privileged: true
-  hostPID: true
-  allowedCapabilities: ['*']
-  fsGroup:
-    rule: RunAsAny
-  runAsUser:
-    rule: RunAsAny
-  seLinux:
-    rule: RunAsAny
-  supplementalGroups:
-    rule: RunAsAny
-  volumes: ['*']
-{{- end }}

charts/kured/templates/role.yaml

@@ -1,30 +0,0 @@
-{{- if .Values.rbac.create -}}
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  namespace: {{ .Release.Namespace }}
-  name: {{ template "kured.fullname" . }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-rules:
-  # Allow kured to lock/unlock itself
-  - apiGroups:     ["extensions"]
-    resources:     ["daemonsets"]
-    resourceNames: ["{{ template "kured.fullname" . }}"]
-    verbs:         ["update", "patch"]
-  - apiGroups:     ["apps"]
-    resources:     ["daemonsets"]
-    resourceNames: ["{{ template "kured.fullname" . }}"]
-    verbs:         ["update", "patch"]
-{{- if .Values.podSecurityPolicy.create }}
-  - apiGroups:     ["extensions"]
-    resources:     ["podsecuritypolicies"]
-    resourceNames: ["{{ template "kured.fullname" . }}"]
-    verbs:         ["use"]
-  - apiGroups:     ["policy"]
-    resources:     ["podsecuritypolicies"]
-    resourceNames: ["{{ template "kured.fullname" . }}"]
-    verbs:         ["use"]
-{{- end }}
-
-{{- end -}}

charts/kured/templates/rolebinding.yaml

@@ -1,17 +0,0 @@
-{{- if .Values.rbac.create -}}
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  namespace: {{ .Release.Namespace }}
-  name: {{ template "kured.fullname" . }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-subjects:
-- kind: ServiceAccount
-  namespace: {{ .Release.Namespace }}
-  name: {{ template "kured.serviceAccountName" . }}
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: {{ template "kured.fullname" . }}
-{{- end -}}

charts/kured/templates/service.yaml

@@ -1,29 +0,0 @@
-{{- if or .Values.service.create .Values.metrics.create }}
-apiVersion: v1
-kind: Service
-metadata:
-  {{- if .Values.service.name }}
-  name: {{ .Values.service.name }}
-  {{- else }}
-  name: {{ template "kured.fullname" . }}
-  {{- end }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-  {{- if .Values.service.annotations }}
-  annotations:
-  {{- range $key, $value := .Values.service.annotations }}
-    {{ $key }}: {{ $value | quote }}
-  {{- end }}
-  {{- end }}
-spec:
-  type: {{ .Values.service.type }}
-  ports:
-    - name: metrics
-      port: {{ .Values.service.port }}
-      targetPort: 8080
-      {{- if eq .Values.service.type "NodePort" }}
-      nodePort: {{ .Values.service.nodePort }}
-      {{- end }}
-  selector:
-    {{- include "kured.matchLabels" . | nindent 4 }}
-{{- end }}

charts/kured/templates/serviceaccount.yaml

@@ -1,9 +0,0 @@
-{{- if .Values.serviceAccount.create -}}
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  name: {{ template "kured.serviceAccountName" . }}
-  namespace: {{ .Release.Namespace }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-{{- end -}}

charts/kured/templates/servicemonitor.yaml

@@ -1,31 +0,0 @@
-{{- if .Values.metrics.create }}
-apiVersion: monitoring.coreos.com/v1
-kind: ServiceMonitor
-metadata:
-  name: {{ template "kured.fullname" . }}
-  {{- if .Values.metrics.namespace }}
-  namespace: {{ .Values.metrics.namespace }}
-  {{- end }}
-  labels:
-    {{- include "kured.labels" . | nindent 4 }}
-    {{- if .Values.metrics.labels }}
-    {{- toYaml .Values.metrics.labels | nindent 4 }}
-    {{- end }}
-spec:
-  endpoints:
-  - interval: {{ .Values.metrics.interval }}
-    {{- if .Values.metrics.scrapeTimeout }}
-    scrapeTimeout: {{ .Values.metrics.scrapeTimeout }}
-    {{- end }}
-    honorLabels: true
-    targetPort: 8080
-    path: /metrics
-    scheme: http
-  jobLabel: "{{ .Release.Name }}"
-  selector:
-    matchLabels:
-      {{- include "kured.matchLabels" . | nindent 6 }}
-  namespaceSelector:
-    matchNames:
-      - {{ .Release.Namespace }}
-{{- end }}

charts/kured/values.minikube.yaml

@@ -1,31 +0,0 @@
-image:
-  repository: weaveworks/kured
-  tag: latest
-
-configuration:
-  # annotationTtl: 0          # force clean annotation after this amount of time (default 0, disabled)
-  # alertFilterRegexp: ""     # alert names to ignore when checking for active alerts
-  # alertFiringOnly: false     # only consider firing alerts when checking for active alerts
-  # blockingPodSelector: []   # label selector identifying pods whose presence should prevent reboots
-  # endTime: ""               # only reboot before this time of day (default "23:59")
-  # lockAnnotation: ""        # annotation in which to record locking node (default "weave.works/kured-node-lock")
-  period: "1m"                # reboot check period (default 1h0m0s)
-  # forceReboot: false        # force a reboot even if the drain fails or times out (default: false)
-  # drainGracePeriod: ""      # time in seconds given to each pod to terminate gracefully, if negative, the default value specified in the pod will be used (default: -1)
-  # drainTimeout: ""          # timeout after which the drain is aborted (default: 0, infinite time)
-  # skipWaitForDeleteTimeout: ""  # when time is greater than zero, skip waiting for the pods whose deletion timestamp is older than N seconds while draining a node (default: 0)
-  # prometheusUrl: ""         # Prometheus instance to probe for active alerts
-  # rebootDays: []            # only reboot on these days (default [su,mo,tu,we,th,fr,sa])
-  # rebootSentinel: ""        # path to file whose existence signals need to reboot (default "/var/run/reboot-required")
-  # rebootSentinelCommand: ""  # command for which a successful run signals need to reboot (default ""). If non-empty, sentinel file will be ignored.
-  # slackChannel: ""          # slack channel for reboot notfications
-  # slackHookUrl: ""          # slack hook URL for reboot notfications
-  # slackUsername: ""         # slack username for reboot notfications (default "kured")
-  # notifyUrl: ""             # notification URL with the syntax as follows: https://containrrr.dev/shoutrrr/services/overview/
-  # messageTemplateDrain: ""  # slack message template when notifying about a node being drained (default "Draining node %s")
-  # messageTemplateReboot: "" # slack message template when notifying about a node being rebooted (default "Rebooted node %s")
-  # startTime: ""             # only reboot after this time of day (default "0:00")
-  # timeZone: ""              # time-zone to use (valid zones from "time" golang package)
-  # annotateNodes: false      # enable 'weave.works/kured-reboot-in-progress' and 'weave.works/kured-most-recent-reboot-needed' node annotations to signify kured reboot operations
-  # lockReleaseDelay: "5m"    # hold lock after reboot by this amount of time (default 0, disabled)
-  # logFormat: "text"         # log format specified as text or json, defaults to text

charts/kured/values.yaml

@@ -1,95 +0,0 @@
-image:
-  repository: weaveworks/kured
-  tag: ""  # will default to the appVersion in Chart.yaml
-  pullPolicy: IfNotPresent
-  pullSecrets: []
-
-updateStrategy: RollingUpdate
-#  requires RollingUpdate updateStrategy
-maxUnavailable: 1
-
-podAnnotations: {}
-
-extraArgs: {}
-
-extraEnvVars:
-#  - name: slackHookUrl
-#    valueFrom:
-#      secretKeyRef:
-#        name: secret_name
-#        key: secret_key
-#  - name: regularEnvVariable
-#    value: 123
-
-configuration:
-  lockTtl: 0                 # force clean annotation after this amount of time (default 0, disabled)
-  alertFilterRegexp: ""      # alert names to ignore when checking for active alerts
-  alertFiringOnly: false     # only consider firing alerts when checking for active alerts
-  blockingPodSelector: []    # label selector identifying pods whose presence should prevent reboots
-  endTime: ""                # only reboot before this time of day (default "23:59")
-  lockAnnotation: ""         # annotation in which to record locking node (default "weave.works/kured-node-lock")
-  period: ""                 # reboot check period (default 1h0m0s)
-  forceReboot: false         # force a reboot even if the drain fails or times out (default: false)
-  drainGracePeriod: ""       # time in seconds given to each pod to terminate gracefully, if negative, the default value specified in the pod will be used (default: -1)
-  drainTimeout: ""           # timeout after which the drain is aborted (default: 0, infinite time)
-  skipWaitForDeleteTimeout: ""  # when time is greater than zero, skip waiting for the pods whose deletion timestamp is older than N seconds while draining a node (default: 0)
-  prometheusUrl: ""          # Prometheus instance to probe for active alerts
-  rebootDays: []             # only reboot on these days (default [su,mo,tu,we,th,fr,sa])
-  rebootSentinel: ""         # path to file whose existence signals need to reboot (default "/var/run/reboot-required")
-  rebootSentinelCommand: ""  # command for which a successful run signals need to reboot (default ""). If non-empty, sentinel file will be ignored.
-  rebootCommand: "/bin/systemctl reboot"  # command to run when a reboot is required by the sentinel
-  rebootDelay: ""            # add a delay after drain finishes but before the reboot command is issued
-  slackChannel: ""           # slack channel for reboot notfications
-  slackHookUrl: ""           # slack hook URL for reboot notfications
-  slackUsername: ""          # slack username for reboot notfications (default "kured")
-  notifyUrl: ""              # notification URL with the syntax as follows: https://containrrr.dev/shoutrrr/services/overview/
-  messageTemplateDrain: ""   # slack message template when notifying about a node being drained (default "Draining node %s")
-  messageTemplateReboot: ""  # slack message template when notifying about a node being rebooted (default "Rebooted node %s")
-  startTime: ""              # only reboot after this time of day (default "0:00")
-  timeZone: ""               # time-zone to use (valid zones from "time" golang package)
-  annotateNodes: false       # enable 'weave.works/kured-reboot-in-progress' and 'weave.works/kured-most-recent-reboot-needed' node annotations to signify kured reboot operations
-  lockReleaseDelay: 0        # hold lock after reboot by this amount of time (default 0, disabled)
-  preferNoScheduleTaint: ""  # Taint name applied during pending node reboot (to prevent receiving additional pods from other rebooting nodes). Disabled by default. Set e.g. to "weave.works/kured-node-reboot" to enable tainting.
-  logFormat: "text"          # log format specified as text or json, defaults to text
-
-rbac:
-  create: true
-
-serviceAccount:
-  create: true
-  name:
-
-podSecurityPolicy:
-  create: false
-
-resources: {}
-
-metrics:
-  create: false
-  namespace: ""
-  labels: {}
-  interval: 60s
-  scrapeTimeout: ""
-
-service:
-  create: false
-  port: 8080
-  annotations: {}
-  name: ""
-  type: ClusterIP
-
-podLabels: {}
-
-priorityClassName: ""
-
-tolerations:
-  - key: node-role.kubernetes.io/master
-    effect: NoSchedule
-
-affinity: {}
-
-nodeSelector: {}
-
-volumeMounts: []
-
-volumes: []

cmd/kured/Dockerfile

@@ -1,4 +0,0 @@
-FROM alpine:3.15.0
-RUN apk update --no-cache && apk upgrade --no-cache && apk add --no-cache ca-certificates tzdata
-COPY ./kured /usr/bin/kured
-ENTRYPOINT ["/usr/bin/kured"]

cmd/kured/main_test.go

@@ -3,233 +3,74 @@ package main
 import (
 	"reflect"
 	"testing"
-
-	log "github.com/sirupsen/logrus"
-	"github.com/spf13/cobra"
-	"github.com/weaveworks/kured/pkg/alerts"
-	assert "gotest.tools/v3/assert"
-
-	papi "github.com/prometheus/client_golang/api"
 )
 
-type BlockingChecker struct {
-	blocking bool
-}
+func TestValidateNotificationURL(t *testing.T) {
 
-func (fbc BlockingChecker) isBlocked() bool {
-	return fbc.blocking
-}
-
-var _ RebootBlocker = BlockingChecker{}       // Verify that Type implements Interface.
-var _ RebootBlocker = (*BlockingChecker)(nil) // Verify that *Type implements Interface.
-
-func Test_flagCheck(t *testing.T) {
-	var cmd *cobra.Command
-	var args []string
-	slackHookURL = "https://hooks.slack.com/services/BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET"
-	flagCheck(cmd, args)
-	if notifyURL != "slack://BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET" {
-		t.Errorf("Slack URL Parsing is wrong: expecting %s  but got %s\n", "slack://BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET", notifyURL)
-	}
-}
-func Test_rebootBlocked(t *testing.T) {
-	noCheckers := []RebootBlocker{}
-	nonblockingChecker := BlockingChecker{blocking: false}
-	blockingChecker := BlockingChecker{blocking: true}
-
-	// Instantiate a prometheusClient with a broken_url
-	promClient, err := alerts.NewPromClient(papi.Config{Address: "broken_url"})
-	if err != nil {
-		log.Fatal("Can't create prometheusClient: ", err)
-	}
-	brokenPrometheusClient := PrometheusBlockingChecker{promClient: promClient, filter: nil, firingOnly: false}
-
-	type args struct {
-		blockers []RebootBlocker
-	}
 	tests := []struct {
-		name string
-		args args
-		want bool
+		name         string
+		slackHookURL string
+		notifyURL    string
+		expected     string
 	}{
-		{
-			name: "Do not block on no blocker defined",
-			args: args{blockers: noCheckers},
-			want: false,
-		},
-		{
-			name: "Ensure a blocker blocks",
-			args: args{blockers: []RebootBlocker{blockingChecker}},
-			want: true,
-		},
-		{
-			name: "Ensure a non-blocker doesn't block",
-			args: args{blockers: []RebootBlocker{nonblockingChecker}},
-			want: false,
-		},
-		{
-			name: "Ensure one blocker is enough to block",
-			args: args{blockers: []RebootBlocker{nonblockingChecker, blockingChecker}},
-			want: true,
-		},
-		{
-			name: "Do block on error contacting prometheus API",
-			args: args{blockers: []RebootBlocker{brokenPrometheusClient}},
-			want: true,
-		},
+		{"slackHookURL only works fine", "https://hooks.slack.com/services/BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET", "", "slack://BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET"},
+		{"slackHookURL and notify URL together only keeps notifyURL", "\"https://hooks.slack.com/services/BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET\"", "teams://79b4XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX@acd8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX/204cXXXXXXXXXXXXXXXXXXXXXXXXXXXX/a1f8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX?host=XXXX.webhook.office.com", "teams://79b4XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX@acd8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX/204cXXXXXXXXXXXXXXXXXXXXXXXXXXXX/a1f8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX?host=XXXX.webhook.office.com"},
+		{"slackHookURL removes extraneous double quotes", "\"https://hooks.slack.com/services/BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET\"", "", "slack://BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET"},
+		{"slackHookURL removes extraneous single quotes", "'https://hooks.slack.com/services/BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET'", "", "slack://BLABLABA12345/IAM931A0VERY/COMPLICATED711854TOKEN1SET"},
+		{"notifyURL removes extraneous double quotes", "", "\"teams://79b4XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX@acd8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX/204cXXXXXXXXXXXXXXXXXXXXXXXXXXXX/a1f8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX?host=XXXX.webhook.office.com\"", "teams://79b4XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX@acd8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX/204cXXXXXXXXXXXXXXXXXXXXXXXXXXXX/a1f8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX?host=XXXX.webhook.office.com"},
+		{"notifyURL removes extraneous single quotes", "", "'teams://79b4XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX@acd8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX/204cXXXXXXXXXXXXXXXXXXXXXXXXXXXX/a1f8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX?host=XXXX.webhook.office.com'", "teams://79b4XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX@acd8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX/204cXXXXXXXXXXXXXXXXXXXXXXXXXXXX/a1f8XXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX?host=XXXX.webhook.office.com"},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			if got := rebootBlocked(tt.args.blockers...); got != tt.want {
-				t.Errorf("rebootBlocked() = %v, want %v", got, tt.want)
+			if got := validateNotificationURL(tt.notifyURL, tt.slackHookURL); !reflect.DeepEqual(got, tt.expected) {
+				t.Errorf("validateNotificationURL() = %v, expected %v", got, tt.expected)
 			}
 		})
 	}
 }
 
-func Test_buildHostCommand(t *testing.T) {
-	type args struct {
-		pid     int
-		command []string
-	}
+func Test_stripQuotes(t *testing.T) {
 	tests := []struct {
-		name string
-		args args
-		want []string
+		name     string
+		input    string
+		expected string
 	}{
 		{
-			name: "Ensure command will run with nsenter",
-			args: args{pid: 1, command: []string{"ls", "-Fal"}},
-			want: []string{"/usr/bin/nsenter", "-m/proc/1/ns/mnt", "--", "ls", "-Fal"},
+			name:     "string with no surrounding quotes is unchanged",
+			input:    "Hello, world!",
+			expected: "Hello, world!",
+		},
+		{
+			name:     "string with surrounding double quotes should strip quotes",
+			input:    "\"Hello, world!\"",
+			expected: "Hello, world!",
+		},
+		{
+			name:     "string with surrounding single quotes should strip quotes",
+			input:    "'Hello, world!'",
+			expected: "Hello, world!",
+		},
+		{
+			name:     "string with unbalanced surrounding quotes is unchanged",
+			input:    "'Hello, world!\"",
+			expected: "'Hello, world!\"",
+		},
+		{
+			name:     "string with length of one is unchanged",
+			input:    "'",
+			expected: "'",
+		},
+		{
+			name:     "string with length of zero is unchanged",
+			input:    "",
+			expected: "",
 		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
-			if got := buildHostCommand(tt.args.pid, tt.args.command); !reflect.DeepEqual(got, tt.want) {
-				t.Errorf("buildHostCommand() = %v, want %v", got, tt.want)
+			if got := stripQuotes(tt.input); !reflect.DeepEqual(got, tt.expected) {
+				t.Errorf("stripQuotes() = %v, expected %v", got, tt.expected)
 			}
 		})
 	}
 }
-
-func Test_buildSentinelCommand(t *testing.T) {
-	type args struct {
-		rebootSentinelFile    string
-		rebootSentinelCommand string
-	}
-	tests := []struct {
-		name string
-		args args
-		want []string
-	}{
-		{
-			name: "Ensure a sentinelFile generates a shell 'test' command with the right file",
-			args: args{
-				rebootSentinelFile:    "/test1",
-				rebootSentinelCommand: "",
-			},
-			want: []string{"test", "-f", "/test1"},
-		},
-		{
-			name: "Ensure a sentinelCommand has priority over a sentinelFile if both are provided (because sentinelFile is always provided)",
-			args: args{
-				rebootSentinelFile:    "/test1",
-				rebootSentinelCommand: "/sbin/reboot-required -r",
-			},
-			want: []string{"/sbin/reboot-required", "-r"},
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			if got := buildSentinelCommand(tt.args.rebootSentinelFile, tt.args.rebootSentinelCommand); !reflect.DeepEqual(got, tt.want) {
-				t.Errorf("buildSentinelCommand() = %v, want %v", got, tt.want)
-			}
-		})
-	}
-}
-
-func Test_parseRebootCommand(t *testing.T) {
-	type args struct {
-		rebootCommand string
-	}
-	tests := []struct {
-		name string
-		args args
-		want []string
-	}{
-		{
-			name: "Ensure a reboot command is properly parsed",
-			args: args{
-				rebootCommand: "/sbin/systemctl reboot",
-			},
-			want: []string{"/sbin/systemctl", "reboot"},
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			if got := parseRebootCommand(tt.args.rebootCommand); !reflect.DeepEqual(got, tt.want) {
-				t.Errorf("parseRebootCommand() = %v, want %v", got, tt.want)
-			}
-		})
-	}
-}
-
-func Test_rebootRequired(t *testing.T) {
-	type args struct {
-		sentinelCommand []string
-	}
-	tests := []struct {
-		name string
-		args args
-		want bool
-	}{
-		{
-			name: "Ensure rc = 0 means reboot required",
-			args: args{
-				sentinelCommand: []string{"true"},
-			},
-			want: true,
-		},
-		{
-			name: "Ensure rc != 0 means reboot NOT required",
-			args: args{
-				sentinelCommand: []string{"false"},
-			},
-			want: false,
-		},
-	}
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			if got := rebootRequired(tt.args.sentinelCommand); got != tt.want {
-				t.Errorf("rebootRequired() = %v, want %v", got, tt.want)
-			}
-		})
-	}
-}
-
-func Test_rebootRequired_fatals(t *testing.T) {
-	cases := []struct {
-		param       []string
-		expectFatal bool
-	}{
-		{
-			param:       []string{"true"},
-			expectFatal: false,
-		},
-		{
-			param:       []string{"./babar"},
-			expectFatal: true,
-		},
-	}
-
-	defer func() { log.StandardLogger().ExitFunc = nil }()
-	var fatal bool
-	log.StandardLogger().ExitFunc = func(int) { fatal = true }
-
-	for _, c := range cases {
-		fatal = false
-		rebootRequired(c.param)
-		assert.Equal(t, c.expectFatal, fatal)
-	}
-
-}

cmd/kured/pflags.go

@@ -5,14 +5,14 @@ import (
 )
 
 type regexpValue struct {
-	value **regexp.Regexp
+	*regexp.Regexp
 }
 
 func (rev *regexpValue) String() string {
-	if *rev.value == nil {
+	if rev.Regexp == nil {
 		return ""
 	}
-	return (*rev.value).String()
+	return rev.Regexp.String()
 }
 
 func (rev *regexpValue) Set(s string) error {
@@ -20,12 +20,11 @@ func (rev *regexpValue) Set(s string) error {
 	if err != nil {
 		return err
 	}
-
-	*rev.value = value
-
+	rev.Regexp = value
 	return nil
 }
 
+// Type method returns the type of the flag as a string
 func (rev *regexpValue) Type() string {
-	return "regexp.Regexp"
+	return "regexp"
 }

go.mod

@@ -1,20 +1,90 @@
-module github.com/weaveworks/kured
+module github.com/kubereboot/kured
 
-go 1.16
+go 1.24.11
 
 require (
-	github.com/containrrr/shoutrrr v0.5.2
+	github.com/containrrr/shoutrrr v0.8.0
 	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510
-	github.com/prometheus/client_golang v1.11.0
-	github.com/prometheus/common v0.32.1
-	github.com/sirupsen/logrus v1.8.1
-	github.com/spf13/cobra v1.3.0
-	github.com/spf13/pflag v1.0.5
-	github.com/spf13/viper v1.10.1
-	github.com/stretchr/testify v1.7.0
-	gotest.tools/v3 v3.0.3
-	k8s.io/api v0.22.4
-	k8s.io/apimachinery v0.22.4
-	k8s.io/client-go v0.22.4
-	k8s.io/kubectl v0.22.4
+	github.com/prometheus/client_golang v1.23.2
+	github.com/prometheus/common v0.67.5
+	github.com/sirupsen/logrus v1.9.3
+	github.com/spf13/pflag v1.0.10
+	github.com/stretchr/testify v1.11.1
+	k8s.io/api v0.34.3
+	k8s.io/apimachinery v0.34.3
+	k8s.io/client-go v0.34.3
+	k8s.io/kubectl v0.34.3
+)
+
+require (
+	github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 // indirect
+	github.com/MakeNowJust/heredoc v1.0.0 // indirect
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/blang/semver/v4 v4.0.0 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
+	github.com/chai2010/gettext-go v1.0.2 // indirect
+	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
+	github.com/emicklei/go-restful/v3 v3.12.2 // indirect
+	github.com/exponent-io/jsonpath v0.0.0-20210407135951-1de76d718b3f // indirect
+	github.com/fatih/color v1.15.0 // indirect
+	github.com/fxamacker/cbor/v2 v2.9.0 // indirect
+	github.com/go-errors/errors v1.4.2 // indirect
+	github.com/go-logr/logr v1.4.2 // indirect
+	github.com/go-openapi/jsonpointer v0.21.0 // indirect
+	github.com/go-openapi/jsonreference v0.20.2 // indirect
+	github.com/go-openapi/swag v0.23.0 // indirect
+	github.com/gogo/protobuf v1.3.2 // indirect
+	github.com/google/btree v1.1.3 // indirect
+	github.com/google/gnostic-models v0.7.0 // indirect
+	github.com/google/uuid v1.6.0 // indirect
+	github.com/gorilla/websocket v1.5.4-0.20250319132907-e064f32e3674 // indirect
+	github.com/gregjones/httpcache v0.0.0-20190611155906-901d90724c79 // indirect
+	github.com/inconshreveable/mousetrap v1.1.0 // indirect
+	github.com/josharian/intern v1.0.0 // indirect
+	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/liggitt/tabwriter v0.0.0-20181228230101-89fcab3d43de // indirect
+	github.com/mailru/easyjson v0.7.7 // indirect
+	github.com/mattn/go-colorable v0.1.13 // indirect
+	github.com/mattn/go-isatty v0.0.17 // indirect
+	github.com/mitchellh/go-wordwrap v1.0.1 // indirect
+	github.com/moby/spdystream v0.5.0 // indirect
+	github.com/moby/term v0.5.0 // indirect
+	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
+	github.com/modern-go/reflect2 v1.0.3-0.20250322232337-35a7c28c31ee // indirect
+	github.com/monochromegane/go-gitignore v0.0.0-20200626010858-205db1a8cc00 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f // indirect
+	github.com/peterbourgon/diskv v2.0.1+incompatible // indirect
+	github.com/pkg/errors v0.9.1 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+	github.com/prometheus/client_model v0.6.2 // indirect
+	github.com/prometheus/procfs v0.16.1 // indirect
+	github.com/russross/blackfriday/v2 v2.1.0 // indirect
+	github.com/spf13/cobra v1.9.1 // indirect
+	github.com/x448/float16 v0.8.4 // indirect
+	github.com/xlab/treeprint v1.2.0 // indirect
+	go.yaml.in/yaml/v2 v2.4.3 // indirect
+	go.yaml.in/yaml/v3 v3.0.4 // indirect
+	golang.org/x/net v0.48.0 // indirect
+	golang.org/x/oauth2 v0.34.0 // indirect
+	golang.org/x/sync v0.19.0 // indirect
+	golang.org/x/sys v0.39.0 // indirect
+	golang.org/x/term v0.38.0 // indirect
+	golang.org/x/text v0.32.0 // indirect
+	golang.org/x/time v0.9.0 // indirect
+	google.golang.org/protobuf v1.36.11 // indirect
+	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
+	gopkg.in/inf.v0 v0.9.1 // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
+	k8s.io/cli-runtime v0.34.3 // indirect
+	k8s.io/component-base v0.34.3 // indirect
+	k8s.io/klog/v2 v2.130.1 // indirect
+	k8s.io/kube-openapi v0.0.0-20250710124328-f3f2b991d03b // indirect
+	k8s.io/utils v0.0.0-20250604170112-4c0f3b243397 // indirect
+	sigs.k8s.io/json v0.0.0-20241014173422-cfa47c3a1cc8 // indirect
+	sigs.k8s.io/kustomize/api v0.20.1 // indirect
+	sigs.k8s.io/kustomize/kyaml v0.20.1 // indirect
+	sigs.k8s.io/randfill v1.0.0 // indirect
+	sigs.k8s.io/structured-merge-diff/v6 v6.3.0 // indirect
+	sigs.k8s.io/yaml v1.6.0 // indirect
 )

internal/validators.go

@@ -0,0 +1,41 @@
+// Package internal provides convenient tools which shouldn't be in cmd/main
+// It will eventually provide internal validation and chaining logic to select
+// appropriate reboot and sentinel check methods based on configuration.
+// It validates user input and instantiates the correct checker and rebooter implementations
+// for use elsewhere in kured.
+package internal
+
+import (
+	"fmt"
+
+	"github.com/kubereboot/kured/pkg/checkers"
+	"github.com/kubereboot/kured/pkg/reboot"
+	log "github.com/sirupsen/logrus"
+)
+
+// NewRebooter validates the rebootMethod, rebootCommand, and rebootSignal input,
+// then chains to the right constructor.
+func NewRebooter(rebootMethod string, rebootCommand string, rebootSignal int) (reboot.Rebooter, error) {
+	switch rebootMethod {
+	case "command":
+		log.Infof("Reboot command: %s", rebootCommand)
+		return reboot.NewCommandRebooter(rebootCommand)
+	case "signal":
+		log.Infof("Reboot signal: %d", rebootSignal)
+		return reboot.NewSignalRebooter(rebootSignal)
+	default:
+		return nil, fmt.Errorf("invalid reboot-method configured %s, expected signal or command", rebootMethod)
+	}
+}
+
+// NewRebootChecker validates the rebootSentinelCommand, rebootSentinelFile input,
+// then chains to the right constructor.
+func NewRebootChecker(rebootSentinelCommand string, rebootSentinelFile string) (checkers.Checker, error) {
+	// An override of rebootSentinelCommand means a privileged command
+	if rebootSentinelCommand != "" {
+		log.Infof("Sentinel checker is (privileged) user provided command: %s", rebootSentinelCommand)
+		return checkers.NewCommandChecker(rebootSentinelCommand, 1, true)
+	}
+	log.Infof("Sentinel checker is (unprivileged) testing for the presence of: %s", rebootSentinelFile)
+	return checkers.NewFileRebootChecker(rebootSentinelFile)
+}

kured-ds-signal.yaml

@@ -0,0 +1,100 @@
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kured
+  namespace: kube-system
+---
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: kured # Must match `--ds-name`
+  namespace: kube-system # Must match `--ds-namespace`
+spec:
+  selector:
+    matchLabels:
+      name: kured
+  updateStrategy:
+    type: RollingUpdate
+  template:
+    metadata:
+      labels:
+        name: kured
+    spec:
+      serviceAccountName: kured
+      tolerations:
+        - key: node-role.kubernetes.io/control-plane
+          effect: NoSchedule
+        - key: node-role.kubernetes.io/master
+          effect: NoSchedule
+      hostPID: true # Facilitate entering the host mount namespace via init
+      restartPolicy: Always
+      volumes:
+        - name: sentinel
+          hostPath:
+            path: /var/run
+            type: Directory
+      containers:
+        - name: kured
+          # If you find yourself here wondering why there is no
+          # :latest tag on Docker Hub,see the FAQ in the README
+          image: ghcr.io/kubereboot/kured:1.21.0
+          imagePullPolicy: IfNotPresent
+          securityContext:
+            privileged: false # Give permission to nsenter /proc/1/ns/mnt
+            readOnlyRootFilesystem: true
+            allowPrivilegeEscalation: false
+            capabilities:
+              drop: ["*"]
+              add: ["CAP_KILL"]
+          ports:
+            - containerPort: 8080
+              name: metrics
+          env:
+            # Pass in the name of the node on which this pod is scheduled
+            # for use with drain/uncordon operations and lock acquisition
+            - name: KURED_NODE_ID
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+          volumeMounts:
+            - mountPath: /sentinel
+              name: sentinel
+              readOnly: true
+          command:
+            - /usr/bin/kured
+            - --reboot-sentinel=/sentinel/reboot-required
+            - --reboot-method=signal
+#            - --reboot-signal=39
+#            - --force-reboot=false
+#            - --drain-grace-period=-1
+#            - --skip-wait-for-delete-timeout=0
+#            - --drain-timeout=0
+#            - --period=1h
+#            - --ds-namespace=kube-system
+#            - --ds-name=kured
+#            - --lock-annotation=weave.works/kured-node-lock
+#            - --lock-ttl=0
+#            - --prometheus-url=http://prometheus.monitoring.svc.cluster.local
+#            - --alert-filter-regexp=^RebootRequired$
+#            - --alert-firing-only=false
+#            - --prefer-no-schedule-taint=""
+#            - --reboot-sentinel-command=""
+#            - --slack-hook-url=https://hooks.slack.com/...
+#            - --slack-username=prod
+#            - --slack-channel=alerting
+#            - --notify-url="" # See also shoutrrr url format
+#            - --message-template-drain=Draining node %s
+#            - --message-template-reboot=Rebooting node %s
+#            - --message-template-uncordon=Node %s rebooted & uncordoned successfully!
+#            - --blocking-pod-selector=runtime=long,cost=expensive
+#            - --blocking-pod-selector=name=temperamental
+#            - --blocking-pod-selector=...
+#            - --reboot-days=sun,mon,tue,wed,thu,fri,sat
+#            - --reboot-delay=90s
+#            - --start-time=0:00
+#            - --end-time=23:59:59
+#            - --time-zone=UTC
+#            - --annotate-nodes=false
+#            - --lock-release-delay=30m
+#            - --log-format=text

kured-ds.yaml

@@ -8,14 +8,14 @@ metadata:
 apiVersion: apps/v1
 kind: DaemonSet
 metadata:
-  name: kured            # Must match `--ds-name`
+  name: kured # Must match `--ds-name`
   namespace: kube-system # Must match `--ds-namespace`
 spec:
   selector:
     matchLabels:
       name: kured
   updateStrategy:
-   type: RollingUpdate
+    type: RollingUpdate
   template:
     metadata:
       labels:
@@ -23,18 +23,29 @@ spec:
     spec:
       serviceAccountName: kured
       tolerations:
+        - key: node-role.kubernetes.io/control-plane
+          effect: NoSchedule
         - key: node-role.kubernetes.io/master
           effect: NoSchedule
       hostPID: true # Facilitate entering the host mount namespace via init
       restartPolicy: Always
+      volumes:
+        - name: sentinel
+          hostPath:
+            path: /var/run
+            type: Directory
       containers:
         - name: kured
-          image: docker.io/weaveworks/kured:1.9.1
-                 # If you find yourself here wondering why there is no
-                 # :latest tag on Docker Hub,see the FAQ in the README
+          # If you find yourself here wondering why there is no
+          # :latest tag on Docker Hub,see the FAQ in the README
+          image: ghcr.io/kubereboot/kured:1.21.0
           imagePullPolicy: IfNotPresent
           securityContext:
             privileged: true # Give permission to nsenter /proc/1/ns/mnt
+            readOnlyRootFilesystem: true
+          ports:
+            - containerPort: 8080
+              name: metrics
           env:
             # Pass in the name of the node on which this pod is scheduled
             # for use with drain/uncordon operations and lock acquisition
@@ -42,12 +53,19 @@ spec:
               valueFrom:
                 fieldRef:
                   fieldPath: spec.nodeName
+          volumeMounts:
+            - mountPath: /sentinel
+              name: sentinel
+              readOnly: true
           command:
             - /usr/bin/kured
+            - --reboot-sentinel=/sentinel/reboot-required
 #            - --force-reboot=false
 #            - --drain-grace-period=-1
 #            - --skip-wait-for-delete-timeout=0
+#            - --drain-delay=0
 #            - --drain-timeout=0
+#            - --drain-pod-selector=""
 #            - --period=1h
 #            - --ds-namespace=kube-system
 #            - --ds-name=kured
@@ -55,16 +73,19 @@ spec:
 #            - --lock-ttl=0
 #            - --prometheus-url=http://prometheus.monitoring.svc.cluster.local
 #            - --alert-filter-regexp=^RebootRequired$
+#            - --alert-filter-match-only=false
 #            - --alert-firing-only=false
-#            - --reboot-sentinel=/var/run/reboot-required
 #            - --prefer-no-schedule-taint=""
 #            - --reboot-sentinel-command=""
+#            - --reboot-method=command
+#            - --reboot-signal=39
 #            - --slack-hook-url=https://hooks.slack.com/...
 #            - --slack-username=prod
 #            - --slack-channel=alerting
 #            - --notify-url="" # See also shoutrrr url format
 #            - --message-template-drain=Draining node %s
-#            - --message-template-drain=Rebooting node %s
+#            - --message-template-reboot=Rebooting node %s
+#            - --message-template-uncordon=Node %s rebooted & uncordoned successfully!
 #            - --blocking-pod-selector=runtime=long,cost=expensive
 #            - --blocking-pod-selector=name=temperamental
 #            - --blocking-pod-selector=...
@@ -76,3 +97,6 @@ spec:
 #            - --annotate-nodes=false
 #            - --lock-release-delay=30m
 #            - --log-format=text
+#            - --metrics-host=""
+#            - --metrics-port=8080
+#            - --concurrency=1

pkg/alerts/prometheus.go

@@ -1,69 +0,0 @@
-package alerts
-
-import (
-	"context"
-	"fmt"
-	"regexp"
-	"sort"
-	"time"
-
-	papi "github.com/prometheus/client_golang/api"
-	v1 "github.com/prometheus/client_golang/api/prometheus/v1"
-	"github.com/prometheus/common/model"
-)
-
-// PromClient is a wrapper around the Prometheus Client interface and implements the api
-// This way, the PromClient can be instantiated with the configuration the Client needs, and
-// the ability to use the methods the api has, like Query and so on.
-type PromClient struct {
-	papi papi.Client
-	api  v1.API
-}
-
-// NewPromClient creates a new client to the Prometheus API.
-// It returns an error on any problem.
-func NewPromClient(conf papi.Config) (*PromClient, error) {
-	promClient, err := papi.NewClient(conf)
-	if err != nil {
-		return nil, err
-	}
-	client := PromClient{papi: promClient, api: v1.NewAPI(promClient)}
-	return &client, nil
-}
-
-// ActiveAlerts is a method of type PromClient, it returns a list of names of active alerts
-// (e.g. pending or firing), filtered by the supplied regexp or by the includeLabels query.
-// filter by regexp means when the regex finds the alert-name; the alert is exluded from the
-// block-list and will NOT block rebooting. query by includeLabel means,
-// if the query finds an alert, it will include it to the block-list and it WILL block rebooting.
-func (p *PromClient) ActiveAlerts(filter *regexp.Regexp, firingOnly bool) ([]string, error) {
-
-	// get all alerts from prometheus
-	value, _, err := p.api.Query(context.Background(), "ALERTS", time.Now())
-	if err != nil {
-		return nil, err
-	}
-
-	if value.Type() == model.ValVector {
-		if vector, ok := value.(model.Vector); ok {
-			activeAlertSet := make(map[string]bool)
-			for _, sample := range vector {
-				if alertName, isAlert := sample.Metric[model.AlertNameLabel]; isAlert && sample.Value != 0 {
-					if (filter == nil || !filter.MatchString(string(alertName))) && (!firingOnly || sample.Metric["alertstate"] == "firing") {
-						activeAlertSet[string(alertName)] = true
-					}
-				}
-			}
-
-			var activeAlerts []string
-			for activeAlert := range activeAlertSet {
-				activeAlerts = append(activeAlerts, activeAlert)
-			}
-			sort.Strings(activeAlerts)
-
-			return activeAlerts, nil
-		}
-	}
-
-	return nil, fmt.Errorf("Unexpected value type: %v", value)
-}

pkg/alerts/prometheus_test.go

@@ -1,141 +0,0 @@
-package alerts
-
-import (
-	"log"
-	"net/http"
-	"net/http/httptest"
-
-	"regexp"
-	"testing"
-
-	"github.com/prometheus/client_golang/api"
-
-	"github.com/stretchr/testify/assert"
-)
-
-type MockResponse struct {
-	StatusCode int
-	Body       []byte
-}
-
-// MockServerProperties ties a mock response to a url and a method
-type MockServerProperties struct {
-	URI        string
-	HTTPMethod string
-	Response   MockResponse
-}
-
-// NewMockServer sets up a new MockServer with properties ad starts the server.
-func NewMockServer(props ...MockServerProperties) *httptest.Server {
-
-	handler := http.HandlerFunc(
-		func(w http.ResponseWriter, r *http.Request) {
-			for _, proc := range props {
-				_, err := w.Write(proc.Response.Body)
-				if err != nil {
-					log.Fatal(err)
-				}
-			}
-		})
-	return httptest.NewServer(handler)
-}
-
-func TestActiveAlerts(t *testing.T) {
-	responsebody := `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"GatekeeperViolations","alertstate":"firing","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"PodCrashing-dev","alertstate":"firing","container":"deployment","instance":"1.2.3.4:8080","job":"kube-state-metrics","namespace":"dev","pod":"dev-deployment-78dcbmf25v","severity":"critical","team":"dev"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"PodRestart-dev","alertstate":"firing","container":"deployment","instance":"1.2.3.4:1234","job":"kube-state-metrics","namespace":"qa","pod":"qa-job-deployment-78dcbmf25v","severity":"warning","team":"qa"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"PrometheusTargetDown","alertstate":"firing","job":"kubernetes-pods","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"ScheduledRebootFailing","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`
-	addr := "http://localhost:10001"
-
-	for _, tc := range []struct {
-		it         string
-		rFilter    string
-		respBody   string
-		aName      string
-		wantN      int
-		firingOnly bool
-	}{
-		{
-			it:         "should return no active alerts",
-			respBody:   responsebody,
-			rFilter:    "",
-			wantN:      0,
-			firingOnly: false,
-		},
-		{
-			it:         "should return a subset of all alerts",
-			respBody:   responsebody,
-			rFilter:    "Pod",
-			wantN:      3,
-			firingOnly: false,
-		},
-		{
-			it:         "should return all active alerts by regex",
-			respBody:   responsebody,
-			rFilter:    "*",
-			wantN:      5,
-			firingOnly: false,
-		},
-		{
-			it:         "should return all active alerts by regex filter",
-			respBody:   responsebody,
-			rFilter:    "*",
-			wantN:      5,
-			firingOnly: false,
-		},
-		{
-			it:         "should return only firing alerts if firingOnly is true",
-			respBody:   responsebody,
-			rFilter:    "*",
-			wantN:      4,
-			firingOnly: true,
-		},
-		{
-			it:         "should return ScheduledRebootFailing active alerts",
-			respBody:   `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"ScheduledRebootFailing","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`,
-			aName:      "ScheduledRebootFailing",
-			rFilter:    "*",
-			wantN:      1,
-			firingOnly: false,
-		},
-		{
-			it:         "should not return an active alert if RebootRequired is firing (regex filter)",
-			respBody:   `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"RebootRequired","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`,
-			rFilter:    "RebootRequired",
-			wantN:      0,
-			firingOnly: false,
-		},
-	} {
-		// Start mockServer
-		mockServer := NewMockServer(MockServerProperties{
-			URI:        addr,
-			HTTPMethod: http.MethodPost,
-			Response: MockResponse{
-				Body: []byte(tc.respBody),
-			},
-		})
-		// Close mockServer after all connections are gone
-		defer mockServer.Close()
-
-		t.Run(tc.it, func(t *testing.T) {
-
-			// regex filter
-			regex, _ := regexp.Compile(tc.rFilter)
-
-			// instantiate the prometheus client with the mockserver-address
-			p, err := NewPromClient(api.Config{Address: mockServer.URL})
-			if err != nil {
-				log.Fatal(err)
-			}
-
-			result, err := p.ActiveAlerts(regex, tc.firingOnly)
-			if err != nil {
-				log.Fatal(err)
-			}
-
-			// assert
-			assert.Equal(t, tc.wantN, len(result), "expected amount of alerts %v, got %v", tc.wantN, len(result))
-
-			if tc.aName != "" {
-				assert.Equal(t, tc.aName, result[0], "expected active alert %v, got %v", tc.aName, result[0])
-			}
-		})
-	}
-}

pkg/blockers/blockers.go

@@ -0,0 +1,21 @@
+// Package blockers provides interfaces and implementations for determining
+// whether a system should be prevented to reboot.
+// You can use that package if you fork Kured's main loop.
+package blockers
+
+// RebootBlocked checks that a single block Checker
+// will block the reboot or not.
+func RebootBlocked(blockers ...RebootBlocker) bool {
+	for _, blocker := range blockers {
+		if blocker.IsBlocked() {
+			return true
+		}
+	}
+	return false
+}
+
+// RebootBlocker interface should be implemented by types
+// to know if their instantiations should block a reboot
+type RebootBlocker interface {
+	IsBlocked() bool
+}

pkg/blockers/blockers_test.go

@@ -0,0 +1,65 @@
+package blockers
+
+import (
+	papi "github.com/prometheus/client_golang/api"
+	"testing"
+)
+
+type BlockingChecker struct {
+	blocking bool
+}
+
+func (fbc BlockingChecker) IsBlocked() bool {
+	return fbc.blocking
+}
+
+func Test_rebootBlocked(t *testing.T) {
+	noCheckers := []RebootBlocker{}
+	nonblockingChecker := BlockingChecker{blocking: false}
+	blockingChecker := BlockingChecker{blocking: true}
+
+	// Instantiate a prometheusClient with a broken_url
+	brokenPrometheusClient := NewPrometheusBlockingChecker(papi.Config{Address: "broken_url"}, nil, false, false)
+
+	type args struct {
+		blockers []RebootBlocker
+	}
+	tests := []struct {
+		name string
+		args args
+		want bool
+	}{
+		{
+			name: "Do not block on no blocker defined",
+			args: args{blockers: noCheckers},
+			want: false,
+		},
+		{
+			name: "Ensure a blocker blocks",
+			args: args{blockers: []RebootBlocker{blockingChecker}},
+			want: true,
+		},
+		{
+			name: "Ensure a non-blocker doesn't block",
+			args: args{blockers: []RebootBlocker{nonblockingChecker}},
+			want: false,
+		},
+		{
+			name: "Ensure one blocker is enough to block",
+			args: args{blockers: []RebootBlocker{nonblockingChecker, blockingChecker}},
+			want: true,
+		},
+		{
+			name: "Do block on error contacting prometheus API",
+			args: args{blockers: []RebootBlocker{brokenPrometheusClient}},
+			want: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := RebootBlocked(tt.args.blockers...); got != tt.want {
+				t.Errorf("rebootBlocked() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

pkg/blockers/kubernetespod.go

@@ -0,0 +1,64 @@
+package blockers
+
+import (
+	"context"
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/kubernetes"
+)
+
+// Compile-time checks to ensure the type implements the interface
+var (
+	_ RebootBlocker = (*KubernetesBlockingChecker)(nil)
+)
+
+// KubernetesBlockingChecker contains info for connecting
+// to k8s, and can give info about whether a reboot should be blocked
+type KubernetesBlockingChecker struct {
+	// client used to contact kubernetes API
+	client   *kubernetes.Clientset
+	nodeName string
+	// lised used to filter pods (podSelector)
+	filter []string
+}
+
+// NewKubernetesBlockingChecker creates a new KubernetesBlockingChecker using the provided Kubernetes client,
+// node name, and pod selectors.
+func NewKubernetesBlockingChecker(client *kubernetes.Clientset, nodename string, podSelectors []string) *KubernetesBlockingChecker {
+	return &KubernetesBlockingChecker{
+		client:   client,
+		nodeName: nodename,
+		filter:   podSelectors,
+	}
+}
+
+// IsBlocked for the KubernetesBlockingChecker will check if a pod, for the node, is preventing
+// the reboot. It will warn in the logs about blocking, but does not return an error.
+func (kb KubernetesBlockingChecker) IsBlocked() bool {
+	fieldSelector := fmt.Sprintf("spec.nodeName=%s,status.phase!=Succeeded,status.phase!=Failed,status.phase!=Unknown", kb.nodeName)
+	for _, labelSelector := range kb.filter {
+		podList, err := kb.client.CoreV1().Pods("").List(context.TODO(), metav1.ListOptions{
+			LabelSelector: labelSelector,
+			FieldSelector: fieldSelector,
+			Limit:         10})
+		if err != nil {
+			log.Warnf("Reboot blocked: pod query error: %v", err)
+			return true
+		}
+
+		if len(podList.Items) > 0 {
+			podNames := make([]string, 0, len(podList.Items))
+			for _, pod := range podList.Items {
+				podNames = append(podNames, pod.Name)
+			}
+			if len(podList.Continue) > 0 {
+				podNames = append(podNames, "...")
+			}
+			log.Warnf("Reboot blocked: matching pods: %v", podNames)
+			return true
+		}
+	}
+	return false
+}

pkg/blockers/prometheus.go

@@ -0,0 +1,121 @@
+package blockers
+
+import (
+	"context"
+	"fmt"
+	"regexp"
+	"sort"
+	"time"
+
+	papi "github.com/prometheus/client_golang/api"
+	v1 "github.com/prometheus/client_golang/api/prometheus/v1"
+	"github.com/prometheus/common/model"
+	log "github.com/sirupsen/logrus"
+)
+
+// Compile-time checks to ensure the type implements the interface
+var (
+	_ RebootBlocker = (*PrometheusBlockingChecker)(nil)
+)
+
+// PrometheusBlockingChecker contains info for connecting
+// to prometheus, and can give info about whether a reboot should be blocked
+type PrometheusBlockingChecker struct {
+	promConfig papi.Config
+	// regexp used to get alerts
+	filter *regexp.Regexp
+	// bool to indicate if only firing alerts should be considered
+	firingOnly bool
+	// bool to indicate that we're only blocking on alerts which match the filter
+	filterMatchOnly bool
+	// storing the promClient
+	promClient papi.Client
+}
+
+// NewPrometheusBlockingChecker creates a new PrometheusBlockingChecker using the given
+// Prometheus API config, alert filter, and filtering options.
+func NewPrometheusBlockingChecker(config papi.Config, alertFilter *regexp.Regexp, firingOnly bool, filterMatchOnly bool) PrometheusBlockingChecker {
+	promClient, _ := papi.NewClient(config)
+
+	return PrometheusBlockingChecker{
+		promConfig:      config,
+		filter:          alertFilter,
+		firingOnly:      firingOnly,
+		filterMatchOnly: filterMatchOnly,
+		promClient:      promClient,
+	}
+}
+
+// IsBlocked for the prometheus will check if there are active alerts matching
+// the arguments given into the PrometheusBlockingChecker which would actively
+// block the reboot.
+// As of today, no blocker information is shared as a return of the method,
+// and the information is simply logged.
+func (pb PrometheusBlockingChecker) IsBlocked() bool {
+	alertNames, err := pb.ActiveAlerts()
+	if err != nil {
+		log.Warnf("Reboot blocked: prometheus query error: %v", err)
+		return true
+	}
+	count := len(alertNames)
+	if count > 10 {
+		alertNames = append(alertNames[:10], "...")
+	}
+	if count > 0 {
+		log.Warnf("Reboot blocked: %d active alerts: %v", count, alertNames)
+		return true
+	}
+	return false
+}
+
+// MetricLabel is used to give a fancier name
+// than the type to the label for rebootBlockedCounter
+func (pb PrometheusBlockingChecker) MetricLabel() string {
+	return "prometheus"
+}
+
+// ActiveAlerts is a method of type promClient, it returns a list of names of active alerts
+// (e.g. pending or firing), filtered by the supplied regexp or by the includeLabels query.
+// filter by regexp means when the regexp finds the alert-name; the alert is excluded from the
+// block-list and will NOT block rebooting. query by includeLabel means,
+// if the query finds an alert, it will include it to the block-list, and it WILL block rebooting.
+func (pb PrometheusBlockingChecker) ActiveAlerts() ([]string, error) {
+	api := v1.NewAPI(pb.promClient)
+
+	// get all alerts from prometheus
+	value, _, err := api.Query(context.Background(), "ALERTS", time.Now())
+	if err != nil {
+		return nil, err
+	}
+
+	if value.Type() == model.ValVector {
+		if vector, ok := value.(model.Vector); ok {
+			activeAlertSet := make(map[string]bool)
+			for _, sample := range vector {
+				if alertName, isAlert := sample.Metric[model.AlertNameLabel]; isAlert && sample.Value != 0 {
+					if matchesRegex(pb.filter, string(alertName), pb.filterMatchOnly) && (!pb.firingOnly || sample.Metric["alertstate"] == "firing") {
+						activeAlertSet[string(alertName)] = true
+					}
+				}
+			}
+
+			var activeAlerts []string
+			for activeAlert := range activeAlertSet {
+				activeAlerts = append(activeAlerts, activeAlert)
+			}
+			sort.Strings(activeAlerts)
+
+			return activeAlerts, nil
+		}
+	}
+
+	return nil, fmt.Errorf("unexpected value type %v", value)
+}
+
+func matchesRegex(filter *regexp.Regexp, alertName string, filterMatchOnly bool) bool {
+	if filter == nil {
+		return true
+	}
+
+	return filter.MatchString(alertName) == filterMatchOnly
+}

pkg/blockers/prometheus_test.go

@@ -0,0 +1,163 @@
+package blockers
+
+import (
+	"log"
+	"net/http"
+	"net/http/httptest"
+
+	"regexp"
+	"testing"
+
+	"github.com/prometheus/client_golang/api"
+
+	"github.com/stretchr/testify/assert"
+)
+
+type MockResponse struct {
+	StatusCode int
+	Body       []byte
+}
+
+// MockServerProperties ties a mock response to a url and a method
+type MockServerProperties struct {
+	URI        string
+	HTTPMethod string
+	Response   MockResponse
+}
+
+// NewMockServer sets up a new MockServer with properties ad starts the server.
+func NewMockServer(props ...MockServerProperties) *httptest.Server {
+
+	handler := http.HandlerFunc(
+		func(w http.ResponseWriter, r *http.Request) {
+			for _, proc := range props {
+				_, err := w.Write(proc.Response.Body)
+				if err != nil {
+					log.Fatal(err)
+				}
+			}
+		})
+	return httptest.NewServer(handler)
+}
+
+func TestActiveAlerts(t *testing.T) {
+	responsebody := `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"GatekeeperViolations","alertstate":"firing","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"PodCrashing-dev","alertstate":"firing","container":"deployment","instance":"1.2.3.4:8080","job":"kube-state-metrics","namespace":"dev","pod":"dev-deployment-78dcbmf25v","severity":"critical","team":"dev"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"PodRestart-dev","alertstate":"firing","container":"deployment","instance":"1.2.3.4:1234","job":"kube-state-metrics","namespace":"qa","pod":"qa-job-deployment-78dcbmf25v","severity":"warning","team":"qa"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"PrometheusTargetDown","alertstate":"firing","job":"kubernetes-pods","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]},{"metric":{"__name__":"ALERTS","alertname":"ScheduledRebootFailing","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`
+	addr := "http://localhost:10001"
+
+	for _, tc := range []struct {
+		it              string
+		rFilter         string
+		respBody        string
+		aName           string
+		wantN           int
+		firingOnly      bool
+		filterMatchOnly bool
+	}{
+		{
+			it:              "should return no active alerts",
+			respBody:        responsebody,
+			rFilter:         "",
+			wantN:           0,
+			firingOnly:      false,
+			filterMatchOnly: false,
+		},
+		{
+			it:              "should return a subset of all alerts",
+			respBody:        responsebody,
+			rFilter:         "Pod",
+			wantN:           3,
+			firingOnly:      false,
+			filterMatchOnly: false,
+		},
+		{
+			it:              "should return a subset of all alerts",
+			respBody:        responsebody,
+			rFilter:         "Gatekeeper",
+			wantN:           1,
+			firingOnly:      false,
+			filterMatchOnly: true,
+		},
+		{
+			it:              "should return all active alerts by regex",
+			respBody:        responsebody,
+			rFilter:         "*",
+			wantN:           5,
+			firingOnly:      false,
+			filterMatchOnly: false,
+		},
+		{
+			it:              "should return all active alerts by regex filter",
+			respBody:        responsebody,
+			rFilter:         "*",
+			wantN:           5,
+			firingOnly:      false,
+			filterMatchOnly: false,
+		},
+		{
+			it:              "should return only firing alerts if firingOnly is true",
+			respBody:        responsebody,
+			rFilter:         "*",
+			wantN:           4,
+			firingOnly:      true,
+			filterMatchOnly: false,
+		},
+
+		{
+			it:              "should return ScheduledRebootFailing active alerts",
+			respBody:        `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"ScheduledRebootFailing","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`,
+			aName:           "ScheduledRebootFailing",
+			rFilter:         "*",
+			wantN:           1,
+			firingOnly:      false,
+			filterMatchOnly: false,
+		},
+		{
+			it:              "should not return an active alert if RebootRequired is firing (regex filter)",
+			respBody:        `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"RebootRequired","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`,
+			rFilter:         "RebootRequired",
+			wantN:           0,
+			firingOnly:      false,
+			filterMatchOnly: false,
+		},
+		{
+			it:              "should not return an active alert if RebootRequired is firing (regex filter)",
+			respBody:        `{"status":"success","data":{"resultType":"vector","result":[{"metric":{"__name__":"ALERTS","alertname":"RebootRequired","alertstate":"pending","severity":"warning","team":"platform-infra"},"value":[1622472933.973,"1"]}]}}`,
+			rFilter:         "RebootRequired",
+			wantN:           1,
+			firingOnly:      false,
+			filterMatchOnly: true,
+		},
+	} {
+		// Start mockServer
+		mockServer := NewMockServer(MockServerProperties{
+			URI:        addr,
+			HTTPMethod: http.MethodPost,
+			Response: MockResponse{
+				Body: []byte(tc.respBody),
+			},
+		})
+		// Close mockServer after all connections are gone
+		defer mockServer.Close()
+
+		t.Run(tc.it, func(t *testing.T) {
+
+			// regex filter
+			regex, _ := regexp.Compile(tc.rFilter)
+
+			// instantiate the prometheus client with the mockserver-address
+			p := NewPrometheusBlockingChecker(api.Config{Address: mockServer.URL}, regex, tc.firingOnly, tc.filterMatchOnly)
+
+			result, err := p.ActiveAlerts()
+			if err != nil {
+				log.Fatal(err)
+			}
+
+			// assert
+			assert.Equal(t, tc.wantN, len(result), "expected amount of alerts %v, got %v", tc.wantN, len(result))
+
+			if tc.aName != "" {
+				assert.Equal(t, tc.aName, result[0], "expected active alert %v, got %v", tc.aName, result[0])
+			}
+		})
+	}
+}

pkg/checkers/checker.go

@@ -0,0 +1,117 @@
+// Package checkers provides interfaces and implementations for determining
+// whether a system reboot is required. It includes checkers based on file
+// presence or custom commands, and supports privileged command execution
+// in containerized environments. These checkers are used by kured to
+// detect conditions that should trigger node reboots.
+// You can use that package if you fork Kured's main loop.
+package checkers
+
+import (
+	"bytes"
+	"fmt"
+	"os"
+	"os/exec"
+	"strings"
+
+	"github.com/google/shlex"
+	log "github.com/sirupsen/logrus"
+)
+
+// Checker is the standard interface to use to check
+// if a reboot is required. Its types must implement a
+// CheckRebootRequired method which returns a single boolean
+// clarifying whether a reboot is expected or not.
+type Checker interface {
+	RebootRequired() bool
+}
+
+// FileRebootChecker is the default reboot checker.
+// It is unprivileged, and tests the presence of a files
+type FileRebootChecker struct {
+	FilePath string
+}
+
+// RebootRequired checks the file presence
+// needs refactoring to also return an error, instead of leaking it inside the code.
+// This needs refactoring to get rid of NewCommand
+// This needs refactoring to only contain file location, instead of CheckCommand
+func (rc FileRebootChecker) RebootRequired() bool {
+	if _, err := os.Stat(rc.FilePath); err == nil {
+		return true
+	}
+	return false
+}
+
+// NewFileRebootChecker is the constructor for the file based reboot checker
+// TODO: Add extra input validation on filePath string here
+func NewFileRebootChecker(filePath string) (*FileRebootChecker, error) {
+	return &FileRebootChecker{
+		FilePath: filePath,
+	}, nil
+}
+
+// CommandChecker is using a custom command to check
+// if a reboot is required. There are two modes of behaviour,
+// if Privileged is granted, the NamespacePid is used to nsenter
+// the given PID's namespace.
+type CommandChecker struct {
+	CheckCommand []string
+	NamespacePid int
+	Privileged   bool
+}
+
+// RebootRequired for CommandChecker runs a command without returning
+// any eventual error. This should be later refactored to return the errors,
+// instead of logging and fataling them here.
+func (rc CommandChecker) RebootRequired() bool {
+	bufStdout := new(bytes.Buffer)
+	bufStderr := new(bytes.Buffer)
+	// #nosec G204 -- CheckCommand is controlled and validated internally
+	cmd := exec.Command(rc.CheckCommand[0], rc.CheckCommand[1:]...)
+	cmd.Stdout = bufStdout
+	cmd.Stderr = bufStderr
+
+	if err := cmd.Run(); err != nil {
+		switch err := err.(type) {
+		case *exec.ExitError:
+			// We assume a non-zero exit code means 'reboot not required', but of course
+			// the user could have misconfigured the sentinel command or something else
+			// went wrong during its execution. In that case, not entering a reboot loop
+			// is the right thing to do, and we are logging stdout/stderr of the command
+			// so it should be obvious what is wrong.
+			if cmd.ProcessState.ExitCode() != 1 {
+				log.Warn(fmt.Sprintf("sentinel command ended with unexpected exit code: %v", cmd.ProcessState.ExitCode()), "cmd", strings.Join(cmd.Args, " "), "stdout", bufStdout.String(), "stderr", bufStderr.String())
+			}
+			return false
+		default:
+			// Something was grossly misconfigured, such as the command path being wrong.
+			log.Fatal(fmt.Sprintf("Error invoking sentinel command: %v", err), "cmd", strings.Join(cmd.Args, " "), "stdout", bufStdout.String(), "stderr", bufStderr.String())
+		}
+	}
+	log.Info("checking if reboot is required", "cmd", strings.Join(cmd.Args, " "), "stdout", bufStdout.String(), "stderr", bufStderr.String())
+	return true
+}
+
+// NewCommandChecker is the constructor for the commandChecker, and by default
+// runs new commands in a privileged fashion.
+// Privileged means wrapping the command with nsenter.
+// It allows to run a command from systemd's namespace for example (pid 1)
+// This relies on hostPID:true and privileged:true to enter host mount space
+// For info, rancher based need different pid, which should be user given.
+// until we have a better discovery mechanism.
+func NewCommandChecker(sentinelCommand string, pid int, privileged bool) (*CommandChecker, error) {
+	var cmd []string
+	if privileged {
+		cmd = append(cmd, "/usr/bin/nsenter", fmt.Sprintf("-m/proc/%d/ns/mnt", pid), "--")
+	}
+	parsedCommand, err := shlex.Split(sentinelCommand)
+	if err != nil {
+		return nil, fmt.Errorf("error parsing provided sentinel command: %v", err)
+	}
+	cmd = append(cmd, parsedCommand...)
+	return &CommandChecker{
+		CheckCommand: cmd,
+		NamespacePid: pid,
+		Privileged:   privileged,
+	}, nil
+}

pkg/checkers/checker_test.go

@@ -0,0 +1,87 @@
+package checkers
+
+import (
+	log "github.com/sirupsen/logrus"
+	"reflect"
+	"testing"
+)
+
+func Test_nsEntering(t *testing.T) {
+	type args struct {
+		pid        int
+		command    string
+		privileged bool
+	}
+	tests := []struct {
+		name string
+		args args
+		want []string
+	}{
+		{
+			name: "Ensure command will run with nsenter",
+			args: args{pid: 1, command: "ls -Fal", privileged: true},
+			want: []string{"/usr/bin/nsenter", "-m/proc/1/ns/mnt", "--", "ls", "-Fal"},
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			cc, _ := NewCommandChecker(tt.args.command, tt.args.pid, tt.args.privileged)
+			if !reflect.DeepEqual(cc.CheckCommand, tt.want) {
+				t.Errorf("command parsed as %v, want %v", cc.CheckCommand, tt.want)
+			}
+		})
+	}
+}
+
+func Test_rebootRequired(t *testing.T) {
+	type args struct {
+		sentinelCommand []string
+	}
+	tests := []struct {
+		name   string
+		args   args
+		want   bool
+		fatals bool
+	}{
+		{
+			name: "Ensure rc = 0 means reboot required",
+			args: args{
+				sentinelCommand: []string{"true"},
+			},
+			want:   true,
+			fatals: false,
+		},
+		{
+			name: "Ensure rc != 0 means reboot NOT required",
+			args: args{
+				sentinelCommand: []string{"false"},
+			},
+			want:   false,
+			fatals: false,
+		},
+		{
+			name: "Ensure a wrong command fatals",
+			args: args{
+				sentinelCommand: []string{"./babar"},
+			},
+			want:   true,
+			fatals: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			defer func() { log.StandardLogger().ExitFunc = nil }()
+			fatal := false
+			log.StandardLogger().ExitFunc = func(int) { fatal = true }
+
+			a := CommandChecker{CheckCommand: tt.args.sentinelCommand, NamespacePid: 1, Privileged: false}
+
+			if got := a.RebootRequired(); got != tt.want {
+				t.Errorf("rebootRequired() = %v, want %v", got, tt.want)
+			}
+			if tt.fatals != fatal {
+				t.Errorf("fatal flag is %v, want fatal %v", fatal, tt.fatals)
+			}
+		})
+	}
+}

pkg/daemonsetlock/daemonsetlock.go

@@ -1,11 +1,18 @@
+// Package daemonsetlock provides mechanisms for leader election and locking
+// using Kubernetes DaemonSets. It enables distributed coordination of operations
+// (such as reboots) by ensuring only one node acts as the leader at any time,
+// leveraging Kubernetes primitives for safe, atomic locking in clusters.
 package daemonsetlock
 
 import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 	"time"
 
+	log "github.com/sirupsen/logrus"
+
 	v1 "k8s.io/api/apps/v1"
 	"k8s.io/apimachinery/pkg/api/errors"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
@@ -18,6 +25,25 @@ const (
 	k8sAPICallRetryTimeout = 5 * time.Minute // How long to wait until we determine that the k8s API is definitively unavailable
 )
 
+// Lock defines the interface for acquiring, releasing, and checking
+// the status of a reboot coordination lock.
+type Lock interface {
+	Acquire(NodeMeta) (bool, string, error)
+	Release() error
+	Holding() (bool, LockAnnotationValue, error)
+}
+
+// GenericLock holds the configuration for lock TTL and the delay before releasing it.
+type GenericLock struct {
+	TTL          time.Duration
+	releaseDelay time.Duration
+}
+
+// NodeMeta contains metadata about a node relevant to scheduling decisions.
+type NodeMeta struct {
+	Unschedulable bool `json:"unschedulable"`
+}
+
 // DaemonSetLock holds all necessary information to do actions
 // on the kured ds which holds lock info through annotations.
 type DaemonSetLock struct {
@@ -28,29 +54,98 @@ type DaemonSetLock struct {
 	annotation string
 }
 
-type lockAnnotationValue struct {
+// DaemonSetSingleLock holds all necessary information to do actions
+// on the kured ds which holds lock info through annotations.
+type DaemonSetSingleLock struct {
+	GenericLock
+	DaemonSetLock
+}
+
+// DaemonSetMultiLock holds all necessary information to do actions
+// on the kured ds which holds lock info through annotations, valid
+// for multiple nodes
+type DaemonSetMultiLock struct {
+	GenericLock
+	DaemonSetLock
+	maxOwners int
+}
+
+// LockAnnotationValue contains the lock data,
+// which allows persistence across reboots, particularily recording if the
+// node was already unschedulable before kured reboot.
+// To be modified when using another type of lock storage.
+type LockAnnotationValue struct {
 	NodeID   string        `json:"nodeID"`
-	Metadata interface{}   `json:"metadata,omitempty"`
+	Metadata NodeMeta      `json:"metadata,omitempty"`
 	Created  time.Time     `json:"created"`
 	TTL      time.Duration `json:"TTL"`
 }
 
+type multiLockAnnotationValue struct {
+	MaxOwners       int                   `json:"maxOwners"`
+	LockAnnotations []LockAnnotationValue `json:"locks"`
+}
+
 // New creates a daemonsetLock object containing the necessary data for follow up k8s requests
-func New(client *kubernetes.Clientset, nodeID, namespace, name, annotation string) *DaemonSetLock {
-	return &DaemonSetLock{client, nodeID, namespace, name, annotation}
+func New(client *kubernetes.Clientset, nodeID, namespace, name, annotation string, TTL time.Duration, concurrency int, lockReleaseDelay time.Duration) Lock {
+	if concurrency > 1 {
+		return &DaemonSetMultiLock{
+			GenericLock: GenericLock{
+				TTL:          TTL,
+				releaseDelay: lockReleaseDelay,
+			},
+			DaemonSetLock: DaemonSetLock{
+				client:     client,
+				nodeID:     nodeID,
+				namespace:  namespace,
+				name:       name,
+				annotation: annotation,
+			},
+			maxOwners: concurrency,
+		}
+	}
+	return &DaemonSetSingleLock{
+		GenericLock: GenericLock{
+			TTL:          TTL,
+			releaseDelay: lockReleaseDelay,
+		},
+		DaemonSetLock: DaemonSetLock{
+			client:     client,
+			nodeID:     nodeID,
+			namespace:  namespace,
+			name:       name,
+			annotation: annotation,
+		},
+	}
+}
+
+// GetDaemonSet returns the named DaemonSet resource from the DaemonSetLock's configured client
+func (dsl *DaemonSetLock) GetDaemonSet(sleep, timeout time.Duration) (*v1.DaemonSet, error) {
+	var ds *v1.DaemonSet
+	var lastError error
+	err := wait.PollUntilContextTimeout(context.Background(), sleep, timeout, true, func(ctx context.Context) (bool, error) {
+		if ds, lastError = dsl.client.AppsV1().DaemonSets(dsl.namespace).Get(ctx, dsl.name, metav1.GetOptions{}); lastError != nil {
+			return false, nil
+		}
+		return true, nil
+	})
+	if err != nil {
+		return nil, fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %v", dsl.name, dsl.namespace, lastError)
+	}
+	return ds, nil
 }
 
 // Acquire attempts to annotate the kured daemonset with lock info from instantiated DaemonSetLock using client-go
-func (dsl *DaemonSetLock) Acquire(metadata interface{}, TTL time.Duration) (bool, string, error) {
+func (dsl *DaemonSetSingleLock) Acquire(nodeMetadata NodeMeta) (bool, string, error) {
 	for {
 		ds, err := dsl.GetDaemonSet(k8sAPICallRetrySleep, k8sAPICallRetryTimeout)
 		if err != nil {
 			return false, "", fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
 		}
 
-		valueString, exists := ds.ObjectMeta.Annotations[dsl.annotation]
+		valueString, exists := ds.Annotations[dsl.annotation]
 		if exists {
-			value := lockAnnotationValue{}
+			value := LockAnnotationValue{}
 			if err := json.Unmarshal([]byte(valueString), &value); err != nil {
 				return false, "", err
 			}
@@ -60,15 +155,22 @@ func (dsl *DaemonSetLock) Acquire(metadata interface{}, TTL time.Duration) (bool
 			}
 		}
 
-		if ds.ObjectMeta.Annotations == nil {
-			ds.ObjectMeta.Annotations = make(map[string]string)
+		if ds.Annotations == nil {
+			ds.Annotations = make(map[string]string)
 		}
-		value := lockAnnotationValue{NodeID: dsl.nodeID, Metadata: metadata, Created: time.Now().UTC(), TTL: TTL}
+
+		value := LockAnnotationValue{
+			NodeID:   dsl.nodeID,
+			Metadata: nodeMetadata,
+			Created:  time.Now().UTC(),
+			TTL:      dsl.TTL,
+		}
+
 		valueBytes, err := json.Marshal(&value)
 		if err != nil {
 			return false, "", err
 		}
-		ds.ObjectMeta.Annotations[dsl.annotation] = string(valueBytes)
+		ds.Annotations[dsl.annotation] = string(valueBytes)
 
 		_, err = dsl.client.AppsV1().DaemonSets(dsl.namespace).Update(context.TODO(), ds, metav1.UpdateOptions{})
 		if err != nil {
@@ -76,59 +178,64 @@ func (dsl *DaemonSetLock) Acquire(metadata interface{}, TTL time.Duration) (bool
 				// Something else updated the resource between us reading and writing - try again soon
 				time.Sleep(time.Second)
 				continue
-			} else {
-				return false, "", err
 			}
+			return false, "", err
 		}
+
 		return true, dsl.nodeID, nil
 	}
 }
 
-// Test attempts to check the kured daemonset lock status (existence, expiry) from instantiated DaemonSetLock using client-go
-func (dsl *DaemonSetLock) Test(metadata interface{}) (bool, error) {
+// Holding checks if the current node still holds the lock based on the DaemonSet annotation.
+func (dsl *DaemonSetSingleLock) Holding() (bool, LockAnnotationValue, error) {
+	var lockData LockAnnotationValue
 	ds, err := dsl.GetDaemonSet(k8sAPICallRetrySleep, k8sAPICallRetryTimeout)
 	if err != nil {
-		return false, fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
+		return false, lockData, fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
 	}
 
-	valueString, exists := ds.ObjectMeta.Annotations[dsl.annotation]
+	valueString, exists := ds.Annotations[dsl.annotation]
 	if exists {
-		value := lockAnnotationValue{Metadata: metadata}
+		value := LockAnnotationValue{}
 		if err := json.Unmarshal([]byte(valueString), &value); err != nil {
-			return false, err
+			return false, lockData, err
 		}
 
 		if !ttlExpired(value.Created, value.TTL) {
-			return value.NodeID == dsl.nodeID, nil
+			return value.NodeID == dsl.nodeID, value, nil
 		}
 	}
 
-	return false, nil
+	return false, lockData, nil
 }
 
 // Release attempts to remove the lock data from the kured ds annotations using client-go
-func (dsl *DaemonSetLock) Release() error {
+func (dsl *DaemonSetSingleLock) Release() error {
+	if dsl.releaseDelay > 0 {
+		log.Infof("Waiting %v before releasing lock", dsl.releaseDelay)
+		time.Sleep(dsl.releaseDelay)
+	}
 	for {
 		ds, err := dsl.GetDaemonSet(k8sAPICallRetrySleep, k8sAPICallRetryTimeout)
 		if err != nil {
 			return fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
 		}
 
-		valueString, exists := ds.ObjectMeta.Annotations[dsl.annotation]
+		valueString, exists := ds.Annotations[dsl.annotation]
 		if exists {
-			value := lockAnnotationValue{}
+			value := LockAnnotationValue{}
 			if err := json.Unmarshal([]byte(valueString), &value); err != nil {
 				return err
 			}
 
 			if value.NodeID != dsl.nodeID {
-				return fmt.Errorf("Not lock holder: %v", value.NodeID)
+				return fmt.Errorf("not lock holder: %v", value.NodeID)
 			}
 		} else {
-			return fmt.Errorf("Lock not held")
+			return fmt.Errorf("lock not held")
 		}
 
-		delete(ds.ObjectMeta.Annotations, dsl.annotation)
+		delete(ds.Annotations, dsl.annotation)
 
 		_, err = dsl.client.AppsV1().DaemonSets(dsl.namespace).Update(context.TODO(), ds, metav1.UpdateOptions{})
 		if err != nil {
@@ -136,35 +243,179 @@ func (dsl *DaemonSetLock) Release() error {
 				// Something else updated the resource between us reading and writing - try again soon
 				time.Sleep(time.Second)
 				continue
-			} else {
-				return err
 			}
+			return err
 		}
 		return nil
 	}
 }
 
-// GetDaemonSet returns the named DaemonSet resource from the DaemonSetLock's configured client
-func (dsl *DaemonSetLock) GetDaemonSet(sleep, timeout time.Duration) (*v1.DaemonSet, error) {
-	var ds *v1.DaemonSet
-	var lastError error
-	err := wait.PollImmediate(sleep, timeout, func() (bool, error) {
-		ctx, cancel := context.WithTimeout(context.Background(), timeout)
-		defer cancel()
-		if ds, lastError = dsl.client.AppsV1().DaemonSets(dsl.namespace).Get(ctx, dsl.name, metav1.GetOptions{}); lastError != nil {
-			return false, nil
-		}
-		return true, nil
-	})
-	if err != nil {
-		return nil, fmt.Errorf("Timed out trying to get daemonset %s in namespace %s: %v", dsl.name, dsl.namespace, lastError)
-	}
-	return ds, nil
-}
-
 func ttlExpired(created time.Time, ttl time.Duration) bool {
 	if ttl > 0 && time.Since(created) >= ttl {
 		return true
 	}
 	return false
 }
+
+func nodeIDsFromMultiLock(annotation multiLockAnnotationValue) []string {
+	nodeIDs := make([]string, 0, len(annotation.LockAnnotations))
+	for _, nodeLock := range annotation.LockAnnotations {
+		nodeIDs = append(nodeIDs, nodeLock.NodeID)
+	}
+	return nodeIDs
+}
+
+func (dsl *DaemonSetLock) canAcquireMultiple(annotation multiLockAnnotationValue, metadata NodeMeta, TTL time.Duration, maxOwners int) (bool, multiLockAnnotationValue) {
+	newAnnotation := multiLockAnnotationValue{MaxOwners: maxOwners}
+	freeSpace := false
+	if annotation.LockAnnotations == nil || len(annotation.LockAnnotations) < maxOwners {
+		freeSpace = true
+		newAnnotation.LockAnnotations = annotation.LockAnnotations
+	} else {
+		for _, nodeLock := range annotation.LockAnnotations {
+			if ttlExpired(nodeLock.Created, nodeLock.TTL) {
+				freeSpace = true
+				continue
+			}
+			newAnnotation.LockAnnotations = append(
+				newAnnotation.LockAnnotations,
+				nodeLock,
+			)
+		}
+	}
+
+	if freeSpace {
+		newAnnotation.LockAnnotations = append(
+			newAnnotation.LockAnnotations,
+			LockAnnotationValue{
+				NodeID:   dsl.nodeID,
+				Metadata: metadata,
+				Created:  time.Now().UTC(),
+				TTL:      TTL,
+			},
+		)
+		return true, newAnnotation
+	}
+
+	return false, multiLockAnnotationValue{}
+}
+
+// Acquire creates and annotates the daemonset with a multiple owner lock
+func (dsl *DaemonSetMultiLock) Acquire(nodeMetaData NodeMeta) (bool, string, error) {
+	for {
+		ds, err := dsl.GetDaemonSet(k8sAPICallRetrySleep, k8sAPICallRetryTimeout)
+		if err != nil {
+			return false, "", fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
+		}
+
+		annotation := multiLockAnnotationValue{}
+		valueString, exists := ds.Annotations[dsl.annotation]
+		if exists {
+			if err := json.Unmarshal([]byte(valueString), &annotation); err != nil {
+				return false, "", fmt.Errorf("error getting multi lock: %w", err)
+			}
+		}
+
+		lockPossible, newAnnotation := dsl.canAcquireMultiple(annotation, nodeMetaData, dsl.TTL, dsl.maxOwners)
+		if !lockPossible {
+			return false, strings.Join(nodeIDsFromMultiLock(newAnnotation), ","), nil
+		}
+
+		if ds.Annotations == nil {
+			ds.Annotations = make(map[string]string)
+		}
+		newAnnotationBytes, err := json.Marshal(&newAnnotation)
+		if err != nil {
+			return false, "", fmt.Errorf("error marshalling new annotation lock: %w", err)
+		}
+		ds.Annotations[dsl.annotation] = string(newAnnotationBytes)
+
+		_, err = dsl.client.AppsV1().DaemonSets(dsl.namespace).Update(context.Background(), ds, metav1.UpdateOptions{})
+		if err != nil {
+			if se, ok := err.(*errors.StatusError); ok && se.ErrStatus.Reason == metav1.StatusReasonConflict {
+				time.Sleep(time.Second)
+				continue
+			}
+			return false, "", fmt.Errorf("error updating daemonset with multi lock: %w", err)
+
+		}
+		return true, strings.Join(nodeIDsFromMultiLock(newAnnotation), ","), nil
+	}
+}
+
+// Holding checks whether the current node is holding a valid lock for the DaemonSetMultiLock.
+func (dsl *DaemonSetMultiLock) Holding() (bool, LockAnnotationValue, error) {
+	var lockdata LockAnnotationValue
+	ds, err := dsl.GetDaemonSet(k8sAPICallRetrySleep, k8sAPICallRetryTimeout)
+	if err != nil {
+		return false, lockdata, fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
+	}
+
+	valueString, exists := ds.Annotations[dsl.annotation]
+	if exists {
+		value := multiLockAnnotationValue{}
+		if err := json.Unmarshal([]byte(valueString), &value); err != nil {
+			return false, lockdata, err
+		}
+
+		for _, nodeLock := range value.LockAnnotations {
+			if nodeLock.NodeID == dsl.nodeID && !ttlExpired(nodeLock.Created, nodeLock.TTL) {
+				return true, nodeLock, nil
+			}
+		}
+	}
+
+	return false, lockdata, nil
+}
+
+// Release attempts to remove the lock data for a single node from the multi node annotation
+func (dsl *DaemonSetMultiLock) Release() error {
+	if dsl.releaseDelay > 0 {
+		log.Infof("Waiting %v before releasing lock", dsl.releaseDelay)
+		time.Sleep(dsl.releaseDelay)
+	}
+	for {
+		ds, err := dsl.GetDaemonSet(k8sAPICallRetrySleep, k8sAPICallRetryTimeout)
+		if err != nil {
+			return fmt.Errorf("timed out trying to get daemonset %s in namespace %s: %w", dsl.name, dsl.namespace, err)
+		}
+
+		valueString, exists := ds.Annotations[dsl.annotation]
+		modified := false
+		value := multiLockAnnotationValue{}
+		if exists {
+			if err := json.Unmarshal([]byte(valueString), &value); err != nil {
+				return err
+			}
+
+			for idx, nodeLock := range value.LockAnnotations {
+				if nodeLock.NodeID == dsl.nodeID {
+					value.LockAnnotations = append(value.LockAnnotations[:idx], value.LockAnnotations[idx+1:]...)
+					modified = true
+					break
+				}
+			}
+		}
+
+		if !exists || !modified {
+			return fmt.Errorf("Lock not held")
+		}
+
+		newAnnotationBytes, err := json.Marshal(value)
+		if err != nil {
+			return fmt.Errorf("error marshalling new annotation on release: %v", err)
+		}
+		ds.Annotations[dsl.annotation] = string(newAnnotationBytes)
+
+		_, err = dsl.client.AppsV1().DaemonSets(dsl.namespace).Update(context.TODO(), ds, metav1.UpdateOptions{})
+		if err != nil {
+			if se, ok := err.(*errors.StatusError); ok && se.ErrStatus.Reason == metav1.StatusReasonConflict {
+				// Something else updated the resource between us reading and writing - try again soon
+				time.Sleep(time.Second)
+				continue
+			}
+			return err
+		}
+		return nil
+	}
+}

pkg/daemonsetlock/daemonsetlock_test.go

@@ -1,6 +1,8 @@
 package daemonsetlock
 
 import (
+	"reflect"
+	"sort"
 	"testing"
 	"time"
 )
@@ -26,3 +28,181 @@ func TestTtlExpired(t *testing.T) {
 		}
 	}
 }
+
+func multiLockAnnotationsAreEqualByNodes(src, dst multiLockAnnotationValue) bool {
+	srcNodes := []string{}
+	for _, srcLock := range src.LockAnnotations {
+		srcNodes = append(srcNodes, srcLock.NodeID)
+	}
+	sort.Strings(srcNodes)
+
+	dstNodes := []string{}
+	for _, dstLock := range dst.LockAnnotations {
+		dstNodes = append(dstNodes, dstLock.NodeID)
+	}
+	sort.Strings(dstNodes)
+
+	return reflect.DeepEqual(srcNodes, dstNodes)
+}
+
+func TestCanAcquireMultiple(t *testing.T) {
+	node1Name := "n1"
+	node2Name := "n2"
+	node3Name := "n3"
+	testCases := []struct {
+		name          string
+		daemonSetLock DaemonSetLock
+		maxOwners     int
+		current       multiLockAnnotationValue
+		desired       multiLockAnnotationValue
+		lockPossible  bool
+	}{
+		{
+			name: "empty_lock",
+			daemonSetLock: DaemonSetLock{
+				nodeID: node1Name,
+			},
+			maxOwners: 2,
+			current:   multiLockAnnotationValue{},
+			desired: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{NodeID: node1Name},
+				},
+			},
+			lockPossible: true,
+		},
+		{
+			name: "partial_lock",
+			daemonSetLock: DaemonSetLock{
+				nodeID: node1Name,
+			},
+			maxOwners: 2,
+			current: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{NodeID: node2Name},
+				},
+			},
+			desired: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{NodeID: node1Name},
+					{NodeID: node2Name},
+				},
+			},
+			lockPossible: true,
+		},
+		{
+			name: "full_lock",
+			daemonSetLock: DaemonSetLock{
+				nodeID: node1Name,
+			},
+			maxOwners: 2,
+			current: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{
+						NodeID:  node2Name,
+						Created: time.Now().UTC().Add(-1 * time.Minute),
+						TTL:     time.Hour,
+					},
+					{
+						NodeID:  node3Name,
+						Created: time.Now().UTC().Add(-1 * time.Minute),
+						TTL:     time.Hour,
+					},
+				},
+			},
+			desired: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{NodeID: node2Name},
+					{NodeID: node3Name},
+				},
+			},
+			lockPossible: false,
+		},
+		{
+			name: "full_with_one_expired_lock",
+			daemonSetLock: DaemonSetLock{
+				nodeID: node1Name,
+			},
+			maxOwners: 2,
+			current: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{
+						NodeID:  node2Name,
+						Created: time.Now().UTC().Add(-1 * time.Hour),
+						TTL:     time.Minute,
+					},
+					{
+						NodeID:  node3Name,
+						Created: time.Now().UTC().Add(-1 * time.Minute),
+						TTL:     time.Hour,
+					},
+				},
+			},
+			desired: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{NodeID: node1Name},
+					{NodeID: node3Name},
+				},
+			},
+			lockPossible: true,
+		},
+		{
+			name: "full_with_all_expired_locks",
+			daemonSetLock: DaemonSetLock{
+				nodeID: node1Name,
+			},
+			maxOwners: 2,
+			current: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{
+						NodeID:  node2Name,
+						Created: time.Now().UTC().Add(-1 * time.Hour),
+						TTL:     time.Minute,
+					},
+					{
+						NodeID:  node3Name,
+						Created: time.Now().UTC().Add(-1 * time.Hour),
+						TTL:     time.Minute,
+					},
+				},
+			},
+			desired: multiLockAnnotationValue{
+				MaxOwners: 2,
+				LockAnnotations: []LockAnnotationValue{
+					{NodeID: node1Name},
+				},
+			},
+			lockPossible: true,
+		},
+	}
+	nm := NodeMeta{Unschedulable: false}
+	for _, testCase := range testCases {
+		t.Run(testCase.name, func(t *testing.T) {
+			lockPossible, actual := testCase.daemonSetLock.canAcquireMultiple(testCase.current, nm, time.Minute, testCase.maxOwners)
+			if lockPossible != testCase.lockPossible {
+				t.Fatalf(
+					"unexpected result for lock possible (got %t expected %t new annotation %v",
+					lockPossible,
+					testCase.lockPossible,
+					actual,
+				)
+			}
+
+			if lockPossible && (!multiLockAnnotationsAreEqualByNodes(actual, testCase.desired) || testCase.desired.MaxOwners != actual.MaxOwners) {
+				t.Fatalf(
+					"expected lock %v but got %v",
+					testCase.desired,
+					actual,
+				)
+			}
+		})
+	}
+}

pkg/delaytick/delaytick.go

@@ -1,3 +1,9 @@
+// Package delaytick provides utilities for scheduling periodic events
+// with an initial randomized delay. It is primarily used to delay the
+// start of regular ticks, helping to avoid thundering herd problems
+// when multiple nodes begin operations simultaneously.
+// You can use that a random ticker in other projects, but there is
+// no garantee that it will stay (initial plan was to move it to internal)
 package delaytick
 
 import (
@@ -10,6 +16,7 @@ func New(s rand.Source, d time.Duration) <-chan time.Time {
 	c := make(chan time.Time)
 
 	go func() {
+		// #nosec G404 -- math/rand is used here for non-security timing jitter
 		random := rand.New(s)
 		time.Sleep(time.Duration(float64(d)/2 + float64(d)*random.Float64()))
 		c <- time.Now()

pkg/reboot/command.go

@@ -0,0 +1,49 @@
+package reboot
+
+import (
+	"bytes"
+	"fmt"
+	"os/exec"
+	"strings"
+
+	"github.com/google/shlex"
+	log "github.com/sirupsen/logrus"
+)
+
+// CommandRebooter holds context-information for a reboot with command
+type CommandRebooter struct {
+	RebootCommand []string
+}
+
+// Reboot triggers the reboot command
+func (c CommandRebooter) Reboot() error {
+	log.Infof("Invoking command: %s", c.RebootCommand)
+
+	bufStdout := new(bytes.Buffer)
+	bufStderr := new(bytes.Buffer)
+	cmd := exec.Command(c.RebootCommand[0], c.RebootCommand[1:]...) // #nosec G204
+	cmd.Stdout = bufStdout
+	cmd.Stderr = bufStderr
+
+	if err := cmd.Run(); err != nil {
+		return fmt.Errorf("error invoking reboot command %s: %v (stdout: %v, stderr: %v)", c.RebootCommand, err, bufStdout.String(), bufStderr.String())
+	}
+	log.Info("Invoked reboot command", "cmd", strings.Join(cmd.Args, " "), "stdout", bufStdout.String(), "stderr", bufStderr.String())
+	return nil
+}
+
+// NewCommandRebooter is the constructor to create a CommandRebooter from a string not
+// yet shell lexed. You can skip this constructor if you parse the data correctly first
+// when instantiating a CommandRebooter instance.
+func NewCommandRebooter(rebootCommand string) (*CommandRebooter, error) {
+	if rebootCommand == "" {
+		return nil, fmt.Errorf("no reboot command specified")
+	}
+	cmd := []string{"/usr/bin/nsenter", fmt.Sprintf("-m/proc/%d/ns/mnt", 1), "--"}
+	parsedCommand, err := shlex.Split(rebootCommand)
+	if err != nil {
+		return nil, fmt.Errorf("error %v when parsing reboot command %s", err, rebootCommand)
+	}
+	cmd = append(cmd, parsedCommand...)
+	return &CommandRebooter{RebootCommand: cmd}, nil
+}

pkg/reboot/command_test.go

@@ -0,0 +1,43 @@
+package reboot
+
+import (
+	"reflect"
+	"testing"
+)
+
+func TestNewCommandRebooter(t *testing.T) {
+	type args struct {
+		rebootCommand string
+	}
+	tests := []struct {
+		name    string
+		args    args
+		want    *CommandRebooter
+		wantErr bool
+	}{
+		{
+			name:    "Ensure command is nsenter wrapped",
+			args:    args{"ls -Fal"},
+			want:    &CommandRebooter{RebootCommand: []string{"/usr/bin/nsenter", "-m/proc/1/ns/mnt", "--", "ls", "-Fal"}},
+			wantErr: false,
+		},
+		{
+			name:    "Ensure empty command is erroring",
+			args:    args{""},
+			want:    nil,
+			wantErr: true,
+		},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := NewCommandRebooter(tt.args.rebootCommand)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("NewCommandRebooter() error = %v, wantErr %v", err, tt.wantErr)
+				return
+			}
+			if !reflect.DeepEqual(got, tt.want) {
+				t.Errorf("NewCommandRebooter() got = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

pkg/reboot/reboot.go

@@ -0,0 +1,13 @@
+// Package reboot provides mechanisms to trigger node reboots using different
+// methods, like custom commands or signals.
+// Each of those includes constructors and interfaces for handling different reboot
+// strategies, supporting privileged command execution via nsenter for containerized environments.
+package reboot
+
+// Rebooter is the standard interface to use to execute
+// the reboot, after it has been considered as necessary.
+// The Reboot method does not expect any return, yet should
+// most likely be refactored in the future to return an error
+type Rebooter interface {
+	Reboot() error
+}

pkg/reboot/signal.go

@@ -0,0 +1,37 @@
+package reboot
+
+import (
+	"fmt"
+	"os"
+	"syscall"
+)
+
+// SignalRebooter holds context-information for a signal reboot.
+type SignalRebooter struct {
+	Signal int
+}
+
+// Reboot triggers the reboot signal
+func (c SignalRebooter) Reboot() error {
+	process, err := os.FindProcess(1)
+	if err != nil {
+		return fmt.Errorf("not running on Unix: %v", err)
+	}
+
+	err = process.Signal(syscall.Signal(c.Signal))
+	// Either PID does not exist, or the signal does not work. Hoping for
+	// a decent enough error.
+	if err != nil {
+		return fmt.Errorf("signal of SIGRTMIN+5 failed: %v", err)
+	}
+	return nil
+}
+
+// NewSignalRebooter is the constructor which sets the signal number.
+// The constructor does not yet validate any input. It should be done in a later commit.
+func NewSignalRebooter(sig int) (*SignalRebooter, error) {
+	if sig < 1 {
+		return nil, fmt.Errorf("invalid signal: %v", sig)
+	}
+	return &SignalRebooter{Signal: sig}, nil
+}

pkg/taints/taints.go

@@ -1,3 +1,6 @@
+// Package taints provides utilities to manage Kubernetes node taints for controlling
+// pod scheduling and execution. It allows setting, removing, and checking taints on nodes,
+// using Kubernetes client-go and JSON patching for atomic updates.
 package taints
 
 import (

pkg/timewindow/days.go

@@ -50,7 +50,7 @@ func parseWeekdays(days []string) (weekdays, error) {
 		if err != nil {
 			return weekdays(0), err
 		}
-
+		// #nosec G115 -- weekday is guaranteed to be between 0–6 by parseWeekday()
 		result |= 1 << uint32(weekday)
 	}
 
@@ -59,6 +59,7 @@ func parseWeekdays(days []string) (weekdays, error) {
 
 // Contains returns true if the specified weekday is a member of this set.
 func (w weekdays) Contains(day time.Weekday) bool {
+	// #nosec G115 -- day is time.Weekday [0-6], shift safe within uint32
 	return uint32(w)&(1<<uint32(day)) != 0
 }
 
@@ -81,11 +82,11 @@ func parseWeekday(day string) (time.Weekday, error) {
 		if n >= 0 && n < 7 {
 			return time.Weekday(n), nil
 		}
-		return time.Sunday, fmt.Errorf("Invalid weekday, number out of range: %s", day)
+		return time.Sunday, fmt.Errorf("invalid weekday, number out of range: %s", day)
 	}
 
 	if weekday, ok := dayStrings[strings.ToLower(day)]; ok {
 		return weekday, nil
 	}
-	return time.Sunday, fmt.Errorf("Invalid weekday: %s", day)
+	return time.Sunday, fmt.Errorf("invalid weekday: %s", day)
 }

pkg/timewindow/timewindow.go

@@ -1,3 +1,7 @@
+// Package timewindow provides utilities for handling days of the week,
+// including parsing, representing, and manipulating sets of weekdays.
+// It enables flexible specification of time windows for reboot operations
+// in kured, supporting various formats and convenience functions.
 package timewindow
 
 import (
@@ -77,5 +81,5 @@ func parseTime(s string, loc *time.Location) (time.Time, error) {
 		}
 	}
 
-	return time.Now(), fmt.Errorf("Invalid time format: %s", s)
+	return time.Now(), fmt.Errorf("invalid time format: %s", s)
 }

tests/kind/create-reboot-sentinels.sh

@@ -1,12 +0,0 @@
-#!/usr/bin/env bash
-
-# USE KUBECTL_CMD to pass context and/or namespaces.
-KUBECTL_CMD="${KUBECTL_CMD:-kubectl}"
-SENTINEL_FILE="${SENTINEL_FILE:-/var/run/reboot-required}"
-
-echo "Creating reboot sentinel on all nodes"
-
-for nodename in $("$KUBECTL_CMD" get nodes -o name); do
-    docker exec "${nodename/node\//}" hostname
-    docker exec "${nodename/node\//}" touch "${SENTINEL_FILE}"
-done

tests/kind/main_test.go

@@ -0,0 +1,429 @@
+package kind
+
+import (
+	"bytes"
+	"fmt"
+	"math/rand"
+	"os/exec"
+	"strconv"
+	"testing"
+	"time"
+)
+
+const (
+	kuredDevImage string = "kured:dev"
+)
+
+// KindTest cluster deployed by each TestMain function, prepared to run a given test scenario.
+type KindTest struct {
+	kindConfigPath  string
+	clusterName     string
+	timeout         time.Duration
+	deployManifests []string
+	localImages     []string
+	logsDir         string
+	logBuffer       bytes.Buffer
+	testInstance    *testing.T // Maybe move this to testing.TB
+}
+
+func (k *KindTest) Write(p []byte) (n int, err error) {
+	k.testInstance.Helper()
+	k.logBuffer.Write(p)
+	return len(p), nil
+}
+
+func (k *KindTest) FlushLog() {
+	k.testInstance.Helper()
+	k.testInstance.Log(k.logBuffer.String())
+	k.logBuffer.Reset()
+}
+
+func (k *KindTest) RunCmd(cmdDetails ...string) error {
+	cmd := exec.Command(cmdDetails[0], cmdDetails[1:]...)
+	// by making KindTest a Writer, we can simply wire k to logs
+	// writing to k will write to proper logs.
+	cmd.Stdout = k
+	cmd.Stderr = k
+
+	err := cmd.Run()
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+// Option that can be passed to the NewKind function in order to change the configuration
+// of the test cluster
+type Option func(k *KindTest)
+
+// Deploy can be passed to NewKind to deploy extra components, in addition to the base deployment.
+func Deploy(manifest string) Option {
+	return func(k *KindTest) {
+		k.deployManifests = append(k.deployManifests, manifest)
+	}
+}
+
+// ExportLogs can be passed to NewKind to specify the folder where the kubernetes logs will be exported after the tests.
+func ExportLogs(folder string) Option {
+	return func(k *KindTest) {
+		k.logsDir = folder
+	}
+}
+
+// Timeout for long-running operations (e.g. deployments, readiness probes...)
+func Timeout(t time.Duration) Option {
+	return func(k *KindTest) {
+		k.timeout = t
+	}
+}
+
+// LocalImage is passed to NewKind to allow loading a local Docker image into the cluster
+func LocalImage(nameTag string) Option {
+	return func(k *KindTest) {
+		k.localImages = append(k.localImages, nameTag)
+	}
+}
+
+// NewKind creates a kind cluster given a name and set of Option instances.
+func NewKindTester(kindClusterName string, filePath string, t *testing.T, options ...Option) *KindTest {
+
+	k := &KindTest{
+		clusterName:    kindClusterName,
+		timeout:        10 * time.Minute,
+		kindConfigPath: filePath,
+		testInstance:   t,
+	}
+	for _, option := range options {
+		option(k)
+	}
+	return k
+}
+
+// Prepare the kind cluster.
+func (k *KindTest) Create() error {
+	err := k.RunCmd("kind", "create", "cluster", "--name", k.clusterName, "--config", k.kindConfigPath)
+
+	if err != nil {
+		return fmt.Errorf("failed to create cluster: %v", err)
+	}
+
+	for _, img := range k.localImages {
+		if err := k.RunCmd("kind", "load", "docker-image", "--name", k.clusterName, img); err != nil {
+			return fmt.Errorf("failed to load image: %v", err)
+		}
+	}
+	for _, mf := range k.deployManifests {
+		kubectlContext := fmt.Sprintf("kind-%v", k.clusterName)
+		if err := k.RunCmd("kubectl", "--context", kubectlContext, "apply", "-f", mf); err != nil {
+			return fmt.Errorf("failed to deploy manifest: %v", err)
+		}
+	}
+	return nil
+}
+
+func (k *KindTest) Destroy() error {
+	if k.logsDir != "" {
+		if err := k.RunCmd("kind", "export", "logs", k.logsDir, "--name", k.clusterName); err != nil {
+			return fmt.Errorf("failed to export logs: %v. will not teardown", err)
+		}
+	}
+
+	if err := k.RunCmd("kind", "delete", "cluster", "--name", k.clusterName); err != nil {
+		return fmt.Errorf("failed to destroy cluster: %v", err)
+	}
+	return nil
+}
+
+func TestE2EWithCommand(t *testing.T) {
+	t.Parallel()
+	if testing.Short() {
+		t.Skip("skipping test in short mode.")
+	}
+
+	var kindClusterConfigs = []string{
+		"previous",
+		"current",
+		"next",
+	}
+	// Iterate over each Kubernetes version
+	for _, version := range kindClusterConfigs {
+		version := version
+		// Define a subtest for each combination
+		t.Run(version, func(t *testing.T) {
+			t.Parallel() // Allow tests to run in parallel
+
+			randomInt := strconv.Itoa(rand.Intn(100))
+			kindClusterName := fmt.Sprintf("kured-e2e-command-%v-%v", version, randomInt)
+			kindClusterConfigFile := fmt.Sprintf("../../.github/kind-cluster-%v.yaml", version)
+			kindContext := fmt.Sprintf("kind-%v", kindClusterName)
+
+			k := NewKindTester(kindClusterName, kindClusterConfigFile, t, LocalImage(kuredDevImage), Deploy("../../kured-rbac.yaml"), Deploy("testfiles/kured-ds.yaml"))
+			defer k.FlushLog()
+
+			err := k.Create()
+			if err != nil {
+				t.Fatalf("Error creating cluster %v", err)
+			}
+			defer func(k *KindTest) {
+				err := k.Destroy()
+				if err != nil {
+					t.Fatalf("Error destroying cluster %v", err)
+				}
+			}(k)
+
+			k.Write([]byte("Now running e2e tests"))
+
+			if err := k.RunCmd("bash", "testfiles/create-reboot-sentinels.sh", kindContext); err != nil {
+				t.Fatalf("failed to create sentinels: %v", err)
+			}
+
+			if err := k.RunCmd("bash", "testfiles/follow-coordinated-reboot.sh", kindContext); err != nil {
+				t.Fatalf("failed to follow reboot: %v", err)
+			}
+		})
+	}
+}
+
+func TestE2EWithSignal(t *testing.T) {
+	t.Parallel()
+	if testing.Short() {
+		t.Skip("skipping test in short mode.")
+	}
+
+	var kindClusterConfigs = []string{
+		"previous",
+		"current",
+		"next",
+	}
+	// Iterate over each Kubernetes version
+	for _, version := range kindClusterConfigs {
+		version := version
+		// Define a subtest for each combination
+		t.Run(version, func(t *testing.T) {
+			t.Parallel() // Allow tests to run in parallel
+
+			randomInt := strconv.Itoa(rand.Intn(100))
+			kindClusterName := fmt.Sprintf("kured-e2e-signal-%v-%v", version, randomInt)
+			kindClusterConfigFile := fmt.Sprintf("../../.github/kind-cluster-%v.yaml", version)
+			kindContext := fmt.Sprintf("kind-%v", kindClusterName)
+
+			k := NewKindTester(kindClusterName, kindClusterConfigFile, t, LocalImage(kuredDevImage), Deploy("../../kured-rbac.yaml"), Deploy("testfiles/kured-ds-signal.yaml"))
+			defer k.FlushLog()
+
+			err := k.Create()
+			if err != nil {
+				t.Fatalf("Error creating cluster %v", err)
+			}
+			defer func(k *KindTest) {
+				err := k.Destroy()
+				if err != nil {
+					t.Fatalf("Error destroying cluster %v", err)
+				}
+			}(k)
+
+			k.Write([]byte("Now running e2e tests"))
+
+			if err := k.RunCmd("bash", "testfiles/create-reboot-sentinels.sh", kindContext); err != nil {
+				t.Fatalf("failed to create sentinels: %v", err)
+			}
+
+			if err := k.RunCmd("bash", "testfiles/follow-coordinated-reboot.sh", kindContext); err != nil {
+				t.Fatalf("failed to follow reboot: %v", err)
+			}
+		})
+	}
+}
+
+func TestE2EConcurrentWithCommand(t *testing.T) {
+	t.Parallel()
+	if testing.Short() {
+		t.Skip("skipping test in short mode.")
+	}
+
+	var kindClusterConfigs = []string{
+		"previous",
+		"current",
+		"next",
+	}
+	// Iterate over each Kubernetes version
+	for _, version := range kindClusterConfigs {
+		version := version
+		// Define a subtest for each combination
+		t.Run(version, func(t *testing.T) {
+			t.Parallel() // Allow tests to run in parallel
+
+			randomInt := strconv.Itoa(rand.Intn(100))
+			kindClusterName := fmt.Sprintf("kured-e2e-concurrentcommand-%v-%v", version, randomInt)
+			kindClusterConfigFile := fmt.Sprintf("../../.github/kind-cluster-%v.yaml", version)
+			kindContext := fmt.Sprintf("kind-%v", kindClusterName)
+
+			k := NewKindTester(kindClusterName, kindClusterConfigFile, t, LocalImage(kuredDevImage), Deploy("../../kured-rbac.yaml"), Deploy("testfiles/kured-ds-concurrent-command.yaml"))
+			defer k.FlushLog()
+
+			err := k.Create()
+			if err != nil {
+				t.Fatalf("Error creating cluster %v", err)
+			}
+			defer func(k *KindTest) {
+				err := k.Destroy()
+				if err != nil {
+					t.Fatalf("Error destroying cluster %v", err)
+				}
+			}(k)
+
+			k.Write([]byte("Now running e2e tests"))
+
+			if err := k.RunCmd("bash", "testfiles/create-reboot-sentinels.sh", kindContext); err != nil {
+				t.Fatalf("failed to create sentinels: %v", err)
+			}
+
+			if err := k.RunCmd("bash", "testfiles/follow-coordinated-reboot.sh", kindContext); err != nil {
+				t.Fatalf("failed to follow reboot: %v", err)
+			}
+		})
+	}
+}
+
+func TestE2EConcurrentWithSignal(t *testing.T) {
+	t.Parallel()
+	if testing.Short() {
+		t.Skip("skipping test in short mode.")
+	}
+
+	var kindClusterConfigs = []string{
+		"previous",
+		"current",
+		"next",
+	}
+	// Iterate over each Kubernetes version
+	for _, version := range kindClusterConfigs {
+		version := version
+		// Define a subtest for each combination
+		t.Run(version, func(t *testing.T) {
+			t.Parallel() // Allow tests to run in parallel
+
+			randomInt := strconv.Itoa(rand.Intn(100))
+			kindClusterName := fmt.Sprintf("kured-e2e-concurrentsignal-%v-%v", version, randomInt)
+			kindClusterConfigFile := fmt.Sprintf("../../.github/kind-cluster-%v.yaml", version)
+			kindContext := fmt.Sprintf("kind-%v", kindClusterName)
+
+			k := NewKindTester(kindClusterName, kindClusterConfigFile, t, LocalImage(kuredDevImage), Deploy("../../kured-rbac.yaml"), Deploy("testfiles/kured-ds-concurrent-signal.yaml"))
+			defer k.FlushLog()
+
+			err := k.Create()
+			if err != nil {
+				t.Fatalf("Error creating cluster %v", err)
+			}
+			defer func(k *KindTest) {
+				err := k.Destroy()
+				if err != nil {
+					t.Fatalf("Error destroying cluster %v", err)
+				}
+			}(k)
+
+			k.Write([]byte("Now running e2e tests"))
+
+			if err := k.RunCmd("bash", "testfiles/create-reboot-sentinels.sh", kindContext); err != nil {
+				t.Fatalf("failed to create sentinels: %v", err)
+			}
+
+			if err := k.RunCmd("bash", "testfiles/follow-coordinated-reboot.sh", kindContext); err != nil {
+				t.Fatalf("failed to follow reboot: %v", err)
+			}
+		})
+	}
+}
+
+func TestCordonningIsKept(t *testing.T) {
+	t.Parallel()
+	if testing.Short() {
+		t.Skip("skipping test in short mode.")
+	}
+
+	var kindClusterConfigs = []string{
+		"concurrency1",
+		"concurrency2",
+	}
+	// Iterate over each test variant
+	for _, variant := range kindClusterConfigs {
+		variant := variant
+		// Define a subtest for each combination
+		t.Run(variant, func(t *testing.T) {
+			t.Parallel() // Allow tests to run in parallel
+
+			randomInt := strconv.Itoa(rand.Intn(100))
+			kindClusterName := fmt.Sprintf("kured-e2e-cordon-%v-%v", variant, randomInt)
+			kindClusterConfigFile := "../../.github/kind-cluster-next.yaml"
+			kindContext := fmt.Sprintf("kind-%v", kindClusterName)
+
+			var manifest string
+			if variant == "concurrency1" {
+				manifest = "testfiles/kured-ds-signal.yaml"
+			} else {
+				manifest = "testfiles/kured-ds-concurrent-signal.yaml"
+			}
+			k := NewKindTester(kindClusterName, kindClusterConfigFile, t, LocalImage(kuredDevImage), Deploy("../../kured-rbac.yaml"), Deploy(manifest))
+			defer k.FlushLog()
+
+			err := k.Create()
+			if err != nil {
+				t.Fatalf("Error creating cluster %v", err)
+			}
+			defer func(k *KindTest) {
+				err := k.Destroy()
+				if err != nil {
+					t.Fatalf("Error destroying cluster %v", err)
+				}
+			}(k)
+
+			k.Write([]byte("Now running e2e tests"))
+
+			if err := k.RunCmd("bash", "testfiles/node-stays-as-cordonned.sh", kindContext); err != nil {
+				t.Fatalf("node did not reboot in time: %v", err)
+			}
+		})
+	}
+}
+func TestE2EBlocker(t *testing.T) {
+	t.Parallel()
+	if testing.Short() {
+		t.Skip("skipping test in short mode.")
+	}
+
+	var kindClusterConfigs = []string{
+		"podblocker",
+	}
+	// Iterate over each variant of the test
+	for _, variant := range kindClusterConfigs {
+		variant := variant
+		// Define a subtest for each combination
+		t.Run(variant, func(t *testing.T) {
+			t.Parallel() // Allow tests to run in parallel
+
+			randomInt := strconv.Itoa(rand.Intn(100))
+			kindClusterName := fmt.Sprintf("kured-e2e-cordon-%v-%v", variant, randomInt)
+			kindClusterConfigFile := "../../.github/kind-cluster-next.yaml"
+			kindContext := fmt.Sprintf("kind-%v", kindClusterName)
+
+			k := NewKindTester(kindClusterName, kindClusterConfigFile, t, LocalImage(kuredDevImage), Deploy("../../kured-rbac.yaml"), Deploy(fmt.Sprintf("testfiles/kured-ds-%v.yaml", variant)))
+			defer k.FlushLog()
+
+			err := k.Create()
+			if err != nil {
+				t.Fatalf("Error creating cluster %v", err)
+			}
+			defer func(k *KindTest) {
+				err := k.Destroy()
+				if err != nil {
+					t.Fatalf("Error destroying cluster %v", err)
+				}
+			}(k)
+
+			k.Write([]byte("Now running e2e tests"))
+
+			if err := k.RunCmd("bash", fmt.Sprintf("testfiles/%v.sh", variant), kindContext); err != nil {
+				t.Fatalf("node blocker test did not succeed: %v", err)
+			}
+		})
+	}
+}

tests/kind/testfiles/create-reboot-sentinels.sh

@@ -0,0 +1,11 @@
+#!/usr/bin/env bash
+
+kubectl_flags=( )
+[[ "$1" != "" ]] && kubectl_flags=("${kubectl_flags[@]}" --context "$1")
+
+# To speed up the system, let's not kill the control plane.
+for nodename in $(${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" get nodes -o name | grep -v control-plane); do
+    echo "Creating reboot sentinel on $nodename"
+    docker exec "${nodename/node\//}" hostname
+    docker exec "${nodename/node\//}" touch "${SENTINEL_FILE:-/var/run/reboot-required}"
+done

tests/kind/testfiles/follow-coordinated-reboot.sh

@@ -1,11 +1,14 @@
 #!/usr/bin/env bash
 
-NODECOUNT=${NODECOUNT:-5}
-KUBECTL_CMD="${KUBECTL_CMD:-kubectl}"
+REBOOTCOUNT=${REBOOTCOUNT:-2} # By default we only create two sentinels in create-reboot-sentinels.
 DEBUG="${DEBUG:-false}"
 CONTAINER_NAME_FORMAT=${CONTAINER_NAME_FORMAT:-"chart-testing-*"}
 
+kubectl_flags=( )
+[[ "$1" != "" ]] && kubectl_flags=("${kubectl_flags[@]}" --context "$1")
+
 tmp_dir=$(mktemp -d -t kured-XXXX)
+
 function gather_logs_and_cleanup {
     if [[ -f "$tmp_dir"/node_output ]]; then
         rm "$tmp_dir"/node_output
@@ -18,15 +21,15 @@ function gather_logs_and_cleanup {
         # This is useful to see if containers have crashed.
         echo "docker ps -a:"
         docker ps -a
-	echo "docker journal logs"
-	journalctl -u docker --no-pager
+	      echo "docker journal logs"
+	      journalctl -u docker --no-pager
 
         # This is useful to see if the nodes have _properly_ rebooted.
         # It should show the reboot/two container starts per node.
-        for name in $(docker ps -a -f "name=${CONTAINER_NAME_FORMAT}" -q); do
+        for id in $(docker ps -a -q); do
             echo "############################################################"
-            echo "docker logs for container $name:"
-            docker logs "$name"
+            echo "docker logs for container $id:"
+            docker logs "$id"
         done
 
     fi
@@ -35,24 +38,28 @@ trap gather_logs_and_cleanup EXIT
 
 declare -A was_unschedulable
 declare -A has_recovered
-max_attempts="60"
-sleep_time=60
+max_attempts="200"
+sleep_time=5
 attempt_num=1
 
+# Get docker info of each of those kind containers. If one has crashed, restart it.
+
 set +o errexit
-echo "There are $NODECOUNT nodes in the cluster"
-until [ ${#was_unschedulable[@]} == "$NODECOUNT" ] && [ ${#has_recovered[@]} == "$NODECOUNT" ]
+echo "There are $REBOOTCOUNT nodes total needing reboot in the cluster"
+until [ ${#was_unschedulable[@]} == "$REBOOTCOUNT" ] && [ ${#has_recovered[@]} == "$REBOOTCOUNT" ]
 do
     echo "${#was_unschedulable[@]} nodes were removed from pool once:" "${!was_unschedulable[@]}"
     echo "${#has_recovered[@]} nodes removed from the pool are now back:" "${!has_recovered[@]}"
 
-    "$KUBECTL_CMD" get nodes -o custom-columns=NAME:.metadata.name,SCHEDULABLE:.spec.unschedulable --no-headers > "$tmp_dir"/node_output
+
+    ${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" get nodes -o custom-columns=NAME:.metadata.name,SCHEDULABLE:.spec.unschedulable --no-headers | grep -v control-plane > "$tmp_dir"/node_output
     if [[ "$DEBUG" == "true" ]]; then
         # This is useful to see if a node gets stuck after drain, and doesn't
         # come back up.
-        echo "Result of command $KUBECTL_CMD get nodes ... showing unschedulable nodes:"
+        echo "Result of command kubectl unschedulable nodes:"
         cat "$tmp_dir"/node_output
     fi
+
     while read -r node; do
         unschedulable=$(echo "$node" | grep true | cut -f 1 -d ' ')
         if [ -n "$unschedulable" ] && [ -z ${was_unschedulable["$unschedulable"]+x} ] ; then
@@ -64,9 +71,15 @@ do
             echo "$schedulable has recovered!"
             has_recovered["$schedulable"]=1
         fi
+
+        # If the container has crashed, restart it.
+        node_name=$(echo "$node" | cut -f 1 -d ' ')
+        stopped_container_id=$(docker container ls --filter=name="$node_name" --filter=status=exited -q)
+        if [ -n "$stopped_container_id" ]; then echo "Node $stopped_container_id needs restart"; docker start "$stopped_container_id"; echo "Container started."; fi
+
     done < "$tmp_dir"/node_output
 
-    if [[ "${#has_recovered[@]}" == "$NODECOUNT" ]]; then
+    if [[ "${#has_recovered[@]}" == "$REBOOTCOUNT" ]]; then
         echo "All nodes recovered."
         break
     else

tests/kind/testfiles/node-stays-as-cordonned.sh

@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+
+kubectl_flags=( )
+[[ "$1" != "" ]] && kubectl_flags=("${kubectl_flags[@]}" --context "$1")
+
+cordon() {
+  kubectl "${kubectl_flags[@]}" cordon "${precordonned_node}"
+}
+
+create_sentinel() {
+  docker exec "${precordonned_node}" touch "${SENTINEL_FILE:-/var/run/reboot-required}"
+  docker exec "${notcordonned_node}" touch "${SENTINEL_FILE:-/var/run/reboot-required}"
+}
+
+check_reboot_required() {
+  while true;
+  do
+    docker exec "${precordonned_node}" stat /var/run/reboot-required > /dev/null && echo "Reboot still required" || return 0
+    sleep 3
+  done
+}
+
+check_node_back_online_as_cordonned() {
+  sleep 5 # For safety, wait for 5 seconds, so that the kubectl command succeeds.
+  # This test might be giving us false positive until we work on reliability of the
+  # test.
+  while true;
+  do
+    result=$(kubectl "${kubectl_flags[@]}" get node "${precordonned_node}" --no-headers | awk '{print $2;}')
+    test "${result}" != "Ready,SchedulingDisabled" && echo "Node ${precordonned_node} in state ${result}" || return 0
+    sleep 3
+  done
+}
+
+check_node_back_online_as_uncordonned() {
+  while true;
+  do
+    result=$(kubectl "${kubectl_flags[@]}" get node "${notcordonned_node}" --no-headers | awk '{print $2;}')
+    test "${result}" != "Ready" && echo "Node ${notcordonned_node} in state ${result}" || return 0
+    sleep 3
+  done
+}
+### Start main
+
+worker_nodes=$(${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" get nodes -o custom-columns=name:metadata.name --no-headers | grep worker)
+precordonned_node=$(echo "$worker_nodes" | head -n 1)
+notcordonned_node=$(echo "$worker_nodes" | tail -n 1)
+
+# Wait for kured to install correctly
+sleep 15
+cordon
+create_sentinel
+check_reboot_required
+echo "Node has rebooted, but may take time to come back ready"
+check_node_back_online_as_cordonned
+check_node_back_online_as_uncordonned
+echo "Showing final node state"
+${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" get nodes
+echo "Test successful"

tests/kind/testfiles/podblocker.sh

@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+
+kubectl_flags=( )
+[[ "$1" != "" ]] && kubectl_flags=("${kubectl_flags[@]}" --context "$1")
+
+function gather_logs_and_cleanup {
+      for id in $(docker ps -q); do
+          echo "############################################################"
+          echo "docker logs for container $id:"
+          docker logs "$id"
+      done
+      ${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" logs ds/kured --all-pods -n kube-system
+}
+trap gather_logs_and_cleanup EXIT
+
+set +o errexit
+worker=$(${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" get nodes -o custom-columns=name:metadata.name --no-headers | grep worker | head -n 1)
+
+${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" label nodes "$worker" blocked-host=yes
+
+${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" apply -f - << EOF
+apiVersion: v1
+kind: Pod
+metadata:
+  name: nginx
+  labels:
+    app: blocker
+spec:
+  containers:
+    - name: nginx
+      image: nginx
+      imagePullPolicy: IfNotPresent
+  nodeSelector:
+    blocked-host: "yes"
+EOF
+
+docker exec "$worker" touch "${SENTINEL_FILE:-/var/run/reboot-required}"
+
+set -o errexit
+max_attempts="100"
+attempt_num=1
+sleep_time=5
+
+until ${KUBECTL_CMD:-kubectl} "${kubectl_flags[@]}" logs ds/kured --all-pods -n kube-system  | grep -i -e "Reboot.*blocked"
+do
+  if (( attempt_num == max_attempts )); then
+      echo "Attempt $attempt_num failed and there are no more attempts left!"
+      exit 1
+  else
+      echo "Did not find 'reboot blocked' in the log, retrying in $sleep_time seconds (Attempt #$attempt_num)"
+      sleep "$sleep_time"
+  fi
+  (( attempt_num++ ))
+done