feat: upgrade to support Kubernetes 1.30

.github/workflows/ci.yaml

@@ -12,14 +12,17 @@ jobs:
   test:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
-    - uses: actions/setup-go@v3
+    - uses: actions/checkout@v4
+    - uses: actions/setup-go@v5
       with:
-        go-version: "1.19"
+        go-version: "1.22"
+        check-latest: true
+        cache: true
     - run: make test
 
   docker-build:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
+    - uses: docker/setup-buildx-action@v3
     - run: make docker-build

.github/workflows/release.yaml

@@ -10,13 +10,23 @@ on:
 jobs:
   run:
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
+    - uses: docker/setup-buildx-action@v3
     - name: Login to GitHub Container Registry
-      uses: docker/login-action@v2
+      uses: docker/login-action@v3
       with:
         registry: ghcr.io
         username: ${{ github.actor }}
         password: ${{ secrets.GITHUB_TOKEN }}
-    - run: make docker-build
-    - run: make docker-push
+    - name: Build and push
+      uses: docker/build-push-action@v5
+      with:
+        context: .
+        push: true
+        tags: |
+          ghcr.io/${{ github.repository }}:latest
+          ghcr.io/${{ github.repository }}:${{ github.ref_name }}

.github/workflows/tagpr.yaml

@@ -7,16 +7,21 @@ on:
 jobs:
   tagpr:
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
     - id: tagpr
       name: Tagpr
       uses: Songmu/tagpr@v1
       env:
         GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
 
     - name: Trigger Release Workflow(only when tagged)
-      uses: actions/github-script@v6
+      uses: actions/github-script@v7
       if: "steps.tagpr.outputs.tag != ''"
       with:
         script: |

Dockerfile

@@ -1,33 +1,27 @@
-FROM golang:1.19 AS base
+# Build the manager binary
+FROM golang:1.22 as builder
 
 WORKDIR /workspace
 # Copy the Go Modules manifests
-COPY go.* .
+COPY go.mod go.mod
+COPY go.sum go.sum
 # cache deps before building and copying source so that we don't need to re-download as much
 # and so that source changes don't invalidate our downloaded layer
-RUN --mount=type=cache,target=/go/pkg/mod \
-    go mod download
+RUN go mod download
 
-FROM golangci/golangci-lint:v1.49 AS lint-base
-FROM base AS lint
-RUN --mount=target=. \
-    --mount=from=lint-base,src=/usr/bin/golangci-lint,target=/usr/bin/golangci-lint \
-    --mount=type=cache,target=/go/pkg/mod \
-    --mount=type=cache,target=/root/.cache/go-build \
-    --mount=type=cache,target=/root/.cache/golangci-lint \
-    golangci-lint run --timeout 10m0s ./...
+# Copy the go source
+COPY main.go main.go
+COPY api/ api/
+COPY controllers/ controllers/
 
-FROM base AS build
-# Build the manager binary
-RUN --mount=target=. \
-    --mount=type=cache,target=/go/pkg/mod \
-    --mount=type=cache,target=/root/.cache/go-build \
-    CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -a -o /out/manager main.go
+# Build
+RUN CGO_ENABLED=0 GOOS=linux GOARCH=amd64 GO111MODULE=on go build -a -o manager main.go
 
 # Use distroless as minimal base image to package the manager binary
 # Refer to https://github.com/GoogleContainerTools/distroless for more details
 FROM gcr.io/distroless/static:nonroot
 WORKDIR /
-COPY --from=build /out/manager .
+COPY --from=builder /workspace/manager .
+USER 65532:65532
 
 ENTRYPOINT ["/manager"]

controllers/nodeoperation_controller.go

@@ -28,7 +28,7 @@
 	corev1 "k8s.io/api/core/v1"
 	"k8s.io/apimachinery/pkg/api/errors"
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/labels"
 	"k8s.io/apimachinery/pkg/runtime"
 	"k8s.io/client-go/kubernetes"
 	"k8s.io/client-go/tools/record"
@@ -36,6 +36,7 @@
 	ctrl "sigs.k8s.io/controller-runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/log"
+	"sigs.k8s.io/controller-runtime/pkg/predicate"
 )
 
 var controllerTaint = corev1.Taint{
@@ -87,16 +88,21 @@
 func (r *NodeOperationReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {
 	logger := log.FromContext(ctx)
 
+	// Add timeout to context
+	ctx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
+
 	nodeOp := &nodeopsv1alpha1.NodeOperation{}
 	if err := r.Get(ctx, req.NamespacedName, nodeOp); err != nil {
 		sterr, ok := err.(*errors.StatusError)
-		if ok && sterr.Status().Code == 404 {
+		if ok && sterr.Status().Code == http.StatusNotFound {
 			if err := r.removeTaints(ctx); err != nil {
+				logger.Error(err, "failed to remove taints")
 				return ctrl.Result{}, err
 			}
 			return ctrl.Result{}, nil
 		}
-		return ctrl.Result{}, err
+		return ctrl.Result{}, client.IgnoreNotFound(err)
 	}
 
 	var result ctrl.Result
@@ -410,7 +416,7 @@
 func (r *NodeOperationReconciler) SetupWithManager(mgr ctrl.Manager) error {
 	r.clientset = kubernetes.NewForConfigOrDie(mgr.GetConfig())
 	r.mutex = sync.Mutex{}
-	// create index for NodeOperation name
+	// Create a new indexer for jobs that references NodeOperations
 	if err := mgr.GetFieldIndexer().IndexField(context.Background(), &batchv1.Job{}, jobOwnerKey, func(rawObj client.Object) []string {
 		job := rawObj.(*batchv1.Job)
 		owner := metav1.GetControllerOf(job)
@@ -431,6 +437,7 @@
 	return ctrl.NewControllerManagedBy(mgr).
 		For(&nodeopsv1alpha1.NodeOperation{}).
 		Owns(&batchv1.Job{}).
+		WithEventFilter(predicate.GenerationChangedPredicate{}).
 		Complete(r)
 }
 

controllers/suite_test.go

@@ -30,19 +30,20 @@ import (
 
 	. "github.com/onsi/ginkgo/v2"
 	. "github.com/onsi/gomega"
-	"sigs.k8s.io/controller-runtime/pkg/manager"
-
-	batchv1 "k8s.io/api/batch/v1"
-	corev1 "k8s.io/api/core/v1"
-	apierrors "k8s.io/apimachinery/pkg/api/errors"
-	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/client-go/kubernetes/scheme"
 	"k8s.io/client-go/rest"
+	ctrl "sigs.k8s.io/controller-runtime"
 	"sigs.k8s.io/controller-runtime/pkg/client"
 	"sigs.k8s.io/controller-runtime/pkg/envtest"
 	logf "sigs.k8s.io/controller-runtime/pkg/log"
 	"sigs.k8s.io/controller-runtime/pkg/log/zap"
 
+	batchv1 "k8s.io/api/batch/v1"
+	corev1 "k8s.io/api/core/v1"
+	apierrors "k8s.io/apimachinery/pkg/api/errors"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/rest"
+
 	nodeopsv1alpha1 "github.com/pfnet-research/node-operation-controller/api/v1alpha1"
 	//+kubebuilder:scaffold:imports
 )
@@ -53,6 +54,8 @@ import (
 var cfg *rest.Config
 var k8sClient client.Client
 var testEnv *envtest.Environment
+var ctx context.Context
+var cancel context.CancelFunc
 
 func TestAPIs(t *testing.T) {
 	RegisterFailHandler(Fail)
@@ -63,12 +66,12 @@ func TestAPIs(t *testing.T) {
 var _ = BeforeSuite(func() {
 	logf.SetLogger(zap.New(zap.WriteTo(GinkgoWriter), zap.UseDevMode(true)))
 
+	ctx, cancel = context.WithCancel(context.Background())
+
 	By("bootstrapping test environment")
-	trueV := true
 	testEnv = &envtest.Environment{
 		CRDDirectoryPaths:     []string{filepath.Join("..", "config", "crd", "bases")},
 		ErrorIfCRDPathMissing: true,
-		UseExistingCluster:    &trueV,
 	}
 
 	var err error
@@ -85,35 +88,40 @@ var _ = BeforeSuite(func() {
 	Expect(err).NotTo(HaveOccurred())
 	Expect(k8sClient).NotTo(BeNil())
 
-	mgr, err := manager.New(cfg, manager.Options{})
-	Expect(err).NotTo(HaveOccurred())
+	k8sManager, err := ctrl.NewManager(cfg, ctrl.Options{
+		Scheme: scheme.Scheme,
+	})
+	Expect(err).ToNot(HaveOccurred())
 
 	err = (&NodeOperationReconciler{
-		Client: mgr.GetClient(),
-		Scheme: scheme.Scheme,
-	}).SetupWithManager(mgr)
+		Client:           k8sManager.GetClient(),
+		Scheme:          k8sManager.GetScheme(),
+		DrainInterval:    1 * time.Second,
+		NDBRetryInterval: 1 * time.Second,
+	}).SetupWithManager(k8sManager)
 	Expect(err).ToNot(HaveOccurred())
 
 	err = (&NodeRemediationReconciler{
-		Client: mgr.GetClient(),
-		Scheme: scheme.Scheme,
-	}).SetupWithManager(mgr)
+		Client: k8sManager.GetClient(),
+		Scheme: k8sManager.GetScheme(),
+	}).SetupWithManager(k8sManager)
 	Expect(err).ToNot(HaveOccurred())
 
 	err = (&NodeRemediationTemplateReconciler{
-		Client: mgr.GetClient(),
-		Scheme: scheme.Scheme,
-	}).SetupWithManager(mgr)
+		Client: k8sManager.GetClient(),
+		Scheme: k8sManager.GetScheme(),
+	}).SetupWithManager(k8sManager)
 	Expect(err).ToNot(HaveOccurred())
 
 	go func() {
-		err = mgr.Start(context.Background())
+		defer GinkgoRecover()
+		err = k8sManager.Start(ctx)
+		Expect(err).ToNot(HaveOccurred(), "failed to run manager")
 	}()
-	Expect(err).ToNot(HaveOccurred())
 
 	Eventually(func() bool {
 		nodeList := &corev1.NodeList{}
-		Expect(k8sClient.List(context.Background(), nodeList)).NotTo(HaveOccurred())
+		Expect(k8sClient.List(ctx, nodeList)).NotTo(HaveOccurred())
 		for _, node := range nodeList.Items {
 			for _, c := range node.Status.Conditions {
 				if c.Type == corev1.NodeReady && c.Status == corev1.ConditionFalse {
@@ -126,6 +134,7 @@ var _ = BeforeSuite(func() {
 })
 
 var _ = AfterSuite(func() {
+	cancel()
 	By("tearing down the test environment")
 	err := testEnv.Stop()
 	Expect(err).NotTo(HaveOccurred())

go.mod

@@ -1,16 +1,16 @@
 module github.com/pfnet-research/node-operation-controller
 
-go 1.19
+go 1.22
 
 require (
-	github.com/google/go-cmp v0.5.9
-	github.com/onsi/ginkgo/v2 v2.6.1
-	github.com/onsi/gomega v1.24.1
-	github.com/stretchr/testify v1.8.0
-	k8s.io/api v0.26.1
-	k8s.io/apimachinery v0.26.1
-	k8s.io/client-go v0.26.1
-	sigs.k8s.io/controller-runtime v0.14.1
+	github.com/google/go-cmp v0.6.0
+	github.com/onsi/ginkgo/v2 v2.15.0
+	github.com/onsi/gomega v1.31.1
+	github.com/stretchr/testify v1.8.4
+	k8s.io/api v0.29.2
+	k8s.io/apimachinery v0.29.2
+	k8s.io/client-go v0.29.2
+	sigs.k8s.io/controller-runtime v0.17.2
 )
 
 require (