fixup! fixup! fixup! fixup! fixup! fixup! Improve helm chart allowing for lock of the worker image

chart/Chart.yaml

@@ -10,9 +10,9 @@ description: |
 
 type: application
 
-version: 0.5.52
+version: 0.5.53
 
-appVersion: "0.5.52"
+appVersion: "0.5.53"
 
 home: https://github.com/lukaszraczylo/kubernetes-images-sync-operator
 

chart/values.yaml

@@ -11,10 +11,10 @@ sa:
         drop:
         - ALL
     env:
-      workerImage: ghcr.io/lukaszraczylo/kubernetes-images-sync-worker:0.5.52
+      workerImage: ghcr.io/lukaszraczylo/kubernetes-images-sync-worker:0.5.53
     image:
       repository: ghcr.io/lukaszraczylo/kubernetes-images-sync-operator
-      tag: 0.5.52
+      tag: 0.5.53
     resources:
       limits:
         cpu: 500m

config/rbac/role.yaml

@@ -4,70 +4,71 @@ kind: ClusterRole
 metadata:
   name: impex-mgr
 rules:
-- apiGroups:
-  - ""
-  resources:
-  - pods
-  verbs:
-  - create
-  - delete
-  - get
-  - list
-  - patch
-  - update
-  - watch
-- apiGroups:
-  - apps
-  resources:
-  - daemonsets
-  - deployments
-  verbs:
-  - get
-  - list
-  - watch
-- apiGroups:
-  - batch
-  resources:
-  - cronjobs
-  verbs:
-  - get
-  - list
-  - watch
-- apiGroups:
-  - batch
-  resources:
-  - jobs
-  verbs:
-  - create
-  - delete
-  - get
-  - list
-  - patch
-  - update
-  - watch
-- apiGroups:
-  - raczylo.com
-  resources:
-  - '*'
-  verbs:
-  - create
-  - delete
-  - get
-  - list
-  - patch
-  - update
-  - watch
-- apiGroups:
-  - raczylo.com
-  resources:
-  - '*/finalizers'
-  verbs:
-  - update
-- apiGroups:
-  - raczylo.com
-  resources:
-  - '*/status'
-  verbs:
-  - get
-  - patch
-  - update
+  - apiGroups:
+      - ""
+    resources:
+      - pods
+    verbs:
+      - create
+      - delete
+      - deletecollection
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - apps
+    resources:
+      - daemonsets
+      - deployments
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - batch
+    resources:
+      - cronjobs
+    verbs:
+      - get
+      - list
+      - watch
+  - apiGroups:
+      - batch
+    resources:
+      - jobs
+    verbs:
+      - create
+      - delete
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - raczylo.com
+    resources:
+      - "*"
+    verbs:
+      - create
+      - delete
+      - get
+      - list
+      - patch
+      - update
+      - watch
+  - apiGroups:
+      - raczylo.com
+    resources:
+      - "*/finalizers"
+    verbs:
+      - update
+  - apiGroups:
+      - raczylo.com
+    resources:
+      - "*/status"
+    verbs:
+      - get
+      - patch
+      - update

internal/controller/raczylo.com/clusterimage_controller.go

@@ -36,7 +36,7 @@ type ClusterImageReconciler struct {
 // +kubebuilder:rbac:groups=raczylo.com,resources=*/finalizers,verbs=update
 // # additional RBAC rules - create and manage jobs
 // +kubebuilder:rbac:groups=batch,resources=jobs,verbs=get;list;watch;create;update;patch;delete
-// +kubebuilder:rbac:groups="",resources=pods,verbs=get;list;watch;create;update;patch;delete
+// +kubebuilder:rbac:groups="",resources=pods,verbs=get;list;watch;create;update;patch;delete;deletecollection
 // add access to secrets
 // +kubebuilder:rbac:groups="",resources=secrets,verbs=get;list;watch
 func (r *ClusterImageReconciler) Reconcile(ctx context.Context, req ctrl.Request) (ctrl.Result, error) {

internal/controller/raczylo.com/clusterimageexport_controller.go

@@ -181,7 +181,9 @@ func (r *ClusterImageExportReconciler) Reconcile(ctx context.Context, req ctrl.R
 	}
 
 	// Check completion status and update counts
-	completedCount := 0
+	successCount := 0
+	failedCount := 0
+	pendingCount := 0
 	clusterImageList := &raczylocomv1.ClusterImageList{}
 	if err := r.List(ctx, clusterImageList, client.InNamespace(clusterImageExport.Namespace), 
 		client.MatchingFields{"spec.exportName": clusterImageExport.Name}); err != nil {
@@ -190,30 +192,37 @@ func (r *ClusterImageExportReconciler) Reconcile(ctx context.Context, req ctrl.R
 	}
 
 	for _, ci := range clusterImageList.Items {
-		if ci.Status.Progress == shared.STATUS_SUCCESS || ci.Status.Progress == shared.STATUS_PRESENT {
-			completedCount++
+		switch ci.Status.Progress {
+		case shared.STATUS_SUCCESS, shared.STATUS_PRESENT:
+			successCount++
+		case shared.STATUS_FAILED:
+			failedCount++
+		case shared.STATUS_PENDING, shared.STATUS_RUNNING, shared.STATUS_RETRYING:
+			pendingCount++
 		}
 	}
 
+	completedCount := successCount + failedCount
+
 	// Update status with completion info
-	if completedCount == totalImages && totalImages > 0 {
-		if err := r.updateStatusWithRetry(ctx, clusterImageExport, func(export *raczylocomv1.ClusterImageExport) error {
-			export.Status.Progress = shared.STATUS_SUCCESS
-			export.Status.CompletedImages = completedCount
-			return nil
-		}); err != nil {
-			l.Error(err, "unable to update ClusterImageExport status")
-			return ctrl.Result{}, err
-		}
-		return ctrl.Result{}, nil
-	} else {
-		if err := r.updateStatusWithRetry(ctx, clusterImageExport, func(export *raczylocomv1.ClusterImageExport) error {
-			export.Status.CompletedImages = completedCount
-			return nil
-		}); err != nil {
-			l.Error(err, "unable to update ClusterImageExport status")
-			return ctrl.Result{}, err
+	if err := r.updateStatusWithRetry(ctx, clusterImageExport, func(export *raczylocomv1.ClusterImageExport) error {
+		export.Status.CompletedImages = completedCount
+		if completedCount == totalImages && totalImages > 0 {
+			if failedCount > 0 {
+				export.Status.Progress = shared.STATUS_FAILED
+			} else {
+				export.Status.Progress = shared.STATUS_SUCCESS
+			}
 		}
+		return nil
+	}); err != nil {
+		l.Error(err, "unable to update ClusterImageExport status")
+		return ctrl.Result{}, err
+	}
+
+	// If there are still pending images, requeue
+	if pendingCount > 0 {
+		return ctrl.Result{Requeue: true}, nil
 	}
 
 	return ctrl.Result{Requeue: true}, nil
@@ -401,7 +410,7 @@ func (r *ClusterImageExportReconciler) runCleanupJob(ctx context.Context, cluste
 
 	// Set up the cleanup job with retry limits and TTL
 	backoffLimit := int32(2) // 3 total attempts (initial + 2 retries)
-	ttlSecondsAfterFinished := int32(30) // Delete job 30 seconds after completion
+	ttlSecondsAfterFinished := int32(300) // Delete job 5 minutes after completion
 
 	// Merge annotations from different sources
 	mergedAnnotations := make(map[string]string)