track status of each deployed component in AppWrapper Status (#139)

Author: dgrove-oss

api/v1beta2/appwrapper_types.go

@@ -105,6 +105,34 @@ type AppWrapperStatus struct {
 	//+listType=map
 	//+listMapKey=type
 	Conditions []metav1.Condition `json:"conditions,omitempty" patchStrategy:"merge" patchMergeKey:"type"`
+
+	// ComponentStatus parallels the Components array in the Spec and tracks the actually deployed resources
+	ComponentStatus []AppWrapperComponentStatus `json:"componentStatus,omitempty"`
+}
+
+// AppWrapperComponentStatus tracks the status of a single managed Component
+type AppWrapperComponentStatus struct {
+	// Name is the name of the Component
+	Name string `json:"name"`
+
+	// Kind is the Kind of the Component
+	Kind string `json:"kind"`
+
+	// APIVersion is the APIVersion of the Component
+	APIVersion string `json:"apiVersion"`
+
+	// Conditions hold the latest available observations of the Component's current state.
+	//
+	// The type of the condition could be:
+	//
+	// - ResourcesDeployed: The component is deployed on the cluster
+	//
+	//+optional
+	//+patchMergeKey=type
+	//+patchStrategy=merge
+	//+listType=map
+	//+listMapKey=type
+	Conditions []metav1.Condition `json:"conditions,omitempty" patchStrategy:"merge" patchMergeKey:"type"`
 }
 
 // AppWrapperPhase is the phase of the appwrapper

api/v1beta2/zz_generated.deepcopy.go

@@ -165,6 +165,111 @@ spec:
           status:
             description: AppWrapperStatus defines the observed state of the appwrapper
             properties:
+              componentStatus:
+                description: ComponentStatus parallels the Components array in the
+                  Spec and tracks the actually deployed resources
+                items:
+                  description: AppWrapperComponentStatus tracks the status of a single
+                    managed Component
+                  properties:
+                    apiVersion:
+                      description: APIVersion is the APIVersion of the Component
+                      type: string
+                    conditions:
+                      description: |-
+                        Conditions hold the latest available observations of the Component's current state.
+
+
+                        The type of the condition could be:
+
+
+                        - ResourcesDeployed: The component is deployed on the cluster
+                      items:
+                        description: "Condition contains details for one aspect of
+                          the current state of this API Resource.\n---\nThis struct
+                          is intended for direct use as an array at the field path
+                          .status.conditions.  For example,\n\n\n\ttype FooStatus
+                          struct{\n\t    // Represents the observations of a foo's
+                          current state.\n\t    // Known .status.conditions.type are:
+                          \"Available\", \"Progressing\", and \"Degraded\"\n\t    //
+                          +patchMergeKey=type\n\t    // +patchStrategy=merge\n\t    //
+                          +listType=map\n\t    // +listMapKey=type\n\t    Conditions
+                          []metav1.Condition `json:\"conditions,omitempty\" patchStrategy:\"merge\"
+                          patchMergeKey:\"type\" protobuf:\"bytes,1,rep,name=conditions\"`\n\n\n\t
+                          \   // other fields\n\t}"
+                        properties:
+                          lastTransitionTime:
+                            description: |-
+                              lastTransitionTime is the last time the condition transitioned from one status to another.
+                              This should be when the underlying condition changed.  If that is not known, then using the time when the API field changed is acceptable.
+                            format: date-time
+                            type: string
+                          message:
+                            description: |-
+                              message is a human readable message indicating details about the transition.
+                              This may be an empty string.
+                            maxLength: 32768
+                            type: string
+                          observedGeneration:
+                            description: |-
+                              observedGeneration represents the .metadata.generation that the condition was set based upon.
+                              For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
+                              with respect to the current state of the instance.
+                            format: int64
+                            minimum: 0
+                            type: integer
+                          reason:
+                            description: |-
+                              reason contains a programmatic identifier indicating the reason for the condition's last transition.
+                              Producers of specific condition types may define expected values and meanings for this field,
+                              and whether the values are considered a guaranteed API.
+                              The value should be a CamelCase string.
+                              This field may not be empty.
+                            maxLength: 1024
+                            minLength: 1
+                            pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
+                            type: string
+                          status:
+                            description: status of the condition, one of True, False,
+                              Unknown.
+                            enum:
+                            - "True"
+                            - "False"
+                            - Unknown
+                            type: string
+                          type:
+                            description: |-
+                              type of condition in CamelCase or in foo.example.com/CamelCase.
+                              ---
+                              Many .condition.type values are consistent across resources like Available, but because arbitrary conditions can be
+                              useful (see .node.status.conditions), the ability to deconflict is important.
+                              The regex it matches is (dns1123SubdomainFmt/)?(qualifiedNameFmt)
+                            maxLength: 316
+                            pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
+                            type: string
+                        required:
+                        - lastTransitionTime
+                        - message
+                        - reason
+                        - status
+                        - type
+                        type: object
+                      type: array
+                      x-kubernetes-list-map-keys:
+                      - type
+                      x-kubernetes-list-type: map
+                    kind:
+                      description: Kind is the Kind of the Component
+                      type: string
+                    name:
+                      description: Name is the name of the Component
+                      type: string
+                  required:
+                  - apiVersion
+                  - kind
+                  - name
+                  type: object
+                type: array
               conditions:
                 description: |-
                   Conditions hold the latest available observations of the AppWrapper current state.

config/crd/bases/workload.codeflare.dev_appwrappers.yaml

@@ -144,6 +144,7 @@ func (r *AppWrapperReconciler) Reconcile(ctx context.Context, req ctrl.Request)
 				return ctrl.Result{}, err
 			}
 		}
+		aw.Status.ComponentStatus = make([]workloadv1beta2.AppWrapperComponentStatus, len(aw.Spec.Components))
 		return r.updateStatus(ctx, aw, workloadv1beta2.AppWrapperSuspended)
 
 	case workloadv1beta2.AppWrapperSuspended: // no components deployed

internal/controller/appwrapper/appwrapper_controller.go

@@ -179,42 +179,67 @@ func (r *AppWrapperReconciler) createComponent(ctx context.Context, aw *workload
 
 func (r *AppWrapperReconciler) createComponents(ctx context.Context, aw *workloadv1beta2.AppWrapper) (error, bool) {
 	for componentIdx := range aw.Spec.Components {
-		_, err, fatal := r.createComponent(ctx, aw, componentIdx)
-		if err != nil {
-			return err, fatal
+		if !meta.IsStatusConditionTrue(aw.Status.ComponentStatus[componentIdx].Conditions, string(workloadv1beta2.ResourcesDeployed)) {
+			obj, err, fatal := r.createComponent(ctx, aw, componentIdx)
+			if err != nil {
+				return err, fatal
+			}
+			aw.Status.ComponentStatus[componentIdx].Name = obj.GetName()
+			aw.Status.ComponentStatus[componentIdx].Kind = obj.GetKind()
+			aw.Status.ComponentStatus[componentIdx].APIVersion = obj.GetAPIVersion()
+			meta.SetStatusCondition(&aw.Status.ComponentStatus[componentIdx].Conditions, metav1.Condition{
+				Type:   string(workloadv1beta2.ResourcesDeployed),
+				Status: metav1.ConditionTrue,
+				Reason: "CompononetCreated",
+			})
 		}
 	}
 	return nil, false
 }
 
 func (r *AppWrapperReconciler) deleteComponents(ctx context.Context, aw *workloadv1beta2.AppWrapper) bool {
+	deleteIfPresent := func(idx int, opts ...client.DeleteOption) bool {
+		cs := &aw.Status.ComponentStatus[idx]
+		if !meta.IsStatusConditionTrue(cs.Conditions, string(workloadv1beta2.ResourcesDeployed)) {
+			return false // not present
+		}
+		obj := &metav1.PartialObjectMetadata{
+			TypeMeta:   metav1.TypeMeta{Kind: cs.Kind, APIVersion: cs.APIVersion},
+			ObjectMeta: metav1.ObjectMeta{Name: cs.Name, Namespace: aw.Namespace},
+		}
+		if err := r.Delete(ctx, obj, opts...); err != nil {
+			if apierrors.IsNotFound(err) {
+				// Has already been undeployed; update componentStatus and return not present
+				meta.SetStatusCondition(&cs.Conditions, metav1.Condition{
+					Type:   string(workloadv1beta2.ResourcesDeployed),
+					Status: metav1.ConditionFalse,
+					Reason: "CompononetDeleted",
+				})
+				return false
+			} else {
+				log.FromContext(ctx).Error(err, "Deletion error")
+				return true // unexpected error ==> still present
+			}
+		}
+		return true // still present
+	}
+
 	meta.SetStatusCondition(&aw.Status.Conditions, metav1.Condition{
 		Type:   string(workloadv1beta2.DeletingResources),
 		Status: metav1.ConditionTrue,
 		Reason: "DeletionInitiated",
 	})
-	log := log.FromContext(ctx)
-	remaining := 0
-	for _, component := range aw.Spec.Components {
-		obj, err := parseComponent(aw, component.Template.Raw)
-		if err != nil {
-			log.Error(err, "Parsing error")
-			continue
-		}
-		if err := r.Delete(ctx, obj, client.PropagationPolicy(metav1.DeletePropagationBackground)); err != nil {
-			if !apierrors.IsNotFound(err) {
-				log.Error(err, "Deletion error")
-			}
-			continue
-		}
-		remaining++ // no error deleting resource, resource therefore still exists
+
+	componentsRemaining := false
+	for componentIdx := range aw.Spec.Components {
+		componentsRemaining = deleteIfPresent(componentIdx, client.PropagationPolicy(metav1.DeletePropagationBackground)) || componentsRemaining
 	}
 
 	deletionGracePeriod := r.forcefulDeletionGraceDuration(ctx, aw)
 	whenInitiated := meta.FindStatusCondition(aw.Status.Conditions, string(workloadv1beta2.DeletingResources)).LastTransitionTime
 	gracePeriodExpired := time.Now().After(whenInitiated.Time.Add(deletionGracePeriod))
 
-	if remaining > 0 && !gracePeriodExpired {
+	if componentsRemaining && !gracePeriodExpired {
 		// Resources left and deadline hasn't expired, just requeue the deletion
 		return false
 	}
@@ -224,10 +249,10 @@ func (r *AppWrapperReconciler) deleteComponents(ctx context.Context, aw *workloa
 		client.UnsafeDisableDeepCopy,
 		client.InNamespace(aw.Namespace),
 		client.MatchingLabels{AppWrapperLabel: aw.Name}); err != nil {
-		log.Error(err, "Pod list error")
+		log.FromContext(ctx).Error(err, "Pod list error")
 	}
 
-	if remaining == 0 && len(pods.Items) == 0 {
+	if !componentsRemaining && len(pods.Items) == 0 {
 		// no resources or pods left; deletion is complete
 		clearCondition(aw, workloadv1beta2.DeletingResources, "DeletionComplete", "")
 		return true
@@ -238,20 +263,13 @@ func (r *AppWrapperReconciler) deleteComponents(ctx context.Context, aw *workloa
 			// force deletion of pods first
 			for _, pod := range pods.Items {
 				if err := r.Delete(ctx, &pod, client.GracePeriodSeconds(0)); err != nil {
-					log.Error(err, "Forceful pod deletion error")
+					log.FromContext(ctx).Error(err, "Forceful pod deletion error")
 				}
 			}
 		} else {
 			// force deletion of wrapped resources once pods are gone
-			for _, component := range aw.Spec.Components {
-				obj, err := parseComponent(aw, component.Template.Raw)
-				if err != nil {
-					log.Error(err, "Parsing error")
-					continue
-				}
-				if err := r.Delete(ctx, obj, client.GracePeriodSeconds(0)); err != nil && !apierrors.IsNotFound(err) {
-					log.Error(err, "Forceful deletion error")
-				}
+			for componentIdx := range aw.Spec.Components {
+				_ = deleteIfPresent(componentIdx, client.GracePeriodSeconds(0))
 			}
 		}
 	}