feat: add optional Prometheus monitoring via OperatorConfig

api/v1alpha1/operatorconfig_types.go

@@ -436,6 +436,27 @@ func (c *WorkspacesConfig) GetAutoPauseTimeoutMinutes() int32 {
 	return DefaultAutoPauseTimeoutMinutes
 }
 
+// MonitoringConfig defines configuration for Prometheus metrics collection
+type MonitoringConfig struct {
+	// Enabled determines if a ServiceMonitor should be deployed for Prometheus scraping
+	// +kubebuilder:default=false
+	Enabled bool `json:"enabled"`
+
+	// Interval defines the Prometheus scrape interval
+	// Default: "30s"
+	// +optional
+	// +kubebuilder:validation:Pattern=`^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$`
+	Interval string `json:"interval,omitempty"`
+}
+
+// GetInterval returns the scrape interval, falling back to "30s"
+func (c *MonitoringConfig) GetInterval() string {
+	if c != nil && c.Interval != "" {
+		return c.Interval
+	}
+	return "30s"
+}
+
 // OperatorConfigSpec defines the desired state of OperatorConfig
 type OperatorConfigSpec struct {
 	// OSBuilds defines the configuration for OS build operations
@@ -461,6 +482,10 @@ type OperatorConfigSpec struct {
 	// Workspaces defines configuration for developer workspaces
 	// +optional
 	Workspaces *WorkspacesConfig `json:"workspaces,omitempty"`
+
+	// Monitoring defines configuration for Prometheus metrics collection
+	// +optional
+	Monitoring *MonitoringConfig `json:"monitoring,omitempty"`
 }
 
 // OSBuildsConfig defines configuration for OS build operations
@@ -642,6 +667,9 @@ type OperatorConfigStatus struct {
 	// UserNamespacesSupported indicates if the cluster supports user namespaces in pods
 	// (SCC userNamespaceLevel field). When false, workspace pods use privileged mode.
 	UserNamespacesSupported bool `json:"userNamespacesSupported,omitempty"`
+
+	// MonitoringEnabled indicates if the ServiceMonitor is currently deployed
+	MonitoringEnabled bool `json:"monitoringEnabled,omitempty"`
 }
 
 // +kubebuilder:object:root=true

config/crd/bases/automotive.sdv.cloud.redhat.com_operatorconfigs.yaml

@@ -684,6 +684,24 @@ spec:
                       exporter configurations
                     type: object
                 type: object
+              monitoring:
+                description: Monitoring defines configuration for Prometheus metrics
+                  collection
+                properties:
+                  enabled:
+                    default: false
+                    description: Enabled determines if a ServiceMonitor should be
+                      deployed for Prometheus scraping
+                    type: boolean
+                  interval:
+                    description: |-
+                      Interval defines the Prometheus scrape interval
+                      Default: "30s"
+                    pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$
+                    type: string
+                required:
+                - enabled
+                type: object
               osBuilds:
                 description: OSBuilds defines the configuration for OS build operations
                 properties:
@@ -1065,6 +1083,10 @@ spec:
               message:
                 description: Message provides detail about the current phase
                 type: string
+              monitoringEnabled:
+                description: MonitoringEnabled indicates if the ServiceMonitor is
+                  currently deployed
+                type: boolean
               observedGeneration:
                 description: ObservedGeneration is the most recent generation observed
                   by the controller.

config/rbac/role.yaml

@@ -135,6 +135,18 @@ rules:
   - imagestreamtags
   verbs:
   - delete
+- apiGroups:
+  - monitoring.coreos.com
+  resources:
+  - servicemonitors
+  verbs:
+  - create
+  - delete
+  - get
+  - list
+  - patch
+  - update
+  - watch
 - apiGroups:
   - networking.k8s.io
   resources:

config/samples/automotive_v1_operatorconfig.yaml

@@ -50,6 +50,13 @@ spec:
     #   value: "automotive"
     #   effect: "NoExecute"
 
+  # Monitoring configuration for Prometheus ServiceMonitor
+  # Requires user-workload-monitoring enabled on the cluster
+  # monitoring:
+  #   enabled: true
+  #   # Optional: scrape interval (default: 30s)
+  #   # interval: "15s"
+
   # BuildAPI configuration for the Build API server
   buildAPI:
     # Optional: Authentication configuration for OIDC/JWT providers