feat: add Prometheus metrics and ServiceMonitor support

Add custom Prometheus metrics for operator observability:
- openvox_server_replicas_desired/ready per Server CR
- openvox_certificate_expiry_timestamp_seconds for certs and CAs

Helm chart changes:
- metrics.enabled toggle (default: true, set false to disable)
- metrics.port exposed in Deployment containerPorts
- metrics Service for scraping
- optional ServiceMonitor for Prometheus Operator

Closes #33

Signed-off-by: Simon Lauger <simon@lauger.de>

Author: slauger

charts/openvox-db-postgres/values.schema.json

@@ -1,32 +1,32 @@
 {
-    "$schema": "https://json-schema.org/draft/2020-12/schema",
-    "type": "object",
-    "properties": {
-        "database": {
-            "description": "PostgreSQL database name.",
-            "type": "string"
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "type": "object",
+  "properties": {
+    "database": {
+      "description": "PostgreSQL database name.",
+      "type": "string"
+    },
+    "instances": {
+      "description": "Number of PostgreSQL instances.",
+      "type": "integer",
+      "minimum": 1
+    },
+    "postInitSQL": {
+      "description": "Extra SQL statements to run after database creation (pg_trgm is always included).",
+      "type": "array"
+    },
+    "storage": {
+      "type": "object",
+      "properties": {
+        "size": {
+          "description": "PVC size for each PostgreSQL instance.",
+          "type": "string"
         },
-        "instances": {
-            "description": "Number of PostgreSQL instances.",
-            "type": "integer",
-            "minimum": 1
-        },
-        "postInitSQL": {
-            "description": "Extra SQL statements to run after database creation (pg_trgm is always included).",
-            "type": "array"
-        },
-        "storage": {
-            "type": "object",
-            "properties": {
-                "size": {
-                    "description": "PVC size for each PostgreSQL instance.",
-                    "type": "string"
-                },
-                "storageClass": {
-                    "description": "Storage class for PostgreSQL PVCs. Empty uses cluster default.",
-                    "type": "string"
-                }
-            }
+        "storageClass": {
+          "description": "Storage class for PostgreSQL PVCs. Empty uses cluster default.",
+          "type": "string"
         }
+      }
     }
+  }
 }

charts/openvox-operator/README.md

@@ -46,6 +46,12 @@ To deploy a complete OpenVox stack after installing the operator, use the
 | image.tag | string | `"latest"` | Image tag. Ignored if digest is set. |
 | imagePullSecrets | list | `[]` | Image pull secrets for private registries. |
 | leaderElect | bool | `true` | Enable leader election for controller manager. |
+| metrics.enabled | bool | `true` | Enable the metrics endpoint. |
+| metrics.port | int | `8080` | Port for the metrics endpoint. |
+| metrics.service.enabled | bool | `true` | Create a Service for the metrics endpoint. |
+| metrics.serviceMonitor.enabled | bool | `false` | Create a Prometheus ServiceMonitor resource. |
+| metrics.serviceMonitor.interval | string | `"30s"` | Scrape interval for the ServiceMonitor. |
+| metrics.serviceMonitor.labels | object | `{}` | Additional labels for the ServiceMonitor. |
 | nodeSelector | object | `{}` | Node selector for pod scheduling. |
 | podAnnotations | object | `{}` | Annotations applied to the operator Pod template (e.g. for log collectors, Prometheus scraping, or forcing rollouts via a checksum annotation). |
 | replicaCount | int | `1` | Number of operator pod replicas. |

charts/openvox-operator/templates/deployment.yaml

@@ -49,10 +49,20 @@ spec:
             {{- if not .Values.gatewayAPI.enabled }}
             - --enable-gateway-api=false
             {{- end }}
+            {{- if .Values.metrics.enabled }}
+            - --metrics-bind-address=:{{ .Values.metrics.port | default 8080 }}
+            {{- else }}
+            - --metrics-bind-address=0
+            {{- end }}
           ports:
             - name: health
               containerPort: 8081
               protocol: TCP
+            {{- if .Values.metrics.enabled }}
+            - name: metrics
+              containerPort: {{ .Values.metrics.port | default 8080 }}
+              protocol: TCP
+            {{- end }}
             {{- if .Values.webhook.enabled }}
             - name: webhook
               containerPort: {{ .Values.webhook.port | default 9443 }}

charts/openvox-operator/templates/metrics-service.yaml

@@ -0,0 +1,18 @@
+{{- if and .Values.metrics.enabled .Values.metrics.service.enabled }}
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "openvox-operator.fullname" . }}-metrics
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "openvox-operator.labels" . | nindent 4 }}
+spec:
+  type: ClusterIP
+  ports:
+    - name: metrics
+      port: {{ .Values.metrics.port | default 8080 }}
+      targetPort: metrics
+      protocol: TCP
+  selector:
+    {{- include "openvox-operator.selectorLabels" . | nindent 4 }}
+{{- end }}

charts/openvox-operator/templates/servicemonitor.yaml

@@ -0,0 +1,19 @@
+{{- if and .Values.metrics.enabled .Values.metrics.serviceMonitor.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ include "openvox-operator.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "openvox-operator.labels" . | nindent 4 }}
+    {{- with .Values.metrics.serviceMonitor.labels }}
+    {{- toYaml . | nindent 4 }}
+    {{- end }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "openvox-operator.selectorLabels" . | nindent 6 }}
+  endpoints:
+    - port: metrics
+      interval: {{ .Values.metrics.serviceMonitor.interval | default "30s" }}
+{{- end }}