Feat/add servicemonitor and prometheusrule

helm/templates/prometheus-rule.yaml

@@ -0,0 +1,25 @@
+{{- if .Values.metrics.prometheusRule.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PrometheusRule
+metadata:
+  name: {{ .Chart.Name | trimSuffix "-chart" | trunc 44 }}-controller-rules
+  namespace: {{ .Release.Namespace }}
+  labels:
+    app.kubernetes.io/name: {{ include "ack-rds-controller.app.name" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+    k8s-app: {{ include "ack-rds-controller.app.name" . }}
+    helm.sh/chart: {{ include "ack-rds-controller.chart.name-version" . }}
+{{- with .Values.metrics.prometheusRule.additionalLabels }}
+{{ toYaml . | indent 4 }}
+{{- end }}
+spec:
+  groups:
+    - name: {{ include "ack-rds-controller.app.name" . }}
+      rules:
+{{- with .Values.metrics.prometheusRule.rules }}
+{{ toYaml . | indent 8 }}
+{{- end }}
+{{- end }}
+

helm/templates/service-monitor.yaml

@@ -0,0 +1,36 @@
+{{- if .Values.metrics.serviceMonitor.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: ServiceMonitor
+metadata:
+  name: {{ .Chart.Name | trimSuffix "-chart" | trunc 44 }}-controller-metrics
+  namespace: {{ .Release.Namespace }}
+  labels:
+    app.kubernetes.io/name: {{ include "ack-rds-controller.app.name" . }}
+    app.kubernetes.io/instance: {{ .Release.Name }}
+    app.kubernetes.io/managed-by: Helm
+    app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+    k8s-app: {{ include "ack-rds-controller.app.name" . }}
+    helm.sh/chart: {{ include "ack-rds-controller.chart.name-version" . }}
+{{- with .Values.metrics.serviceMonitor.additionalLabels }}
+{{ toYaml . | indent 4 }}
+{{- end }}
+spec:
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: {{ include "ack-rds-controller.app.name" . }}
+      app.kubernetes.io/instance: {{ .Release.Name }}
+      app.kubernetes.io/managed-by: Helm
+      k8s-app: {{ include "ack-rds-controller.app.name" . }}
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace }}
+  endpoints:
+    - port: metricsport
+      {{- with .Values.metrics.serviceMonitor.interval }}
+      interval: {{ . }}
+      {{- end }}
+      {{- with .Values.metrics.serviceMonitor.scrapeTimeout }}
+      scrapeTimeout: {{ . }}
+      {{- end }}
+{{- end }}
+

helm/values.schema.json

@@ -104,6 +104,59 @@
               "type"
           ],
           "type": "object"
+        },
+        "serviceMonitor": {
+          "description": "Prometheus ServiceMonitor settings",
+          "properties": {
+            "enabled": {
+              "type": "boolean"
+            },
+            "additionalLabels": {
+              "type": "object"
+            },
+            "interval": {
+              "type": "string"
+            },
+            "scrapeTimeout": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "prometheusRule": {
+          "description": "Prometheus PrometheusRule settings",
+          "properties": {
+            "enabled": {
+              "type": "boolean"
+            },
+            "additionalLabels": {
+              "type": "object"
+            },
+            "rules": {
+              "type": "array",
+              "items": {
+                "type": "object",
+                "properties": {
+                  "alert": {
+                    "type": "string"
+                  },
+                  "expr": {
+                    "type": "string"
+                  },
+                  "for": {
+                    "type": "string"
+                  },
+                  "labels": {
+                    "type": "object"
+                  },
+                  "annotations": {
+                    "type": "object"
+                  }
+                }
+              }
+            }
+          },
+          "type": "object"
         }
       },
       "required": [

helm/values.yaml

@@ -77,6 +77,32 @@ metrics:
     # Which Type to use for the Kubernetes Service?
     # See: https://kubernetes.io/docs/concepts/services-networking/service/#publishing-services-service-types
     type: "ClusterIP"
+  serviceMonitor:
+    # Set to true to automatically create a Prometheus ServiceMonitor resource
+    # Requires the Prometheus Operator CRDs to be installed
+    enabled: false
+    # Additional labels for the ServiceMonitor (e.g., for Prometheus selector)
+    additionalLabels: {}
+    # Scrape interval
+    interval: 30s
+    # Scrape timeout
+    scrapeTimeout: 10s
+  prometheusRule:
+    # Set to true to automatically create a Prometheus PrometheusRule resource
+    # Requires the Prometheus Operator CRDs to be installed
+    enabled: false
+    # Additional labels for the PrometheusRule (e.g., for Prometheus selector)
+    additionalLabels: {}
+    # Alert rules (can be overridden or extended)
+    rules:
+      - alert: RDSControllerSyncErrors
+        expr: sum by (controller) (rate(controller_runtime_reconcile_errors_total{job="rds-controller-metrics"}[10m])) > 0.5
+        for: 5m
+        labels:
+          severity: critical
+        annotations:
+          description: RDS controller having sync errors in the last 10 minutes for controller {{ $labels.controller }}
+          summary: RDS controller having sync errors with one or more objects
 
 resources:
   requests: