[FEAT] chart enhancements for version monitoring (#83)

* [FEAT] chart enhancements for version monitoring * [BUILD] publish artefacts * Revert "[BUILD] publish artefacts" This reverts commit 0e267bf. * configurable volumes and mounts for controller and subscription server * adjust helm-docs
SAP · Sep 25, 2024 · 65812ac · 65812ac
1 parent f48e81c
commit 65812ac
Show file tree

Hide file tree

Showing 6 changed files with 118 additions and 9 deletions.
diff --git a/chart/README.md b/chart/README.md
@@ -33,7 +33,12 @@ Helm chart to deploy CAP Operator https://sap.github.io/cap-operator/
 | controller.resources.limits.cpu | float | `0.2` | CPU limit |
 | controller.resources.requests.memory | string | `"50Mi"` | Memory request |
 | controller.resources.requests.cpu | float | `0.02` | CPU request |
+| controller.volumes | list | `[]` | Optionally specify list of additional volumes for the controller pod(s) |
+| controller.volumeMounts | list | `[]` | Optionally specify list of additional volumeMounts for the controller container(s) |
 | controller.dnsTarget | string | `""` | The dns target mentioned on the public ingress gateway service used in the cluster |
+| controller.versionMonitoring.prometheusAddress | string | `""` | The URL of the Prometheus server from which metrics related to managed application versions can be queried  |
+| controller.versionMonitoring.metricsEvaluationInterval | string | `"1h"` | The duration (example 2h) after which versions are evaluated for deletion; based on specified workload metrics |
+| controller.versionMonitoring.promClientAcquireRetryDelay | string | `"1h"` | The duration (example 10m) to wait before retrying to acquire Prometheus client and verify connection, after a failed attempt |
 | subscriptionServer.replicas | int | `1` | Replicas |
 | subscriptionServer.image.repository | string | `"ghcr.io/sap/cap-operator/server"` | Image repository |
 | subscriptionServer.image.tag | string | `""` | Image tag |
@@ -50,6 +55,8 @@ Helm chart to deploy CAP Operator https://sap.github.io/cap-operator/
 | subscriptionServer.resources.limits.cpu | float | `0.1` | CPU limit |
 | subscriptionServer.resources.requests.memory | string | `"20Mi"` | Memory request |
 | subscriptionServer.resources.requests.cpu | float | `0.01` | CPU request |
+| subscriptionServer.volumes | list | `[]` | Optionally specify list of additional volumes for the server pod(s) |
+| subscriptionServer.volumeMounts | list | `[]` | Optionally specify list of additional volumeMounts for the server container(s) |
 | subscriptionServer.port | int | `4000` | Service port |
 | subscriptionServer.istioSystemNamespace | string | `"istio-system"` | The namespace in the cluster where istio system components are installed |
 | subscriptionServer.ingressGatewayLabels | object | `{"app":"istio-ingressgateway","istio":"ingressgateway"}` | Labels used to identify the istio ingress-gateway component |
@@ -76,4 +83,3 @@ Helm chart to deploy CAP Operator https://sap.github.io/cap-operator/
 | webhook.service.type | string | `"ClusterIP"` | Service type |
 | webhook.service.port | int | `443` | Service port |
 | webhook.service.targetPort | int | `1443` | Target port |
-
diff --git a/chart/crds/sme.sap.com_capapplicationversions.yaml b/chart/crds/sme.sap.com_capapplicationversions.yaml
@@ -1375,6 +1375,57 @@ spec:
                               format: int32
                               type: integer
                           type: object
+                        monitoring:
+                          properties:
+                            deletionRules:
+                              oneOf:
+                              - required:
+                                - metrics
+                              - required:
+                                - expression
+                              properties:
+                                expression:
+                                  type: string
+                                metrics:
+                                  items:
+                                    properties:
+                                      calculationPeriod:
+                                        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
+                                      name:
+                                        type: string
+                                      thresholdValue:
+                                        format: double
+                                        type: string
+                                      type:
+                                        enum:
+                                        - Gauge
+                                        - Counter
+                                        type: string
+                                    required:
+                                    - calculationPeriod
+                                    - name
+                                    - thresholdValue
+                                    - type
+                                    type: object
+                                  type: array
+                              type: object
+                            scrapeConfig:
+                              properties:
+                                interval:
+                                  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
+                                path:
+                                  type: string
+                                port:
+                                  type: string
+                                scrapeTimeout:
+                                  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:
+                              - port
+                              type: object
+                          type: object
                         nodeName:
                           type: string
                         nodeSelector:

diff --git a/chart/templates/controller-deployment.yaml b/chart/templates/controller-deployment.yaml
@@ -47,6 +47,10 @@ spec:
       topologySpreadConstraints:
         {{- toYaml . | nindent 8 }}
       {{- end }}
+      {{- with .Values.controller.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
         - name: controller
           image: {{ .Values.controller.image.repository }}:{{ .Values.controller.image.tag | default .Values.image.tag | default .Chart.AppVersion }}
@@ -58,12 +62,30 @@ spec:
           resources:
             {{- toYaml .Values.controller.resources | nindent 12 }}
           env:
-          - name: CERT_MANAGER
-            value: {{ .Capabilities.APIVersions.Has "cert.gardener.cloud/v1alpha1" | ternary "gardener" "cert-manager.io" }}
-          - name: DNS_MANAGER
-            value: {{ .Capabilities.APIVersions.Has "dns.gardener.cloud/v1alpha1" | ternary "gardener" "kubernetes" }}
-          {{- if .Values.controller.dnsTarget }}
-          - name: DNS_TARGET
-            value: {{ .Values.controller.dnsTarget }}
+            - name: CERT_MANAGER
+              value: {{ .Capabilities.APIVersions.Has "cert.gardener.cloud/v1alpha1" | ternary "gardener" "cert-manager.io" }}
+            - name: DNS_MANAGER
+              value: {{ .Capabilities.APIVersions.Has "dns.gardener.cloud/v1alpha1" | ternary "gardener" "kubernetes" }}
+            {{- if .Values.controller.dnsTarget }}
+            - name: DNS_TARGET
+              value: {{ .Values.controller.dnsTarget }}
+            {{- end }}
+            {{- with .Values.controller.versionMonitoring }}
+            {{- if .prometheusAddress }}
+            - name: PROMETHEUS_ADDRESS
+              value: {{ .prometheusAddress }}
+            {{- end }}
+            {{- if .metricsEvaluationInterval }}
+            - name: METRICS_EVAL_INTERVAL
+              value: {{ .metricsEvaluationInterval }}
+            {{- end }}
+            {{- if .promClientAcquireRetryDelay }}
+            - name: PROM_ACQUIRE_CLIENT_RETRY_DELAY
+              value: {{ .promClientAcquireRetryDelay }}
+            {{- end }}
+            {{- end }}
+          {{- with .Values.controller.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
           {{- end }}
       serviceAccountName: {{.Release.Name}}-controller
diff --git a/chart/templates/controller-rbac.yaml b/chart/templates/controller-rbac.yaml
@@ -53,6 +53,12 @@ rules:
 - apiGroups: ["coordination.k8s.io"]
   resources: ["leases"]
   verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
+- apiGroups: ["monitoring.coreos.com"]
+  resources: ["servicemonitors"]
+  verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
+- apiGroups: ["apiextensions.k8s.io"]
+  resources: ["customresourcedefinitions"]
+  verbs: ["get"]
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding

diff --git a/chart/templates/server-deployment.yaml b/chart/templates/server-deployment.yaml
@@ -48,6 +48,10 @@ spec:
       topologySpreadConstraints:
         {{- toYaml . | nindent 8 }}
       {{- end }}
+      {{- with .Values.subscriptionServer.volumes }}
+      volumes:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
       containers:
         - name: server
           image: {{ .Values.subscriptionServer.image.repository }}:{{ .Values.subscriptionServer.image.tag | default .Values.image.tag | default .Chart.AppVersion }}
@@ -58,6 +62,10 @@ spec:
           {{- end }}
           resources:
             {{- toYaml .Values.subscriptionServer.resources | nindent 12 }}
+          {{- with .Values.subscriptionServer.volumeMounts }}
+          volumeMounts:
+            {{- toYaml . | nindent 12 }}
+          {{- end }}
           ports:
             - name: server-port
               containerPort: 4000

diff --git a/chart/values.yaml b/chart/values.yaml
@@ -55,9 +55,20 @@ controller:
       memory: 50Mi
       # -- CPU request
       cpu: 0.02
+  # -- Optionally specify list of additional volumes for the controller pod(s)
+  volumes: []
+  # -- Optionally specify list of additional volumeMounts for the controller container(s)
+  volumeMounts: []
   # -- The dns target mentioned on the public ingress gateway service used in the cluster
   dnsTarget: ""
-
+  versionMonitoring:
+    # -- The URL of the Prometheus server from which metrics related to managed application versions can be queried 
+    prometheusAddress: ""
+    # -- The duration (example 2h) after which versions are evaluated for deletion; based on specified workload metrics
+    metricsEvaluationInterval: "1h"
+    # -- The duration (example 10m) to wait before retrying to acquire Prometheus client and verify connection, after a failed attempt
+    promClientAcquireRetryDelay: "1h"
+
 subscriptionServer:
   # -- Replicas
   replicas: 1
@@ -95,6 +106,10 @@ subscriptionServer:
       memory: 20Mi
       # -- CPU request
       cpu: 0.01
+  # -- Optionally specify list of additional volumes for the server pod(s)
+  volumes: []
+  # -- Optionally specify list of additional volumeMounts for the server container(s)
+  volumeMounts: []
   # -- Service port
   port: 4000
   # -- The namespace in the cluster where istio system components are installed
@@ -107,6 +122,7 @@ subscriptionServer:
   dnsTarget: public-ingress.clusters.cs.services.sap # replace with the actual cluster domain
   # -- The domain under which the cap operator subscription server would be available
   domain: cap-operator.clusters.cs.services.sap # replace with actual cluster domain
+
 webhook:
   # -- Side car to mount admission review
   sidecar: false