feat: Prod 2299/coreos pod monitor for deployment operator chart

charts/deployment-operator/templates/_helpers.tpl

@@ -67,7 +67,7 @@ We truncate at 63 chars because some Kubernetes name fields are limited to this
 If release name contains chart name it will be used as a full name.
 */}}
 {{- define "agentk.fullname" -}}
-{{- include "deployment-operator.fullname"}}-agentk
+{{- include "deployment-operator.fullname" . }}-agentk
 {{- end }}
 
 {{/*

charts/deployment-operator/templates/deployment.yaml

@@ -16,6 +16,11 @@
       {{- with .Values.podAnnotations }}
         {{- toYaml . | nindent 8 }}
       {{- end }}
+      {{- if .Values.monitoring.enabled }}
+        {{- with .Values.monitoring.podAnnotations }}
+          {{- toYaml . | nindent 8 }}
+        {{- end }}
+      {{- end }}
       labels:
         {{- include "deployment-operator.selectorLabels" . | nindent 8 }}
       {{- with .Values.podLabels }}
@@ -53,50 +58,56 @@
             - name: http
               containerPort: {{ .Values.service.port }}
               protocol: TCP
+          {{- if .Values.monitoring.enabled }}
+            - name: observability
+              containerPort: {{ .Values.monitoring.metricsPort }}
+            - name: metrics
+              containerPort: 8080
+          {{- end }}
           livenessProbe:
             httpGet:
               path: /healthz
               port: http
           readinessProbe:
             httpGet:
               path: /healthz
               port: http
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
           {{ if .Values.additionalVolumeMounts }}
           volumeMounts:
             - name: temp
               mountPath: /tmp
             {{ toYaml .Values.additionalVolumeMounts | nindent 12 }}
           {{ end }}
         - name: {{ .Chart.Name }}-agentk
           securityContext:
             {{- toYaml .Values.securityContext | nindent 12 }}
           image: {{ .Values.agentk.image.repository }}:{{ .Values.agentk.image.tag }}
           imagePullPolicy: {{ .Values.agentk.image.pullPolicy }}
           terminationMessagePolicy: {{ .Values.agentk.terminationMessagePolicy }}
           {{ $kasAddress := replace "gql" "kas" (default "" .Values.consoleUrl) | replace "https" "wss" }}
           args:
             - --token-file=/etc/agentk/secrets/token
             - --kas-address={{ $kasAddress }}
             - --observability-listen-address=:8081
             {{- if .Values.agentk.config.caCert }}
             - --ca-cert-file=/etc/agentk/config/ca.crt
             {{- end }}
             {{- if .Values.agentk.config.kasHeaders }}
             {{- range .Values.agentk.config.kasHeaders }}
             - --kas-header
             - {{ . | quote }}
             {{- end }}
             {{- end }}
             {{- range .Values.agentk.extraArgs }}
             - {{ . }}
             {{- end }}
           livenessProbe:
             httpGet:
               path: /liveness
               port: 8081
             initialDelaySeconds: 15
             periodSeconds: 20
           readinessProbe:
             httpGet:

charts/deployment-operator/templates/podmonitor.yaml

@@ -0,0 +1,22 @@
+{{ if .Values.monitoring.enabled }}
+apiVersion: monitoring.coreos.com/v1
+kind: PodMonitor
+metadata:
+  name: {{ include "deployment-operator.fullname" . }}-podmonitor
+  labels:
+{{ include "deployment-operator.labels" . | indent 4 }}
+spec:
+  podMetricsEndpoints:
+    - port: metrics
+      path: '/metrics'
+  namespaceSelector:
+    matchNames:
+      - {{ .Release.Namespace }}
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: {{ include "deployment-operator.fullname" . }}
+      app.kubernetes.io/instance: {{ .Release.Name }}
+  podTargetLabels:
+    - app.kubernetes.io/name
+    - app.kubernetes.io/instance
+{{ end }}

charts/deployment-operator/templates/servicemonitor.yaml

@@ -1,4 +1,4 @@
-{{- if (.Values.agentk.serviceMonitor).enabled }}
+{{- if .Values.monitoring.enabled }}
 apiVersion: v1
 kind: Service
 metadata:
@@ -8,7 +8,7 @@ metadata:
 spec:
   type: ClusterIP
   ports:
-    - port: 8080
+    - port: {{ .Values.monitoring.metricsPort }}
       protocol: TCP
       name: observability
   selector:
@@ -29,6 +29,6 @@ spec:
     - {{ .Release.Namespace | quote }}
   endpoints:
   - port: observability
-    interval: 30s
-    scrapeTimeout: 25s
+    interval: 10s
+    scrapeTimeout: 9s
 {{- end }}

charts/deployment-operator/values.yaml

@@ -42,9 +42,6 @@ rbac:
 
 podLabels: {}
 podAnnotations: {}
-#  prometheus.io/scrape: "true"
-#  prometheus.io/path: "/metrics"
-#  prometheus.io/port: "8080"
 
 podSecurityContext: {}
   # fsGroup: 2000
@@ -57,6 +54,15 @@ securityContext: {}
   # runAsNonRoot: true
   # runAsUser: 1000
 
+monitoring:
+  enabled: false
+  prometheus: "k8s"
+  metricsPort: 8000
+  podAnnotations:
+    prometheus.io/scrape: "true"
+    prometheus.io/path: "/metrics"
+    prometheus.io/port: "8000"
+
 service:
   type: ClusterIP
   port: 9001
@@ -135,6 +141,3 @@ agentk:
   # requests:
   #   cpu: 100m
   #   memory: 128Mi
-  serviceMonitor:
-    # Specifies whether to create a ServiceMonitor resource for collecting Prometheus metrics
-    enabled: false