monitoring services

monitoring/grafana-datasource.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: grafana-datasources
+  namespace: monitoring
+data:
+  prometheus.yaml: |
+    apiVersion: 1
+    datasources:
+    - name: Prometheus
+      type: prometheus
+      access: proxy
+      url: http://prometheus:9090
+      isDefault: true
+      editable: true

monitoring/grafana-deployment.yaml

@@ -0,0 +1,49 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: grafana
+  namespace: monitoring
+  labels:
+    app: grafana
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: grafana
+  template:
+    metadata:
+      labels:
+        app: grafana
+    spec:
+      containers:
+        - name: grafana
+          image: grafana/grafana:10.2.3
+          ports:
+            - containerPort: 3000
+              name: http
+          env:
+            - name: GF_SECURITY_ADMIN_USER
+              value: "admin"
+            - name: GF_SECURITY_ADMIN_PASSWORD
+              value: "admin"
+            - name: GF_INSTALL_PLUGINS
+              value: ""
+          volumeMounts:
+            - name: grafana-storage
+              mountPath: /var/lib/grafana
+            - name: grafana-datasources
+              mountPath: /etc/grafana/provisioning/datasources
+          resources:
+            requests:
+              memory: "256Mi"
+              cpu: "250m"
+            limits:
+              memory: "512Mi"
+              cpu: "500m"
+      volumes:
+        - name: grafana-storage
+          persistentVolumeClaim:
+            claimName: grafana-storage
+        - name: grafana-datasources
+          configMap:
+            name: grafana-datasources

monitoring/grafana-pvc.yaml

@@ -0,0 +1,11 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: grafana-storage
+  namespace: monitoring
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 5Gi

monitoring/grafana-service.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: grafana
+  namespace: monitoring
+  labels:
+    app: grafana
+spec:
+  type: ClusterIP
+  ports:
+    - port: 80
+      targetPort: 3000
+      protocol: TCP
+      name: http
+  selector:
+    app: grafana

monitoring/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: monitoring

monitoring/prometheus-config.yaml

@@ -0,0 +1,115 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: prometheus-config
+  namespace: monitoring
+data:
+  prometheus.yml: |
+    global:
+      scrape_interval: 15s
+      evaluation_interval: 15s
+
+    scrape_configs:
+      - job_name: 'prometheus'
+        static_configs:
+          - targets: ['localhost:9090']
+
+      - job_name: 'kubernetes-apiservers'
+        kubernetes_sd_configs:
+          - role: endpoints
+        scheme: https
+        tls_config:
+          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+        relabel_configs:
+          - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
+            action: keep
+            regex: default;kubernetes;https
+
+      - job_name: 'kubernetes-nodes'
+        kubernetes_sd_configs:
+          - role: node
+        scheme: https
+        tls_config:
+          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+        relabel_configs:
+          - action: labelmap
+            regex: __meta_kubernetes_node_label_(.+)
+          - target_label: __address__
+            replacement: kubernetes.default.svc:443
+          - source_labels: [__meta_kubernetes_node_name]
+            regex: (.+)
+            target_label: __metrics_path__
+            replacement: /api/v1/nodes/${1}/proxy/metrics
+
+      - job_name: 'kubernetes-cadvisor'
+        kubernetes_sd_configs:
+          - role: node
+        scheme: https
+        tls_config:
+          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
+        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
+        relabel_configs:
+          - action: labelmap
+            regex: __meta_kubernetes_node_label_(.+)
+          - target_label: __address__
+            replacement: kubernetes.default.svc:443
+          - source_labels: [__meta_kubernetes_node_name]
+            regex: (.+)
+            target_label: __metrics_path__
+            replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
+
+      - job_name: 'kubernetes-service-endpoints'
+        kubernetes_sd_configs:
+          - role: endpoints
+        relabel_configs:
+          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
+            action: keep
+            regex: true
+          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
+            action: replace
+            target_label: __scheme__
+            regex: (https?)
+          - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
+            action: replace
+            target_label: __metrics_path__
+            regex: (.+)
+          - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
+            action: replace
+            target_label: __address__
+            regex: ([^:]+)(?::\d+)?;(\d+)
+            replacement: $1:$2
+          - action: labelmap
+            regex: __meta_kubernetes_service_label_(.+)
+          - source_labels: [__meta_kubernetes_namespace]
+            action: replace
+            target_label: kubernetes_namespace
+          - source_labels: [__meta_kubernetes_service_name]
+            action: replace
+            target_label: kubernetes_name
+
+      - job_name: 'kubernetes-pods'
+        kubernetes_sd_configs:
+          - role: pod
+        relabel_configs:
+          - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
+            action: keep
+            regex: true
+          - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
+            action: replace
+            target_label: __metrics_path__
+            regex: (.+)
+          - source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
+            action: replace
+            regex: ([^:]+)(?::\d+)?;(\d+)
+            replacement: $1:$2
+            target_label: __address__
+          - action: labelmap
+            regex: __meta_kubernetes_pod_label_(.+)
+          - source_labels: [__meta_kubernetes_namespace]
+            action: replace
+            target_label: kubernetes_namespace
+          - source_labels: [__meta_kubernetes_pod_name]
+            action: replace
+            target_label: kubernetes_pod_name

monitoring/prometheus-deployment.yaml

@@ -0,0 +1,50 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app: prometheus
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: prometheus
+  template:
+    metadata:
+      labels:
+        app: prometheus
+    spec:
+      serviceAccountName: prometheus
+      containers:
+        - name: prometheus
+          image: prom/prometheus:v2.48.1
+          args:
+            - '--config.file=/etc/prometheus/prometheus.yml'
+            - '--storage.tsdb.path=/prometheus'
+            - '--web.console.libraries=/etc/prometheus/console_libraries'
+            - '--web.console.templates=/etc/prometheus/consoles'
+            - '--storage.tsdb.retention.time=15d'
+            - '--web.enable-lifecycle'
+          ports:
+            - containerPort: 9090
+              name: web
+          volumeMounts:
+            - name: prometheus-config
+              mountPath: /etc/prometheus
+            - name: prometheus-storage
+              mountPath: /prometheus
+          resources:
+            requests:
+              memory: "512Mi"
+              cpu: "500m"
+            limits:
+              memory: "1Gi"
+              cpu: "1000m"
+      volumes:
+        - name: prometheus-config
+          configMap:
+            name: prometheus-config
+        - name: prometheus-storage
+          persistentVolumeClaim:
+            claimName: prometheus-storage

monitoring/prometheus-pvc.yaml

@@ -0,0 +1,11 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: prometheus-storage
+  namespace: monitoring
+spec:
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 10Gi

monitoring/prometheus-rbac.yaml

@@ -0,0 +1,39 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus
+  namespace: monitoring
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: prometheus
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+      - nodes/proxy
+      - services
+      - endpoints
+      - pods
+    verbs: ["get", "list", "watch"]
+  - apiGroups:
+      - extensions
+    resources:
+      - ingresses
+    verbs: ["get", "list", "watch"]
+  - nonResourceURLs: ["/metrics"]
+    verbs: ["get"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+  - kind: ServiceAccount
+    name: prometheus
+    namespace: monitoring

monitoring/prometheus-service.yaml

@@ -0,0 +1,16 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app: prometheus
+spec:
+  type: ClusterIP
+  ports:
+    - port: 9090
+      targetPort: 9090
+      protocol: TCP
+      name: web
+  selector:
+    app: prometheus