adding monitoring

infra/beszel-agent.yaml

@@ -22,7 +22,7 @@ spec:
             secretKeyRef:
               name: beszel-key
               key: SECRET-KEY
-        image: henrygd/beszel-agent:0.12.10
+        image: henrygd/beszel-agent:0.14.1
         imagePullPolicy: Always
         name: beszel-agent
         ports:

infra/beszel.yaml

@@ -17,13 +17,8 @@ spec:
     spec:
       containers:
         - name: beszel
-          image: ghcr.io/henrygd/beszel/beszel:0.12.10
+          image: ghcr.io/henrygd/beszel/beszel:14.1
           imagePullPolicy: Always
-          env:
-            - name: PUID
-              value: "1000"
-            - name: PGID
-              value: "1000"
           ports:
             - containerPort: 8090
               name: beszel-port

monitoring/grafana.yaml

@@ -0,0 +1,105 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  labels:
+    app: grafana
+  name: grafana
+  namespace: monitoring
+spec:
+  selector:
+    matchLabels:
+      app: grafana
+  template:
+    metadata:
+      labels:
+        app: grafana
+    spec:
+      securityContext:
+        fsGroup: 472
+        supplementalGroups:
+          - 0
+      containers:
+        - name: grafana
+          image: grafana/grafana:latest
+          imagePullPolicy: Always
+          ports:
+            - containerPort: 3000
+              name: http-grafana
+              protocol: TCP
+          readinessProbe:
+            failureThreshold: 3
+            httpGet:
+              path: /robots.txt
+              port: 3000
+              scheme: HTTP
+            initialDelaySeconds: 10
+            periodSeconds: 30
+            successThreshold: 1
+            timeoutSeconds: 2
+          livenessProbe:
+            failureThreshold: 3
+            initialDelaySeconds: 30
+            periodSeconds: 10
+            successThreshold: 1
+            tcpSocket:
+              port: 3000
+            timeoutSeconds: 1
+          resources:
+            requests:
+              cpu: 250m
+              memory: 750Mi
+          volumeMounts:
+            - mountPath: /var/lib/grafana
+              name: grafana-pv
+      volumes:
+        - name: grafana-pv
+          persistentVolumeClaim:
+            claimName: grafana-pvc
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: grafana-pvc
+  namespace: monitoring
+  annotations:
+    nfs.io/storage-path: "grafana-data"
+spec:
+  storageClassName: "nfs-client"
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 1Gi
+---
+apiVersion: v1
+kind: Service
+metadata:
+  namespace: monitoring
+  name: grafana
+spec:
+  ports:
+    - port: 3000
+      protocol: TCP
+      targetPort: http-grafana
+  selector:
+    app: grafana
+  type: ClusterIP
+---
+apiVersion: networking.k8s.io/v1
+kind: Ingress
+metadata:
+  namespace: monitoring
+  name: grafana
+spec:
+  ingressClassName: nginx
+  rules:
+    - host: grafana.haven
+      http:
+        paths:
+          - path: /
+            pathType: Prefix
+            backend:
+              service:
+                name: grafana
+                port:
+                  number: 3000

monitoring/kube-state-metrics.yaml

@@ -0,0 +1,109 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: kube-state-metrics
+rules:
+  - apiGroups: [""]
+    resources:
+      - nodes
+      - pods
+      - services
+      - endpoints
+      - namespaces
+      - replicationcontrollers
+    verbs: ["list", "watch"]
+  - apiGroups: ["extensions", "apps"]
+    resources:
+      - daemonsets
+      - deployments
+      - replicasets
+      - statefulsets
+    verbs: ["list", "watch"]
+  - apiGroups: ["batch"]
+    resources:
+      - cronjobs
+      - jobs
+    verbs: ["list", "watch"]
+  - apiGroups: ["autoscaling"]
+    resources:
+      - horizontalpodautoscalers
+    verbs: ["list", "watch"]
+  - apiGroups: ["policy"]
+    resources:
+      - poddisruptionbudgets
+    verbs: ["list", "watch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources:
+      - storageclasses
+      - volumeattachments
+    verbs: ["list", "watch"]
+  - apiGroups: ["apps"]
+    resources:
+      - replicasets
+    verbs: ["list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: kube-state-metrics
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: kube-state-metrics
+subjects:
+  - kind: ServiceAccount
+    name: kube-state-metrics
+    namespace: monitoring
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+  labels:
+    app: kube-state-metrics
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app: kube-state-metrics
+  template:
+    metadata:
+      labels:
+        app: kube-state-metrics
+    spec:
+      serviceAccountName: kube-state-metrics
+      containers:
+        - name: kube-state-metrics
+          image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.13.0
+          ports:
+            - name: http-metrics
+              containerPort: 8080
+          resources:
+            requests:
+              cpu: 50m
+              memory: 64Mi
+            limits:
+              cpu: 200m
+              memory: 256Mi
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: kube-state-metrics
+  namespace: monitoring
+  labels:
+    app: kube-state-metrics
+spec:
+  ports:
+    - name: http-metrics
+      port: 8080
+      targetPort: http-metrics
+  selector:
+    app: kube-state-metrics

monitoring/nodeexporter.yaml

@@ -0,0 +1,56 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: node-exporter
+  namespace: monitoring
+  labels:
+    app: node-exporter
+spec:
+  selector:
+    matchLabels:
+      app: node-exporter
+  template:
+    metadata:
+      labels:
+        app: node-exporter
+    spec:
+      hostNetwork: true
+      containers:
+        - name: node-exporter
+          image: prom/node-exporter:latest
+          imagePullPolicy: Always
+          args:
+            - "--path.rootfs=/host"
+          ports:
+            - containerPort: 9100
+              hostPort: 9100
+              name: metrics
+              protocol: TCP
+          resources:
+            requests:
+              memory: "50Mi"
+              cpu: "100m"
+            limits:
+              memory: "100Mi"
+              cpu: "200m"
+          volumeMounts:
+            - name: host
+              mountPath: /host
+              readOnly: true
+      volumes:
+        - name: host
+          hostPath:
+            path: /
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: node-exporter
+  namespace: monitoring
+spec:
+  selector:
+    app: node-exporter
+  ports:
+    - name: metrics
+      port: 9100
+      targetPort: metrics

monitoring/prometheus.yaml

@@ -0,0 +1,130 @@
+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:latest
+          args:
+            - "--config.file=/etc/prometheus/prometheus.yml"
+            - "--storage.tsdb.path=/prometheus"
+            - "--storage.tsdb.retention.time=3d"
+            - "--web.enable-lifecycle"
+          ports:
+            - containerPort: 9090
+              name: web
+          volumeMounts:
+            - name: prometheus-config-volume
+              mountPath: /etc/prometheus
+            - name: prometheus-storage
+              mountPath: /prometheus
+          resources:
+            requests:
+              memory: "500Mi"
+              cpu: "200m"
+            limits:
+              memory: "1Gi"
+              cpu: "500m"
+      volumes:
+        - name: prometheus-config-volume
+          persistentVolumeClaim:
+            claimName: prometheus-pvc
+        - name: prometheus-storage
+          emptyDir:
+            medium: Memory
+            sizeLimit: 256Mi
+---
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: prometheus-pvc
+  namespace: monitoring
+  annotations:
+    nfs.io/storage-path: "prometheus-config"
+spec:
+  storageClassName: "nfs-client"
+  accessModes:
+    - ReadWriteOnce
+  resources:
+    requests:
+      storage: 1Gi
+---
+# Service URL - http://prometheus.monitoring.svc.cluster.local:9090
+apiVersion: v1
+kind: Service
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app: prometheus
+spec:
+  ports:
+    - name: web
+      port: 9090
+      targetPort: web
+  selector:
+    app: prometheus
+  type: ClusterIP
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app: prometheus
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app: prometheus
+rules:
+- apiGroups: [""]
+  resources:
+  - nodes
+  - nodes/proxy
+  - services
+  - endpoints
+  - pods
+  verbs: ["get", "list", "watch"]
+- apiGroups: ["extensions"]
+  resources:
+  - ingresses
+  verbs: ["get", "list", "watch"]
+- apiGroups: ["networking.k8s.io"]
+  resources:
+  - ingresses
+  verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: prometheus
+  namespace: monitoring
+  labels:
+    app: prometheus
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: prometheus
+subjects:
+- kind: ServiceAccount
+  name: prometheus
+  namespace: monitoring