monitoring.yaml

---
apiVersion: v1
kind: Namespace
metadata:
  name: 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: default
  namespace: monitoring
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-server-conf
  labels:
    name: prometheus-server-conf
  namespace: monitoring
data:
  prometheus.yml: |-
    global:
      scrape_interval: 5s
      evaluation_interval: 5s
    scrape_configs:    
      - 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
    
      - job_name: 'kubernetes-cadvisor'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
          insecure_skip_verify: true
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
        - target_label: __address__
          replacement: kubernetes.default.svc.cluster.local:443
        - source_labels: [__meta_kubernetes_node_name]
          regex: (.+)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
      - job_name: 'kubernetes-nodes'
        scheme: https
        tls_config:
          ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
          insecure_skip_verify: true
        bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        kubernetes_sd_configs:
        - role: node
        relabel_configs:
        - action: labelmap
          regex: __meta_kubernetes_node_label_(.+)
        - target_label: __address__
          replacement: kubernetes.default.svc.cluster.local:443
        - source_labels: [__meta_kubernetes_node_name]
          regex: (.+)
          target_label: __metrics_path__
          replacement: /api/v1/nodes/${1}/proxy/metrics
      - job_name: kube-proxy
        honor_labels: true
        kubernetes_sd_configs:
        - role: pod
        relabel_configs:
        - action: keep
          source_labels:
          - __meta_kubernetes_namespace
          - __meta_kubernetes_pod_name
          separator: '/'
          regex: 'kube-system/kube-proxy.+'
        - source_labels:
          - __address__
          action: replace
          target_label: __address__
          regex: (.+?)(\\:\\d+)?
          replacement: $1:10249
      - job_name: 'node-exporter'
        kubernetes_sd_configs:
          - role: endpoints
        relabel_configs:
          - source_labels: [__meta_kubernetes_endpoints_name]
            regex: 'node-exporter'
            action: keep
---          
apiVersion: v1
kind: Pod
metadata:
  name: prometheus
  namespace: monitoring
  labels:
    app: prometheus-server
spec:
  nodeSelector:
    node-role.kubernetes.io/control-plane: ""
  tolerations:
  - key: CriticalAddonsOnly
    operator: Exists
  - effect: NoSchedule
    key: node-role.kubernetes.io/master
  - effect: NoSchedule
    key: node-role.kubernetes.io/control-plane
  containers:
    - name: prometheus
      image: prom/prometheus:v2.26.0
      args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus/"
        - "--web.enable-admin-api"
      ports:
        - containerPort: 9090
      volumeMounts:
        - name: prometheus-config-volume
          mountPath: /etc/prometheus/
        - name: prometheus-storage-volume
          mountPath: /prometheus/
  volumes:
    - name: prometheus-config-volume
      configMap:
        defaultMode: 420
        name: prometheus-server-conf
    - name: prometheus-storage-volume
      emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: prometheus
  namespace: monitoring
  annotations:
    prometheus.io/scrape: 'true'
    prometheus.io/port:   '9090'
spec:
  selector:
    app: prometheus-server
  clusterIP: 10.96.0.20
  type: NodePort
  ports:
    - port: 9090
      nodePort: 30090
      targetPort: 9090
---
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-grafana-datasource
  namespace: monitoring
  labels:
    grafana_datasource: '1'
data:
  grafana.ini: |+

  datasource.yml: |-
    apiVersion: 1
    datasources:
    - name: Prometheus
      type: prometheus
      access: proxy
      orgId: 1
      url: http://prometheus.monitoring.svc.cluster.local:9090
---
apiVersion: v1
kind: Pod
metadata:
  labels:
    app: grafana
  name: grafana
  namespace: monitoring
spec:
  containers:
    - name: grafana
      image: grafana/grafana:latest
      imagePullPolicy: IfNotPresent
      ports:
        - containerPort: 3000
          name: http-grafana
          protocol: TCP
      volumeMounts:
        - name: grafana-config-volume
          mountPath: /etc/grafana/
  volumes:
    - name: grafana-config-volume
      configMap:
        name: prometheus-grafana-datasource
        items:
        - key: grafana.ini
          path: grafana.ini
        - key: datasource.yml
          path: provisioning/datasources/datasource.yml
---
apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: monitoring
spec:
  ports:
    - port: 3000
      nodePort: 30030
      protocol: TCP
      targetPort: http-grafana
  selector:
    app: grafana
  sessionAffinity: None
  type: NodePort
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    app: node-exporter
  name: node-exporter
  namespace: monitoring
spec:
  selector:
    matchLabels:
      app: node-exporter
  template:
    metadata:
      annotations:
        cluster-autoscaler.kubernetes.io/safe-to-evict: "true"
      labels:
        app: node-exporter
    spec:
      containers:
        - args:
            - --web.listen-address=0.0.0.0:9100
            - --path.procfs=/host/proc
            - --path.sysfs=/host/sys
          image: quay.io/prometheus/node-exporter:v1.8.2
          imagePullPolicy: IfNotPresent
          name: node-exporter
          ports:
            - containerPort: 9100
              hostPort: 9100
              name: metrics
              protocol: TCP
          resources:
            limits:
              cpu: 200m
              memory: 50Mi
            requests:
              cpu: 100m
              memory: 30Mi
          volumeMounts:
            - mountPath: /host/proc
              name: proc
              readOnly: true
            - mountPath: /host/sys
              name: sys
              readOnly: true
      hostNetwork: true
      hostPID: true
      restartPolicy: Always
      tolerations:
        - effect: NoSchedule
          operator: Exists
        - effect: NoExecute
          operator: Exists
      volumes:
        - hostPath:
            path: /proc
            type: ""
          name: proc
        - hostPath:
            path: /sys
            type: ""
          name: sys
---
apiVersion: v1
kind: Service
metadata:
  labels:
    app: node-exporter
  name: node-exporter
  namespace: monitoring
spec:
  ports:
    - name: node-exporter
      port: 9100
      protocol: TCP
      targetPort: 9100
  selector:
    app: node-exporter
  sessionAffinity: None
  type: ClusterIP