Prometheus Kubernetes Deployment

prometheus.yaml

---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    app: prometheus
    component: kube-state-metrics
  name: kube-state-metrics
  namespace: prometheus
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    app: prometheus
    component: alertmanager
  name: alertmanager
  namespace: prometheus
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    app: prometheus
    component: node-exporter
  name: node-exporter
  namespace: prometheus
---
apiVersion: v1
kind: ServiceAccount
metadata:
  labels:
    component: prometheus
    app: prometheus
  name: prometheus
  namespace: prometheus
---
apiVersion: v1
kind: ConfigMap
metadata:
  labels:
    component: alertmanager
    app: prometheus
  name: alertmanager-config
  namespace: prometheus
data:
  alertmanager.yml: |
    global: {}
    receivers:
    - name: default-receiver
    route:
      group_interval: 5m
      group_wait: 10s
      receiver: default-receiver
      repeat_interval: 3h
---
apiVersion: v1
kind: ConfigMap
metadata:
  labels:
    component: prometheus
    app: prometheus
  name: prometheus-config
  namespace: prometheus
data:
  alerting_rules.yml: |
    {}
  alerts: |
    {}
  prometheus.yml: |
    global:
      evaluation_interval: 1m
      scrape_interval: 1m
      scrape_timeout: 10s
    rule_files:
    - /etc/config/recording_rules.yml
    - /etc/config/alerting_rules.yml
    - /etc/config/rules
    - /etc/config/alerts
    scrape_configs:
    - job_name: prometheus
      static_configs:
      - targets:
        - localhost:9090
    - bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      job_name: kubernetes-apiservers
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - action: keep
        regex: default;kubernetes;https
        source_labels:
        - __meta_kubernetes_namespace
        - __meta_kubernetes_service_name
        - __meta_kubernetes_endpoint_port_name
      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
      job_name: kubernetes-nodes
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - replacement: kubernetes.default.svc:443
        target_label: __address__
      - regex: (.+)
        replacement: /api/v1/nodes/$1/proxy/metrics
        source_labels:
        - __meta_kubernetes_node_name
        target_label: __metrics_path__
      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
      job_name: kubernetes-nodes-cadvisor
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - replacement: kubernetes.default.svc:443
        target_label: __address__
      - regex: (.+)
        replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
        source_labels:
        - __meta_kubernetes_node_name
        target_label: __metrics_path__
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
        insecure_skip_verify: true
    - job_name: kubernetes-service-endpoints
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_scrape
      - action: replace
        regex: (https?)
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_scheme
        target_label: __scheme__
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        - __address__
        - __meta_kubernetes_service_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_service_name
        target_label: kubernetes_name
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: kubernetes_node
    - job_name: kubernetes-service-endpoints-slow
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_scrape_slow
      - action: replace
        regex: (https?)
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_scheme
        target_label: __scheme__
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        - __address__
        - __meta_kubernetes_service_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_service_name
        target_label: kubernetes_name
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_node_name
        target_label: kubernetes_node
      scrape_interval: 5m
      scrape_timeout: 30s
    - honor_labels: true
      job_name: prometheus-pushgateway
      kubernetes_sd_configs:
      - role: service
      relabel_configs:
      - action: keep
        regex: pushgateway
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_probe
    - job_name: kubernetes-services
      kubernetes_sd_configs:
      - role: service
      metrics_path: /probe
      params:
        module:
        - http_2xx
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_service_annotation_prometheus_io_probe
      - source_labels:
        - __address__
        target_label: __param_target
      - replacement: blackbox
        target_label: __address__
      - source_labels:
        - __param_target
        target_label: instance
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - source_labels:
        - __meta_kubernetes_service_name
        target_label: kubernetes_name
    - job_name: kubernetes-pods
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_scrape
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        - __address__
        - __meta_kubernetes_pod_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: kubernetes_pod_name
    - job_name: kubernetes-pods-slow
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_scrape_slow
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        - __address__
        - __meta_kubernetes_pod_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: kubernetes_pod_name
      scrape_interval: 5m
      scrape_timeout: 30s
    alerting:
      alertmanagers:
      - kubernetes_sd_configs:
          - role: pod
        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]
          regex: prometheus
          action: keep
        - source_labels: [__meta_kubernetes_pod_label_app]
          regex: prometheus
          action: keep
        - source_labels: [__meta_kubernetes_pod_label_component]
          regex: alertmanager
          action: keep
        - source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_probe]
          regex: .*
          action: keep
        - source_labels: [__meta_kubernetes_pod_container_port_number]
          regex:
          action: drop
  recording_rules.yml: |
    {}
  rules: |
    {}
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
  name: kube-state-metrics
  labels:
    component: kube-state-metrics
    app: prometheus
rules:
- apiGroups: ["certificates.k8s.io"]
  resources:
  - certificatesigningrequests
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - configmaps
  verbs: ["list", "watch"]
- apiGroups: ["batch"]
  resources:
  - cronjobs
  verbs: ["list", "watch"]
- apiGroups: ["extensions", "apps"]
  resources:
  - daemonsets
  verbs: ["list", "watch"]
- apiGroups: ["extensions", "apps"]
  resources:
  - deployments
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - endpoints
  verbs: ["list", "watch"]
- apiGroups: ["autoscaling"]
  resources:
  - horizontalpodautoscalers
  verbs: ["list", "watch"]
- apiGroups: ["extensions", "networking.k8s.io"]
  resources:
  - ingresses
  verbs: ["list", "watch"]
- apiGroups: ["batch"]
  resources:
  - jobs
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - limitranges
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - namespaces
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - nodes
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - persistentvolumeclaims
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - persistentvolumes
  verbs: ["list", "watch"]
- apiGroups: ["policy"]
  resources:
    - poddisruptionbudgets
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - pods
  verbs: ["list", "watch"]
- apiGroups: ["extensions", "apps"]
  resources:
  - replicasets
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - replicationcontrollers
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - resourcequotas
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - secrets
  verbs: ["list", "watch"]
- apiGroups: [""]
  resources:
  - services
  verbs: ["list", "watch"]
- apiGroups: ["apps"]
  resources:
  - statefulsets
  verbs: ["list", "watch"]
- apiGroups: ["storage.k8s.io"]
  resources:
    - storageclasses
  verbs: ["list", "watch"]
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
  labels:
    component: alertmanager
    app: prometheus
  name: alertmanager
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRole
metadata:
  labels:
    component: prometheus
    app: prometheus
  name: prometheus
rules:
  - apiGroups:
      - ""
    resources:
      - nodes
      - nodes/proxy
      - nodes/metrics
      - services
      - endpoints
      - pods
      - ingresses
      - configmaps
    verbs:
      - get
      - list
      - watch
  - apiGroups:
      - "extensions"
    resources:
      - ingresses/status
      - ingresses
    verbs:
      - get
      - list
      - watch
  - nonResourceURLs:
      - "/metrics"
    verbs:
      - get
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
  labels:
    component: kube-state-metrics
    app: prometheus
  name: kube-state-metrics
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: kube-state-metrics
subjects:
- kind: ServiceAccount
  name: kube-state-metrics
  namespace: prometheus
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
  labels:
    component: alertmanager
    app: prometheus
  name: alertmanager
subjects:
  - kind: ServiceAccount
    name: alertmanager
    namespace: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: alertmanager
---
apiVersion: rbac.authorization.k8s.io/v1beta1
kind: ClusterRoleBinding
metadata:
  labels:
    component: prometheus
    app: prometheus
  name: prometheus
subjects:
  - kind: ServiceAccount
    name: prometheus
    namespace: prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: prometheus
---
apiVersion: v1
kind: Service
metadata:
  name: kube-state-metrics
  namespace: prometheus
  labels:
    app: prometheus
    component: kube-state-metrics
  annotations:
    prometheus.io/scrape: 'true'
spec:
  type: "ClusterIP"
  ports:
  - name: "http"
    protocol: TCP
    port: 8080
    targetPort: 8080
  selector:
    component: kube-state-metrics
    app: prometheus
---
apiVersion: v1
kind: Service
metadata:
  labels:
    component: alertmanager
    app: prometheus
  name: alertmanager
  namespace: prometheus
spec:
  ports:
    - name: http
      port: 80
      protocol: TCP
      targetPort: 9093
  selector:
    component: alertmanager
    app: prometheus
  sessionAffinity: None
  type: "ClusterIP"
---
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: "true"
  labels:
    component: node-exporter
    app: prometheus
  name: node-exporter
  namespace: prometheus
spec:
  clusterIP: None
  ports:
    - name: metrics
      port: 9100
      protocol: TCP
      targetPort: 9100
  selector:
    component: node-exporter
    app: prometheus
  type: "ClusterIP"
---
apiVersion: v1
kind: Service
metadata:
  labels:
    component: prometheus
    app: prometheus
  name: prometheus
  namespace: prometheus
spec:
  ports:
    - name: http
      port: 80
      protocol: TCP
      targetPort: 9090
  selector:
    component: prometheus
    app: prometheus
  sessionAffinity: None
  type: "ClusterIP"
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  labels:
    component: node-exporter
    app: prometheus
  name: node-exporter
  namespace: prometheus
spec:
  selector:
    matchLabels:
      component: node-exporter
      app: prometheus
  updateStrategy:
    type: RollingUpdate
  template:
    metadata:
      labels:
        component: node-exporter
        app: prometheus
    spec:
      tolerations:
        - operator: Exists
          effect: NoSchedule
      serviceAccountName: node-exporter
      containers:
        - name: node-exporter
          image: "prom/node-exporter:v0.18.1"
          imagePullPolicy: "IfNotPresent"
          args:
            - --path.procfs=/host/proc
            - --path.sysfs=/host/sys
          ports:
            - name: metrics
              containerPort: 9100
              hostPort: 9100
          resources:
            {}
          volumeMounts:
            - name: proc
              mountPath: /host/proc
              readOnly:  true
            - name: sys
              mountPath: /host/sys
              readOnly: true
      hostNetwork: true
      hostPID: true
      volumes:
        - name: proc
          hostPath:
            path: /proc
        - name: sys
          hostPath:
            path: /sys
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: kube-state-metrics
  namespace: prometheus
  labels:
    app: prometheus
    component: kube-state-metrics
spec:
  selector:
    matchLabels:
      app: prometheus
      component: kube-state-metrics
  replicas: 1
  template:
    metadata:
      labels:
        app: prometheus
        component: kube-state-metrics
    spec:
      hostNetwork: false
      serviceAccountName: kube-state-metrics
      securityContext:
        fsGroup: 65534
        runAsUser: 65534
      containers:
      - name: kube-state-metrics
        args:
        - --collectors=certificatesigningrequests
        - --collectors=configmaps
        - --collectors=cronjobs
        - --collectors=daemonsets
        - --collectors=deployments
        - --collectors=endpoints
        - --collectors=horizontalpodautoscalers
        - --collectors=ingresses
        - --collectors=jobs
        - --collectors=limitranges
        - --collectors=namespaces
        - --collectors=nodes
        - --collectors=persistentvolumeclaims
        - --collectors=persistentvolumes
        - --collectors=poddisruptionbudgets
        - --collectors=pods
        - --collectors=replicasets
        - --collectors=replicationcontrollers
        - --collectors=resourcequotas
        - --collectors=secrets
        - --collectors=services
        - --collectors=statefulsets
        - --collectors=storageclasses
        imagePullPolicy: IfNotPresent
        image: "quay.io/coreos/kube-state-metrics:v1.9.5"
        ports:
        - containerPort: 8080
        livenessProbe:
          httpGet:
            path: /healthz
            port: 8080
          initialDelaySeconds: 5
          timeoutSeconds: 5
        readinessProbe:
          httpGet:
            path: /
            port: 8080
          initialDelaySeconds: 5
          timeoutSeconds: 5
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    component: alertmanager
    app: prometheus
  name: alertmanager
  namespace: prometheus
spec:
  selector:
    matchLabels:
      component: alertmanager
      app: prometheus
  replicas: 1
  template:
    metadata:
      labels:
        component: alertmanager
        app: prometheus
    spec:
      serviceAccountName: alertmanager
      containers:
        - name: alertmanager
          image: "prom/alertmanager:v0.20.0"
          imagePullPolicy: "IfNotPresent"
          env:
            - name: POD_IP
              valueFrom:
                fieldRef:
                  apiVersion: v1
                  fieldPath: status.podIP
          args:
            - --config.file=/etc/config/alertmanager.yml
            - --storage.path=/data
            - --cluster.advertise-address=$(POD_IP):6783
            - --web.external-url=http://localhost:9093
          ports:
            - containerPort: 9093
          readinessProbe:
            httpGet:
              path: /-/ready
              port: 9093
            initialDelaySeconds: 30
            timeoutSeconds: 30
          resources:
            {}
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
            - name: storage-volume
              mountPath: "/data"
              subPath: ""
        - name: alertmanager-configmap-reload
          image: "jimmidyson/configmap-reload:v0.3.0"
          imagePullPolicy: "IfNotPresent"
          args:
            - --volume-dir=/etc/config
            - --webhook-url=http://127.0.0.1:9093/-/reload
          resources:
            {}
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
              readOnly: true
      securityContext:
        fsGroup: 65534
        runAsGroup: 65534
        runAsNonRoot: true
        runAsUser: 65534
      volumes:
        - name: config-volume
          configMap:
            name: alertmanager-config
        - name: storage-volume
          emptyDir: {}
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    component: prometheus
    app: prometheus
  name: prometheus
  namespace: prometheus
spec:
  selector:
    matchLabels:
      component: prometheus
      app: prometheus
  replicas: 1
  template:
    metadata:
      labels:
        component: prometheus
        app: prometheus
    spec:
      serviceAccountName: prometheus
      containers:
        - name: prometheus-configmap-reload
          image: "jimmidyson/configmap-reload:v0.3.0"
          imagePullPolicy: "IfNotPresent"
          args:
            - --volume-dir=/etc/config
            - --webhook-url=http://127.0.0.1:9090/-/reload
          resources:
            {}
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
              readOnly: true
        - name: prometheus
          image: "prom/prometheus:v2.16.0"
          imagePullPolicy: "IfNotPresent"
          args:
            - --storage.tsdb.retention.time=15d
            - --config.file=/etc/config/prometheus.yml
            - --storage.tsdb.path=/data
            - --web.console.libraries=/etc/prometheus/console_libraries
            - --web.console.templates=/etc/prometheus/consoles
            - --web.enable-lifecycle
          ports:
            - containerPort: 9090
          readinessProbe:
            httpGet:
              path: /-/ready
              port: 9090
            initialDelaySeconds: 30
            timeoutSeconds: 30
            failureThreshold: 3
            successThreshold: 1
          livenessProbe:
            httpGet:
              path: /-/healthy
              port: 9090
            initialDelaySeconds: 30
            timeoutSeconds: 30
            failureThreshold: 3
            successThreshold: 1
          resources:
            {}
          volumeMounts:
            - name: config-volume
              mountPath: /etc/config
            - name: storage-volume
              mountPath: /data
              subPath: ""
      securityContext:
        fsGroup: 65534
        runAsGroup: 65534
        runAsNonRoot: true
        runAsUser: 65534
      terminationGracePeriodSeconds: 300
      volumes:
        - name: config-volume
          configMap:
            name: prometheus-config
        - name: storage-volume
          emptyDir: {}
---
apiVersion: networking.k8s.io/v1beta1
kind: Ingress
metadata:
  name: prometheus
  namespace: prometheus
  labels:
    app: prometheus
    component: prometheus
spec:
  rules:
  - host: prometheus.apps.mdlwr.se
    http:
      paths:
      - path: /
        backend:
          serviceName: prometheus
          servicePort: 80
---
apiVersion: networking.k8s.io/v1beta1
kind: Ingress
metadata:
  name: alertmanager
  namespace: prometheus
  labels:
    app: prometheus
    component: alertmanager
spec:
  rules:
  - host: alertmanager.apps.mdlwr.se
    http:
      paths:
      - path: /
        backend:
          serviceName: alertmanager
          servicePort: 80