rancher-partner-charts/charts/avesha/kubeslice-controller/templates/prometheus.yaml

---
  {{ if .Values.kubeslice.prometheus.enabled}}
apiVersion: v1
data:
  prometheus.rules: |-
    groups:
    - name: Resource Quota violation alerts
      rules:
      - alert: Slice Resource Quota Violation
        expr: kubeslice_controller_slice_quota_violation > 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Slice Resource Usage Exceeded Quota"
          description: "The slice {{ "{{" }} $labels.slice_name}} has CPU usage {{ "{{" }} $labels.cpu}} and memory usage {{ "{{" }} $labels.memory}}: violated by {{ "{{" }} $labels.violated_resource_type}}"
      - alert: Cluster Resource Quota Violation
        expr: kubeslice_controller_cluster_quota_violation > 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Cluster Resource Usage Exceeded Quota"
          description: "The cluster {{ "{{" }} $labels.cluster_name}} has CPU usage {{ "{{" }} $labels.cpu}} and memory usage {{ "{{" }} $labels.memory}}: violated by {{ "{{" }} $labels.violated_resource_type}}"
      - alert: Namespace Resource Quota Violation
        expr: kubeslice_controller_namespace_quota_violation > 0
        for: 1m
        labels:
          severity: critical
        annotations:
          summary: "Namespace Resource Usage Exceeded Quota"
          description: "The namespace {{ "{{" }}$labels.namespace}} has CPU usage {{ "{{" }}$labels.cpu}} and memory usage {{ "{{" }}$labels.memory}}: violated by {{ "{{" }}$labels.violated_resource_type}}"    
  prometheus.yml: |-
    global:
      scrape_interval: 5s
      evaluation_interval: 5s
    rule_files:
      - /etc/prometheus/prometheus.rules
    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    
kind: ConfigMap
metadata:
  labels:
    name: prometheus-server-conf
  name: kubeslice-controller-prometheus-server-conf
  namespace: kubeslice-controller
  {{ end }}

---
  {{ if .Values.kubeslice.prometheus.enabled}}
apiVersion: v1
kind: Service
metadata:
  name: kubeslice-controller-prometheus-service
  namespace: kubeslice-controller
spec:
  ports:
    - port: 9090
      targetPort: 9090
  selector:
    app: prometheus-server
  type: ClusterIP
  {{ end }}

---
  {{ if .Values.kubeslice.prometheus.enabled}}
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: prometheus-server
  name: kubeslice-controller-prometheus
  namespace: kubeslice-controller
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus-server
  strategy:
    rollingUpdate:
      maxSurge: 1
      maxUnavailable: 0
    type: RollingUpdate
  template:
    metadata:
      labels:
        app: prometheus-server
    spec:
      containers:
        - args:
            - --config.file=/etc/prometheus/prometheus.yml
            - --storage.tsdb.path=/prometheus/
          image: prom/prometheus
          name: prometheus
          ports:
            - containerPort: 9090
          volumeMounts:
            - mountPath: /etc/prometheus/
              name: prometheus-config-volume
            - mountPath: /prometheus/
              name: prometheus-storage-volume
      volumes:
        - configMap:
            defaultMode: 420
            name: kubeslice-controller-prometheus-server-conf
          name: prometheus-config-volume
        - emptyDir: {}
          name: prometheus-storage-volume
  {{ end }}

---
  {{ if .Values.kubeslice.prometheus.enabled}}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  name: kubeslice-controller-prometheus
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: kubeslice-controller-prometheus
subjects:
  - kind: ServiceAccount
    name: default
    namespace: kubeslice-controller
  {{ end }}

---
  {{ if .Values.kubeslice.prometheus.enabled}}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  name: kubeslice-controller-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
  {{ end }}
---
  {{ if .Values.kubeslice.prometheus.enabled}}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  labels:
    app.kubernetes.io/name: kube-state-metrics
    app.kubernetes.io/version: v1.8.0
  name: kubeslice-controller-kube-state-metrics
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: kubeslice-controller-kube-state-metrics
subjects:
  - kind: ServiceAccount
    name: kube-state-metrics
    namespace: kube-system
  {{ end }}