apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: terway-metric-proxy
  namespace: kube-system
spec:
  template:
    metadata:
      labels:
        app: terway-metric-proxy
      annotations:
        scheduler.alpha.kubernetes.io/critical-pod: ''
    spec:
      nodeSelector:
        beta.kubernetes.io/arch: amd64
      tolerations:
      - operator: "Exists"
      hostNetwork: true
      containers:
      - name: proxy
        image: alpine/socat
        command: [ "socat", "-d", "-d", "TCP4-LISTEN:15432,fork", "UNIX-CONNECT:/var/run/eni/eni_debug.socket" ]
        volumeMounts:
        - name: terway-metric
          mountPath: /var/run/eni/
      volumes:
      - name: terway-metric
        hostPath:
          path: /var/run/eni/

---
# namespace
apiVersion: v1
kind: Namespace
metadata:
  name: monitoring-terway
---
# rbac
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-k8s
  namespace: monitoring-terway
---
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: [""]
  resources:
  - configmaps
  verbs: ["get"]
- nonResourceURLs: ["/metrics"]
  verbs: ["get"]
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: prometheus-k8s
  namespace: monitoring-terway
---
# config
apiVersion: v1
data:
  prometheus.yaml: |
    global:
      scrape_interval: 10s
      scrape_timeout: 10s
      evaluation_interval: 10s
    rule_files:
      - "/etc/prometheus-rules/*.rules"
    scrape_configs:
      - job_name: terway-metric
        scrape_interval: 1m
        scrape_timeout: 10s
        metrics_path: /metrics
        scheme: http
        kubernetes_sd_configs:
        - role: pod
        relabel_configs:
        - source_labels: [__meta_kubernetes_pod_label_app]
          regex: terway-metric-proxy
          replacement: $1
          action: keep
        - source_labels: [__meta_kubernetes_namespace]
          regex: kube-system
          action: keep
        - source_labels: [__address__]
          separator: ;
          regex: (.*)
          target_label: __address__
          replacement: $1:15432
          action: replace
        - separator: ;
          regex: __meta_kubernetes_pod_(.+)
          replacement: $1
          action: labelmap
kind: ConfigMap
metadata:
  creationTimestamp: null
  name: prometheus-core
  namespace: monitoring-terway

---
# rule
apiVersion: v1
data:
  cpu-usage.rules: |
    ALERT NodeCPUUsage
      IF (100 - (avg by (instance) (irate(node_cpu{name="node-exporter",mode="idle"}[5m])) * 100)) > 75
      FOR 2m
      LABELS {
        severity="page"
      }
      ANNOTATIONS {
        SUMMARY = "{{$labels.instance}}: High CPU usage detected",
        DESCRIPTION = "{{$labels.instance}}: CPU usage is above 75% (current value is: {{ $value }})"
      }
  instance-availability.rules: |
    ALERT InstanceDown
      IF up == 0
      FOR 1m
      LABELS { severity = "page" }
      ANNOTATIONS {
        summary = "Instance {{ $labels.instance }} down",
        description = "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 1 minute.",
      }
  low-disk-space.rules: |
    ALERT NodeLowRootDisk
      IF ((node_filesystem_size{mountpoint="/root-disk"} - node_filesystem_free{mountpoint="/root-disk"} ) / node_filesystem_size{mountpoint="/root-disk"} * 100) > 75
      FOR 2m
      LABELS {
        severity="page"
      }
      ANNOTATIONS {
        SUMMARY = "{{$labels.instance}}: Low root disk space",
        DESCRIPTION = "{{$labels.instance}}: Root disk usage is above 75% (current value is: {{ $value }})"
      }
    ALERT NodeLowDataDisk
      IF ((node_filesystem_size{mountpoint="/data-disk"} - node_filesystem_free{mountpoint="/data-disk"} ) / node_filesystem_size{mountpoint="/data-disk"} * 100) > 75
      FOR 2m
      LABELS {
        severity="page"
      }
      ANNOTATIONS {
        SUMMARY = "{{$labels.instance}}: Low data disk space",
        DESCRIPTION = "{{$labels.instance}}: Data disk usage is above 75% (current value is: {{ $value }})"
      }
  mem-usage.rules: |
    ALERT NodeSwapUsage
      IF (((node_memory_SwapTotal-node_memory_SwapFree)/node_memory_SwapTotal)*100) > 75
      FOR 2m
      LABELS {
        severity="page"
      }
      ANNOTATIONS {
        SUMMARY = "{{$labels.instance}}: Swap usage detected",
        DESCRIPTION = "{{$labels.instance}}: Swap usage usage is above 75% (current value is: {{ $value }})"
      }
    ALERT NodeMemoryUsage
      IF (((node_memory_MemTotal-node_memory_MemFree-node_memory_Cached)/(node_memory_MemTotal)*100)) > 75
      FOR 2m
      LABELS {
        severity="page"
      }
      ANNOTATIONS {
        SUMMARY = "{{$labels.instance}}: High memory usage detected",
        DESCRIPTION = "{{$labels.instance}}: Memory usage is above 75% (current value is: {{ $value }})"
      }
kind: ConfigMap
metadata:
  creationTimestamp: null
  name: prometheus-rules
  namespace: monitoring-terway

---
# deploy
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: prometheus-terway
  namespace: monitoring-terway
  labels:
    app: prometheus-terway
spec:
  replicas: 1
  template:
    metadata:
      name: prometheus-terway
      labels:
        app: prometheus-terway
    spec:
      serviceAccountName: prometheus-k8s
      containers:
      - name: prometheus
        image: prom/prometheus:v1.7.0
        args:
        - '-storage.local.retention=12h'
        - '-storage.local.memory-chunks=500000'
        - '-config.file=/etc/prometheus/prometheus.yaml'
        ports:
        - name: webui
          containerPort: 9090
        volumeMounts:
        - name: config-volume
          mountPath: /etc/prometheus
        - name: rules-volume
          mountPath: /etc/prometheus-rules
      volumes:
      - name: config-volume
        configMap:
          name: prometheus-core
      - name: rules-volume
        configMap:
          name: prometheus-rules
---
# service
apiVersion: v1
kind: Service
metadata:
  name: prometheus-terway
  namespace: monitoring-terway
  labels:
    app: prometheus-terway
  annotations:
    service.beta.kubernetes.io/backend-type: eni
spec:
  ports:
  - name: http
    port: 9090
    protocol: TCP
    targetPort: 9090
  type: LoadBalancer
  selector:
    app: prometheus-terway