categraf/k8s/deployment-etcd-http.yaml

---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
  annotations: {}
  labels:
    app: n9e
    component: categraf
  name: categraf-role
rules:
  - apiGroups: [""]
    resources:
      - nodes
      - nodes/metrics
      - services
      - endpoints
      - pods
    verbs: ["get", "list", "watch"]
  - apiGroups:
      - extensions
      - networking.k8s.io
    resources:
      - ingresses
    verbs: ["get", "list", "watch"]
  - nonResourceURLs: ["/metrics", "/metrics/cadvisor"]
    verbs: ["get"]
---
apiVersion: v1
kind: ServiceAccount
metadata:
  annotations: {}
  labels:
    app: n9e
    component: categraf
  name: categraf-serviceaccount
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
  annotations: {}
  labels:
    app: n9e
    component: categraf
  name: categraf-rolebinding
roleRef:
  apiGroup: rbac.authorization.k8s.io
  kind: ClusterRole
  name: categraf-role
subjects:
- kind: ServiceAccount
  name: categraf-serviceaccount
  namespace: ${CATEGRAF_NAMESPACE}
---
kind: ConfigMap
metadata:
  name: categraf-config
apiVersion: v1
data:
  config.toml: |
    [global]
    # whether print configs
    print_configs = true

    # add label(agent_hostname) to series
    # "" -> auto detect hostname
    # "xx" -> use specified string xx
    # "$hostname" -> auto detect hostname
    # "$ip" -> auto detect ip
    # "$hostname-$ip" -> auto detect hostname and ip to replace the vars
    hostname = "$HOSTNAME"

    # will not add label(agent_hostname) if true
    omit_hostname = false

    # s | ms
    precision = "ms"

    # global collect interval
    interval = 15

    # [global.labels]
    # region = "shanghai"
    # env = "localhost"

    [writer_opt]
    # default: 2000
    batch = 2000
    # channel(as queue) size
    chan_size = 10000

    [[writers]]
    url = "http://${NSERVER_SERVICE_WITH_PORT}/prometheus/v1/write"

    # Basic auth username
    basic_auth_user = ""

    # Basic auth password
    basic_auth_pass = ""

    # timeout settings, unit: ms
    timeout = 5000
    dial_timeout = 2500
    max_idle_conns_per_host = 100    
  prometheus.toml: |
    [prometheus]
    enable = true
    scrape_config_file="/opt/categraf/scrape/in_cluster_scrape.yaml"
    ## log level, debug warn info error
    log_level="info"
    ## wal reserve time duration, default value is 2 hour
    # wal_min_duration=2    
---
kind: ConfigMap
metadata:
  name: scrape-config
apiVersion: v1
data:
  in_cluster_scrape.yaml: |
    global:
      scrape_interval: 15s
      #external_labels:
      #  cluster: test
      #  replica: 0
    scrape_configs:
      - job_name: "apiserver"
        metrics_path: "/metrics"
        kubernetes_sd_configs:
          - role: endpoints
        scheme: https
        tls_config:
          insecure_skip_verify: true
        authorization:
          credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
          - source_labels:
              [
                __meta_kubernetes_namespace,
                __meta_kubernetes_service_name,
                __meta_kubernetes_endpoint_port_name,
              ]
            action: keep
            regex: default;kubernetes;https

      - job_name: "controller-manager"
        metrics_path: "/metrics"
        kubernetes_sd_configs:
          - role: endpoints
        scheme: https
        tls_config:
          insecure_skip_verify: true
        authorization:
          credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
          - source_labels:
              [
                __meta_kubernetes_namespace,
                __meta_kubernetes_service_name,
                __meta_kubernetes_endpoint_port_name,
              ]
            action: keep
            regex: kube-system;kube-controller-manager;https

      - job_name: "scheduler"
        metrics_path: "/metrics"
        kubernetes_sd_configs:
          - role: endpoints
        scheme: https
        tls_config:
          insecure_skip_verify: true
        authorization:
          credentials_file: /var/run/secrets/kubernetes.io/serviceaccount/token
        relabel_configs:
          - source_labels:
              [
                __meta_kubernetes_namespace,
                __meta_kubernetes_service_name,
                __meta_kubernetes_endpoint_port_name,
              ]
            action: keep
            regex: kube-system;kube-scheduler;https

      - job_name: "etcd"
        metrics_path: "/metrics"
        kubernetes_sd_configs:
          - role: endpoints
        scheme: http
        relabel_configs:
          - source_labels:
              [
                __meta_kubernetes_namespace,
                __meta_kubernetes_service_name,
                __meta_kubernetes_endpoint_port_name,
              ]
            action: keep
            regex: kube-system;etcd;http

      - job_name: "coredns"
        metrics_path: "/metrics"
        kubernetes_sd_configs:
          - role: endpoints
        scheme: http
        relabel_configs:
          - source_labels:
              [
              __meta_kubernetes_namespace,
              __meta_kubernetes_service_name,
              __meta_kubernetes_endpoint_port_name,
              ]
            action: keep
            regex: kube-system;kube-dns;metrics

    remote_write:
      - url: 'http://${NSERVER_SERVICE_WITH_PORT}/prometheus/v1/write'    
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: n9e
    component: categraf
  name: nightingale-categraf
spec:
  replicas: 1
  selector:
    matchLabels:
      app: n9e
      component: categraf
  template:
    metadata:
      labels:
        app: n9e
        component: categraf
    spec:
      containers:
      - env:
        - name: TZ
          value: Asia/Shanghai
        - name: HOSTNAME
          valueFrom:
            fieldRef:
              apiVersion: v1
              fieldPath: spec.nodeName
        - name: HOSTIP
          valueFrom:
            fieldRef:
              apiVersion: v1
              fieldPath: status.hostIP
        image: flashcatcloud/categraf:latest
        imagePullPolicy: IfNotPresent
        name: categraf
        command: ["/usr/bin/categraf"]
        args: ["-configs", "/opt/categraf/conf"]
        resources: {}
        terminationMessagePath: /dev/termination-log
        terminationMessagePolicy: File
        volumeMounts:
        - mountPath: /opt/categraf/conf
          name: categraf-config
        - mountPath: /opt/categraf/scrape
          name: scrape-config
      dnsPolicy: ClusterFirst
      hostNetwork: false
      restartPolicy: Always
      schedulerName: default-scheduler
      securityContext: {}
      serviceAccountName: categraf-serviceaccount
      terminationGracePeriodSeconds: 30
      tolerations:
      - effect: NoSchedule
        operator: Exists
      volumes:
      - configMap:
          defaultMode: 420
          name: categraf-config
        name: categraf-config
      - configMap:
          defaultMode: 420
          name: scrape-config
        name: scrape-config