环境介绍

# 关于k8s的集群部署，可以查看我其他博客
[root@master ~]# cat /etc/redhat-release
CentOS Linux release 7.6.1810 (Core)
[root@master ~]# uname -r
4.4.235-1.el7.elrepo.x86_64
[root@master grafana]# docker --version
Docker version 19.03.8, build afacb8b7f0
[root@master ~]# kubectl get nodes
NAME              STATUS                     ROLES    AGE   VERSION
192.168.131.150   Ready,SchedulingDisabled   master   53m   v1.18.3
192.168.131.151   Ready                      node     52m   v1.18.3
192.168.131.152   Ready                      node     52m   v1.18.3

[root@master ~]# cd /etc/kubernetes/
[root@master kubernetes]# ls
[root@master kubernetes]# mkdir prometheusGrafana
[root@master kubernetes]# cd prometheusGrafana/

创建node-exporter

[root@master prometheusGrafana]# cat node-exporter.yaml
---
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: kube-system
  labels:
    k8s-app: node-exporter
spec:
  selector:
    matchLabels:
      k8s-app: node-exporter
  template:
    metadata:
      labels:
        k8s-app: node-exporter
    spec:
      containers:
      - image: prom/node-exporter
        name: node-exporter
        ports:
        - containerPort: 9100
          protocol: TCP
          name: http
---
apiVersion: v1
kind: Service
metadata:
  labels:
    k8s-app: node-exporter
  name: node-exporter
  namespace: kube-system
spec:
  ports:
  - name: http
    port: 9100
    nodePort: 31672
    protocol: TCP
  type: NodePort
  selector:
    k8s-app: node-exporter

[root@master prometheusGrafana]# kubectl label nodes 192.168.131.151 k8s-app=node-exporter
node/192.168.131.151 labeled
[root@master prometheusGrafana]# kubectl apply -f node-exporter.yaml
daemonset.apps/node-exporter created
service/node-exporter created

创建Prometheus

[root@master prometheusGrafana]# mkdir ./{prometheus,grafana}
[root@master prometheusGrafana]# cd prometheus/
[root@master prometheus]# ls
configmap.yaml  prometheus.deploy.yaml  prometheus.svc.yaml  rbac-setup.yaml

[root@master prometheus]# cat configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-config
  namespace: kube-system
data:
  prometheus.yml: |
    global:
      scrape_interval:     15s
      evaluation_interval: 15s
    scrape_configs:

    - job_name: 'kubernetes-apiservers'
      kubernetes_sd_configs:
      - role: endpoints
      scheme: https
      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, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
        action: keep
        regex: default;kubernetes;https

    - job_name: 'kubernetes-nodes'
      kubernetes_sd_configs:
      - role: node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics

    - job_name: 'kubernetes-cadvisor'
      kubernetes_sd_configs:
      - role: node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor

    - job_name: 'kubernetes-service-endpoints'
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        action: replace
        target_label: __scheme__
        regex: (https?)
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name

    - job_name: 'kubernetes-services'
      kubernetes_sd_configs:
      - role: service
      metrics_path: /probe
      params:
        module: [http_2xx]
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
        action: keep
        regex: true
      - source_labels: [__address__]
        target_label: __param_target
      - target_label: __address__
        replacement: blackbox-exporter.example.com:9115
      - 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-ingresses'
      kubernetes_sd_configs:
      - role: ingress
      relabel_configs:
      - source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_ingress_scheme,__address__,__meta_kubernetes_ingress_path]
        regex: (.+);(.+);(.+)
        replacement: ${1}://${2}${3}
        target_label: __param_target
      - target_label: __address__
        replacement: blackbox-exporter.example.com:9115
      - source_labels: [__param_target]
        target_label: instance
      - action: labelmap
        regex: __meta_kubernetes_ingress_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_ingress_name]
        target_label: kubernetes_name

    - 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

[root@master prometheus]# cat prometheus.deploy.yaml
---
apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    name: prometheus-deployment
  name: prometheus
  namespace: kube-system
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
  template:
    metadata:
      labels:
        app: prometheus
    spec:
      containers:
      - image: prom/prometheus:v2.0.0
        name: prometheus
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"
        - "--storage.tsdb.retention=24h"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: "/prometheus"
          name: data
        - mountPath: "/etc/prometheus"
          name: config-volume
        resources:
          requests:
            cpu: 100m
            memory: 100Mi
          limits:
            cpu: 500m
            memory: 2500Mi
      serviceAccountName: prometheus
      volumes:
      - name: data
        emptyDir: {}
      - name: config-volume
        configMap:
          name: prometheus-config

[root@master prometheus]# cat prometheus.svc.yaml
---
kind: Service
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus
  namespace: kube-system
spec:
  type: NodePort
  ports:
  - port: 9090
    targetPort: 9090
    nodePort: 30003
  selector:
    app: prometheus

[root@master prometheus]# cat rbac-setup.yaml
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: v1
kind: ServiceAccount
metadata:
  name: prometheus
  namespace: kube-system
---
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
  namespace: kube-system

[root@master prometheus]# kubectl apply -f .
configmap/prometheus-config created
deployment.apps/prometheus created
service/prometheus created
clusterrole.rbac.authorization.k8s.io/prometheus created
serviceaccount/prometheus created
clusterrolebinding.rbac.authorization.k8s.io/prometheus created

创建Grafana

[root@master prometheus]# cd ../grafana/
[root@master grafana]# ls
grafana-deploy.yaml  grafana-ing.yaml  grafana-svc.yaml
[root@master grafana]# kubectl label nodes 192.168.131.151 app=grafana
node/192.168.131.151 labeled

[root@master grafana]# cat grafana-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana-core
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  replicas: 2
  selector:
    matchLabels:
      app: grafana
  template:
    metadata:
      labels:
        app: grafana
        component: core
    spec:
      containers:
      - image: grafana/grafana:4.2.0
        name: grafana-core
        imagePullPolicy: IfNotPresent
        # env:
        resources:
          # keep request = limit to keep this container in guaranteed class
          limits:
            cpu: 100m
            memory: 100Mi
          requests:
            cpu: 100m
            memory: 100Mi
        env:
          # The following env variables set up basic auth twith the default admin user and admin password.
          - name: GF_AUTH_BASIC_ENABLED
            value: "true"
          - name: GF_AUTH_ANONYMOUS_ENABLED
            value: "false"
          # - name: GF_AUTH_ANONYMOUS_ORG_ROLE
          #   value: Admin
          # does not really work, because of template variables in exported dashboards:
          # - name: GF_DASHBOARDS_JSON_ENABLED
          #   value: "true"
        readinessProbe:
          httpGet:
            path: /login
            port: 3000
          # initialDelaySeconds: 30
          # timeoutSeconds: 1
        volumeMounts:
        - name: grafana-persistent-storage
          mountPath: /var
      volumes:
      - name: grafana-persistent-storage
        emptyDir: {}

[root@master grafana]# cat grafana-ing.yaml
apiVersion: extensions/v1beta1
kind: Ingress
metadata:
   name: grafana
   namespace: kube-system
spec:
   rules:
   - host: k8s.grafana
     http:
       paths:
       - path: /
         backend:
          serviceName: grafana
          servicePort: 3000

[root@master grafana]# cat grafana-svc.yaml
apiVersion: v1
kind: Service
metadata:
  name: grafana
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  type: NodePort
  ports:
    - port: 3000
  selector:
    app: grafana
    component: core

[root@master grafana]# kubectl apply -f .
deployment.apps/grafana-core created
ingress.extensions/grafana created
service/grafana created

测试

[root@master prometheusGrafana]# kubectl get svc -A
NAMESPACE     NAME                        TYPE        CLUSTER-IP      EXTERNAL-IP   PORT(S)                  AGE
default       kubernetes                  ClusterIP   10.68.0.1       <none>        443/TCP                  44m
kube-system   dashboard-metrics-scraper   ClusterIP   10.68.145.87    <none>        8000/TCP                 41m
kube-system   grafana                     NodePort    10.68.162.32    <none>        3000:26421/TCP           5m45s
kube-system   kube-dns                    ClusterIP   10.68.0.2       <none>        53/UDP,53/TCP,9153/TCP   41m
kube-system   kubernetes-dashboard        NodePort    10.68.47.65     <none>        443:32507/TCP            41m
kube-system   metrics-server              ClusterIP   10.68.127.89    <none>        443/TCP                  41m
kube-system   node-exporter               NodePort    10.68.108.115   <none>        9100:31672/TCP           26m
kube-system   prometheus                  NodePort    10.68.103.46    <none>        9090:30003/TCP           14m
# 浏览器访问：
http://192.168.131.150:31672            # 访问Metrics采集器
http://192.168.131.150:26421            # 访问grafana（默认用户名和密码都是admin）
http://192.168.131.150:30003/targets    # 访问Prometheus