k8b部署prometheus+grafana

来源：
https://juejin.im/post/5c36054251882525a50bbdf0
https://github.com/redhatxl/k8s-prometheus-grafana

Prometheus

master/node节点环境部署

git clone https://github.com/redhatxl/k8s-prometheus-grafana.git

在node节点下载监控所需镜像（在所有节点也下载了）

docker pull prom/node-exporter
docker pull prom/prometheus:v2.0.0
docker pull grafana/grafana:4.2.0

采用daemonset方式部署node-exporter组件
kubectl create -f node-exporter.yaml

部署prometheus组件
rbac文件
kubectl create -f k8s-prometheus-grafana/prometheus/rbac-setup.yaml

以configmap的形式管理prometheus组件的配置文件
kubectl create -f k8s-prometheus-grafana/prometheus/configmap.yaml

Prometheus deployment 文件
kubectl create -f k8s-prometheus-grafana/prometheus/prometheus.deploy.yml

Prometheus service文件
kubectl create -f k8s-prometheus-grafana/prometheus/prometheus.svc.yml

部署grafana组件

grafana deployment配置文件
kubectl create -f k8s-prometheus-grafana/grafana/grafana-deploy.yaml
grafana service配置文件
kubectl create -f k8s-prometheus-grafana/grafana/grafana-svc.yaml

grafana ingress配置文件
kubectl create -f k8s-prometheus-grafana/grafana/grafana-ing.yaml

访问

 k get po -n kube-system   -owide
NAME                                 READY   STATUS    RESTARTS   AGE     IP                NODE         NOMINATED NODE   READINESS GATES
coredns-5c98db65d4-j2925             1/1     Running   4          2d23h   10.244.0.13       k8s-master   <none>           <none>
coredns-5c98db65d4-k2rcj             1/1     Running   4          2d23h   10.244.0.12       k8s-master   <none>           <none>
etcd-k8s-master                      1/1     Running   4          2d23h   192.168.190.140   k8s-master   <none>           <none>
grafana-core-6ff599bfdc-pbdzf        1/1     Running   0          99m     10.244.1.66       k8s-node1    <none>           <none>
kube-apiserver-k8s-master            1/1     Running   4          2d23h   192.168.190.140   k8s-master   <none>           <none>
kube-controller-manager-k8s-master   1/1     Running   4          2d23h   192.168.190.140   k8s-master   <none>           <none>
kube-flannel-ds-amd64-6rq62          1/1     Running   5          2d23h   192.168.190.140   k8s-master   <none>           <none>
kube-flannel-ds-amd64-ctmdz          1/1     Running   4          2d23h   192.168.190.141   k8s-node1    <none>           <none>
kube-proxy-kmgc5                     1/1     Running   4          2d23h   192.168.190.140   k8s-master   <none>           <none>
kube-proxy-ss8jr                     1/1     Running   4          2d23h   192.168.190.141   k8s-node1    <none>           <none>
kube-scheduler-k8s-master            1/1     Running   4          2d23h   192.168.190.140   k8s-master   <none>           <none>
node-exporter-fsfkb                  1/1     Running   0          102m    10.244.1.64       k8s-node1    <none>           <none>
prometheus-68545d4fd8-hnltb          1/1     Running   0          101m    10.244.1.65       k8s-node1    <none>           <none>

k get svc  -n kube-system   
NAME            TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                  AGE
grafana         NodePort    10.106.70.200    <none>        3000:30592/TCP           98m
kube-dns        ClusterIP   10.96.0.10       <none>        53/UDP,53/TCP,9153/TCP   2d23h
node-exporter   NodePort    10.102.245.168   <none>        9100:31672/TCP           101m
prometheus      NodePort    10.101.205.6     <none>        9090:30003/TCP           99m
 

访问prometheus ：
任一个节点的物理地址+暴露的端口（9090:30003/TCP ）

访问grafana:
任一个节点的物理地址+暴露的端口（3000:30592/TCP）
输入密码登录：
admin/admin

添加数据源
类型：prometheus
url: http://prometheus:9090

save& test

导入模板
模板下载地址https:///dashboards/315， 或在线导入315

各配置文件

daemonset方式部署的node-exporter

cat   node-exporter.yaml 
---
apiVersion: extensions/v1beta1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: kube-system
  labels:
    k8s-app: node-exporter
spec:
  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

prometheus的rbac-setup.yaml

 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

prometheus的configmap

 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

Prometheus deployment

cat  prometheus.deploy.yml        
---
apiVersion: apps/v1beta2
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   

prometheus的service

cat  prometheus.svc.yml 
---
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

grafana-deployment配置文件

cat grafana-deploy.yaml 
apiVersion: extensions/v1beta1
kind: Deployment
metadata:
  name: grafana-core
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  replicas: 1
  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: {}

grafana service

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

grafana ingress

 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

来源：https://www.cnblogs.com/g2thend/p/11856658.html