第二十五章 Kubernetes部署Promethus集群资源监控

一、监控指标

#1.集群监控
1）节点资源利用率
2）节点数
3）运行的pods

#2.Pod监控
1）容器指标
2）应用程序

二、部署应用Promethus

1.创建promethus目录

[root@kubernetes-master-001 ~]# mkdir -p monitor && cd monitor/
[root@kubernetes-master-001 ~/monitor]# mkdir -p  promethus && cd promethus

2.创建deployment文件

[root@kubernetes-master-001 ~/monitor/promethus]# vi promethus_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

3.创建service文件

[root@kubernetes-master-001 ~/monitor/promethus]# vi promethus_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

4.创建configmap文件

[root@kubernetes-master-001 ~/monitor/promethus]# vi 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

5.创建rabc文件

[root@kubernetes-master-001 ~/monitor/promethus]# vi rabc-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

6.创建应用并验证

[root@kubernetes-master-001 ~/monitor/promethus]# kubectl  create  -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

[root@kubernetes-master-001 ~/monitor/promethus]# kubectl  get pod -n kube-system 
NAME                                            READY   STATUS    RESTARTS   AGE
prometheus-68546b8d9-9mgft                      1/1     Running   0          3m30s

[root@kubernetes-master-001 ~/monitor/promethus]# kubectl  get svc -n kube-system 
NAME             TYPE        CLUSTER-IP      EXTERNAL-IP   PORT(S)                  AGE
kube-dns         ClusterIP   10.96.0.10      <none>        53/UDP,53/TCP,9153/TCP   17d
metrics-server   ClusterIP   10.98.147.122   <none>        443/TCP                  17h
prometheus       NodePort    10.99.251.153   <none>        9090:30003/TCP           12m

三、部署Node_exporter

1.编写yaml文件

[root@kubernetes-master-001 ~/monitor/promethus]# vi node_expoter.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

2.部署node_exporter并验证

[root@kubernetes-master-001 ~/monitor/promethus]# kubectl  create  -f node_expoter.yaml 
daemonset.apps/node-exporter created
service/node-exporter created

[root@kubernetes-master-001 ~/monitor/promethus]# kubectl  get  pod -n kube-system 
NAME                                            READY   STATUS    RESTARTS   AGE
node-exporter-49fkx                             1/1     Running   0          89s
node-exporter-6wdpp                             1/1     Running   0          89s
prometheus-68546b8d9-9mgft                      1/1     Running   0          24m

[root@kubernetes-master-001 ~/monitor/promethus]# kubectl  get  svc -n kube-system 
NAME             TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                  AGE
kube-dns         ClusterIP   10.96.0.10       <none>        53/UDP,53/TCP,9153/TCP   17d
metrics-server   ClusterIP   10.98.147.122    <none>        443/TCP                  18h
node-exporter    NodePort    10.107.177.177   <none>        9100:31672/TCP           91s
prometheus       NodePort    10.99.251.153    <none>        9090:30003/TCP           24m

四、部署Grafana

1.创建grafana目录

[root@kubernetes-master-001 ~/monitor/promethus]# cd ..
[root@kubernetes-master-001 ~/monitor]# mkdir grafana && cd grafana

2.编写deployment文件

[root@kubernetes-master-001 ~/monitor/grafana]# vi grafana-deploy.yaml 

apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana-core
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  selector:
    matchLabels:
      app: grafana
  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: {}

3.编写service文件

[root@kubernetes-master-001 ~/monitor/grafana]# vi 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

4.编写ingress文件

[root@kubernetes-master-001 ~/monitor/grafana]# vi grafana-ing.yaml 

apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
   name: grafana
   namespace: kube-system
   annotations:
     kubernetes.io/ingress.class: nginx
spec:
   rules:
   - host: grafana.test.mydomain.com
     http:
       paths:
       - path: "/"
         pathType: Prefix
         backend:
           service: 
             name: grafana
             port: 
               number: 3000

5.部署应用并验证

[root@kubernetes-master-001 ~/monitor/grafana]# kubectl  create  -f .
deployment.apps/grafana-core created
ingress.networking.k8s.io/grafana created
service/grafana created

[root@kubernetes-master-001 ~/monitor/grafana]# kubectl  get pod -n kube-system 
NAME                                            READY   STATUS    RESTARTS   AGE
grafana-core-85587c9c49-945lv                   1/1     Running   0          3m28s
metrics-server-599cdf68d4-cbngr                 1/1     Running   0          18h
node-exporter-49fkx                             1/1     Running   0          41m
node-exporter-6wdpp                             1/1     Running   0          41m
prometheus-68546b8d9-9mgft                      1/1     Running   0          64m

[root@kubernetes-master-001 ~/monitor/grafana]# kubectl  get svc -n kube-system 
NAME             TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                  AGE
grafana          NodePort    10.111.128.51    <none>        3000:30369/TCP           3m42s
kube-dns         ClusterIP   10.96.0.10       <none>        53/UDP,53/TCP,9153/TCP   17d
metrics-server   ClusterIP   10.98.147.122    <none>        443/TCP                  18h
node-exporter    NodePort    10.107.177.177   <none>        9100:31672/TCP           41m
prometheus       NodePort    10.99.251.153    <none>        9090:30003/TCP           64m

五、浏览器验证部署

1.Promethus访问测试

2.Grafana访问测试

#1.通过域名访问：grafana.test.mydomain.com，默认用户名密码：admin

#2.登录成功后出现以下界面

#3.配置数据源，使用promethus

#4.设置显示数据模板

#5.查看dashboard界面