k8s环境下部署Prometheus+Grafana监控

环境：k8s-master  192.168.1.130   

　　　k8s-master 192.168.1.131

期望效果：可以看到个节点的监控情况

 

 

 node-exporter用以采集信息

获取镜像

[root@k8s-node ~]# docker search node-exporter

[root@k8s-node ~]# docker pull prom/node-exporter

[root@k8s-node ~]# docker images
REPOSITORY                                                        TAG                 IMAGE ID            CREATED             SIZE
prom/node-exporter                                                latest              1dbe0e931976        4 weeks ago         20.9M

如果有本地镜像

[root@k8s-node ~]# docker load -i node-exporter 

 

node-exporter.yaml文件

[root@k8s-master ~]# cat node-exporter.yaml 
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: kube-system
  labels:
    name: node-exporter
spec:
  selector:
    matchLabels:
     name: node-exporter
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostPID: true
      hostIPC: true
      hostNetwork: true
      containers:
      - name: node-exporter
        image: prom/node-exporter:latest
        ports:
        - containerPort: 9100
        resources:
          requests:
            cpu: 0.15
        securityContext:
          privileged: true
        args:
        - --path.procfs
        - /host/proc
        - --path.sysfs
        - /host/sys
        - --collector.filesystem.ignored-mount-points
        - '"^/(sys|proc|dev|host|etc)($|/)"'
        volumeMounts:
        - name: dev
          mountPath: /host/dev
        - name: proc
          mountPath: /host/proc
        - name: sys
          mountPath: /host/sys
        - name: rootfs
          mountPath: /rootfs
      tolerations:
      - key: "node-role.kubernetes.io/master"
        operator: "Exists"
        effect: "NoSchedule"
      volumes:
        - name: proc
          hostPath:
            path: /proc
        - name: dev
          hostPath:
            path: /dev
        - name: sys
          hostPath:
            path: /sys
        - name: rootfs
          hostPath:
            path: /

#  image: prom/node-exporter:latest   根据自己的镜像配置，我的是拉取最新镜像latest

[root@k8s-master ~]# kubectl apply -f node-exporter.yaml 
daemonset.apps/node-exporter created

　查看pods

[root@k8s-master ~]# kubectl get pods -n kube-system
NAME                                       READY   STATUS    RESTARTS   AGE
calico-kube-controllers-6949477b58-vslgj   1/1     Running   4          27h
calico-node-j2tzw                          1/1     Running   7          27h
calico-node-xp5tr                          1/1     Running   7          27h
coredns-7f89b7bc75-bdz9n                   1/1     Running   2          27h
coredns-7f89b7bc75-tt9rr                   1/1     Running   2          27h
etcd-k8s-master                            1/1     Running   2          27h
kube-apiserver-k8s-master                  1/1     Running   2          27h
kube-controller-manager-k8s-master         1/1     Running   4          27h
kube-proxy-2bh6r                           1/1     Running   2          27h
kube-proxy-7xsjb                           1/1     Running   2          27h
kube-scheduler-k8s-master                  1/1     Running   4          27h
node-exporter-b2dt2                        1/1     Running   0          43s
node-exporter-k8vtw                        1/1     Running   0          43s

　 kubectl get pods -n kube-system -o wide

[root@k8s-master ~]# kubectl get pods -n kube-system -o wide
NAME                                       READY   STATUS    RESTARTS   AGE   IP               NODE         NOMINATED NODE   READINESS GATES
calico-kube-controllers-6949477b58-vslgj   1/1     Running   4          27h   10.122.235.207   k8s-master   <none>           <none>
calico-node-j2tzw                          1/1     Running   7          27h   192.168.1.131    k8s-node     <none>           <none>
calico-node-xp5tr                          1/1     Running   7          27h   192.168.1.130    k8s-master   <none>           <none>
coredns-7f89b7bc75-bdz9n                   1/1     Running   2          27h   10.122.235.208   k8s-master   <none>           <none>
coredns-7f89b7bc75-tt9rr                   1/1     Running   2          27h   10.122.235.206   k8s-master   <none>           <none>
etcd-k8s-master                            1/1     Running   2          27h   192.168.1.130    k8s-master   <none>           <none>
kube-apiserver-k8s-master                  1/1     Running   2          27h   192.168.1.130    k8s-master   <none>           <none>
kube-controller-manager-k8s-master         1/1     Running   4          27h   192.168.1.130    k8s-master   <none>           <none>
kube-proxy-2bh6r                           1/1     Running   2          27h   192.168.1.130    k8s-master   <none>           <none>
kube-proxy-7xsjb                           1/1     Running   2          27h   192.168.1.131    k8s-node     <none>           <none>
kube-scheduler-k8s-master                  1/1     Running   4          27h   192.168.1.130    k8s-master   <none>           <none>
node-exporter-b2dt2                        1/1     Running   0          85s   192.168.1.130    k8s-master   <none>           <none>
node-exporter-k8vtw                        1/1     Running   0          85s   192.168.1.131    k8s-node     <none>           <none>

查看 ip:9100

curl 192.168.1.131:9100/metrics
或者
http://192.168.1.130:9100/metrics

由于信息太多，可以输出到文件查看

[root@k8s-master ~]# curl 192.168.1.131:9100/metrics > node-exporter.txt
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100 70951    0 70951    0     0   637k      0 --:--:-- --:--:-- --:--:--  653k

　或者，进行过滤查看

[root@k8s-master ~]# curl 192.168.1.130:9100/metrics | grep node_load
% Total % Received % Xferd Average Speed Time Time Time Current
Dload Upload Total Spent Left Speed
0 0 0 0 0 0 0 0 --:--:-- --:--:-- --:--:-- 0# HELP node_load1 1m load average.
# TYPE node_load1 gauge
node_load1 2.4
# HELP node_load15 15m load average.
# TYPE node_load15 gauge
node_load15 2.4
# HELP node_load5 5m load average.
# TYPE node_load5 gauge
node_load5 2.67
100 86253 0 86253 0 0 301k 0 --:--:-- --:--:-- --:--:-- 307k

 部署prometheus组

[root@k8s-node ~]# docker pull  prom/prometheus:v2.0.0            

　　#获取镜像prometheus

 rbac-setup.yaml文件

[root@k8s-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@k8s-master ~]# kubectl create -f rbac-setup.yaml
clusterrole.rbac.authorization.k8s.io/prometheus created
serviceaccount/prometheus created
clusterrolebinding.rbac.authorization.k8s.io/prometheus created

以configmap的形式管理prometheus组件的配置文件 　

[root@k8s-master ~]# kubectl create -f  configmap.yaml 
configmap/prometheus-config created

　configmap.yaml文件

[root@k8s-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@k8s-master ~]# kubectl create -f  prometheus.deploy.yml
deployment.apps/prometheus created

　prometheus.deploy.yml 文件

[root@k8s-master prometheus]# cat prometheus.deploy.yml 
---
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   

　kubectl get pods -n kube-system

[root@k8s-master ~]#  kubectl get pods -n kube-system
NAME                                       READY   STATUS    RESTARTS   AGE
calico-kube-controllers-6949477b58-vslgj   1/1     Running   4          28h
calico-node-j2tzw                          1/1     Running   12         28h
calico-node-xp5tr                          1/1     Running   9          28h
coredns-7f89b7bc75-bdz9n                   1/1     Running   2          28h
coredns-7f89b7bc75-tt9rr                   1/1     Running   2          28h
etcd-k8s-master                            1/1     Running   2          28h
kube-apiserver-k8s-master                  1/1     Running   2          28h
kube-controller-manager-k8s-master         1/1     Running   4          28h
kube-proxy-2bh6r                           1/1     Running   2          28h
kube-proxy-7xsjb                           1/1     Running   2          28h
kube-scheduler-k8s-master                  1/1     Running   4          28h
node-exporter-b2dt2                        1/1     Running   0          74m
node-exporter-k8vtw                        1/1     Running   0          74m
prometheus-68546b8d9-nvr2v                 1/1     Running   0          2m47s

[root@k8s-master ~]# kubectl create -f  prometheus.svc.yml 
service/prometheus created

prometheus.svc.yml文件

root@k8s-master prometheus]# 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: 
  selector:
    app: prometheus

　kubectl get svc -n kube-system

[root@k8s-master ~]# kubectl  get svc -n kube-system
NAME         TYPE        CLUSTER-IP     EXTERNAL-IP   PORT(S)                  AGE
kube-dns     ClusterIP   10.10.0.10     <none>        53/UDP,53/TCP,9153/TCP   28h
prometheus   NodePort    10.10.10.193   <none>        9090:30003/TCP           68s

　　访问prometheus ：IP：30003

http://192.168.1.130:30003/

  

 部署grafana组件

 

[root@k8s-node ~]# docker pulgrafana:4.2.0

#获取 grafana镜像　　

[root@k8s-master ~]# kubectl create -f   grafana-deploy.yaml
deployment.apps/grafana-core created

　　grafana-deploy.yaml文件

[root@k8s-master ~]# cat  grafana-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: grafana-core
  namespace: kube-system
  labels:
    app: grafana
    component: core
spec:
  replicas: 1
  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: 500Mi
          requests:
            cpu: 100m
            memory: 500Mi
        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: {}

　create -f grafana-svc.yaml

[root@k8s-master ~]# kubectl create -f   grafana-svc.yaml
service/grafana created

　grafana-service.yaml文件

[root@k8s-master ~]# cat grafana-service.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配置文件

kubectl create -f  grafana-ing.yaml

　

[root@k8s-master ~]# kubectl  get svc -n kube-system
NAME         TYPE        CLUSTER-IP     EXTERNAL-IP   PORT(S)                  AGE
grafana      NodePort    10.10.40.199   <none>        3000:32374/TCP           5m56s
kube-dns     ClusterIP   10.10.0.10     <none>        53/UDP,53/TCP,9153/TCP   29h
prometheus   NodePort    10.10.10.193   <none>        9090:30003/TCP           16m

　　kubectl get all -n kube-system

[root@k8s-master ~]# kubectl  get all -n kube-system
NAME                                           READY   STATUS             RESTARTS   AGE
pod/calico-kube-controllers-6949477b58-vslgj   1/1     Running            4          29h
pod/calico-node-j2tzw                          0/1     CrashLoopBackOff   30         29h
pod/calico-node-xp5tr                          0/1     Running            15         29h
pod/coredns-7f89b7bc75-bdz9n                   1/1     Running            2          30h
pod/coredns-7f89b7bc75-tt9rr                   1/1     Running            2          30h
pod/etcd-k8s-master                            1/1     Running            2          30h
pod/grafana-core-6895c7468b-wwn42              1/1     Running            0          73m
pod/kube-apiserver-k8s-master                  1/1     Running            2          30h
pod/kube-controller-manager-k8s-master         1/1     Running            4          30h
pod/kube-proxy-2bh6r                           1/1     Running            2          30h
pod/kube-proxy-7xsjb                           1/1     Running            2          29h
pod/kube-scheduler-k8s-master                  1/1     Running            4          30h
pod/node-exporter-b2dt2                        1/1     Running            0          158m
pod/node-exporter-k8vtw                        1/1     Running            0          158m
pod/prometheus-68546b8d9-nvr2v                 1/1     Running            0          86m

NAME                 TYPE        CLUSTER-IP     EXTERNAL-IP   PORT(S)                  AGE
service/grafana      NodePort    10.10.40.199   <none>        3000:32374/TCP           71m
service/kube-dns     ClusterIP   10.10.0.10     <none>        53/UDP,53/TCP,9153/TCP   30h
service/prometheus   NodePort    10.10.10.193   <none>        9090:30003/TCP           82m

NAME                           DESIRED   CURRENT   READY   UP-TO-DATE   AVAILABLE   NODE SELECTOR            AGE
daemonset.apps/calico-node     2         2         0       2            0           kubernetes.io/os=linux   29h
daemonset.apps/kube-proxy      2         2         2       2            2           kubernetes.io/os=linux   30h
daemonset.apps/node-exporter   2         2         2       2            2           <none>                   158m

NAME                                      READY   UP-TO-DATE   AVAILABLE   AGE
deployment.apps/calico-kube-controllers   1/1     1            1           29h
deployment.apps/coredns                   2/2     2            2           30h
deployment.apps/grafana-core              1/1     1            1           73m
deployment.apps/prometheus                1/1     1            1           86m

NAME                                                 DESIRED   CURRENT   READY   AGE
replicaset.apps/calico-kube-controllers-6949477b58   1         1         1       29h
replicaset.apps/calico-kube-controllers-6dc8c99cbc   0         0         0       29h
replicaset.apps/coredns-7f89b7bc75                   2         2         2       30h
replicaset.apps/grafana-core-6895c7468b              1         1         1       73m
replicaset.apps/prometheus-68546b8d9                 1         1         1       86m

 

访问granfana，默认用户名，密码均为admin

 

 

 

添加数据源

 

 

 导入面板 

 

 

 

 查看