​

kube-prometheus简介

kube-prometheus是coreos的一个开源项目，用于监控kubernetes集群

安装kube-prometheus

1. 安装git工具

yum install git -y

2. 克隆kube-prometheus

git clone https://github.com/coreos/kube-prometheus

3. 查看manifest

[root@k8s-master guoxb]# cd kube-prometheus/manifests/
[root@k8s-master manifests]# ll
total 1652
-rw-r--r-- 1 root root     406 Mar 30 19:38 alertmanager-alertmanager.yaml
-rw-r--r-- 1 root root    1017 Mar 30 19:38 alertmanager-secret.yaml
-rw-r--r-- 1 root root     101 Mar 30 19:38 alertmanager-serviceAccount.yaml
-rw-r--r-- 1 root root     268 Mar 30 19:38 alertmanager-serviceMonitor.yaml
-rw-r--r-- 1 root root     287 Mar 30 19:38 alertmanager-service.yaml
-rw-r--r-- 1 root root     558 Mar 30 19:38 grafana-dashboardDatasources.yaml
-rw-r--r-- 1 root root 1391276 Mar 30 19:38 grafana-dashboardDefinitions.yaml
-rw-r--r-- 1 root root     475 Mar 30 19:38 grafana-dashboardSources.yaml
-rw-r--r-- 1 root root    7737 Mar 30 19:38 grafana-deployment.yaml
-rw-r--r-- 1 root root      91 Mar 30 19:38 grafana-serviceAccount.yaml
-rw-r--r-- 1 root root     220 Mar 30 19:38 grafana-serviceMonitor.yaml
-rw-r--r-- 1 root root     215 Mar 30 19:38 grafana-service.yaml
-rw-r--r-- 1 root root     390 Mar 30 19:38 kube-state-metrics-clusterRoleBinding.yaml
-rw-r--r-- 1 root root    1856 Mar 30 19:38 kube-state-metrics-clusterRole.yaml
-rw-r--r-- 1 root root    1980 Mar 30 19:38 kube-state-metrics-deployment.yaml
-rw-r--r-- 1 root root     199 Mar 30 19:38 kube-state-metrics-serviceAccount.yaml
-rw-r--r-- 1 root root     860 Mar 30 19:38 kube-state-metrics-serviceMonitor.yaml
-rw-r--r-- 1 root root     421 Mar 30 19:38 kube-state-metrics-service.yaml
-rw-r--r-- 1 root root     278 Mar 30 19:38 node-exporter-clusterRoleBinding.yaml
-rw-r--r-- 1 root root     300 Mar 30 19:38 node-exporter-clusterRole.yaml
-rw-r--r-- 1 root root    2833 Mar 30 19:38 node-exporter-daemonset.yaml
-rw-r--r-- 1 root root      97 Mar 30 19:38 node-exporter-serviceAccount.yaml
-rw-r--r-- 1 root root     739 Mar 30 19:38 node-exporter-serviceMonitor.yaml
-rw-r--r-- 1 root root     372 Mar 30 19:38 node-exporter-service.yaml
-rw-r--r-- 1 root root     305 Mar 30 19:38 prometheus-adapter-apiService.yaml
-rw-r--r-- 1 root root     414 Mar 30 19:38 prometheus-adapter-clusterRoleAggregatedMetricsReader.yaml
-rw-r--r-- 1 root root     316 Mar 30 19:38 prometheus-adapter-clusterRoleBindingDelegator.yaml
-rw-r--r-- 1 root root     293 Mar 30 19:38 prometheus-adapter-clusterRoleBinding.yaml
-rw-r--r-- 1 root root     199 Mar 30 19:38 prometheus-adapter-clusterRoleServerResources.yaml
-rw-r--r-- 1 root root     235 Mar 30 19:38 prometheus-adapter-clusterRole.yaml
-rw-r--r-- 1 root root    1314 Mar 30 19:38 prometheus-adapter-configMap.yaml
-rw-r--r-- 1 root root    1379 Mar 30 19:38 prometheus-adapter-deployment.yaml
-rw-r--r-- 1 root root     338 Mar 30 19:38 prometheus-adapter-roleBindingAuthReader.yaml
-rw-r--r-- 1 root root     102 Mar 30 19:38 prometheus-adapter-serviceAccount.yaml
-rw-r--r-- 1 root root     250 Mar 30 19:38 prometheus-adapter-service.yaml
-rw-r--r-- 1 root root     281 Mar 30 19:38 prometheus-clusterRoleBinding.yaml
-rw-r--r-- 1 root root     231 Mar 30 19:38 prometheus-clusterRole.yaml
-rw-r--r-- 1 root root     643 Mar 30 19:38 prometheus-operator-serviceMonitor.yaml
-rw-r--r-- 1 root root     785 Jun  3 20:51 prometheus-prometheus.yaml
-rw-r--r-- 1 root root     306 Mar 30 19:38 prometheus-roleBindingConfig.yaml
-rw-r--r-- 1 root root    1025 Mar 30 19:38 prometheus-roleBindingSpecificNamespaces.yaml
-rw-r--r-- 1 root root     200 Mar 30 19:38 prometheus-roleConfig.yaml
-rw-r--r-- 1 root root     871 Mar 30 19:38 prometheus-roleSpecificNamespaces.yaml
-rw-r--r-- 1 root root   72376 Mar 30 19:38 prometheus-rules.yaml
-rw-r--r-- 1 root root      98 Mar 30 19:38 prometheus-serviceAccount.yaml
-rw-r--r-- 1 root root    6903 Mar 30 19:38 prometheus-serviceMonitorApiserver.yaml
-rw-r--r-- 1 root root     414 Mar 30 19:38 prometheus-serviceMonitorCoreDNS.yaml
-rw-r--r-- 1 root root    6227 Mar 30 19:38 prometheus-serviceMonitorKubeControllerManager.yaml
-rw-r--r-- 1 root root    6855 Mar 30 19:38 prometheus-serviceMonitorKubelet.yaml
-rw-r--r-- 1 root root     365 Mar 30 19:38 prometheus-serviceMonitorKubeScheduler.yaml
-rw-r--r-- 1 root root     261 Mar 30 19:38 prometheus-serviceMonitor.yaml
-rw-r--r-- 1 root root     276 Mar 30 19:38 prometheus-service.yaml
drwxr-xr-x 2 root root    4096 Mar 30 19:38 setup

4. 修改镜像源

国外镜像源某些镜像无法拉取，我们这里修改prometheus-operator，prometheus，alertmanager，kube-state-metrics，node-exporter，prometheus-adapter的镜像源为国内镜像源。我这里使用的是中科大的镜像源。

sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' setup/prometheus-operator-deployment.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' prometheus-prometheus.yaml 
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' alertmanager-alertmanager.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' kube-state-metrics-deployment.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' node-exporter-daemonset.yaml
sed -i 's/quay.io/quay.mirrors.ustc.edu.cn/g' prometheus-adapter-deployment.yaml

5. 修改promethes，alertmanager，grafana的service类型为NodePort类型

为了可以从外部访问prometheus，alertmanager，grafana，我们这里修改promethes，alertmanager，grafana的service类型为NodePort类型。

修改prometheus的service

[root@k8s-master manifests]# cat prometheus-service.yaml 
apiVersion: v1
kind: Service
metadata:
  labels:
    prometheus: k8s
  name: prometheus-k8s
  namespace: monitoring
spec:
  type: NodePort # 新增
  ports:
  - name: web
    port: 9090
    targetPort: web
    nodePort: 30090 # 新增
  selector:
    app: prometheus
    prometheus: k8s
  sessionAffinity: ClientIP

修改alertmanager的service

[root@k8s-master manifests]# cat alertmanager-service.yaml 
apiVersion: v1
kind: Service
metadata:
  labels:
    alertmanager: main
  name: alertmanager-main
  namespace: monitoring
spec:
  type: NodePort # 新增
  ports:
  - name: web
    port: 9093
    targetPort: web
    nodePort: 30093 # 新增
  selector:
    alertmanager: main
    app: alertmanager
  sessionAffinity: ClientIP

修改grafana的service

[root@k8s-master manifests]# cat grafana-service.yaml
apiVersion: v1
kind: Service
metadata:
  labels:
    app: grafana
  name: grafana
  namespace: monitoring
spec:
  type: NodePort # 新增
  ports:
  - name: http
    port: 3000
    targetPort: http
    nodePort: 32000 # 新增
  selector:
    app: grafana

6. 安装kube-prometheus并确认状态

安装CRD和prometheus-operator

[root@k8s-master manifests]# kubectl apply -f setup/
namespace/monitoring created
customresourcedefinition.apiextensions.k8s.io/alertmanagers.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/podmonitors.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/prometheuses.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/prometheusrules.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/servicemonitors.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/thanosrulers.monitoring.coreos.com created
clusterrole.rbac.authorization.k8s.io/prometheus-operator created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-operator created
deployment.apps/prometheus-operator created
service/prometheus-operator created
serviceaccount/prometheus-operator created
[root@k8s-master manifests]# 

下载prometheus-operator镜像需要花费几分钟，这里等待几分钟，直到prometheus-operator变成running状态

[root@k8s-master manifests]# kubectl get pod -n monitoring
NAME                                  READY   STATUS    RESTARTS   AGE
prometheus-operator-c5c9679cd-4wwf7   2/2     Running   0          13s

安装prometheus, alertmanager, grafana, kube-state-metrics, node-exporter等资源

[root@k8s-master manifests]# kubectl apply -f .
alertmanager.monitoring.coreos.com/main created
secret/alertmanager-main created
service/alertmanager-main created
serviceaccount/alertmanager-main created
servicemonitor.monitoring.coreos.com/alertmanager created
secret/grafana-datasources created
configmap/grafana-dashboard-apiserver created
configmap/grafana-dashboard-cluster-total created
configmap/grafana-dashboard-controller-manager created
configmap/grafana-dashboard-k8s-resources-cluster created
configmap/grafana-dashboard-k8s-resources-namespace created
configmap/grafana-dashboard-k8s-resources-node created
configmap/grafana-dashboard-k8s-resources-pod created
configmap/grafana-dashboard-k8s-resources-workload created
configmap/grafana-dashboard-k8s-resources-workloads-namespace created
configmap/grafana-dashboard-kubelet created
configmap/grafana-dashboard-namespace-by-pod created
configmap/grafana-dashboard-namespace-by-workload created
configmap/grafana-dashboard-node-cluster-rsrc-use created
configmap/grafana-dashboard-node-rsrc-use created
configmap/grafana-dashboard-nodes created
configmap/grafana-dashboard-persistentvolumesusage created
configmap/grafana-dashboard-pod-total created
configmap/grafana-dashboard-prometheus-remote-write created
configmap/grafana-dashboard-prometheus created
configmap/grafana-dashboard-proxy created
configmap/grafana-dashboard-scheduler created
configmap/grafana-dashboard-statefulset created
configmap/grafana-dashboard-workload-total created
configmap/grafana-dashboards created
deployment.apps/grafana created
service/grafana created
serviceaccount/grafana created
servicemonitor.monitoring.coreos.com/grafana created
clusterrole.rbac.authorization.k8s.io/kube-state-metrics created
clusterrolebinding.rbac.authorization.k8s.io/kube-state-metrics created
deployment.apps/kube-state-metrics created
service/kube-state-metrics created
serviceaccount/kube-state-metrics created
servicemonitor.monitoring.coreos.com/kube-state-metrics created
clusterrole.rbac.authorization.k8s.io/node-exporter created
clusterrolebinding.rbac.authorization.k8s.io/node-exporter created
daemonset.apps/node-exporter created
service/node-exporter created
serviceaccount/node-exporter created
servicemonitor.monitoring.coreos.com/node-exporter created
apiservice.apiregistration.k8s.io/v1beta1.metrics.k8s.io created
clusterrole.rbac.authorization.k8s.io/prometheus-adapter created
clusterrole.rbac.authorization.k8s.io/system:aggregated-metrics-reader created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-adapter created
clusterrolebinding.rbac.authorization.k8s.io/resource-metrics:system:auth-delegator created
clusterrole.rbac.authorization.k8s.io/resource-metrics-server-resources created
configmap/adapter-config created
deployment.apps/prometheus-adapter created
rolebinding.rbac.authorization.k8s.io/resource-metrics-auth-reader created
service/prometheus-adapter created
serviceaccount/prometheus-adapter created
clusterrole.rbac.authorization.k8s.io/prometheus-k8s created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-k8s created
servicemonitor.monitoring.coreos.com/prometheus-operator created
prometheus.monitoring.coreos.com/k8s created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s-config created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s created
rolebinding.rbac.authorization.k8s.io/prometheus-k8s created
role.rbac.authorization.k8s.io/prometheus-k8s-config created
role.rbac.authorization.k8s.io/prometheus-k8s created
role.rbac.authorization.k8s.io/prometheus-k8s created
role.rbac.authorization.k8s.io/prometheus-k8s created
prometheusrule.monitoring.coreos.com/prometheus-k8s-rules created
service/prometheus-k8s created
serviceaccount/prometheus-k8s created
servicemonitor.monitoring.coreos.com/prometheus created
servicemonitor.monitoring.coreos.com/kube-apiserver created
servicemonitor.monitoring.coreos.com/coredns created
servicemonitor.monitoring.coreos.com/kube-controller-manager created
servicemonitor.monitoring.coreos.com/kube-scheduler created
servicemonitor.monitoring.coreos.com/kubelet created

下载镜像比较花费时间，可以先去泡杯咖啡，等上半小时再回来，然后查看命名空间monitoring下面的pod状态，直到monitoring命名空间下所有pod都变为running状态，就大功告成了。

[root@k8s-master manifests]# kubectl get pod -n monitoring
NAME                                  READY   STATUS    RESTARTS   AGE
alertmanager-main-0                   2/2     Running   0          6m30s
alertmanager-main-1                   2/2     Running   0          6m30s
alertmanager-main-2                   2/2     Running   0          6m30s
grafana-5c55845445-x8s96              1/1     Running   0          6m30s
kube-state-metrics-5848b95f69-jwtkj   3/3     Running   0          6m30s
node-exporter-82zqh                   2/2     Running   0          6m30s
node-exporter-j97g4                   2/2     Running   0          6m30s
node-exporter-tg7c9                   2/2     Running   0          6m30s
prometheus-adapter-7d68d6f886-wjjx4   1/1     Running   0          6m30s
prometheus-k8s-0                      3/3     Running   1          6m29s
prometheus-k8s-1                      3/3     Running   1          6m29s
prometheus-operator-c5c9679cd-4wwf7   2/2     Running   0          88m

访问prometheus，alert-manager，grafana

1. 访问prometheus

浏览器打开http://192.168.92.201:30090，192.168.92.201为master的IP

​

2. 访问alert-manager

浏览器打开http://192.168.92.201:30093

​

3. 访问grafana

浏览器打开http://192.168.92.201:32000

用户名/密码：admin/admin

​

参考资料

https://github.com/coreos/kube-prometheus

https://www.jianshu.com/p/2fbbe767870d

​