关于prometheus:使用kubeprometheus监控k8s平台

43次阅读

共计 17019 个字符,预计需要花费 43 分钟才能阅读完成。

一、环境介绍

相干软件版本:
kubernetets:v1.22.2
kube-prometheus:release 0.9

二、开始部署

在部署之前留神先去官网查看 kube-prometheus 与 k8s 集群的兼容性。kube-prometheus 官网:kube-prometheus

在 master 节点下载相干软件包。

root@master01:~/monitor# git clone https://github.com/prometheus-operator/kube-prometheus.git
Cloning into 'kube-prometheus'...
remote: Enumerating objects: 17447, done.
remote: Counting objects: 100% (353/353), done.
remote: Compressing objects: 100% (129/129), done.
remote: Total 17447 (delta 262), reused 279 (delta 211), pack-reused 17094
Receiving objects: 100% (17447/17447), 9.12 MiB | 5.59 MiB/s, done.
Resolving deltas: 100% (11455/11455), done.
root@master01:~/monitor# ls
kube-prometheus

kube-prometheus 部署:留神 manifests/setup/ 文件夹的资源在部署的时候必须用 create 不能用 apply,否则会提醒“The CustomResourceDefinition “prometheuses.monitoring.coreos.com” is invalid: metadata.annotations: Too long: must have at most 262144 bytes”,manifests 文件夹中的内容能够用 apply 创立。

root@master01:~/monitor# ls
kube-prometheus
root@master01:~/monitor/kube-prometheus# kubectl create -f manifests/setup/
customresourcedefinition.apiextensions.k8s.io/alertmanagerconfigs.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/alertmanagers.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/podmonitors.monitoring.coreos.com created
customresourcedefinition.apiextensions.k8s.io/probes.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
namespace/monitoring created
root@master01:~/monitor/kube-prometheus# kubectl apply -f manifests/
alertmanager.monitoring.coreos.com/main created
networkpolicy.networking.k8s.io/alertmanager-main created
poddisruptionbudget.policy/alertmanager-main created
prometheusrule.monitoring.coreos.com/alertmanager-main-rules created
secret/alertmanager-main created
service/alertmanager-main created
serviceaccount/alertmanager-main created
servicemonitor.monitoring.coreos.com/alertmanager-main created
clusterrole.rbac.authorization.k8s.io/blackbox-exporter created
clusterrolebinding.rbac.authorization.k8s.io/blackbox-exporter created
configmap/blackbox-exporter-configuration created
deployment.apps/blackbox-exporter created
networkpolicy.networking.k8s.io/blackbox-exporter created
service/blackbox-exporter created
serviceaccount/blackbox-exporter created
servicemonitor.monitoring.coreos.com/blackbox-exporter created
secret/grafana-config created
secret/grafana-datasources created
configmap/grafana-dashboard-alertmanager-overview created
configmap/grafana-dashboard-apiserver created
configmap/grafana-dashboard-cluster-total created
configmap/grafana-dashboard-controller-manager created
configmap/grafana-dashboard-grafana-overview 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-darwin 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-workload-total created
configmap/grafana-dashboards created
deployment.apps/grafana created
networkpolicy.networking.k8s.io/grafana created
prometheusrule.monitoring.coreos.com/grafana-rules created
service/grafana created
serviceaccount/grafana created
servicemonitor.monitoring.coreos.com/grafana created
prometheusrule.monitoring.coreos.com/kube-prometheus-rules 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
networkpolicy.networking.k8s.io/kube-state-metrics created
prometheusrule.monitoring.coreos.com/kube-state-metrics-rules created
service/kube-state-metrics created
serviceaccount/kube-state-metrics created
servicemonitor.monitoring.coreos.com/kube-state-metrics created
prometheusrule.monitoring.coreos.com/kubernetes-monitoring-rules 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
clusterrole.rbac.authorization.k8s.io/node-exporter created
clusterrolebinding.rbac.authorization.k8s.io/node-exporter created
daemonset.apps/node-exporter created
networkpolicy.networking.k8s.io/node-exporter created
prometheusrule.monitoring.coreos.com/node-exporter-rules created
service/node-exporter created
serviceaccount/node-exporter created
servicemonitor.monitoring.coreos.com/node-exporter created
clusterrole.rbac.authorization.k8s.io/prometheus-k8s created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-k8s created
networkpolicy.networking.k8s.io/prometheus-k8s created
poddisruptionbudget.policy/prometheus-k8s created
prometheus.monitoring.coreos.com/k8s created
prometheusrule.monitoring.coreos.com/prometheus-k8s-prometheus-rules 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
service/prometheus-k8s created
serviceaccount/prometheus-k8s created
servicemonitor.monitoring.coreos.com/prometheus-k8s 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
networkpolicy.networking.k8s.io/prometheus-adapter created
poddisruptionbudget.policy/prometheus-adapter created
rolebinding.rbac.authorization.k8s.io/resource-metrics-auth-reader created
service/prometheus-adapter created
serviceaccount/prometheus-adapter created
servicemonitor.monitoring.coreos.com/prometheus-adapter created
clusterrole.rbac.authorization.k8s.io/prometheus-operator created
clusterrolebinding.rbac.authorization.k8s.io/prometheus-operator created
deployment.apps/prometheus-operator created
networkpolicy.networking.k8s.io/prometheus-operator created
prometheusrule.monitoring.coreos.com/prometheus-operator-rules created
service/prometheus-operator created
serviceaccount/prometheus-operator created
servicemonitor.monitoring.coreos.com/prometheus-operator created

部署后果验证,能够看到新创建的 monitoring 名称空间中的 POD 全副失常启动,相干资源失常被创立。

root@master01:~/monitor/kube-prometheus# kubectl get po -n monitoring 
NAME                                   READY   STATUS    RESTARTS   AGE
alertmanager-main-0                    2/2     Running   0          2m18s
alertmanager-main-1                    2/2     Running   0          2m18s
alertmanager-main-2                    2/2     Running   0          2m18s
blackbox-exporter-58d99cfb6d-5f44f     3/3     Running   0          2m30s
grafana-5cfbb9b4c5-7qw6c               1/1     Running   0          2m29s
kube-state-metrics-c9f8b947b-xrhbd     3/3     Running   0          2m29s
node-exporter-gzspv                    2/2     Running   0          2m28s
node-exporter-jz588                    2/2     Running   0          2m28s
node-exporter-z8vps                    2/2     Running   0          2m28s
prometheus-adapter-5bf8d6f7c6-5jf6n    1/1     Running   0          2m26s
prometheus-adapter-5bf8d6f7c6-sz4ns    1/1     Running   0          2m27s
prometheus-k8s-0                       2/2     Running   0          2m16s
prometheus-k8s-1                       2/2     Running   0          2m16s
prometheus-operator-6cbd5c84fb-8xslw   2/2     Running   0          2m26s

root@master01:~# kubectl get crd -n monitoring 
NAME                                        CREATED AT
alertmanagerconfigs.monitoring.coreos.com   2023-01-04T14:54:38Z
alertmanagers.monitoring.coreos.com         2023-01-04T14:54:38Z
podmonitors.monitoring.coreos.com           2023-01-04T14:54:38Z
probes.monitoring.coreos.com                2023-01-04T14:54:38Z
prometheuses.monitoring.coreos.com          2023-01-04T14:54:38Z
prometheusrules.monitoring.coreos.com       2023-01-04T14:54:38Z
servicemonitors.monitoring.coreos.com       2023-01-04T14:54:38Z
thanosrulers.monitoring.coreos.com          2023-01-04T14:54:38Z

root@master01:~# kubectl get secret -n monitoring 
NAME                              TYPE                                  DATA   AGE
alertmanager-main                 Opaque                                1      3d21h
alertmanager-main-generated       Opaque                                1      3d21h
alertmanager-main-tls-assets-0    Opaque                                0      3d21h
alertmanager-main-token-6c5pj     kubernetes.io/service-account-token   3      3d21h
alertmanager-main-web-config      Opaque                                1      3d21h
blackbox-exporter-token-22c6s     kubernetes.io/service-account-token   3      3d21h
default-token-kff56               kubernetes.io/service-account-token   3      3d22h
grafana-config                    Opaque                                1      3d21h
grafana-datasources               Opaque                                1      3d21h
grafana-token-7dvc9               kubernetes.io/service-account-token   3      3d21h
kube-state-metrics-token-nzhtn    kubernetes.io/service-account-token   3      3d21h
node-exporter-token-8zrpf         kubernetes.io/service-account-token   3      3d21h
prometheus-adapter-token-jmdch    kubernetes.io/service-account-token   3      3d21h
prometheus-k8s                    Opaque                                1      3d21h
prometheus-k8s-tls-assets-0       Opaque                                0      3d21h
prometheus-k8s-token-jfwmh        kubernetes.io/service-account-token   3      3d21h
prometheus-k8s-web-config         Opaque                                1      3d21h
prometheus-operator-token-w4xcf   kubernetes.io/service-account-token   3      3d21h

三、服务裸露

服务裸露分为两种形式,能够应用 ingress 或 NodePort 的形式将服务裸露进来使宿主机能够进行拜访。留神如果集群应用的如果是 calico 网络的话会默认创立出若干条网络规定导致服务裸露后也无奈在客户端进行拜访。可将网络策略批改或间接删除。(留神图片中所操作的策略也须要删除)。

root@master01:~# kubectl get networkpolicies.networking.k8s.io -n monitoring 
NAME                  POD-SELECTOR                                                                                                                                             AGE
alertmanager-main     app.kubernetes.io/component=alert-router,app.kubernetes.io/instance=main,app.kubernetes.io/name=alertmanager,app.kubernetes.io/part-of=kube-prometheus   14h
blackbox-exporter     app.kubernetes.io/component=exporter,app.kubernetes.io/name=blackbox-exporter,app.kubernetes.io/part-of=kube-prometheus                                  14h
grafana               app.kubernetes.io/component=grafana,app.kubernetes.io/name=grafana,app.kubernetes.io/part-of=kube-prometheus                                             14h
kube-state-metrics    app.kubernetes.io/component=exporter,app.kubernetes.io/name=kube-state-metrics,app.kubernetes.io/part-of=kube-prometheus                                 14h
node-exporter         app.kubernetes.io/component=exporter,app.kubernetes.io/name=node-exporter,app.kubernetes.io/part-of=kube-prometheus                                      14h
prometheus-adapter    app.kubernetes.io/component=metrics-adapter,app.kubernetes.io/name=prometheus-adapter,app.kubernetes.io/part-of=kube-prometheus                          14h
prometheus-operator   app.kubernetes.io/component=controller,app.kubernetes.io/name=prometheus-operator,app.kubernetes.io/part-of=kube-prometheus                              14h
root@master01:~# kubectl delete networkpolicies.networking.k8s.io  grafana -n monitoring 
networkpolicy.networking.k8s.io "grafana" deleted
root@master01:~# kubectl delete networkpolicies.networking.k8s.io alertmanager-main -n monitoring 
networkpolicy.networking.k8s.io "alertmanager-main" deleted

3.1 应用 NodePort 形式裸露服务(可选)

批改 prometheus 的 service 文件

root@master01:~/monitor/kube-prometheus# cat manifests/prometheus-service.yaml 
apiVersion: v1
kind: Service
metadata:
  labels:
    app.kubernetes.io/component: prometheus
    app.kubernetes.io/instance: k8s
    app.kubernetes.io/name: prometheus
    app.kubernetes.io/part-of: kube-prometheus
    app.kubernetes.io/version: 2.41.0
  name: prometheus-k8s
  namespace: monitoring
spec:
  type: NodePort
  ports:
  - name: web
    port: 9090
    targetPort: web
    nodePort: 30090
  - name: reloader-web
    port: 8080
    targetPort: reloader-web
  selector:
    app.kubernetes.io/component: prometheus
    app.kubernetes.io/instance: k8s
    app.kubernetes.io/name: prometheus
    app.kubernetes.io/part-of: kube-prometheus
  sessionAffinity: ClientIP
root@master01:~/monitor/kube-prometheus# kubectl apply -f  manifests/prometheus-service.yaml 
service/prometheus-k8s configured

批改 grafana 和 alert-manager 的 service 文件。

root@master01:~/monitor/kube-prometheus/manifests# cat grafana-service.yaml 
apiVersion: v1
kind: Service
metadata:
  labels:
    app.kubernetes.io/component: grafana
    app.kubernetes.io/name: grafana
    app.kubernetes.io/part-of: kube-prometheus
    app.kubernetes.io/version: 9.3.2
  name: grafana
  namespace: monitoring
spec:
  type: NodePort
  ports:
  - name: http
    port: 3000
    targetPort: http
    nodePort: 30030
  selector:
    app.kubernetes.io/component: grafana
    app.kubernetes.io/name: grafana
    app.kubernetes.io/part-of: kube-prometheus

root@master01:~/monitor/kube-prometheus/manifests# cat alertmanager-service.yaml 
apiVersion: v1
kind: Service
metadata:
  labels:
    app.kubernetes.io/component: alert-router
    app.kubernetes.io/instance: main
    app.kubernetes.io/name: alertmanager
    app.kubernetes.io/part-of: kube-prometheus
    app.kubernetes.io/version: 0.25.0
  name: alertmanager-main
  namespace: monitoring
spec:
  type: NodePort
  ports:
  - name: web
    port: 9093
    targetPort: web
    nodePort: 30093
  - name: reloader-web
    port: 8080
    targetPort: reloader-web
  selector:
    app.kubernetes.io/component: alert-router
    app.kubernetes.io/instance: main
    app.kubernetes.io/name: alertmanager
    app.kubernetes.io/part-of: kube-prometheus
  sessionAffinity: ClientIP

批改完后 apply
root@master01:~/monitor/kube-prometheus/manifests# kubectl apply -f  grafana-service.yaml 
service/grafana configured
root@master01:~/monitor/kube-prometheus/manifests# kubectl apply -f  alertmanager-service.yaml 
service/alertmanager-main configured

批改完相干 service 文件后验证

root@master01:~# kubectl get svc -n monitoring 
NAME                    TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                         AGE
alertmanager-main       NodePort    10.100.23.255    <none>        9093:30093/TCP,8080:32647/TCP   14h
alertmanager-operated   ClusterIP   None             <none>        9093/TCP,9094/TCP,9094/UDP      14h
blackbox-exporter       ClusterIP   10.100.48.67     <none>        9115/TCP,19115/TCP              14h
grafana                 NodePort    10.100.153.195   <none>        3000:30030/TCP                  14h
kube-state-metrics      ClusterIP   None             <none>        8443/TCP,9443/TCP               14h
node-exporter           ClusterIP   None             <none>        9100/TCP                        14h
prometheus-adapter      ClusterIP   10.100.226.131   <none>        443/TCP                         14h
prometheus-k8s          NodePort    10.100.206.216   <none>        9090:30090/TCP,8080:30019/TCP   14h
prometheus-operated     ClusterIP   None             <none>        9090/TCP                        14h
prometheus-operator     ClusterIP   None             <none>        8443/TCP                        14h

在客户端用浏览器进行拜访验证

下面咱们能够看到 Prometheus 的 POD 是两个正本,咱们这里通过 Service 去拜访,按失常来说申请是会去轮询拜访后端的两个 Prometheus 实例的,但实际上咱们这里拜访的时候始终是通过 service 的负载平衡个性调度到后端的任意一个实例下来,因为这里的 Service 在创立的时候增加了 sessionAffinity: ClientIP 这样的属性,会依据 ClientIP 来做 session 亲和性,所以不必放心申请会到不同的正本下来,失常多正本应该是看成高可用的罕用计划,实践上来说不同正本本地的数据是统一的,然而须要留神的是 Prometheus 的被动 Pull 拉取监控指标的形式,因为抓取工夫不能完全一致,即便统一也不肯定就能保障网络没什么问题,所以最终不同正本下存储的数据很大可能是不一样的,所以官网提供的 yaml 文件里配置了 session 亲和性,能够保障咱们在拜访数据的时候始终是统一的。

此时能够应用 admin:admin,登录 granfna 平台。
从内置监控模板中抉择一个模板测试。能够发现曾经能够看到监控数据。

3.2 应用 ingress 形式裸露服务(可选)

ingress 工作逻辑简介:先创立 ingress 控制器,相似于 nginx 主过程,监听一个端口,也就是将宿主机的某个端口映射给 ingress 的 controller,所有的申请先到控制器,各种配置文件都在控制器上,之后再将申请转给各个 ingress 工作线程。

本试验采纳的是 nginx-ingress 测试

root@master01:~# kubectl get svc -n ingress-nginx 
NAME                                 TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                      AGE
ingress-nginx-controller             NodePort    10.100.184.74    <none>        80:30080/TCP,443:30787/TCP   3d6h
ingress-nginx-controller-admission   ClusterIP   10.100.216.215   <none>        443/TCP                      3d6h
root@master01:~# kubectl get po -n ingress-nginx 
NAME                                        READY   STATUS    RESTARTS     AGE
ingress-nginx-controller-69fbfb4bfd-zjs2w   1/1     Running   1 (9h ago)   9h

编写通过 ingress 拜访监控零碎的 yaml 文件,在编写 ingress 的 yaml 文件的时候留神集群版本与 api 变动。
ingress 的 api 版本历经过屡次变动他们的配置项也不太一样别离是:
● extensions/v1beta1:1.16 版本之前应用
● networking.k8s.io/v1beta1:1.19 版本之前应用
● networking.k8s.io/v1:1.19 版本之后应用

编写须要裸露服务的 yaml 文件并创立相干资源。

root@master01:~/ingress/monitor-ingress# cat promethues-ingress.yaml 
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: prometheus-ingress
  namespace: monitoring
spec:
  ingressClassName: nginx #此版本 ingress 控制器由此处指定,不必注解指了
  rules:
  - host: prometheus.snow.com
    http:
      paths:
        - path: /
          pathType: Prefix
          backend: 
            service: 
              name: prometheus-k8s 
              port: 
                number: 9090

root@master01:~/ingress/monitor-ingress# cat grafana-ingress.yaml 
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: grafana-ingress
  namespace: monitoring
spec:
  ingressClassName: nginx
  rules:
  - host: grafana.snow.com
    http:
      paths:
      - path: /
        pathType: Prefix
        backend: 
          service: 
            name: grafana
            port: 
              number: 3000

root@master01:~/ingress/monitor-ingress# cat alert-manager-ingress.yaml 
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
  name: alert-ingress
  namespace: monitoring
spec:
  ingressClassName: nginx
  rules:
  - host: alert.snow.com
    http:
      paths:
      - path: /
        pathType: Prefix
        backend: 
          service: 
            name: alertmanager-main
            port: 
              number: 9093

root@master01:~/ingress/monitor-ingress# kubectl apply -f promethues-ingress.yaml 
ingress.networking.k8s.io/prometheus-ingress created

root@master01:~/ingress/monitor-ingress# kubectl apply -f  grafana-ingress.yaml
ingress.networking.k8s.io/grafana-ingress created

root@master01:~/ingress/monitor-ingress# kubectl apply -f  alert-manager-ingress.yaml 
ingress.networking.k8s.io/alter-ingress created

ingress 资源创立结束后验证

root@master01:~/ingress/monitor-ingress# kubectl get ingress -n monitoring 
NAME                 CLASS   HOSTS                 ADDRESS         PORTS   AGE
alter-ingress        nginx   alert.snow.com        10.100.184.74   80      3m42s
grafana-ingress      nginx   grafana.snow.com      10.100.184.74   80      14h
prometheus-ingress   nginx   prometheus.snow.com   10.100.184.74   80      12h

批改宿主机 hosts 文件,留神在宿主机进行拜访的时候敞开代理工具,clash 会使本机的 hosts 解析生效。

在浏览器应用域名拜访测试

ps:以上内容在自己实现环境中已试验胜利,如发现有问题或表述不清的中央欢送斧正。

正文完
 0