3、Kubernetes集群部署Prometheus和Grafana

Kubernetes 集群部署 Prometheus 和 Grafana node-exporter 安装Prometheus 安装和配置Prometheus 配置热加载Grafana 安装部署Grafana 配置 实验环境 控制节点/master01 192.168.110.10 工作节点/node01 192.168.110.20 工作节点/node02 192.168.110.30

node-exporter 安装 #创建监控 namespace kubectl create ns monitor-sa #部署 node-exporter mkdir /opt/prometheus cd /opt/prometheus/ vim node-export.yaml --- apiVersion: apps/v1 kind: DaemonSet #可以保证 k8s 集群的每个节点都运行完全一样的 pod metadata: name: node-exporter namespace: monitor-sa 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:v0.16.0 ports: - containerPort: 9100 resources: requests: cpu: 0.15 #这个容器运行至少需要0.15核cpu securityContext: privileged: true #开启特权模式 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: / kubectl apply -f node-export.yaml kubectl get pods -n monitor-sa -o wide [root@master01 prometheus]# kubectl get pods -n monitor-sa -o wide NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES node-exporter-4mjm8 1/1 Running 5 3m40s 192.168.110.30 192.168.110.30 <none> <none> node-exporter-kzbpv 1/1 Running 5 3m40s 192.168.110.20 192.168.110.20 <none> <none>

通过 node-exporter 采集数据 node-exporter 默认的监听端口是 9100，可以执行 curl http://主机ip:9100/metrics 获取到主机的所有监控数据

curl -Ls http://192.168.110.20:9100/metrics | grep node_cpu_seconds curl -Ls http://192.168.110.20:9100/metrics | grep node_load [root@node02 ~]# curl -Ls http://192.168.110.20:9100/metrics | grep node_cpu_seconds # HELP node_cpu_seconds_total Seconds the cpus spent in each mode. # TYPE node_cpu_seconds_total counter node_cpu_seconds_total{cpu="0",mode="idle"} 67314.31 node_cpu_seconds_total{cpu="0",mode="iowait"} 5.25 ... ... node_cpu_seconds_total{cpu="3",mode="system"} 768.89 node_cpu_seconds_total{cpu="3",mode="user"} 143.63 [root@node02 ~]# curl -Ls http://192.168.110.20:9100/metrics | grep node_load # HELP node_load1 1m load average. # TYPE node_load1 gauge node_load1 0.41 # HELP node_load15 15m load average. # TYPE node_load15 gauge node_load15 0.75 # HELP node_load5 5m load average. # TYPE node_load5 gauge node_load5 0.62 Prometheus 安装和配置

创建 sa 账号，对 sa 做 rbac 授权

#创建一个 sa 账号 monitor kubectl create serviceaccount monitor -n monitor-sa #把 sa 账号 monitor 通过 clusterrolebing 绑定到 clusterrole 上 kubectl create clusterrolebinding monitor-clusterrolebinding -n monitor-sa --clusterrole=cluster-admin --serviceaccount=monitor-sa:monitor

创建一个 configmap 存储卷，用来存放 prometheus 配置信息

vim prometheus-cfg.yaml --- kind: ConfigMap apiVersion: v1 metadata: labels: app: prometheus name: prometheus-config namespace: monitor-sa data: prometheus.yml: | global: #指定prometheus的全局配置，比如采集间隔，抓取超时时间等 scrape_interval: 15s #采集目标主机监控数据的时间间隔，默认为1m scrape_timeout: 10s #数据采集超时时间，默认10s evaluation_interval: 1m #触发告警生成alert的时间间隔，默认是1m scrape_configs: #配置数据源，称为target，每个target用job_name命名。又分为静态配置和服务发现 - job_name: 'kubernetes-node' kubernetes_sd_configs: # *_sd_configs 指定的是k8s的服务发现 - role: node #使用node角色，它使用默认的kubelet提供的http端口来发现集群中每个node节点 relabel_configs: #重新标记 - source_labels: [__address__] #配置的原始标签，匹配地址 regex: '(.*):10250' #匹配带有10250端口的url replacement: '${1}:9100' #把匹配到的ip:10250的ip保留 target_label: __address__ #新生成的url是${1}获取到的ip:9100 action: replace #动作替换 - action: labelmap regex: __meta_kubernetes_node_label_(.+) #匹配到下面正则表达式的标签会被保留,如果不做regex正则的话，默认只是会显示instance标签 - job_name: 'kubernetes-node-cadvisor' #抓取cAdvisor数据，是获取kubelet上/metrics/cadvisor接口数据来获取容器的资源使用情况 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 #把匹配到的标签保留 regex: __meta_kubernetes_node_label_(.+) #保留匹配到的具有__meta_kubernetes_node_label的标签 - target_label: __address__ #获取到的地址：__address__="192.168.80.20:10250" replacement: kubernetes.default.svc:443 #把获取到的地址替换成新的地址kubernetes.default.svc:443 - source_labels: [__meta_kubernetes_node_name] regex: (.+) #把原始标签中__meta_kubernetes_node_name值匹配到 target_label: __metrics_path__ #获取__metrics_path__对应的值 replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor #把metrics替换成新的值api/v1/nodes/<node_name>/proxy/metrics/cadvisor #${1}是__meta_kubernetes_node_name获取到的值 #最后通过 <apiserver_address>/api/v1/nodes/<node_name>/proxy/metrics/cadvisor来获取对应节点cadvisor监控数据 - job_name: 'kubernetes-apiserver' kubernetes_sd_configs: - role: endpoints #使用k8s中的endpoint服务发现，采集apiserver 6443端口获取到的数据 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] #[endpoint这个对象的名称空间,endpoint对象的服务名,exnpoint的端口名称] action: keep #采集满足条件的实例，其他实例不采集 regex: default;kubernetes;https #正则匹配到的默认空间下的service名字是kubernetes，协议是https的endpoint类型保留下来 - 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 #重新打标仅抓取到的具有"prometheus.io/scrape: true"的annotation的端点， 意思是说如果某个service具有prometheus.io/scrape = true的annotation声明则抓取，annotation本身也是键值结构， 所以这里的源标签设置为键，而regex设置值true，当值匹配到regex设定的内容时则执行keep动作也就是保留，其余则丢弃。 - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme] action: replace target_label: __scheme__ regex: (https?) #重新设置scheme，匹配源标签__meta_kubernetes_service_annotation_prometheus_io_scheme也就是prometheus.io/scheme annotation，如果源标签的值匹配到regex，则把值替换为__scheme__对应的值。 - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path] action: replace target_label: __metrics_path__ regex: (.+) #应用中自定义暴露的指标，也许你暴露的API接口不是/metrics这个路径，那么你可以在这个POD对应的service中做一个 "prometheus.io/path = /mymetrics" 声明，上面的意思就是把你声明的这个路径赋值给__metrics_path__， 其实就是让prometheus来获取自定义应用暴露的metrices的具体路径， 不过这里写的要和service中做好约定，如果service中这样写 prometheus.io/app-metrics-path: '/metrics' 那么你这里就要__meta_kubernetes_service_annotation_prometheus_io_app_metrics_path这样写。 - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port] action: replace target_label: __address__ regex: ([^:]+)(?::\d+)?;(\d+) replacement: $1:$2 #暴露自定义的应用的端口，就是把地址和你在service中定义的 "prometheus.io/port = <port>" 声明做一个拼接， 然后赋值给__address__，这样prometheus就能获取自定义应用的端口，然后通过这个端口再结合__metrics_path__来获取指标，如果__metrics_path__值不是默认的/metrics那么就要使用上面的标签替换来获取真正暴露的具体路径。 - action: labelmap #保留下面匹配到的标签 regex: __meta_kubernetes_service_label_(.+) - source_labels: [__meta_kubernetes_namespace] action: replace #替换__meta_kubernetes_namespace变成kubernetes_namespace target_label: kubernetes_namespace - source_labels: [__meta_kubernetes_service_name] action: replace target_label: kubernetes_name kubectl apply -f prometheus-cfg.yaml

通过 deployment 部署 prometheus

#将 prometheus 调度到 node1 节点，在 node1 节点创建 prometheus 数据存储目录 mkdir /data && chmod 777 /data #通过 deployment 部署 prometheus vim prometheus-deploy.yaml --- apiVersion: apps/v1 kind: Deployment metadata: name: prometheus-server namespace: monitor-sa labels: app: prometheus spec: replicas: 1 selector: matchLabels: app: prometheus component: server #matchExpressions: #- {key: app, operator: In, values: [prometheus]} #- {key: component, operator: In, values: [server]} template: metadata: labels: app: prometheus component: server annotations: prometheus.io/scrape: 'false' spec: nodeName: 192.168.110.20 #指定pod调度到哪个节点上 serviceAccountName: monitor containers: - name: prometheus image: prom/prometheus:v2.2.1 imagePullPolicy: IfNotPresent command: - prometheus - --config.file=/etc/prometheus/prometheus.yml - --storage.tsdb.path=/prometheus #数据存储目录 - --storage.tsdb.retention=720h #数据保存时长 - --web.enable-lifecycle #开启热加载 ports: - containerPort: 9090 protocol: TCP volumeMounts: - mountPath: /etc/prometheus/prometheus.yml name: prometheus-config subPath: prometheus.yml - mountPath: /prometheus/ name: prometheus-storage-volume volumes: - name: prometheus-config configMap: name: prometheus-config items: - key: prometheus.yml path: prometheus.yml mode: 0644 - name: prometheus-storage-volume hostPath: path: /data type: Directory kubectl apply -f prometheus-deploy.yaml kubectl get pods -o wide -n monitor-sa [root@master01 prometheus]# kubectl get pods -o wide -n monitor-sa NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES node-exporter-4mjm8 1/1 Running 5 15m 192.168.110.30 192.168.110.30 <none> <none> node-exporter-kzbpv 1/1 Running 5 15m 192.168.110.20 192.168.110.20 <none> <none> prometheus-server-75fb7f8fc6-9rrl7 0/1 Pending 0 49s <none> node01 <none> <none>

给 prometheus pod 创建一个 service

vim prometheus-svc.yaml --- apiVersion: v1 kind: Service metadata: name: prometheus namespace: monitor-sa labels: app: prometheus spec: type: NodePort ports: - port: 9090 targetPort: 9090 protocol: TCP nodePort: 31000 selector: app: prometheus component: server kubectl apply -f prometheus-svc.yaml kubectl get pods -o wide -n monitor-sa kubectl get svc -n monitor-sa [root@master01 prometheus]# kubectl get pods -o wide -n monitor-sa NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES node-exporter-7lfl8 1/1 Running 9 2d12h 192.168.110.20 192.168.110.20 <none> <none> node-exporter-hnpm2 1/1 Running 0 2d12h 192.168.110.30 192.168.110.30 <none> <none> prometheus-server-84b77ffcf8-mj5rp 1/1 Running 0 5m22s 10.244.60.102 192.168.110.20 <none> <none> [root@master01 prometheus]# kubectl get svc -n monitor-sa NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE prometheus NodePort 10.0.0.113 <none> 9090:31000/TCP 5d5h

如发现镜像拉取失败导致无法建立 pod 检查docker 版本，要使用19.xx.x-22.xx.x 版

通过上面可以看到 service 在 node 节点上映射的端口是 31000，这样我们访问 k8s 集群的 node 节点的 ip:31000，就可以访问到 prometheus 的 web ui 界面了。 浏览器访问 http://192.168.110.20:31000 点击页面的Status->Targets，如看到所有 Target 状态都为 UP，说明我们配置的服务发现可以正常采集数据

查询 K8S 集群中一分钟之内每个 Pod 的 CPU 使用率 sum by (name)( rate(container_cpu_usage_seconds_total{image!=“”, name!=“”}[1m] ) )

Prometheus 配置热加载

为了每次修改配置文件可以热加载prometheus，也就是不停止prometheus就可以使配置生效。想要使配置生效可用如下热加载命令：

kubectl get pods -n monitor-sa -o wide -l app=prometheus [root@master01 prometheus]# kubectl get pods -n monitor-sa -o wide -l app=prometheus NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES prometheus-server-84b77ffcf8-mj5rp 1/1 Running 0 13m 10.244.60.102 192.168.110.20 <none> <none>

想要使配置生效可用如下命令热加载

curl -X POST -Ls http://10.244.60.102:9090/-/reload

查看 log

kubectl logs -n monitor-sa prometheus-server-84b77ffcf8-mj5rp | grep "Loading configuration file" [root@master01 prometheus]# kubectl logs -n monitor-sa prometheus-server-84b77ffcf8-mj5rp | grep "Loading configuration file" level=info ts=2025-02-19T14:18:55.772194011Z caller=main.go:588 msg="Loading configuration file" filename=/etc/prometheus/prometheus.yml

一般热加载速度比较慢，可以暴力重启prometheus，如修改上面的 prometheus-cfg.yaml 文件之后，可用如下命令： 可执行先强制删除，然后再通过 apply 更新

kubectl delete -f prometheus-cfg.yaml kubectl delete -f prometheus-deploy.yaml kubectl apply -f prometheus-cfg.yaml kubectl apply -f prometheus-deploy.yaml Grafana 安装 部署 vim grafana.yaml --- apiVersion: apps/v1 kind: Deployment metadata: name: monitoring-grafana namespace: kube-system spec: replicas: 1 selector: matchLabels: task: monitoring k8s-app: grafana template: metadata: labels: task: monitoring k8s-app: grafana spec: containers: - name: grafana image: grafana/grafana:5.0.4 ports: - containerPort: 3000 protocol: TCP volumeMounts: - mountPath: /etc/ssl/certs name: ca-certificates readOnly: true - mountPath: /var name: grafana-storage env: - name: INFLUXDB_HOST value: monitoring-influxdb - name: GF_SERVER_HTTP_PORT value: "3000" # The following env variables are required to make Grafana accessible via # the kubernetes api-server proxy. On production clusters, we recommend # removing these env variables, setup auth for grafana, and expose the grafana # service using a LoadBalancer or a public IP. - name: GF_AUTH_BASIC_ENABLED value: "false" - name: GF_AUTH_ANONYMOUS_ENABLED value: "true" - name: GF_AUTH_ANONYMOUS_ORG_ROLE value: Admin - name: GF_SERVER_ROOT_URL # If you're only using the API Server proxy, set this value instead: # value: /api/v1/namespaces/kube-system/services/monitoring-grafana/proxy value: / volumes: - name: ca-certificates hostPath: path: /etc/ssl/certs - name: grafana-storage emptyDir: {} --- apiVersion: v1 kind: Service metadata: labels: # For use as a Cluster add-on ( github /kubernetes/kubernetes/tree/master/cluster/addons) # If you are NOT using this as an addon, you should comment out this line. kubernetes.io/cluster-service: 'true' kubernetes.io/name: monitoring-grafana name: monitoring-grafana namespace: kube-system spec: # In a production setup, we recommend accessing Grafana through an external Loadbalancer # or through a public IP. # type: LoadBalancer # You could also use NodePort to expose the service at a randomly-generated port # type: NodePort ports: - port: 80 targetPort: 3000 selector: k8s-app: grafana type: NodePort kubectl apply -f grafana.yaml kubectl get pods -n kube-system -l task=monitoring -o wide kubectl get svc -n kube-system | grep grafana [root@master01 prometheus]# kubectl get pods -n kube-system -l task=monitoring -o wide NAME READY STATUS RESTARTS AGE IP NODE NOMINATED NODE READINESS GATES monitoring-grafana-fd8554c5c-nffvn 1/1 Running 0 3m6s 10.244.60.107 192.168.110.20 <none> <none> [root@master01 prometheus]# kubectl get svc -n kube-system | grep grafana monitoring-grafana NodePort 10.0.0.231 <none> 80:35196/TCP 3m12s Grafana 配置

浏览器访问http://192.168.110.20:35196 ，登陆 grafana

开始配置 grafana 的 web 界面：选择 Add data source 【Name】设置成 Prometheus 【Type】选择 Prometheus 【URL】设置成 http://prometheus.monitor-sa.svc:9090 #使用service的集群内部端口配置服务端地址 点击 【Save & Test】

导入监控模板 官方链接搜索： grafana /dashboards?dataSource=prometheus&search=kubernetes

监控 node 状态 点击左侧+号选择【Import】 点击【Upload .json File】导入 node_exporter.json 模板 【Prometheus】选择 Prometheus 点击【Import】

监控 容器 状态 点击左侧+号选择【Import】 点击【Upload Upload .json File】导入 docker 模板 【Prometheus】选择 Prometheus 点击【Import】

k8s 部署 kube-state-metrics 组件 （1）安装 kube-state-metrics 组件

#创建 sa，并对 sa 授权 vim kube-state-metrics-rbac.yaml --- apiVersion: v1 kind: ServiceAccount metadata: name: kube-state-metrics namespace: kube-system --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRole metadata: name: kube-state-metrics rules: - apiGroups: [""] resources: ["nodes", "pods", "services", "resourcequotas", "replicationcontrollers", "limitranges", "persistentvolumeclaims", "persistentvolumes", "namespaces", "endpoints"] verbs: ["list", "watch"] - apiGroups: ["extensions"] resources: ["daemonsets", "deployments", "replicasets"] verbs: ["list", "watch"] - apiGroups: ["apps"] resources: ["statefulsets"] verbs: ["list", "watch"] - apiGroups: ["batch"] resources: ["cronjobs", "jobs"] verbs: ["list", "watch"] - apiGroups: ["autoscaling"] resources: ["horizontalpodautoscalers"] verbs: ["list", "watch"] --- apiVersion: rbac.authorization.k8s.io/v1 kind: ClusterRoleBinding metadata: name: kube-state-metrics roleRef: apiGroup: rbac.authorization.k8s.io kind: ClusterRole name: kube-state-metrics subjects: - kind: ServiceAccount name: kube-state-metrics namespace: kube-system kubectl apply -f kube-state-metrics-rbac.yaml #安装 kube-state-metrics 组件和 service vim kube-state-metrics-deploy.yaml --- apiVersion: apps/v1 kind: Deployment metadata: name: kube-state-metrics namespace: kube-system spec: replicas: 1 selector: matchLabels: app: kube-state-metrics template: metadata: labels: app: kube-state-metrics spec: serviceAccountName: kube-state-metrics containers: - name: kube-state-metrics image: quay.io/coreos/kube-state-metrics:v1.9.0 ports: - containerPort: 8080 --- apiVersion: v1 kind: Service metadata: annotations: prometheus.io/scrape: 'true' name: kube-state-metrics namespace: kube-system labels: app: kube-state-metrics spec: ports: - name: kube-state-metrics port: 8080 protocol: TCP selector: app: kube-state-metrics kubectl apply -f kube-state-metrics-deploy.yaml kubectl get pods,svc -n kube-system -l app=kube-state-metrics [root@master01 prometheus]# kubectl get pods,svc -n kube-system -l app=kube-state-metrics NAME READY STATUS RESTARTS AGE pod/kube-state-metrics-58d4957bc5-2vx5j 1/1 Running 0 9s NAME TYPE CLUSTER-IP EXTERNAL-IP PORT(S) AGE service/kube-state-metrics ClusterIP 10.0.0.41 <none> 8080/TCP 9s

（2）Grafana 配置 #监控 k8s 群集状态 点击左侧+号选择【Import】 点击【Upload .json File】导入 kubernetes-cluster-prometheus_rev4.json 模板 【Prometheus】选择 Prometheus 点击【Import】

监控 k8s 群集性能状态 点击左侧+号选择【Import】 点击【Upload .json File】导入 kubernetes-cluster-monitoring-via-prometheus_rev3.json 模板 【Prometheus】选择 Prometheus 点击【Import】