当前位置：首页 > news >正文

k8s Prometheus

news 2025/7/12 17:08:09

一、部署 Prometheus

kubectl create ns kube-ops

# 创建 prometheus-cm.yaml
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 15s # 表示 prometheus 抓取指标数据的频率，默认是 15sscrape_timeout: 15s # 表示 prometheus 抓取指标数据的超时时间，默认是 15sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']

# 创建 prometheus-pvc.yaml
kind: PersistentVolumeClaim
apiVersion: v1
metadata:name: prometheusnamespace: kube-ops
spec:storageClassName: nfs-storageaccessModes:- ReadWriteManyresources:requests:storage: 10Gi

# 创建prometheus-pv.yaml
apiVersion: v1
kind: PersistentVolume
metadata:name: prometheus # pv 名字
spec:capacity: # 容量storage: 10Gi # 存储空间accessModes: # 存储模式- ReadWriteMany persistentVolumeReclaimPolicy: Recycle # 持久卷回收策略storageClassName: nfs-storage # 存储类的名字nfs:path: /nfsdata/prometheus # nfs共享路径server: 10.0.17.100 # nfs服务器地址

# 创建 prometheus-rbac.yaml
apiVersion: v1
kind: ServiceAccount
metadata:name: prometheusnamespace: kube-ops
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:name: prometheus
rules:
- apiGroups:- ""resources:- nodes- services- endpoints- pods- nodes/proxyverbs:- get- list- watch
- apiGroups:- ""resources:- configmaps- nodes/metricsverbs:- get
- nonResourceURLs:- /metricsverbs:- get
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:name: prometheus
roleRef:apiGroup: rbac.authorization.k8s.iokind: ClusterRolename: prometheus

# 创建 prometheus-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:name: prometheusnamespace: kube-opslabels:app: prometheus
spec:selector:matchLabels:app: prometheustemplate:metadata:labels:app: prometheusspec:serviceAccountName: prometheuscontainers:- image: prom/prometheus:v2.4.3name: prometheuscommand:- "/bin/prometheus"args:- "--config.file=/etc/prometheus/prometheus.yml"- "--storage.tsdb.path=/prometheus"- "--storage.tsdb.retention=24h"- "--web.enable-admin-api"  # 控制对admin HTTP API的访问，其中包括删除时间序列等功能- "--web.enable-lifecycle"  # 支持热更新，直接执行localhost:9090/-/reload立即生效ports:- containerPort: 9090protocol: TCPname: httpvolumeMounts:- mountPath: "/prometheus"subPath: prometheusname: data- mountPath: "/etc/prometheus"name: config-volumeresources:requests:cpu: 100mmemory: 512Milimits:cpu: 100mmemory: 512MisecurityContext:runAsUser: 0volumes:- name: datapersistentVolumeClaim:claimName: prometheus- configMap:name: prometheus-configname: config-volume

# 创建 prometheus-svc.yaml 
apiVersion: v1
kind: Service
metadata:name: prometheusnamespace: kube-opslabels:app: prometheus
spec:selector:app: prometheustype: NodePortports:- name: webport: 9090targetPort: http

[root@master 01_prometheus]# kubectl get -n kube-ops svc
NAME         TYPE       CLUSTER-IP    EXTERNAL-IP   PORT(S)          AGE
prometheus   NodePort   10.7.124.89   <none>        9090:32010/TCP   30s

二、监控 ingress-nginx

Prometheus 的数据指标是通过一个公开的 HTTP(S) 数据接口获取到的，我们不需要单独安装监控的
agent，只需要暴露一个 metrics 接口，Prometheus 就会定期去拉取数据；对于一些普通的 HTTP 服
务，我们完全可以直接重用这个服务，添加一个 /metrics 接口暴露给 Prometheus

# 创建新的配置文件 prome-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']

# 重载 prometheus
[root@master 02_ingress-nginx]# kubectl get svc -n kube-ops 
NAME         TYPE       CLUSTER-IP    EXTERNAL-IP   PORT(S)          AGE
prometheus   NodePort   10.7.124.89   <none>        9090:32010/TCP   10m
[root@master 02_ingress-nginx]# curl -X POST "http://10.0.17.100:32010/-/reload"
# 查看 http://10.0.17.100:32010/targets# 确认是否捕获数据
PQL：
sum(nginx_ingress_controller_nginx_process_requests_total{controller_class="k8s.io/ingress-nginx",controller_namespace="ingress-nginx"})

三、创建 node-exporter，监控节点资源

node_exporter 就是抓取用于采集服务器节点的各种运行指标，目前 node_exporter 支持几乎所有常见
的监控点，比如 conntrack，cpu，diskstats，filesystem，loadavg，meminfo，netstat 等，详细的
监控点列表可以参考其 Github repo

# 创建 prome-node-exporter.yaml 
apiVersion: apps/v1
kind: DaemonSet
metadata:name: node-exporternamespace: kube-opslabels:name: node-exporter
spec:selector:matchLabels:name: node-exportertemplate:metadata:labels:name: node-exporterspec:hostPID: truehostIPC: truehostNetwork: truecontainers:- name: node-exporterimage: prom/node-exporter:v0.16.0ports:- containerPort: 9100resources:requests:cpu: 0.15securityContext:privileged: trueargs:- --path.procfs- /host/proc- --path.sysfs- /host/sys- --collector.filesystem.ignored-mount-points- '"^/(sys|proc|dev|host|etc)($|/)"'volumeMounts:- name: devmountPath: /host/dev- name: procmountPath: /host/proc- name: sysmountPath: /host/sys- name: rootfsmountPath: /rootfstolerations:- key: "node-role.kubernetes.io/control-plane"operator: "Exists"effect: "NoSchedule"volumes:- name: prochostPath:path: /proc- name: devhostPath:path: /dev- name: syshostPath:path: /sys- name: rootfshostPath:path: /

在 Kubernetes 下，prometheus 通过与 Kubernetes API 集成，目前主要支持5中服务发现模式，分别是：Node、Service、Pod、Endpoints、Ingress通过指定 kubernetes_sd_configs 的模式为 node ，Prometheus 就会自动从 Kubernetes 中发现所
有的 node 节点并作为当前 job 监控的目标实例，发现的节点 /metrics 接口是默认的 kubelet 的HTTP 接口
prometheus 去发现 Node 模式的服务的时候，访问的端口默认是10250，而现在该端口下面已经没有了 /metrics 指标数据了，现在 kubelet 只读的数据接口统一通过10255端口进行暴露了，所以我们应该去替换掉这里的端口，但是我们是要替换成10255端口吗？不是的，因为我们是要去配置上面通过node-exporter 抓取到的节点指标数据，而我们上面是不是指定了 hostNetwork=true ，所以在每个节点上就会绑定一个端口9100，所以我们应该将这里的10250替换成9100
这里我们就需要使用到 Prometheus 提供的 relabel_configs 中的 replace 能力了，relabel 可以在Prometheus 采集数据之前，通过Target 实例的 Metadata 信息，动态重新写入 Label 的值。除此之
外，我们还能根据 Target 实例的 Metadata 信息选择是否采集或者忽略该 Target 实例
添加了一个 action 为 labelmap ，正则表达式是 _meta_kubernetes_node_label(.+) 的配置，这里的意思就是表达式中匹配都的数据也添加到指标数据的 Label 标签中去。
对于 kubernetes_sd_configs 下面可用的标签如下：可用元标签：

_meta_kubernetes_node_name：节点对象的名称
_meta_kubernetes_node_label：节点对象中的每个标签
_meta_kubernetes_node_annotation：来自节点对象的每个注释
_meta_kubernetes_node_address：每个节点地址类型的第一个地址（如果存在） *
关于 kubernets_sd_configs 更多信息可以查看官方文档：kubernetes_sd_config
Kubernetes 1.11+ 版本以后，kubelet 就移除了 10255 端口， metrics 接口又回到了 10250 端口，所以这里不需要替换端口，但是需要使用 https 的协议

# 修改 prometheus 配置文件 prome-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)

[root@master 02_ingress-nginx]# curl -X POST "http://10.0.17.100:32010/-/reload"
# 查看 http://10.0.17.100:32010/targets

四、监控容器资源指标

说到容器监控我们自然会想到 cAdvisor ，我们前面也说过 cAdvisor 已经内置在了 kubelet 组件之中，所以我们不需要单独去安装， cAdvisor 的数据路径为 /api/v1/nodes//proxy/metrics ，同样我们这里使用 node 的服务发现模式，因为每一个节点下面都有 kubelet

# 修改 prometheus 配置文件，prome-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-cadvisor'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- target_label: __address__replacement: kubernetes.default.svc:443- source_labels: [__meta_kubernetes_node_name]regex: (.+)target_label: __metrics_path__replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor

[root@master 02_ingress-nginx]# curl -X POST "http://10.0.17.100:32010/-/reload"
# 查看 http://10.0.17.100:32010/targets

五、监控 ApiServer 指标

# 修改 prometheus 配置文件，prome-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-cadvisor'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- target_label: __address__replacement: kubernetes.default.svc:443- source_labels: [__meta_kubernetes_node_name]regex: (.+)target_label: __metrics_path__replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor- job_name: 'kubernetes-apiservers'kubernetes_sd_configs:- role: endpointsscheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name,__meta_kubernetes_endpoint_port_name]action: keepregex: default;kubernetes;https

[root@master 02_ingress-nginx]# curl -X POST "http://10.0.17.100:32010/-/reload"
# 查看 http://10.0.17.100:32010/targets

六、通过 Service 监控服务

# 修改 prometheus 配置文件，prome-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-cadvisor'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- target_label: __address__replacement: kubernetes.default.svc:443- source_labels: [__meta_kubernetes_node_name]regex: (.+)target_label: __metrics_path__replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor- job_name: 'kubernetes-apiservers'kubernetes_sd_configs:- role: endpointsscheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name,__meta_kubernetes_endpoint_port_name]action: keepregex: default;kubernetes;https- job_name: 'kubernetes-service-endpoints'kubernetes_sd_configs:- role: endpointsrelabel_configs:- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]action: keepregex: true- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]action: replacetarget_label: __scheme__regex: (https?)- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]action: replacetarget_label: __metrics_path__regex: (.+)- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]action: replacetarget_label: __address__regex: ([^:]+)(?::\d+)?;(\d+)replacement: $1:$2- action: labelmapregex: __meta_kubernetes_service_label_(.+)- source_labels: [__meta_kubernetes_namespace]action: replacetarget_label: kubernetes_namespace- source_labels: [__meta_kubernetes_service_name]action: replacetarget_label: kubernetes_name

[root@master 02_ingress-nginx]# curl -X POST "http://10.0.17.100:32010/-/reload"
# 查看 http://10.0.17.100:32010/targets

七、部署 kube-state-metrics，并监控

# 部署 kube-state-metrics，地址 https://github.com/kubernetes/kube-state-metrics
$ kubectl apply -f examples/standard

# 创建 kube-state-metrics 服务的 svc 文件，被监控，svc.yaml 
apiVersion: v1
kind: Service
metadata:annotations:prometheus.io/scrape: 'true'prometheus.io/port: "8080"namespace: kube-systemlabels:app: kube-state-metricsname: kube-state-metrics-exporter
spec:type: ClusterIPports:- name: 80-8080port: 80protocol: TCPtargetPort: 8080selector:app.kubernetes.io/name: kube-state-metrics

八、部署 grafana 服务

# 创建 grafana 部署文件
apiVersion: apps/v1
kind: Deployment
metadata:name: grafananamespace: kube-opslabels:app: grafana
spec:revisionHistoryLimit: 10selector:matchLabels:app: grafanatemplate:metadata:labels:app: grafanaspec:containers:- name: grafanaimage: grafana/grafana:5.3.4imagePullPolicy: IfNotPresentports:- containerPort: 3000name: grafanaenv:- name: GF_SECURITY_ADMIN_USERvalue: admin- name: GF_SECURITY_ADMIN_PASSWORDvalue: admin321readinessProbe:failureThreshold: 10httpGet:path: /api/healthport: 3000scheme: HTTPinitialDelaySeconds: 60periodSeconds: 10successThreshold: 1timeoutSeconds: 30livenessProbe:failureThreshold: 3httpGet:path: /api/healthport: 3000scheme: HTTPperiodSeconds: 10successThreshold: 1timeoutSeconds: 1resources:limits:cpu: 100mmemory: 256Mirequests:cpu: 100mmemory: 256MivolumeMounts:- mountPath: /var/lib/grafanasubPath: grafananame: storagesecurityContext:fsGroup: 472runAsUser: 472volumes:- name: storagepersistentVolumeClaim:claimName: grafana

# 创建 grafana-pvc.yaml
kind: PersistentVolumeClaim
apiVersion: v1
metadata:name: grafananamespace: kube-ops
spec:storageClassName: nfs-storageaccessModes:- ReadWriteManyresources:requests:storage: 1Gi

# 创建prometheus-pv.yaml
apiVersion: v1
kind: PersistentVolume
metadata:name: grafana # pv 名字
spec:capacity: # 容量storage: 1Gi # 存储空间accessModes: # 存储模式- ReadWriteMany persistentVolumeReclaimPolicy: Recycle # 持久卷回收策略storageClassName: nfs-storage # 存储类的名字nfs:path: /nfsdata/grafana # nfs共享路径server: 10.0.17.100 # nfs服务器地址

# 创建 grafan svc 文件，grafana-svc.yaml 
apiVersion: v1
kind: Service
metadata:name: grafananamespace: kube-opslabels:app: grafana
spec:type: NodePortports:- port: 3000selector:app: grafana

# 创建 job，调整 grafana 挂载目录权限，grafana-chown-job.yaml 
apiVersion: batch/v1
kind: Job
metadata:name: grafana-chownnamespace: kube-ops
spec:template:spec:restartPolicy: Nevercontainers:- name: grafana-chowncommand: ["chown", "-R", "472:472", "/var/lib/grafana"]image: busyboximagePullPolicy: IfNotPresentvolumeMounts:- name: storagesubPath: grafanamountPath: /var/lib/grafanavolumes:- name: storagepersistentVolumeClaim:claimName: grafana

http://10.0.17.100:32362
#添加数据源 Type选择Prometheus url由于Prometheus和grafana处于同一pod http://prometheus:9090
# save&test

数据面板json文件

{"annotations": {"list": [{"builtIn": 1,"datasource": "-- Grafana --","enable": true,"hide": true,"iconColor": "rgba(0, 211, 255, 1)","name": "Annotations & Alerts","type": "dashboard"}]},"editable": true,"gnetId": null,"graphTooltip": 0,"id": 1,"links": [],"panels": [{"collapsed": false,"gridPos": {"h": 1,"w": 24,"x": 0,"y": 0},"id": 40,"panels": [],"title": "Kubernetes 指标","type": "row"},{"aliasColors": {},"bars": false,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 7,"w": 8,"x": 0,"y": 1},"id": 38,"legend": {"alignAsTable": false,"avg": false,"current": false,"hideEmpty": false,"max": false,"min": false,"rightSide": false,"show": true,"total": false,"values": false},"lines": true,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "sum(rate(apiserver_request_total[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "一分钟平均","refId": "A"},{"expr": "sum(rate(apiserver_request_total[5m]))","format": "time_series","intervalFactor": 1,"legendFormat": "五分钟平均","refId": "B"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "ApiServer 每分钟请求数","tooltip": {"shared": true,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "time","name": null,"show": true,"values": []},"yaxes": [{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"cacheTimeout": null,"colorBackground": false,"colorValue": false,"colors": ["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource": "prometheus","format": "none","gauge": {"maxValue": 100,"minValue": 0,"show": false,"thresholdLabels": false,"thresholdMarkers": true},"gridPos": {"h": 7,"w": 4,"x": 8,"y": 1},"id": 32,"interval": null,"links": [],"mappingType": 1,"mappingTypes": [{"name": "value to text","value": 1},{"name": "range to text","value": 2}],"maxDataPoints": 100,"nullPointMode": "connected","nullText": null,"postfix": "","postfixFontSize": "50%","prefix": "","prefixFontSize": "50%","rangeMaps": [{"from": "null","text": "N/A","to": "null"}],"sparkline": {"fillColor": "rgba(31, 118, 189, 0.18)","full": false,"lineColor": "rgb(31, 120, 193)","show": false},"tableColumn": "","targets": [{"expr": "kubelet_active_pods{beta_kubernetes_io_arch=\"amd64\",beta_kubernetes_io_os=\"linux\",instance=\"master\",job=\"kubernetes-kubelet\",kubernetes_io_arch=\"amd64\",kubernetes_io_hostname=\"master\",kubernetes_io_os=\"linux\",static=\"\"}","format": "time_series","intervalFactor": 1,"legendFormat": "","refId": "A"}],"thresholds": "","title": "Master Pod 总量","type": "singlestat","valueFontSize": "80%","valueMaps": [{"op": "=","text": "N/A","value": "null"}],"valueName": "avg"},{"cacheTimeout": null,"colorBackground": false,"colorValue": false,"colors": ["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource": "prometheus","format": "none","gauge": {"maxValue": 100,"minValue": 0,"show": false,"thresholdLabels": false,"thresholdMarkers": true},"gridPos": {"h": 7,"w": 4,"x": 12,"y": 1},"id": 34,"interval": null,"links": [],"mappingType": 1,"mappingTypes": [{"name": "value to text","value": 1},{"name": "range to text","value": 2}],"maxDataPoints": 100,"nullPointMode": "connected","nullText": null,"postfix": "","postfixFontSize": "50%","prefix": "","prefixFontSize": "50%","rangeMaps": [{"from": "null","text": "N/A","to": "null"}],"sparkline": {"fillColor": "rgba(31, 118, 189, 0.18)","full": false,"lineColor": "rgb(31, 120, 193)","show": false},"tableColumn": "","targets": [{"expr": "kubelet_active_pods{kubernetes_io_hostname=\"node1\",static=\"\"}","format": "time_series","intervalFactor": 1,"refId": "A"}],"thresholds": "","title": "node1 Pod 总量","type": "singlestat","valueFontSize": "80%","valueMaps": [{"op": "=","text": "N/A","value": "null"}],"valueName": "avg"},{"cacheTimeout": null,"colorBackground": false,"colorValue": false,"colors": ["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource": "prometheus","format": "none","gauge": {"maxValue": 100,"minValue": 0,"show": false,"thresholdLabels": false,"thresholdMarkers": true},"gridPos": {"h": 7,"w": 4,"x": 16,"y": 1},"id": 36,"interval": null,"links": [],"mappingType": 1,"mappingTypes": [{"name": "value to text","value": 1},{"name": "range to text","value": 2}],"maxDataPoints": 100,"nullPointMode": "connected","nullText": null,"postfix": "","postfixFontSize": "50%","prefix": "","prefixFontSize": "50%","rangeMaps": [{"from": "null","text": "N/A","to": "null"}],"sparkline": {"fillColor": "rgba(31, 118, 189, 0.18)","full": false,"lineColor": "rgb(31, 120, 193)","show": false},"tableColumn": "","targets": [{"expr": "kubelet_active_pods{kubernetes_io_hostname=\"node2\",static=\"\"}","format": "time_series","intervalFactor": 1,"refId": "A"}],"thresholds": "","title": "node2 Pod 总量","type": "singlestat","valueFontSize": "80%","valueMaps": [{"op": "=","text": "N/A","value": "null"}],"valueName": "avg"},{"collapsed": false,"gridPos": {"h": 1,"w": 24,"x": 0,"y": 8},"id": 24,"panels": [],"title": "Kubernetes 物理机","type": "row"},{"aliasColors": {},"bars": true,"dashLength": 10,"dashes": false,"datasource": "prometheus","decimals": null,"fill": 4,"gridPos": {"h": 6,"w": 8,"x": 0,"y": 9},"id": 10,"legend": {"alignAsTable": false,"avg": false,"current": false,"hideEmpty": false,"max": false,"min": false,"rightSide": false,"show": true,"total": false,"values": false},"lines": false,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "100 * (1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\", instance=\"master\"}[1m])))  ","format": "time_series","hide": false,"intervalFactor": 1,"legendFormat": "Master01","refId": "A"},{"expr": "100 * (1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\", instance=\"node1\"}[1m])))","format": "time_series","hide": false,"intervalFactor": 1,"legendFormat": "Node01","refId": "B"},{"expr": "100 * (1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\", instance=\"node2\"}[1m])))","format": "time_series","hide": false,"intervalFactor": 1,"legendFormat": "Node02","refId": "C"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "CPU 使用量（百分比）","tooltip": {"shared": false,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "series","name": null,"show": true,"values": ["current"]},"yaxes": [{"format": "none","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"aliasColors": {},"bars": true,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 3,"gridPos": {"h": 6,"w": 8,"x": 8,"y": 9},"id": 2,"legend": {"alignAsTable": false,"avg": false,"current": false,"hideEmpty": false,"max": false,"min": false,"rightSide": false,"show": false,"total": false,"values": false},"lines": false,"linewidth": 3,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "(node_memory_MemTotal_bytes{instance=\"master\"} - (node_memory_MemFree_bytes{instance=\"master\"} + node_memory_Buffers_bytes{instance=\"master\"} + node_memory_Cached_bytes{instance=\"master\"})) / node_memory_MemTotal_bytes{instance=\"master\"} * 100","format": "time_series","intervalFactor": 1,"legendFormat": "Master","refId": "A"},{8"expr": "(node_memory_MemTotal_bytes{instance=\"node1\"} - (node_memory_MemFree_bytes{instance=\"node1\"} + node_memory_Buffers_bytes{instance=\"node1\"} + node_memory_Cached_bytes{instance=\"node1\"})) / node_memory_MemTotal_bytes{instance=\"node1\"} * 100","format": "time_series","intervalFactor": 1,"legendFormat": "node1","refId": "B"},{"expr": "(node_memory_MemTotal_bytes{instance=\"node2\"} - (node_memory_MemFree_bytes{instance=\"node2\"} + node_memory_Buffers_bytes{instance=\"node2\"} + node_memory_Cached_bytes{instance=\"node2\"})) / node_memory_MemTotal_bytes{instance=\"node2\"} * 100","format": "time_series","hide": false,"intervalFactor": 1,"legendFormat": "node2","refId": "C"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "内存使用量（百分比）","tooltip": {"shared": false,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "series","name": null,"show": true,"values": ["current"]},"yaxes": [{"format": "none","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"decimals": null,"format": "none","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"aliasColors": {},"bars": true,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 6,"w": 8,"x": 16,"y": 9},"id": 18,"legend": {"avg": false,"current": false,"max": false,"min": false,"show": false,"total": false,"values": false},"lines": false,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "node_filesystem_avail_bytes{device=\"/dev/mapper/rl-root\",mountpoint=\"/rootfs\",instance=\"master\"}","format": "time_series","intervalFactor": 1,"legendFormat": "Master01","refId": "A"},{"expr": "node_filesystem_avail_bytes{device=\"/dev/mapper/rl-root\",mountpoint=\"/rootfs\",instance=\"node1\"}","format": "time_series","intervalFactor": 1,"legendFormat": "Node01","refId": "B"},{"expr": "node_filesystem_avail_bytes{device=\"/dev/mapper/rl-root\",mountpoint=\"/rootfs\",instance=\"node2\"}","format": "time_series","intervalFactor": 1,"legendFormat": "Node02","refId": "C"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "存储空间剩余量","tooltip": {"shared": false,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "series","name": null,"show": true,"values": ["current"]},"yaxes": [{"format": "bytes","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"aliasColors": {},"bars": false,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 6,"w": 24,"x": 0,"y": 15},"id": 12,"legend": {"avg": false,"current": false,"max": false,"min": false,"show": true,"total": false,"values": false},"lines": true,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": true,"steppedLine": false,"targets": [{"expr": "sum(rate(node_network_receive_bytes_total{instance=\"master\"}[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "Master01 下行","refId": "A"},{"expr": "sum(rate(node_network_transmit_bytes_total{instance=\"master\"}[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "Master01 上行","refId": "B"},{"expr": "sum(rate(node_network_receive_bytes_total{instance=\"node1\"}[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "Node01  下行","refId": "C"},{"expr": "sum(rate(node_network_transmit_bytes_total{instance=\"node1\"}[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "Node01 上行","refId": "D"},{"expr": "sum(rate(node_network_receive_bytes_total{instance=\"node2\"}[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "Node02 下行","refId": "E"},{"expr": "sum(rate(node_network_transmit_bytes_total{instance=\"node2\"}[1m]))","format": "time_series","intervalFactor": 1,"legendFormat": "Node02 上行","refId": "F"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "网络 IO","tooltip": {"shared": true,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "time","name": null,"show": true,"values": []},"yaxes": [{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"collapsed": false,"gridPos": {"h": 1,"w": 24,"x": 0,"y": 21},"id": 16,"panels": [],"repeat": null,"title": "Pod","type": "row"},{"aliasColors": {},"bars": false,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 7,"w": 8,"x": 0,"y": 22},"id": 20,"legend": {"avg": false,"current": false,"max": false,"min": false,"show": true,"total": false,"values": false},"lines": true,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "100 *  (sum(rate(container_cpu_usage_seconds_total{namespace=\"kube-system\", pod=\"kube-apiserver-master\"}[1m])) by (namespace, pod))","format": "time_series","interval": "","intervalFactor": 1,"legendFormat": "apiServer","refId": "A"},{"expr": "","format": "time_series","intervalFactor": 1,"refId": "B"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "Pod  CPU 使用量","tooltip": {"shared": true,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "time","name": null,"show": true,"values": []},"yaxes": [{"format": "none","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"aliasColors": {},"bars": false,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 7,"w": 8,"x": 8,"y": 22},"id": 22,"legend": {"avg": false,"current": false,"max": false,"min": false,"show": true,"total": false,"values": false},"lines": true,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "sum(container_memory_usage_bytes{namespace=\"kube-system\", pod=\"kube-apiserver-master\"}) by (namespace, pod)","format": "time_series","intervalFactor": 1,"legendFormat": "apiServer","refId": "A"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "Pod 内存使用量","tooltip": {"shared": true,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "time","name": null,"show": true,"values": []},"yaxes": [{"format": "bytes","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"collapsed": false,"gridPos": {"h": 1,"w": 24,"x": 0,"y": 29},"id": 8,"panels": [],"title": "Ingress-Nginx","type": "row"},{"cacheTimeout": null,"colorBackground": false,"colorValue": false,"colors": ["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource": "prometheus","format": "none","gauge": {"maxValue": 100,"minValue": 0,"show": false,"thresholdLabels": false,"thresholdMarkers": true},"gridPos": {"h": 2,"w": 4,"x": 0,"y": 30},"id": 28,"interval": null,"links": [],"mappingType": 1,"mappingTypes": [{"name": "value to text","value": 1},{"name": "range to text","value": 2}],"maxDataPoints": 100,"nullPointMode": "connected","nullText": null,"postfix": "","postfixFontSize": "50%","prefix": "","prefixFontSize": "50%","rangeMaps": [{"from": "null","text": "N/A","to": "null"}],"sparkline": {"fillColor": "rgba(31, 118, 189, 0.18)","full": false,"lineColor": "rgb(31, 120, 193)","show": false},"tableColumn": "","targets": [{"expr": "nginx_ingress_controller_success{job=\"ingressnginx12\"}","format": "time_series","intervalFactor": 1,"legendFormat": "node01","refId": "A"},{"expr": "","format": "time_series","intervalFactor": 1,"refId": "B"}],"thresholds": "","title": "node1 Nginx-ingress 重载次数","type": "singlestat","valueFontSize": "80%","valueMaps": [{"op": "=","text": "N/A","value": "null"}],"valueName": "avg"},{"cacheTimeout": null,"colorBackground": false,"colorValue": false,"colors": ["#299c46","rgba(237, 129, 40, 0.89)","#d44a3a"],"datasource": "prometheus","format": "none","gauge": {"maxValue": 100,"minValue": 0,"show": false,"thresholdLabels": false,"thresholdMarkers": true},"gridPos": {"h": 2,"w": 4,"x": 4,"y": 30},"id": 30,"interval": null,"links": [],"mappingType": 1,"mappingTypes": [{"name": "value to text","value": 1},{"name": "range to text","value": 2}],"maxDataPoints": 100,"nullPointMode": "connected","nullText": null,"postfix": "","postfixFontSize": "50%","prefix": "","prefixFontSize": "50%","rangeMaps": [{"from": "null","text": "N/A","to": "null"}],"sparkline": {"fillColor": "rgba(31, 118, 189, 0.18)","full": false,"lineColor": "rgb(31, 120, 193)","show": false},"tableColumn": "","targets": [{"expr": "nginx_ingress_controller_success{job=\"ingressnginx13\"}","format": "time_series","intervalFactor": 1,"refId": "A"}],"thresholds": "","title": "node2 Nginx-ingress 重载次数","type": "singlestat","valueFontSize": "80%","valueMaps": [{"op": "=","text": "N/A","value": "null"}],"valueName": "avg"},{"aliasColors": {},"bars": false,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 5,"w": 8,"x": 0,"y": 32},"id": 4,"legend": {"avg": false,"current": false,"max": false,"min": false,"show": true,"total": false,"values": false},"lines": true,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "nginx_ingress_controller_nginx_process_requests_total{controller_class=\"k8s.io/ingress-nginx\",controller_namespace=\"ingress\",controller_pod=\"ingress-nginx-controller-c5h6j\",instance=\"10.0.17.101:10254\",job=\"ingressnginx12\"}","format": "time_series","intervalFactor": 1,"legendFormat": "node01","refId": "A"},{"expr": "nginx_ingress_controller_nginx_process_requests_total{controller_class=\"k8s.io/ingress-nginx\",controller_namespace=\"ingress\",controller_pod=\"ingress-nginx-controller-c5h6j\",instance=\"10.0.17.102:10254\",job=\"ingressnginx12\"}","format": "time_series","intervalFactor": 1,"legendFormat": "node02","refId": "B"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "Ingress-Nginx 请求量","tooltip": {"shared": true,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "time","name": null,"show": true,"values": []},"yaxes": [{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}},{"collapsed": false,"gridPos": {"h": 1,"w": 24,"x": 0,"y": 37},"id": 6,"panels": [],"title": "NFS-StorageClass","type": "row"},{"aliasColors": {},"bars": false,"dashLength": 10,"dashes": false,"datasource": "prometheus","fill": 1,"gridPos": {"h": 6,"w": 24,"x": 0,"y": 38},"id": 14,"legend": {"avg": false,"current": false,"max": false,"min": false,"show": true,"total": false,"values": false},"lines": true,"linewidth": 1,"links": [],"nullPointMode": "null","percentage": false,"pointradius": 5,"points": false,"renderer": "flot","seriesOverrides": [],"spaceLength": 10,"stack": false,"steppedLine": false,"targets": [{"expr": "node_nfsd_disk_bytes_read_total{beta_kubernetes_io_arch=\"amd64\",beta_kubernetes_io_os=\"linux\",instance=\"master\",job=\"kubernetes-nodes\",kubernetes_io_arch=\"amd64\",kubernetes_io_hostname=\"master\",kubernetes_io_os=\"linux\"}","format": "time_series","intervalFactor": 1,"legendFormat": "读取总量","refId": "A"},{"expr": "node_nfsd_disk_bytes_written_total{beta_kubernetes_io_arch=\"amd64\",beta_kubernetes_io_os=\"linux\",instance=\"master\",job=\"kubernetes-nodes\",kubernetes_io_arch=\"amd64\",kubernetes_io_hostname=\"master\",kubernetes_io_os=\"linux\"}","format": "time_series","intervalFactor": 1,"legendFormat": "写入总量","refId": "B"}],"thresholds": [],"timeFrom": null,"timeShift": null,"title": "NFS storageClass 读取文件总量","tooltip": {"shared": true,"sort": 0,"value_type": "individual"},"type": "graph","xaxis": {"buckets": null,"mode": "time","name": null,"show": true,"values": []},"yaxes": [{"format": "decbytes","label": null,"logBase": 1,"max": null,"min": null,"show": true},{"format": "short","label": null,"logBase": 1,"max": null,"min": null,"show": true}],"yaxis": {"align": false,"alignLevel": null}}],"refresh": false,"schemaVersion": 16,"style": "dark","tags": [],"templating": {"list": []},"time": {"from": "now-6h","to": "now"},"timepicker": {"refresh_intervals": ["5s","10s","30s","1m","5m","15m","30m","1h","2h","1d"],"time_options": ["5m","15m","1h","6h","12h","24h","2d","7d","30d"]},"timezone": "","title": "Kubernetes 监控","uid": "Lwdu47xIk","version": 2
}

九、监控 metrics.server

从 Kubernetes v1.8 开始，资源使用情况的监控可以通过 Metrics API 的形式获取，例如容器 CPU 和内存使用率。这些度量可以由用户直接访问（例如，通过使用 kubectl top 命令），或者由集群中的控制
器（例如，Horizontal Pod Autoscaler）使用来进行决策，具体的组件为 Metrics Server，用来替换之前的 heapster，heapster 从 1.11 开始逐渐被废弃。
Metrics-Server 是集群核心监控数据的聚合器。通俗地说，它存储了集群中各节点的监控数据，并且提供了 API 以供分析和使用。Metrics-Server 作为一个 Deployment 对象默认部署在 Kubernetes 集群
中。不过准确地说，它是 Deployment，Service，ClusterRole，ClusterRoleBinding，APIService，RoleBinding 等资源对象的综合体。

# https://github.com/kubernetes-sigs/metrics-server
kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml

[root@master 09_metrics-server]# kubectl top pod -A
NAMESPACE     NAME                                            CPU(cores)   MEMORY(bytes)   
default       proxyhttps-deploy-69798bfdb9-fwshg              0m           4Mi             
ingress       ingress-nginx-controller-rrh9d                  3m           84Mi            
ingress       ingress-nginx-controller-x4dgn                  1m           89Mi            
ingress       ingress-nginx-defaultbackend-774db5d85d-v2rvr   1m           9Mi             
kube-ops      grafana-b64b67875-4j4ss                         1m           40Mi            
kube-ops      node-exporter-qjpf8                             0m           13Mi            
kube-ops      node-exporter-xfm95                             2m           14Mi            
kube-ops      node-exporter-xvhmg                             2m           19Mi            
kube-ops      prometheus-844847f5c7-hsvlh                     5m           211Mi           
kube-system   calico-kube-controllers-558d465845-btr5r        3m           36Mi            
kube-system   calico-node-f5r9h                               20m          103Mi           
kube-system   calico-node-g2s29                               21m          121Mi           
kube-system   calico-node-x2jq7                               34m          161Mi           
kube-system   calico-typha-5b56944f9b-r96gn                   2m           45Mi            
kube-system   coredns-857d9ff4c9-6cb2b                        3m           48Mi            
kube-system   coredns-857d9ff4c9-tvrff                        2m           50Mi            
kube-system   etcd-master                                     25m          184Mi           
kube-system   kube-apiserver-master                           51m          552Mi           
kube-system   kube-controller-manager-master                  14m          139Mi           
kube-system   kube-proxy-jwvjm                                9m           72Mi            
kube-system   kube-proxy-rf7hf                                14m          32Mi            
kube-system   kube-proxy-s885z                                1m           32Mi            
kube-system   kube-scheduler-master                           5m           69Mi            
kube-system   metrics-server-75bbd6fd46-7j49n                 3m           65Mi            
ubuntu        test-676c94bbbb-gzvmb                           0m           0Mi

apiVersion: v1
kind: ServiceAccount
metadata:labels:k8s-app: metrics-servername: metrics-servernamespace: kube-system
---apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:labels:k8s-app: metrics-serverrbac.authorization.k8s.io/aggregate-to-admin: "true"rbac.authorization.k8s.io/aggregate-to-edit: "true"rbac.authorization.k8s.io/aggregate-to-view: "true"name: system:aggregated-metrics-reader
rules:
- apiGroups:- metrics.k8s.ioresources:- pods- nodesverbs:- get- list- watch
---apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:labels:k8s-app: metrics-servername: system:metrics-server
rules:
- apiGroups:- ""resources:- nodes/metricsverbs:- get
- apiGroups:- ""resources:- pods- nodesverbs:- get- list- watch
---apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:labels:k8s-app: metrics-servername: metrics-server-auth-readernamespace: kube-system
roleRef:apiGroup: rbac.authorization.k8s.iokind: Rolename: extension-apiserver-authentication-reader
subjects:
- kind: ServiceAccountname: metrics-servernamespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:labels:k8s-app: metrics-servername: metrics-server:system:auth-delegator
roleRef:apiGroup: rbac.authorization.k8s.iokind: ClusterRolename: system:auth-delegator
subjects:
- kind: ServiceAccountname: metrics-servernamespace: kube-system
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:labels:k8s-app: metrics-servername: system:metrics-server
roleRef:apiGroup: rbac.authorization.k8s.iokind: ClusterRolename: system:metrics-server
subjects:
- kind: ServiceAccountname: metrics-servernamespace: kube-system
---
apiVersion: v1
kind: Service
metadata:labels:k8s-app: metrics-servername: metrics-servernamespace: kube-system
spec:ports:- name: httpsport: 443protocol: TCPtargetPort: httpsselector:k8s-app: metrics-server
---
apiVersion: apps/v1
kind: Deployment
metadata:labels:k8s-app: metrics-servername: metrics-servernamespace: kube-system
spec:selector:matchLabels:k8s-app: metrics-serverstrategy:rollingUpdate:maxUnavailable: 0template:metadata:labels:k8s-app: metrics-serverspec:containers:- args:- --cert-dir=/tmp- --secure-port=4443- --kubelet-preferred-address-types=InternalIP,ExternalIP,Hostname- --kubelet-use-node-status-port- --metric-resolution=15s- --kubelet-preferred-address-types=InternalIP   # InternalIP\Hostname\InternalDNS\ExternalDNS\ExternalIP, Hostname 默认的通过主机名通讯，InternalIP 需要显示设置后才能通过 IP 通讯- --kubelet-insecure-tls     # 如果不想设置 kubelet 的证书认证，可以通过此选项跳过认证image: registry.k8s.io/metrics-server/metrics-server:v0.6.4imagePullPolicy: IfNotPresentlivenessProbe:failureThreshold: 3httpGet:path: /livezport: httpsscheme: HTTPSperiodSeconds: 10name: metrics-serverports:- containerPort: 4443name: httpsprotocol: TCPreadinessProbe:failureThreshold: 3httpGet:path: /readyzport: httpsscheme: HTTPSinitialDelaySeconds: 20periodSeconds: 10resources:requests:cpu: 100mmemory: 200MisecurityContext:allowPrivilegeEscalation: falsereadOnlyRootFilesystem: truerunAsNonRoot: truerunAsUser: 1000volumeMounts:- mountPath: /tmpname: tmp-dirnodeSelector:kubernetes.io/os: linuxpriorityClassName: system-cluster-criticalserviceAccountName: metrics-servervolumes:- emptyDir: {}name: tmp-dir
---
apiVersion: apiregistration.k8s.io/v1
kind: APIService
metadata:labels:k8s-app: metrics-servername: v1beta1.metrics.k8s.io
spec:group: metrics.k8s.iogroupPriorityMinimum: 100insecureSkipTLSVerify: true #跳过安全认证service:name: metrics-servernamespace: kube-systemversion: v1beta1versionPriority: 100

十、alertmanager 部署

# 创建 alertmanager 配置文件，alertmanager-conf.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: alert-confignamespace: kube-ops
data:config.yml: |-global:  # 在没有报警的情况下声明为已解决的时间resolve_timeout: 5m# 配置邮件发送信息smtp_smarthost: 'smtp.163.com:25'  # smtp服务地址端口smtp_from: 'wangyanglinux@163.com' # smtp服务地址smtp_auth_username: 'wangyanglinux@163.com' # smtp账号smtp_auth_password: 'APYDOSTDPDUOEEHQ' # stmp密码smtp_hello: '163.com'smtp_require_tls: false  # 所有报警信息进入后的根路由，用来设置报警的分发策略route:# 这里的标签列表是接收到报警信息后的重新分组标签，例如，接收到的报警信息里面有许多具有cluster=A 和 alertname=LatncyHigh 这样的标签的报警信息将会批量被聚合到一个分组里面group_by: ['alertname', 'cluster']# 当一个新的报警分组被创建后，需要等待至少group_wait时间来初始化通知，这种方式可以确保您能有足够的时间为同一分组来获取多个警报，然后一起触发这个报警信息。group_wait: 30s# 当第一个报警发送后，等待'group_interval'时间来发送新的一组报警信息。group_interval: 5m# 如果一个报警信息已经发送成功了，等待'repeat_interval'时间来重新发送他们repeat_interval: 5m# 默认的receiver：如果一个报警没有被一个route匹配，则发送给默认的接收器receiver: default# 上面所有的属性都由所有子路由继承，并且可以在每个子路由上进行覆盖。routes:- receiver: emailgroup_wait: 10smatch:team: nodereceivers:- name: 'default'email_configs:- to: 'wangyanglinux@88.com' # 接收邮箱send_resolved: true- name: 'email'email_configs:- to: 'wangyanglinux@88.com'  # 接收邮箱send_resolved: true

# 修改 prometheus 配置文件，prometheus-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-cadvisor'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- target_label: __address__replacement: kubernetes.default.svc:443- source_labels: [__meta_kubernetes_node_name]regex: (.+)target_label: __metrics_path__replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor- job_name: 'kubernetes-apiservers'kubernetes_sd_configs:- role: endpointsscheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]action: keepregex: default;kubernetes;https- job_name: 'kubernetes-service-endpoints'kubernetes_sd_configs:- role: endpointsrelabel_configs:- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]action: keepregex: true- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]action: replacetarget_label: __scheme__regex: (https?)- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]action: replacetarget_label: __metrics_path__regex: (.+)- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]action: replacetarget_label: __address__regex: ([^:]+)(?::\d+)?;(\d+)replacement: $1:$2- action: labelmapregex: __meta_kubernetes_service_label_(.+)- source_labels: [__meta_kubernetes_namespace]action: replacetarget_label: kubernetes_namespace- source_labels: [__meta_kubernetes_service_name]action: replacetarget_label: kubernetes_namealerting:alertmanagers:- static_configs:- targets: ["localhost:9093"]

# 修改 prometheus service 文件， prometheus-svc.yaml
apiVersion: v1
kind: Service
metadata:name: prometheusnamespace: kube-opslabels:app: prometheus
spec:selector:app: prometheustype: NodePortports:- name: webport: 9090targetPort: http- name: altermanagerport: 9093targetPort: 9093

# 合并 altermanager 至 prometheus deploy 文件，promethus-alertmanager-deploy.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:name: prometheusnamespace: kube-opslabels:app: prometheus
spec:selector:matchLabels:app: prometheustemplate:metadata:labels:app: prometheusspec:serviceAccountName: prometheuscontainers:- name: alertmanagerimage: prom/alertmanager:v0.15.3imagePullPolicy: IfNotPresentargs:- "--config.file=/etc/alertmanager/config.yml"- "--storage.path=/alertmanager/data"ports:- containerPort: 9093name: alertmanagervolumeMounts:- mountPath: "/etc/alertmanager"name: alertcfgresources:requests:cpu: 100mmemory: 256Milimits:cpu: 100mmemory: 256Mi- image: prom/prometheus:v2.4.3name: prometheuscommand:- "/bin/prometheus"args:- "--config.file=/etc/prometheus/prometheus.yml"- "--storage.tsdb.path=/prometheus"- "--storage.tsdb.retention=24h"- "--web.enable-admin-api"  # 控制对admin HTTP API的访问，其中包括删除时间序列等功能- "--web.enable-lifecycle"  # 支持热更新，直接执行localhost:9090/-/reload立即生效ports:- containerPort: 9090protocol: TCPname: httpvolumeMounts:- mountPath: "/prometheus"subPath: prometheusname: data- mountPath: "/etc/prometheus"name: config-volumeresources:requests:cpu: 100mmemory: 512Milimits:cpu: 100mmemory: 512MisecurityContext:runAsUser: 0volumes:- name: datapersistentVolumeClaim:claimName: prometheus- configMap:name: prometheus-configname: config-volume- name: alertcfgconfigMap:name: alert-config

添加报警演示

# 修改 prometheus cm，添加监控 mem 使用量，prometheus-cm-test.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:rules.yml: |groups:- name: test-rulerules:- alert: NodeMemoryUsageexpr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 > 20for: 2mlabels:team: nodeannotations:summary: "{{$labels.instance}}: High Memory usage detected"description: "{{$labels.instance}}: Memory usage is above 20% (current 
value is: {{ $value }}"prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-cadvisor'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __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-apiservers'kubernetes_sd_configs:- role: endpointsscheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]action: keepregex: default;kubernetes;https- job_name: 'kubernetes-service-endpoints'kubernetes_sd_configs:- role: endpointsrelabel_configs:- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]action: keepregex: true- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]action: replacetarget_label: __scheme__regex: (https?)- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]action: replacetarget_label: __metrics_path__regex: (.+)- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]action: replacetarget_label: __address__regex: ([^:]+)(?::\d+)?;(\d+)replacement: $1:$2- action: labelmapregex: __meta_kubernetes_service_label_(.+)- source_labels: [__meta_kubernetes_namespace]action: replacetarget_label: kubernetes_namespace- source_labels: [__meta_kubernetes_service_name]action: replacetarget_label: kubernetes_namealerting:alertmanagers:- static_configs:- targets: ["localhost:9093"]rule_files:- /etc/prometheus/rules.yml

去除无效监控项

# 删除监控 mem 项，prometheus-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:name: prometheus-confignamespace: kube-ops
data:rules.yml: |groups:prometheus.yml: |global:scrape_interval: 30sscrape_timeout: 30sscrape_configs:- job_name: 'prometheus'static_configs:- targets: ['localhost:9090']- job_name: 'ingressnginx12'static_configs:- targets: ['10.0.17.101:10254']- job_name: 'ingressnginx13'static_configs:- targets: ['10.0.17.102:10254']- job_name: 'kubernetes-nodes'kubernetes_sd_configs:- role: noderelabel_configs:- source_labels: [__address__]regex: '(.*):10250'replacement: '${1}:9100'target_label: __address__action: replace- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-kubelet'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtinsecure_skip_verify: truebearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- job_name: 'kubernetes-cadvisor'kubernetes_sd_configs:- role: nodescheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- action: labelmapregex: __meta_kubernetes_node_label_(.+)- target_label: __address__replacement: kubernetes.default.svc:443- source_labels: [__meta_kubernetes_node_name]regex: (.+)target_label: __metrics_path__replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor- job_name: 'kubernetes-apiservers'kubernetes_sd_configs:- role: endpointsscheme: httpstls_config:ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crtbearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/tokenrelabel_configs:- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]action: keepregex: default;kubernetes;https- job_name: 'kubernetes-service-endpoints'kubernetes_sd_configs:- role: endpointsrelabel_configs:- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]action: keepregex: true- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]action: replacetarget_label: __scheme__regex: (https?)- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]action: replacetarget_label: __metrics_path__regex: (.+)- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]action: replacetarget_label: __address__regex: ([^:]+)(?::\d+)?;(\d+)replacement: $1:$2- action: labelmapregex: __meta_kubernetes_service_label_(.+)- source_labels: [__meta_kubernetes_namespace]action: replacetarget_label: kubernetes_namespace- source_labels: [__meta_kubernetes_service_name]action: replacetarget_label: kubernetes_namealerting:alertmanagers:- static_configs:- targets: ["localhost:9093"]rule_files:- /etc/prometheus/rules.yml