k8s—Prometheus+Grafana+Altermaneger构建监控平台

# 我直接用的镜像压缩包，上传到服务器然后docker load
# 所有节点都要有这个镜像
[root@k8s-master ~]# docker load -i node-exporter.tar.gz 
ad68498f8d86: Loading layer [==================================================>]  4.628MB/4.628MB
ad8512dce2a7: Loading layer [==================================================>]  2.781MB/2.781MB
cc1adb06ef21: Loading layer [==================================================>]   16.9MB/16.9MB
Loaded image: prom/node-exporter:v0.16.0

2.编写node-export.yaml文件并应用

[root@k8s-master node-exporter]# vim node-export.yaml 
[root@k8s-master node-exporter]# cat node-export.yaml 
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: monitor-sa        #记得创建命名空间，否则后面会出错
  labels:
    name: node-exporter
spec:
  selector:
    matchLabels:
     name: node-exporter
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostPID: true        #表示pod中的容器可以直接使用主机的网络，与宿主机进行通信
      hostIPC: true
      hostNetwork: true        #会直接将宿主机的9100端口映射出来，不需要创建service
      containers:
      - name: node-exporter
        image: prom/node-exporter:v0.16.0
        ports:
        - containerPort: 9100
        resources:
          requests:
            cpu: 0.15        #容器运行至少需要0.15核CPU
        securityContext:
          privileged: true        #开启特权模式
        args:
        - --path.procfs        #配置挂载宿主机的路径
        - /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: /
[root@k8s-master node-exporter]# kubectl apply -f node-export.yaml 
Error from server (NotFound): error when creating "node-export.yaml": namespaces "monitor-sa" not found        #命名空间没有创建；
[root@k8s-master node-exporter]#  kubectl create ns monitor-sa
namespace/monitor-sa created
[root@k8s-master node-exporter]# kubectl apply -f node-export.yaml 
daemonset.apps/node-exporter created

# 查看创建好的pod；发现IP与宿主机IP相同
[root@k8s-master node-exporter]# kubectl get pod -n monitor-sa -o wide
NAME                  READY   STATUS    RESTARTS   AGE     IP               NODE         NOMINATED NODE   READINESS GATES
node-exporter-fdvjc   1/1     Running   0          8m21s   192.168.22.136   k8s-node2    <none>           <none>
node-exporter-gzfnq   1/1     Running   0          8m21s   192.168.22.134   k8s-master   <none>           <none>
node-exporter-r85gw   1/1     Running   0          8m21s   192.168.22.135   k8s-node1    <none>           <none>

3.测试node-exporter并获取数据

# 通过curl  宿主机IP：9100/metrics 采集数据
# 我访问的是node1节点的CPU

[root@k8s-master node-exporter]# curl 192.168.22.135:9100/metrics | grep node_cpu_seconds
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
100 74373  100 74373    0     0   413k      0 --:--:-- --:--:-- --:--:--  417k
# HELP node_cpu_seconds_total Seconds the cpus spent in each mode.    #解释当前指标的含义
# TYPE node_cpu_seconds_total counter        #说明当前指标的数据类型
node_cpu_seconds_total{cpu="0",mode="idle"} 18145.96
node_cpu_seconds_total{cpu="0",mode="iowait"} 1.43
node_cpu_seconds_total{cpu="0",mode="irq"} 0
node_cpu_seconds_total{cpu="0",mode="nice"} 0.05
node_cpu_seconds_total{cpu="0",mode="softirq"} 29.26
node_cpu_seconds_total{cpu="0",mode="steal"} 0
node_cpu_seconds_total{cpu="0",mode="system"} 443.06
node_cpu_seconds_total{cpu="0",mode="user"} 383.4
node_cpu_seconds_total{cpu="1",mode="idle"} 18073.89
node_cpu_seconds_total{cpu="1",mode="iowait"} 1.23
node_cpu_seconds_total{cpu="1",mode="irq"} 0
node_cpu_seconds_total{cpu="1",mode="nice"} 0.02
node_cpu_seconds_total{cpu="1",mode="softirq"} 61.35
node_cpu_seconds_total{cpu="1",mode="steal"} 0
node_cpu_seconds_total{cpu="1",mode="system"} 446.99
node_cpu_seconds_total{cpu="1",mode="user"} 361.69

# node1节点的负载情况

[root@k8s-master node-exporter]# curl 192.168.22.135:9100/metrics | grep node_load
  % Total    % Received % Xferd  Average Speed   Time    Time     Time  Current
                                 Dload  Upload   Total   Spent    Left  Speed
  0     0    0     0    0     0      0      0 --:--:-- --:--:-- --:--:--     0# HELP node_load1 1m load average.
# TYPE node_load1 gauge
node_load1 0.1        #最近一分钟以内的负载情况
# HELP node_load15 15m load average.
# TYPE node_load15 gauge
node_load15 0.09
# HELP node_load5 5m load average.
# TYPE node_load5 gauge
node_load5 0.04
100 74460  100 74460    0     0  6343k      0 --:--:-- --:--:-- --:--:-- 6610k

二、Prometheus server安装和配置

1.创建sa(serviceaccount)账号，对sa做rabc授权

1）创建一个 sa 账号 monitor

[root@k8s-master node-exporter]# kubectl create serviceaccount monitor -n monitor-sa
serviceaccount/monitor created

2）把 sa 账号 monitor 通过 clusterrolebing 绑定到 clusterrole 上

[root@k8s-master node-exporter]# kubectl create clusterrolebinding monitor-clusterrolebinding -n monitor-sa --clusterrole=cluster-admin --serviceaccount=monitor-sa:monitor
clusterrolebinding.rbac.authorization.k8s.io/monitor-clusterrolebinding created

2.创建Prometheus数据存储目录

# 在node1节点创建目录

[root@k8s-node1 ~]# mkdir /data
[root@k8s-node1 ~]# chmod 777 /data

3.安装Prometheus server服务

3.1创建configmap用来存放Prometheus配置信息

1）创建yaml文件

[root@k8s-master yaml]# vim prometheus-cfg.yaml 
[root@k8s-master yaml]# cat prometheus-cfg.yaml
---
kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yml: |
    global:
      scrape_interval: 15s        #采集目标主机监控数据的时间间隔
      scrape_timeout: 10s        #数据采集超时时间，默认10秒
      evaluation_interval: 1m        #触发告警检测的时间，默认是1m
    scrape_configs:                #配置数据源，称为target，每个target用job_name命名
    - job_name: 'kubernetes-node'
      kubernetes_sd_configs:        #使用的是k8s的服务发现
      - role: node           #使用node角色，它使用默认的kubelet提供的http端口来发现集群中的每个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
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
    - 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_(.+)
      - 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-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
    - 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 annotation 声明则抓取
      - 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,不过这里写的要和 service 中做好约定，如果 service 中这样写 prometheus.io/app-metricspath: '/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
      - 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

2）应用并查看

[root@k8s-master yaml]# kubectl apply -f prometheus-cfg.yaml 
configmap/prometheus-config created
[root@k8s-master yaml]# kubectl get cm -n monitor-sa
NAME                DATA   AGE
prometheus-config   1      48m

3.2 通过deployment部署prometheus

1）上传所需镜像

# node1节点，定义的yaml文件中指定了k8s-node1节点

[root@k8s-node1 ~]# docker load -i prometheus-2-2-1.tar.gz 
6a749002dd6a: Loading layer  1.338MB/1.338MB
5f70bf18a086: Loading layer  1.024kB/1.024kB
1692ded805c8: Loading layer  2.629MB/2.629MB
035489d93827: Loading layer  66.18MB/66.18MB
8b6ef3a2ab2c: Loading layer   44.5MB/44.5MB
ff98586f6325: Loading layer  3.584kB/3.584kB
017a13aba9f4: Loading layer   12.8kB/12.8kB
4d04d79bb1a5: Loading layer  27.65kB/27.65kB
75f6c078fa6b: Loading layer  10.75kB/10.75kB
5e8313e8e2ba: Loading layer  6.144kB/6.144kB
Loaded image: prom/prometheus:v2.2.1

2）编写yaml文件

[root@k8s-master yaml]# vim prometheus-deploy.yaml 
[root@k8s-master yaml]# cat 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: k8s-node1
      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        #旧数据存储目录
          - --storage.tsdb.retention=720h        #何时删除旧数据，默认为 15 天
          - --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

3）应用并查看

[root@k8s-master yaml]# kubectl apply -f prometheus-deploy.yaml 
deployment.apps/prometheus-server created
[root@k8s-master yaml]# kubectl get deploy -n monitor-sa
NAME                READY   UP-TO-DATE   AVAILABLE   AGE
prometheus-server   1/1     1            1           26s

3.3给Prometheus pod创建一个service

1）编写yaml文件

[root@k8s-master yaml]# vim prometheus-svc.yaml 
[root@k8s-master yaml]# cat 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
  selector:
    app: prometheus
    component: server

2）应用并查看

[root@k8s-master yaml]# kubectl apply -f prometheus-svc.yaml 
service/prometheus created
[root@k8s-master yaml]# kubectl get svc -n monitor-sa
NAME         TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)          AGE
prometheus   NodePort   10.104.137.10   <none>        9090:30481/TCP   12s

3）结果测试

通过查询可以看到service在宿主机上映射的端口是30481，访问k8s集群的node1节点的IP:端口/graph，就可以访问到web ui界面

点击上方的Status中的Targets，可以看到以下界面：

3.4 Prometheus 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

curl -X POST http://podIP:9090/-/reload

三、Grafana的安装和配置

1.Grafana介绍

Grafana 是一个跨平台的开源的度量分析和可视化工具，可以将采集的数据可视化的展示，并及时通知给告警接收方。它主要有以下特点：
1）展示方式：快速灵活的客户端图表，面板插件有许多不同方式的可视化指标和日志，官方库中具有丰富的仪表盘插件，比如热图、折线图、图表等多种展示方式；
2）数据源：Graphite，InfluxDB，OpenTSDB，Prometheus，Elasticsearch，CloudWatch 和 KairosDB 等；
3）通知提醒：以可视方式定义最重要指标的警报规则，Grafana 将不断计算并发送通知，在数据达到阈值时通过 Slack、PagerDuty 等获得通知；
4）混合展示：在同一图表中混合使用不同的数据源，可以基于每个查询指定数据源，甚至自定义数据源；
5）注释：使用来自不同数据源的丰富事件注释图表，将鼠标悬停在事件上会显示完整的事件元数据和标记

2.安装和Grafana

1）上传镜像

# node1节点

[root@k8s-node1 images-prometheus]# docker load -i heapster-grafana-amd64_v5_0_4.tar.gz 
6816d98be637: Loading layer  4.642MB/4.642MB
523feee8e0d3: Loading layer  161.5MB/161.5MB
43d2638621da: Loading layer  230.4kB/230.4kB
f24c0fa82e54: Loading layer   2.56kB/2.56kB
334547094992: Loading layer  5.826MB/5.826MB
Loaded image: k8s.gcr.io/heapster-grafana-amd64:v5.0.4

2）编写yaml文件

[root@k8s-master yaml]# vim grafana.yaml 
[root@k8s-master yaml]# cat 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:
      nodeName: k8s-node1
      containers:
      - name: grafana
        image: k8s.gcr.io/heapster-grafana-amd64:v5.0.4
        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 (https://github.com/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

3）应用并查看

[root@k8s-master yaml]# kubectl apply -f grafana.yaml 
deployment.apps/monitoring-grafana created
service/monitoring-grafana created
[root@k8s-master yaml]# kubectl get pod -n kube-system -o wide | grep monitor
monitoring-grafana-7979b958c7-rxcw7   1/1     Running   0          64s     10.244.1.23      k8s-node1    <none>           <none>
[root@k8s-master yaml]# kubectl get svc -n kube-system
NAME                 TYPE        CLUSTER-IP     EXTERNAL-IP   PORT(S)                  AGE
kube-dns             ClusterIP   10.96.0.10     <none>        53/UDP,53/TCP,9153/TCP   3d16h
monitoring-grafana   NodePort    10.107.203.6   <none>        80:30244/TCP             3m48s

3.Grafana接入Prometheus数据源

3.1 浏览器访问

经上述查看，映射端口为30244，在浏览器输入IP:端口号即可访问

3.2 配置grafana界面

1）选择Create your first data source

2）导入监控模板

监控模板链接：https://grafana.com/dashboards

此处导入的是node_exporter.json文件

3）导入docker_rev1.json监控模板

跟上一步操作一样

4）如果 Grafana 导入 Prometheusz 之后，发现仪表盘没有数据，如何排查？

打开 grafana 界面，找到仪表盘对应无数据的图标

node_memory_MemTotal_bytes就是grafana上采集的内存数据，需要到Prometheus ui界面看看指标是否是相同的

四、安装kube-state-metrics组件

1.介绍kube-state-metrics组件

kube-state-metrics 通过监听 API Server 生成有关资源对象的状态指标，比如 Deployment、Node、Pod，需要注意的是 kube-state-metrics 只是简单的提供一个 metrics 数据，并不会存储这些指标数据，所以我们可以使用 Prometheus 来抓取这些数据然后存储，主要关注的是业务相关的一些元数据，比如 Deployment、Pod、副本状态等；调度了多少个 replicas？现在可用的有几个？多少个 Pod 是 running/stopped/terminated 状态？Pod 重启了多少次？我有多少 job 在运行中

2.安装kube-state-metrics组件

1）创建sa并对其授权

[root@k8s-master yaml]# vim kube-state-metrics-rbac.yaml 
[root@k8s-master yaml]# cat 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
[root@k8s-master yaml]# kubectl apply -f kube-state-metrics-rbac.yaml 
serviceaccount/kube-state-metrics created
clusterrole.rbac.authorization.k8s.io/kube-state-metrics created
clusterrolebinding.rbac.authorization.k8s.io/kube-state-metrics created
[root@k8s-master yaml]# kubectl get sa -n kube-system | grep state
kube-state-metrics                   1         11m

2）上传镜像

[root@k8s-node1 images-prometheus]# docker load -i kube-state-metrics_1_9_0.tar.gz 
932da5156413: Loading layer  3.062MB/3.062MB
bd8df7c22fdb: Loading layer     31MB/31MB
Loaded image: quay.io/coreos/kube-state-metrics:v1.9.0
[root@k8s-node1 images-prometheus]# docker images | grep state
quay.io/coreos/kube-state-metrics                                v1.9.0              101b910a2162        4 years ago         32.8MB

3）编写yaml文件并应用

[root@k8s-master yaml]# vim kube-state-metrics-deploy.yaml 
[root@k8s-master yaml]# cat 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:
      nodeName: k8s-node1
      serviceAccountName: kube-state-metrics
      containers:
      - name: kube-state-metrics
        image: quay.io/coreos/kube-state-metrics:v1.9.0
        ports:
        - containerPort: 8080
[root@k8s-master yaml]# kubectl apply -f kube-state-metrics-deploy.yaml 
deployment.apps/kube-state-metrics created
[root@k8s-master yaml]# kubectl get pod -n kube-system | grep kube-state
kube-state-metrics-7684896db9-l5vsz   1/1     Running   0          61s

4）创建service

[root@k8s-master yaml]# vim kube-state-metrics-svc.yaml 
[root@k8s-master yaml]# cat kube-state-metrics-svc.yaml 
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
[root@k8s-master yaml]# kubectl apply -f kube-state-metrics-svc.yaml 
service/kube-state-metrics created
[root@k8s-master yaml]# kubectl get svc -n kube-system
NAME                 TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)                  AGE
kube-dns             ClusterIP   10.96.0.10       <none>        53/UDP,53/TCP,9153/TCP   3d18h
kube-state-metrics   ClusterIP   10.104.238.225   <none>        8080/TCP                 19s
monitoring-grafana   NodePort    10.107.203.6     <none>        80:30244/TCP             148m
[root@k8s-master yaml]#

5）导入监控模板

两个模板：

Kubernetes Cluster (Prometheus)-1577674936972.json

Kubernetes cluster monitoring (via Prometheus) (k8s 1.16)-1577691996738.json

五、配置alertmanager组件

1.创建alertmanager-cm.yaml配置文件

[root@k8s-master yaml]# vim alertmanager-cm.yaml 
[root@k8s-master yaml]# cat alertmanager-cm.yaml 
kind: ConfigMap
apiVersion: v1
metadata:
  name: alertmanager
  namespace: monitor-sa
data:
  alertmanager.yml: |-
    global:
      resolve_timeout: 1m
      smtp_smarthost: 'smtp.163.com:25'        #网易163邮箱
      smtp_from: '198********@163.com'        #从哪个邮箱发送邮件
      smtp_auth_username: '198********'        #发送邮件的用户
      smtp_auth_password: 'YLOPKFRHHONSHHXM'        #网易邮箱的授权码，要用自己的
      smtp_require_tls: false
    route:
      group_by: [alertname]         # 采用哪个标签来作为分组依据
      group_wait: 10s            # 组告警等待时间。也就是告警产生后等待 10s，如果有同组告警一起发出
      group_interval: 10s        # 上下两组发送告警的间隔时间
      repeat_interval: 10m        # 重复发送告警的时间，减少相同邮件的发送频率，默认是 1h
      receiver: default-receiver
    receivers:
    - name: 'default-receiver'
      email_configs:
      - to: '178******@qq.com'        #接受邮件的邮箱，不能跟上面的邮箱相同
        send_resolved: true
[root@k8s-master yaml]# kubectl apply -f alertmanager-cm.yaml 
configmap/alertmanager created

2.Prometheus报警流程

1）Prometheus Server 监控目标主机上暴露的 http 接口（这里假设接口 A），通过 Promethes 配置的'scrape_interval'定义的时间间隔，定期采集目标主机上监控数据。
2）当接口 A 不可用的时候，Server 端会持续的尝试从接口中取数据，直到"scrape_timeout"时间后停止尝试。这时候把接口的状态变为"DOWN"。
3）Prometheus 同时根据配置的"evaluation_interval"的时间间隔，定期（默认 1min）的对 Alert Rule 进行评估；当到达评估周期的时候，发现接口 A 为 DOWN，即 UP=0 为真，激活Alert，进入"PENDING"状态，并记录当前 active 的时间；
4）当下一个 alert rule 的评估周期到来的时候，发现 UP=0 继续为真，然后判断警报 Active 的时间是否已经超出 rule 里的'for' 持续时间，如果未超出，则进入下一个评估周期；如果时间超出，则 alert 的状态变为"FIRING"；同时调用 Alertmanager 接口，发送相关报警数据。
5）AlertManager 收到报警数据后，会将警报信息进行分组，然后根据 alertmanager 配置的"group_wait"时间先进行等待。等 wait 时间过后再发送报警信息。
6）属于同一个 Alert Group 的警报，在等待的过程中可能进入新的 alert，如果之前的报警已经成功发出，那么间隔"group_interval"的时间间隔后再重新发送报警信息。比如配置的是邮件报警，那么同属一个 group 的报警信息会汇总在一个邮件里进行发送。
7）如果 Alert Group 里的警报一直没发生变化并且已经成功发送，等待'repeat_interval'时间间隔之后再重复发送相同的报警邮件；如果之前的警报没有成功发送，则相当于触发第 6 条条件，则需要等待 group_interval 时间间隔后重复发送

3.创建Prometheus和告警规则的配置文件

1）下图是配置文件中需要修改的地方：

2）删除上次设置的configmap配置

#  先删除上次设置的configmap
[root@k8s-master yaml]# kubectl delete -f prometheus-cfg.yaml 
configmap "prometheus-config" deleted

3）配置文件configmap

#  编写新的configmap配置文件

[root@k8s-master yaml]# vim prometheus-alertmanager-cfg.yaml
[root@k8s-master yaml]# cat prometheus-alertmanager-cfg.yaml 
kind: ConfigMap
apiVersion: v1
metadata:
  labels:
    app: prometheus
  name: prometheus-config
  namespace: monitor-sa
data:
  prometheus.yml: |
    rule_files:
    - /etc/prometheus/rules.yml
    alerting:
      alertmanagers:
      - static_configs:
        - targets: ["localhost:9093"]
    global:
      scrape_interval: 15s
      scrape_timeout: 10s
      evaluation_interval: 1m
    scrape_configs:
    - job_name: 'kubernetes-node'
      kubernetes_sd_configs:
      - role: node
      relabel_configs:
      - source_labels: [__address__]
        regex: '(.*):10250'
        replacement: '${1}:9100'
        target_label: __address__
        action: replace
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
    - job_name: 'kubernetes-node-cadvisor'
      kubernetes_sd_configs:
      - role:  node
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - action: labelmap
        regex: __meta_kubernetes_node_label_(.+)
      - target_label: __address__
        replacement: kubernetes.default.svc:443
      - source_labels: [__meta_kubernetes_node_name]
        regex: (.+)
        target_label: __metrics_path__
        replacement: /api/v1/nodes/${1}/proxy/metrics/cadvisor
    - job_name: 'kubernetes-apiserver'
      kubernetes_sd_configs:
      - role: endpoints
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
      bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
      relabel_configs:
      - source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
        action: keep
        regex: default;kubernetes;https
    - job_name: 'kubernetes-service-endpoints'
      kubernetes_sd_configs:
      - role: endpoints
      relabel_configs:
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
        action: keep
        regex: true
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scheme]
        action: replace
        target_label: __scheme__
        regex: (https?)
      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
        action: replace
        target_label: __metrics_path__
        regex: (.+)
      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
        action: replace
        target_label: __address__
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
      - action: labelmap
        regex: __meta_kubernetes_service_label_(.+)
      - source_labels: [__meta_kubernetes_namespace]
        action: replace
        target_label: kubernetes_namespace
      - source_labels: [__meta_kubernetes_service_name]
        action: replace
        target_label: kubernetes_name 
    - job_name: 'kubernetes-pods'
      kubernetes_sd_configs:
      - role: pod
      relabel_configs:
      - action: keep
        regex: true
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_scrape
      - action: replace
        regex: (.+)
        source_labels:
        - __meta_kubernetes_pod_annotation_prometheus_io_path
        target_label: __metrics_path__
      - action: replace
        regex: ([^:]+)(?::\d+)?;(\d+)
        replacement: $1:$2
        source_labels:
        - __address__
        - __meta_kubernetes_pod_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: kubernetes_pod_name
    - job_name: 'kubernetes-schedule'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.22.134:10251']
    - job_name: 'kubernetes-controller-manager'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.22.134:10252']
    - job_name: 'kubernetes-kube-proxy'
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.22.134:10249','192.168.22.135:10249','192.168.22.136:10249']
    - job_name: 'kubernetes-etcd'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt
        cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt
        key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key
      scrape_interval: 5s
      static_configs:
      - targets: ['192.168.22.134:2379']
  rules.yml: |
    groups:
    - name: example
      rules:
      - alert: kube-proxy的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  kube-proxy的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: scheduler的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-schedule"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  scheduler的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-schedule"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: controller-manager的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-controller-manager"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  controller-manager的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-controller-manager"}[1m]) * 100 > 0
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: apiserver的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  apiserver的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-apiserver"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: etcd的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过80%"
      - alert:  etcd的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-etcd"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}组件的cpu使用率超过90%"
      - alert: kube-state-metrics的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%"
          value: "{{ $value }}%"
          threshold: "80%"      
      - alert: kube-state-metrics的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-state-metrics"}[1m]) * 100 > 0
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%"
          value: "{{ $value }}%"
          threshold: "90%"      
      - alert: coredns的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过80%"
          value: "{{ $value }}%"
          threshold: "80%"      
      - alert: coredns的cpu使用率大于90%
        expr: rate(process_cpu_seconds_total{k8s_app=~"kube-dns"}[1m]) * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.k8s_app}}组件的cpu使用率超过90%"
          value: "{{ $value }}%"
          threshold: "90%"      
      - alert: kube-proxy打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-kube-proxy"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kube-proxy打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-kube-proxy"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-schedule打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-schedule"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-schedule打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-schedule"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-controller-manager打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-controller-manager"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-controller-manager打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-controller-manager"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-apiserver打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-apiserver"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-apiserver打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-apiserver"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: kubernetes-etcd打开句柄数>600
        expr: process_open_fds{job=~"kubernetes-etcd"}  > 600
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>600"
          value: "{{ $value }}"
      - alert: kubernetes-etcd打开句柄数>1000
        expr: process_open_fds{job=~"kubernetes-etcd"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "{{$labels.instance}}的{{$labels.job}}打开句柄数>1000"
          value: "{{ $value }}"
      - alert: coredns
        expr: process_open_fds{k8s_app=~"kube-dns"}  > 600
        for: 2s
        labels:
          severity: warnning 
        annotations:
          description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过600"
          value: "{{ $value }}"
      - alert: coredns
        expr: process_open_fds{k8s_app=~"kube-dns"}  > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 打开句柄数超过1000"
          value: "{{ $value }}"
      - alert: kube-proxy
        expr: process_virtual_memory_bytes{job=~"kubernetes-kube-proxy"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: scheduler
        expr: process_virtual_memory_bytes{job=~"kubernetes-schedule"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kubernetes-controller-manager
        expr: process_virtual_memory_bytes{job=~"kubernetes-controller-manager"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kubernetes-apiserver
        expr: process_virtual_memory_bytes{job=~"kubernetes-apiserver"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kubernetes-etcd
        expr: process_virtual_memory_bytes{job=~"kubernetes-etcd"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: kube-dns
        expr: process_virtual_memory_bytes{k8s_app=~"kube-dns"}  > 2000000000
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "插件{{$labels.k8s_app}}({{$labels.instance}}): 使用虚拟内存超过2G"
          value: "{{ $value }}"
      - alert: HttpRequestsAvg
        expr: sum(rate(rest_client_requests_total{job=~"kubernetes-kube-proxy|kubernetes-kubelet|kubernetes-schedule|kubernetes-control-manager|kubernetes-apiservers"}[1m]))  > 1000
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): TPS超过1000"
          value: "{{ $value }}"
          threshold: "1000"   
      - alert: Pod_restarts
        expr: kube_pod_container_status_restarts_total{namespace=~"kube-system|default|monitor-sa"} > 0
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "在{{$labels.namespace}}名称空间下发现{{$labels.pod}}这个pod下的容器{{$labels.container}}被重启,这个监控指标是由{{$labels.instance}}采集的"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Pod_waiting
        expr: kube_pod_container_status_waiting_reason{namespace=~"kube-system|default"} == 1
        for: 2s
        labels:
          team: admin
        annotations:
          description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}启动异常等待中"
          value: "{{ $value }}"
          threshold: "1"   
      - alert: Pod_terminated
        expr: kube_pod_container_status_terminated_reason{namespace=~"kube-system|default|monitor-sa"} == 1
        for: 2s
        labels:
          team: admin
        annotations:
          description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.pod}}下的{{$labels.container}}被删除"
          value: "{{ $value }}"
          threshold: "1"
      - alert: Etcd_leader
        expr: etcd_server_has_leader{job="kubernetes-etcd"} == 0
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 当前没有leader"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Etcd_leader_changes
        expr: rate(etcd_server_leader_changes_seen_total{job="kubernetes-etcd"}[1m]) > 0
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 当前leader已发生改变"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Etcd_failed
        expr: rate(etcd_server_proposals_failed_total{job="kubernetes-etcd"}[1m]) > 0
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}}): 服务失败"
          value: "{{ $value }}"
          threshold: "0"
      - alert: Etcd_db_total_size
        expr: etcd_debugging_mvcc_db_total_size_in_bytes{job="kubernetes-etcd"} > 10000000000
        for: 2s
        labels:
          team: admin
        annotations:
          description: "组件{{$labels.job}}({{$labels.instance}})：db空间超过10G"
          value: "{{ $value }}"
          threshold: "10G"
      - alert: Endpoint_ready
        expr: kube_endpoint_address_not_ready{namespace=~"kube-system|default"} == 1
        for: 2s
        labels:
          team: admin
        annotations:
          description: "空间{{$labels.namespace}}({{$labels.instance}}): 发现{{$labels.endpoint}}不可用"
          value: "{{ $value }}"
          threshold: "1"
    - name: 物理节点状态-监控告警
      rules:
      - alert: 物理节点cpu使用率
        expr: 100-avg(irate(node_cpu_seconds_total{mode="idle"}[5m])) by(instance)*100 > 90
        for: 2s
        labels:
          severity: ccritical
        annotations:
          summary: "{{ $labels.instance }}cpu使用率过高"
          description: "{{ $labels.instance }}的cpu使用率超过90%,当前使用率[{{ $value }}],需要排查处理" 
      - alert: 物理节点内存使用率
        expr: (node_memory_MemTotal_bytes - (node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes)) / node_memory_MemTotal_bytes * 100 > 90
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{ $labels.instance }}内存使用率过高"
          description: "{{ $labels.instance }}的内存使用率超过90%,当前使用率[{{ $value }}],需要排查处理"
      - alert: InstanceDown
        expr: up == 0
        for: 2s
        labels:
          severity: critical
        annotations:   
          summary: "{{ $labels.instance }}: 服务器宕机"
          description: "{{ $labels.instance }}: 服务器延时超过2分钟"
      - alert: 物理节点磁盘的IO性能
        expr: 100-(avg(irate(node_disk_io_time_seconds_total[1m])) by(instance)* 100) < 60
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 流入磁盘IO使用率过高！"
          description: "{{$labels.mountpoint }} 流入磁盘IO大于60%(目前使用:{{$value}})"
      - alert: 入网流量带宽
        expr: ((sum(rate (node_network_receive_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 流入网络带宽过高！"
          description: "{{$labels.mountpoint }}流入网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}"
      - alert: 出网流量带宽
        expr: ((sum(rate (node_network_transmit_bytes_total{device!~'tap.*|veth.*|br.*|docker.*|virbr*|lo*'}[5m])) by (instance)) / 100) > 102400
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 流出网络带宽过高！"
          description: "{{$labels.mountpoint }}流出网络带宽持续5分钟高于100M. RX带宽使用率{{$value}}"
      - alert: TCP会话
        expr: node_netstat_Tcp_CurrEstab > 1000
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} TCP_ESTABLISHED过高！"
          description: "{{$labels.mountpoint }} TCP_ESTABLISHED大于1000%(目前使用:{{$value}}%)"
      - alert: 磁盘容量
        expr: 100-(node_filesystem_free_bytes{fstype=~"ext4|xfs"}/node_filesystem_size_bytes {fstype=~"ext4|xfs"}*100) > 80
        for: 2s
        labels:
          severity: critical
        annotations:
          summary: "{{$labels.mountpoint}} 磁盘分区使用率过高！"
          description: "{{$labels.mountpoint }} 磁盘分区使用大于80%(目前使用:{{$value}}%)"

4）应用配置文件

[root@k8s-master yaml]# kubectl apply -f prometheus-alertmanager-cfg.yaml 
configmap/prometheus-config created
[root@k8s-master yaml]# kubectl get cm -n monitor-sa
NAME                DATA   AGE
alertmanager        1      25m
prometheus-config   2      3m20s

4.安装Prometheus和altermanager

4.1 安装

1）删除上述操作步骤安装的Prometheus的deployment资源

[root@k8s-master yaml]# kubectl delete -f prometheus-deploy.yaml 
deployment.apps "prometheus-server" deleted

2）生成etcd-certs

[root@k8s-master yaml]# kubectl -n monitor-sa create secret generic etcd-certs --from-file=/etc/kubernetes/pki/etcd/server.key --from-file=/etc/kubernetes/pki/etcd/server.crt --from-file=/etc/kubernetes/pki/etcd/ca.crt
secret/etcd-certs created

[root@k8s-master yaml]# kubectl get secret -n monitor-sa
NAME                  TYPE                                  DATA   AGE
default-token-jjw8z   kubernetes.io/service-account-token   3      24h
etcd-certs            Opaque                                3      40s
monitor-token-jr24f   kubernetes.io/service-account-token   3      23h

3）拉取镜像

# 此处我用的node2节点

[root@k8s-node2 images-prometheus]# docker load -i alertmanager.tar.gz 
4febd3792a1f: Loading layer   1.36MB/1.36MB
68d1a8b41cc0: Loading layer  2.586MB/2.586MB
5f70bf18a086: Loading layer  1.024kB/1.024kB
30d4e7b232e4: Loading layer  12.77MB/12.77MB
6b961451fcb0: Loading layer  16.59MB/16.59MB
b5abc4736d3f: Loading layer  6.144kB/6.144kB
Loaded image: prom/alertmanager:v0.14.0
[root@k8s-node2 images-prometheus]# scp alertmanager.tar.gz k8s-node2:/root/
root@k8s-node2's password: 
alertmanager.tar.gz                                                100%   32MB  16.1MB/s   00:01    
[root@k8s-node2 images-prometheus]# docker images | grep alert
prom/alertmanager                                                v0.14.0             23744b2d645c        6 years ago         31.9MB

4）编写deployment的yaml文件并应用

[root@k8s-master yaml]# vim prometheus-alertmanager-deploy.yaml 
[root@k8s-master yaml]# cat prometheus-alertmanager-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: k8s-node1            #此处指定的node1节点
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: prom/prometheus:v2.2.1
        imagePullPolicy: IfNotPresent
        command:
        - "/bin/prometheus"
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"
        - "--storage.tsdb.retention=24h"
        - "--web.enable-lifecycle"
        ports:
        - containerPort: 9090
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/prometheus
          name: prometheus-config
        - mountPath: /prometheus/
          name: prometheus-storage-volume
        - name: k8s-certs
          mountPath: /var/run/secrets/kubernetes.io/k8s-certs/etcd/
      - name: alertmanager
        image: prom/alertmanager:v0.14.0
        imagePullPolicy: IfNotPresent
        args:
        - "--config.file=/etc/alertmanager/alertmanager.yml"
        - "--log.level=debug"
        ports:
        - containerPort: 9093
          protocol: TCP
          name: alertmanager
        volumeMounts:
        - name: alertmanager-config
          mountPath: /etc/alertmanager
        - name: alertmanager-storage
          mountPath: /alertmanager
        - name: localtime
          mountPath: /etc/localtime
      volumes:
        - name: prometheus-config
          configMap:
            name: prometheus-config
        - name: prometheus-storage-volume
          hostPath:
           path: /data
           type: Directory
        - name: k8s-certs
          secret:
           secretName: etcd-certs
        - name: alertmanager-config
          configMap:
            name: alertmanager
        - name: alertmanager-storage
          hostPath:
           path: /data/alertmanager
           type: DirectoryOrCreate
        - name: localtime
          hostPath:
           path: /usr/share/zoneinfo/Asia/Shanghai

#  应用yaml文件

[root@k8s-master yaml]# kubectl apply -f prometheus-alertmanager-deploy.yaml 
deployment.apps/prometheus-server created
[root@k8s-master yaml]# kubectl get pod -n monitor-sa
NAME                                 READY   STATUS    RESTARTS   AGE
node-exporter-fdvjc                  1/1     Running   1          24h
node-exporter-gzfnq                  1/1     Running   0          24h
node-exporter-r85gw                  1/1     Running   0          24h
prometheus-server-6c5bc4d65b-9qzn6   2/2     Running   0          39s

5）创建alertmanager的service以便于访问

[root@k8s-master yaml]# vim alertmanager-svc.yaml 
[root@k8s-master yaml]# cat alertmanager-svc.yaml 
---
apiVersion: v1
kind: Service
metadata:
  labels:
    name: prometheus
    kubernetes.io/cluster-service: 'true'
  name: alertmanager
  namespace: monitor-sa
spec:
  ports:
  - name: alertmanager
    nodePort: 30066
    port: 9093
    protocol: TCP
    targetPort: 9093
  selector:
    app: prometheus
  sessionAffinity: None
  type: NodePort
[root@k8s-master yaml]# kubectl apply -f alertmanager-svc.yaml 
service/alertmanager created
[root@k8s-master yaml]# kubectl get svc -n monitor-sa
NAME           TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)          AGE
alertmanager   NodePort   10.98.208.193   <none>        9093:30066/TCP   16s
prometheus     NodePort   10.104.137.10   <none>        9090:30481/TCP   20h

6）浏览器访问测试

通过上述查询，可以看到Prometheus映射的端口为30481，alertmanager映射的端口为30066；浏览器输入192.168.22.135:30066/#/alerts访问；

也就是http://node1节点IP:端口号/#/alerts

4.2 访问web界面查看效果

1）访问Prometheus的web页面

点击status中的targets；

2）修改配置文件

#  kube-schedule：

vim /etc/kubernetes/manifests/kube-scheduler.yaml

#将里面的--bind-address=127.0.0.1改成192.168.22.134；--port=0删除；
#把httpGet：下面的hosts改成192.168.22.134
# 注意是改成master节点的IP


#   kube-controller-manager

vim /etc/kubernetes/manifests/kube-controller-manager.yaml

#将里面的--bind-address=127.0.0.1改成192.168.22.134；--port=0删除；
#把httpGet：下面的hosts改成192.168.22.134
# 注意是改成master节点的IP


#  改完之后重启kubelet

#  查看服务：kubectl  get cs ；status都是healthy即可


#  kube-proxy

kubectl edit configmap kube-proxy -n kube-system

#  把metricsBindAddress这段修改成metricsBindAddress: 0.0.0.0:10249

#然后再删除pod重新创建即可
kubectl get pods -n kube-system | grep kube-proxy |awk '{print $1}' | xargs kubectl delete pods -n kube-system