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

博主： xinyu_he
发布时间：2025 年 05 月 04 日
43 次浏览
暂无评论
42972字数
分类： prometheus

# Kubernetes构建监控可视化告警平台

## 一、部署架构规划

> **部署方式采用 `deployment`方式部署**
>
> **deployment部署流程**
>
> - 创建configmap
> - 创建deployment
> - 创建svc

### 1.1 机器角色分配

| 主机名       | IP地址         | 角色                                                        | 命名空间分配 |
| ------------ | -------------- | ----------------------------------------------------------- | ------------ |
| k8s-master01 | 100.100.157.10 | 操作节点                                                    | `monitor-sa` |
| k8s-work01   | 100.100.157.11 | node-expoter/prometheus/grafana/Altermanege                 | `monitor-sa` |
| k8s-node02   | 100.100.157.12 | node-expoter/prometheus-webhook-dingtalk/kube-state-metrics | `monitor-sa` |

### 1.2 官网地址参考

| 官网                        | URL                                                                       | 用途          | 备注                       |
| --------------------------- | ------------------------------------------------------------------------- | ------------- | -------------------------- |
| grafana                     | [常用模版地址](https://grafana.com/grafana/dashboards/)                   | dashboard模板 | node-exporter 模版id:11074 |
| prometheus-webhook-dingtalk | [github官网](https://github.com/smarterallen/prometheus-webhook-dingtalk) | github代码库  | 使用教程                   |

### 1.3 所需镜像软件版本

| 镜像名称                    | 皆使用最新版本号 |
| --------------------------- | ---------------- |
| prometheus                  | latest           |
| node-expoter                | latest           |
| grafana                     | latest           |
| Altermaneger                | latest           |
| prometheus-webhook-dingtalk | latest           |
| kube-state-metrics          | latest           |

### 1.4 安装前环境准备

- pull镜像并push到harbor镜像仓库

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/598523502.png)

## 二、安装node-exporter

### 2.1 编写node-export.yaml文件并应用

```
1.编写node-export.yaml文件
[root@k8s-master01 prometheus]# cat node-export.yaml 
apiVersion: apps/v1
kind: DaemonSet
metadata:
  name: node-exporter
  namespace: monitor-sa
  labels:
    name: node-exporter
spec:
  selector:
    matchLabels:
     name: node-exporter
  template:
    metadata:
      labels:
        name: node-exporter
    spec:
      hostPID: true        #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: 100.100.157.10:5000/k8s/prometheus/node-expoter:latest
        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: /

2.创建命名空间
kubectl create ns monitor-sa

3.加载文件启动
kubectl apply -f node-export.yaml

4.验证pod创建，验证ip是否与宿主机ip相同
[root@k8s-master01 prometheus]# kubectl get pod -n monitor-sa -o wide

NAME                                 READY   STATUS    RESTARTS   AGE    IP               NODE           NOMINATED NODE   READINESS GATES
node-exporter-8sg29                  1/1     Running   0          165m   100.100.157.12   k8s-node02     <none>           <none>
node-exporter-vwvg6                  1/1     Running   0          165m   100.100.157.10   k8s-master01   <none>           <none>
node-exporter-wv9mw                  1/1     Running   0          165m   100.100.157.11   k8s-work01     <none>           <none>

```

### 2.2 测试node-exporter能否采集到数据

```
# 通过curl  宿主机IP：9100/metrics 采集数据
# 我访问的是master节点的CPU
[root@k8s-master01 prometheus]# curl 100.100.157.10:9100/metrics | grep node_cpu_seconds
  % 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_cpu_seconds_total Seconds the CPUs spent in each mode.
# TYPE node_cpu_seconds_total counter
node_cpu_seconds_total{cpu="0",mode="idle"} 480057.49
node_cpu_seconds_total{cpu="0",mode="iowait"} 1090.83
```

## 三、prometheus-server安装

### 3.1 创建sa（serviceaccount）账号，对sa做rabc授权

```
1.创建一个 sa 账号 monitor
[root@k8s-master01 prometheus]# 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-master01 prometheus]# kubectl create clusterrolebinding monitor-clusterrolebinding -n monitor-sa --clusterrole=cluster-admin --serviceaccount=monitor-sa:monitor
clusterrolebinding.rbac.authorization.k8s.io/monitor-clusterrolebinding created

3.创建数据目录
mkdir /root/hxy/data/prometheus/
chmod 777 /root/hxy/data/prometheus/
```

### 3.2 安装prometheus server服务

```
1.创建configmap用来存放Prometheus配置信息
[root@k8s-master01 prometheus]# 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 
      - 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
kubectl apply -f prometheus-cfg.yaml

3.验证
[root@k8s-master01 prometheus]# kubectl get cm -n monitor-sa |grep con
prometheus-config   1      163m
```

### 3.3通过deployment部署prometheus

```
1.编写yaml文件
[root@k8s-master01 prometheus]# 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-work01
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: 100.100.157.10:5000/k8s/prometheus/prometheus:latest
        imagePullPolicy: IfNotPresent
        command:
          - prometheus
          - --config.file=/etc/prometheus/prometheus.yml
          - --storage.tsdb.path=/prometheus        #旧数据存储目录
          - --storage.tsdb.retention.time=3d       #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: /root/hxy/data/prometheus/
           type: Directory

2.应用
kubectl apply -f prometheus-deploy.yaml

3.验证查看
[root@k8s-master01 prometheus]# kubectl get deploy -n monitor-sa |grep ser
prometheus-server    1/1     1            1           104m
```

### 3.4给prometheus pod创建一个service

```
1.编写yaml文件
[root@k8s-master01 prometheus]# 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
kubectl apply -f prometheus-svc.yaml

3.验证查看
[root@k8s-master01 prometheus]# kubectl get svc -n monitor-sa |grep pro
prometheus           NodePort   10.100.136.90   <none>        9090:31467/TCP   135m
```

### 3.5访问测试

> 通过查询可以看到service在宿主机上映射的端口是31467，访问k8s集群的work1节点的IP:端口/graph，就可以访问到web  ui界面

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/464862746.png)

## 四、Grafana安装

### 4.1编写yaml文件应用

```
1.编写yaml文件
[root@k8s-master01 prometheus]# cat prometheus-deploy.yaml 
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  labels:
    app: prometheus
spec:
  replicas: 1
  selector:
[root@k8s-master01 prometheus]# cat grafana.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: monitoring-grafana
  namespace: monitor-sa
spec:
  replicas: 1
  selector:
    matchLabels:
      task: monitoring
      k8s-app: grafana
  template:
    metadata:
      labels:
        task: monitoring
        k8s-app: grafana
    spec:
      nodeName: k8s-work01
      containers:
      - name: grafana
        image: 100.100.157.10:5000/k8s/prometheus/grafana:latest
        ports:
        - containerPort: 3000
          protocol: TCP
        volumeMounts:
        - mountPath: /etc/ssl/certs
          name: ca-certificates
          readOnly: true
        - mountPath: /var/lib/grafana
          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: monitor-sa
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

2.应用
kubectl apply -f grafana.yaml

3.验证查看
[root@k8s-master01 prometheus]# kubectl get pod -n monitor-sa -o wide | grep monitor
monitoring-grafana-9fd8c4d46-kmxsc   1/1     Running   0          113m   10.244.1.23      k8s-work01     <none>           <none>

[root@k8s-master01 prometheus]# kubectl get svc -n monitor-sa
NAME                 TYPE       CLUSTER-IP      EXTERNAL-IP   PORT(S)          AGE
monitoring-grafana   NodePort   10.103.20.21    <none>        80:30102/TCP     113m
```

### 4.2 访问测试

> 通过查询可以看到service在宿主机上映射的端口是30102，访问k8s集群的work1节点的IP:端口，就可以访问到grafana web  ui界面

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/2679195400.png)

### 4.3 添加监控dashboard模板

- 添加prometheus数据源
- 导入json或dashboard id

- node-exporter为例：导入模版id：11074

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/796876382.png)

## 五、安装kube-state-metrics组件

> 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

### 5.1 创建sa并对其授权

```
1.创建sa并对其授权
[root@k8s-master01 prometheus]#  cat kube-state-metrics-rbac.yaml 
---
apiVersion: v1
kind: ServiceAccount
metadata:
  name: kube-state-metrics
  namespace: monitor-sa
---
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: monitor-sa
```

### 5.2 编写yaml文件并应用

```
1.编写yaml
[root@k8s-master01 prometheus]# cat kube-state-metrics-deploy.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
  name: kube-state-metrics
  namespace: monitor-sa
spec:
  replicas: 1
  selector:
    matchLabels:
      app: kube-state-metrics
  template:
    metadata:
      labels:
        app: kube-state-metrics
    spec:
      nodeName: k8s-node02
      serviceAccountName: kube-state-metrics
      containers:
      - name: kube-state-metrics
        image: 100.100.157.10:5000/k8s/prometheus/kube-state-metrics
        ports:
        - containerPort: 8080

2.应用
kubectl apply -f kube-state-metrics-deploy.yaml

3.验证查看
[root@k8s-master01 prometheus]# kubectl get pod -n monitor-sa -o wide |grep state
kube-state-metrics-5b689dccc7-7pfsv   1/1     Running   0          7m27s   10.244.2.7       k8s-node02     <none>           <none>
```

### 5.3 创建servcie

```
1.编写svc yaml文件
[root@k8s-master01 prometheus]# cat kube-state-metrics-svc.yaml
apiVersion: v1
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: 'true'
  name: kube-state-metrics
  namespace: monitor-sa
  labels:
    app: kube-state-metrics
spec:
  ports:
  - name: kube-state-metrics
    port: 8080
    protocol: TCP
  selector:
    app: kube-state-metrics

2.应用
kubectl apply -f kube-state-metrics-svc.yaml

3.验证查看
[root@k8s-master01 prometheus]# kubectl get svc -n monitor-sa
NAME                 TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)          AGE
kube-state-metrics   ClusterIP   10.105.152.211   <none>        8080/TCP         8m2s
```

### 5.4 导入k8s pod 监控模版

- 添加prometheus数据源
- 导入json或dashboard id
  - `kube-state-metrics`为例：导入模版id： 13105

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/2236964675.png)

## 六、安装alertmanager组件

### 6.1 创建alertmanager-cm.yaml配置文件

```
1.创建configmap
[root@k8s-master01 prometheus]# cat alertmanager-cm.yaml 
apiVersion: v1
kind: ConfigMap
metadata:
  name: alertmanager-config
  namespace: monitor-sa
data:
  alertmanager.yml: |
global:
  resolve_timeout: 15s
inhibit_rules:
- source_match:
    severity: 'critical'
  target_match:
    severity: 'warning'
  equal: ['alertname', 'namespace']
route:
  group_by: ['alertname', 'namespace']
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 1h
  receiver: 'webhook1'
  routes:
  - match:
      severity: 'warning'  # 修正为匹配severity标签
    receiver: 'webhook1'
receivers:
- name: 'webhook1'
  webhook_configs:
  - url: 'http://100.100.157.12:30071/dingtalk/webhook1/send'
    send_resolved: true

2.应用
kubectl apply -f alertmanager-cm.yaml
```

### 6.2 创建alertmanager-deploy

```shell
1.编辑yaml
[root@k8s-master01 prometheus]# cat alertmanager-deploy.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: alertmanager
  namespace: monitor-sa
  labels:
    app: alertmanager
    component: server
spec:
  replicas: 1
  selector:
    matchLabels:
      app: alertmanager
      component: server
  template:
    metadata:
      labels:
        app: alertmanager
        component: server
    spec:
      nodeName: k8s-work01
      containers:
      - name: alertmanager
        image: 100.100.157.10:5000/k8s/prometheus/alertmanager:latest
        args:
        - "--config.file=/etc/alertmanager/alertmanager.yml"
        - "--log.level=debug"
        ports:
        - containerPort: 9093
          name: alertmanager
        volumeMounts:
        - name: alertmanager-config
          mountPath: /etc/alertmanager
        - name: localtime
          mountPath: /etc/localtime
      volumes:
      - name: alertmanager-config
        configMap:
          name: alertmanager
      - name: localtime
        hostPath:
          path: /usr/share/zoneinfo/Asia/Shanghai
2.应用
kubectl -apply -f alertmanager-deploy.yaml 
```

### 6.4 创建altermanager svc yaml

```shell
1.编辑yaml
[root@k8s-master01 prometheus]# cat alertmanager-svc.yaml 
apiVersion: v1
kind: Service
metadata:
  name: alertmanager
  namespace: monitor-sa
  labels:
    app: alertmanager
spec:
  type: NodePort
  ports:
    - port: 9093
      targetPort: 9093
      nodePort: 30903  # 建议显式指定NodePort范围(30000-32767)
      protocol: TCP
  selector:
    app: alertmanager

2. 应用
kubectl apply -f alertmanager-svc.yaml
```

### 6.5 创建prometheus和告警规则的配置文件

```shell
1.#  先删除上次设置的configmap
[root@k8s-master01 prometheus]# kubectl delete -f prometheus-cfg.yaml 
configmap "prometheus-config" deleted

2.新建configmap配置
[root@k8s-master01 prometheus]# 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: ["100.100.157.12:30903"]
    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:$2
        source_labels:
        - __address__
        - __meta_kubernetes_pod_annotation_prometheus_io_port
        target_label: __address__
      - action: labelmap
        regex: __meta_kubernetes_pod_label_(.+)
      - action: replace
        source_labels:
        - __meta_kubernetes_namespace
        target_label: kubernetes_namespace
      - action: replace
        source_labels:
        - __meta_kubernetes_pod_name
        target_label: kubernetes_pod_name
    - job_name: 'kubernetes-kube-proxy'
      scrape_interval: 5s
      static_configs:
      - targets: ['100.100.157.10:10249','100.100.157.11:10249','100.100.157.12:10249']
    - job_name: 'kubernetes-etcd'
      scheme: https
      tls_config:
        ca_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/ca.crt
        cert_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.crt
        key_file: /var/run/secrets/kubernetes.io/k8s-certs/etcd/server.key
      scrape_interval: 5s
      static_configs:
      - targets: ['100.100.157.10:2379']
  rules.yml: |
    groups:
    - name: example
      rules:
      - alert: kube-proxy的cpu使用率大于80%
        expr: rate(process_cpu_seconds_total{job=~"kubernetes-kube-proxy"}[1m]) * 100 > 80
        for: 2s
        labels:
          severity: warnning
        annotations:
          description: "{{$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 }}"

3.应用
[root@k8s-master01 prometheus]# kubectl apply -f prometheus-alertmanager-cfg.yaml 
configmap/prometheus-config created
[root@k8s-master01 prometheus]# kubectl get cm -n monitor-sa
NAME                DATA   AGE
alertmanager        1      25m
prometheus-config   2      3m20s
```

## 七、安装prometheus和altermanager

### 7.1 删除上述操作步骤安装的prometheus的deployment资源

```sh
kubectl delete -f prometheus-deploy.yaml 
deployment.apps "prometheus-server" deleted
```

### 7.2 生成etcd-certs

```shell
[root@k8s-master01 prometheus]# 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-master01 prometheus]# 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
```

### 7.3 编写deployment的yaml

```shell
1.编写prometheus deploy yaml
[root@k8s-master01 prometheus]# cat prometheus-deploy.yaml 
apiVersion: apps/v1
kind: Deployment
metadata:
  name: prometheus-server
  namespace: monitor-sa
  labels:
    app: prometheus
    component: server
spec:
  replicas: 1
  selector:
    matchLabels:
      app: prometheus
      component: server
  template:
    metadata:
      labels:
        app: prometheus
        component: server
    spec:
      nodeName: k8s-work01
      serviceAccountName: monitor
      containers:
      - name: prometheus
        image: 100.100.157.10:5000/k8s/prometheus/prometheus:latest
        imagePullPolicy: IfNotPresent
        args:
        - "--config.file=/etc/prometheus/prometheus.yml"
        - "--storage.tsdb.path=/prometheus"
        - "--web.enable-lifecycle"
        ports:
        - containerPort: 9090
        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/
      volumes:
      - name: prometheus-config
        configMap:
          name: prometheus-config
      - name: prometheus-storage-volume
        hostPath:
          path: /root/hxy/data/prometheus/
          type: DirectoryOrCreate
      - name: k8s-certs
        secret:
          secretName: etcd-certs
```

### 7.4验证

```shell
[root@k8s-master01 prometheus]# kubectl get pod -n monitor-sa
NAME                                  READY   STATUS    RESTARTS   AGE
alertmanager-6746c4b964-fj5sd         1/1     Running   0          10h
kube-state-metrics-5b689dccc7-7pfsv   1/1     Running   0          16h
monitoring-grafana-9fd8c4d46-kmxsc    1/1     Running   0          20h
node-exporter-8sg29                   1/1     Running   0          22h
node-exporter-vwvg6                   1/1     Running   0          22h
node-exporter-wv9mw                   1/1     Running   0          22h
prometheus-server-5875bc5556-9cflt    1/1     Running   0          6m4s

[root@k8s-master01 prometheus]# kubectl get svc  -n monitor-sa
NAME                 TYPE        CLUSTER-IP       EXTERNAL-IP   PORT(S)          AGE
alertmanager         NodePort    10.101.13.179    <none>        9093:30903/TCP   14h
```

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/3609492263.png)

## 八、部署webhook钉钉告警

### 8.1 编辑webhook configmang

```shell
[root@k8s-master01 prometheus]#  cat dingtalk-configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
  name: prometheus-webhook-dingtalk-config
  namespace: monitor-sa
data:
  config.yml: |-
    templates:
      - /etc/prometheus-webhook-dingtalk/default.tmpl
    targets:
      webhook1:
        url: https://oapi.dingtalk.com/robot/send?access_token=0c05f33c5a85757dcc433bada4fc4c8af88b23b20edd628c96a235736aedf408
        secret: SEC50c82183087eea89b8a5eeeb3a3ad9555f5e159f07360a35393ae545db6b4542
        mention:
          all: true
        message:
          text: '{{ template "default.tmpl" . }}'
 
  default.tmpl: |
    {{ define "default.tmpl" }}
 
    {{- if gt (len .Alerts.Firing) 0 -}}
    {{- range $index, $alert := .Alerts -}}
 
    ============ = **<font color='#FF0000'>告警</font>** = =============  #红色字体
  
    **告警名称:**    {{ $alert.Labels.alertname }}   
    **告警级别:**    {{ $alert.Labels.severity }} 级   
    **告警状态:**    {{ .Status }}   
    **告警实例:**    {{ $alert.Labels.instance }} {{ $alert.Labels.device }}   
    **告警概要:**    {{ .Annotations.summary }}   
    **告警详情:**    {{ $alert.Annotations.message }}{{ $alert.Annotations.description}}   
    **故障时间:**    {{ ($alert.StartsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}  
    ============ = end = =============  
    {{- end }}
    {{- end }}
 
    {{- if gt (len .Alerts.Resolved) 0 -}}
    {{- range $index, $alert := .Alerts -}}
 
    ============ = <font color='#00FF00'>恢复</font> = =============   #绿色字体
 
    **告警实例:**    {{ .Labels.instance }}   
    **告警名称:**    {{ .Labels.alertname }}  
    **告警级别:**    {{ $alert.Labels.severity }} 级   
    **告警状态:**    {{   .Status }} 
    **告警概要:**    {{ $alert.Annotations.summary }}  
    **告警详情:**    {{ $alert.Annotations.message }}{{ $alert.Annotations.description}}  
    **故障时间:**    {{ ($alert.StartsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}  
    **恢复时间:**    {{ ($alert.EndsAt.Add 28800e9).Format "2006-01-02 15:04:05" }}  
 
    ============ = **end** = =============
    {{- end }}
    {{- end }}
    {{- end }}
```

### 8.2 编辑deploy文件

```shell
[root@k8s-master01 prometheus]# cat dingtalk-webhook-deploy.yaml 
apiVersion: v1
kind: Service
metadata:
  name: dingtalk
  namespace: monitor-sa
  labels:
    app: dingtalk
spec:
  selector:
    app: dingtalk
  ports:
  - name: dingtalk
    port: 8060
    protocol: TCP
    targetPort: 8060
  
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: dingtalk
  namespace: monitor-sa
spec:
  replicas: 1
  selector:
    matchLabels:
      app: dingtalk
  template:
    metadata:
      name: dingtalk
      labels:
        app: dingtalk
    spec:
      nodeSelector:  # 关键修改：指定调度到 k8s-node02
        kubernetes.io/hostname: k8s-node02  # 使用节点的主机名标签
      containers:
      - name: dingtalk
        image: 100.100.157.10:5000/k8s/prometheus/prometheus-webhook-dingtalk
        imagePullPolicy: IfNotPresent
        args:
        - --web.listen-address=:8060
        - --config.file=/etc/prometheus-webhook-dingtalk/config.yml
        ports:
        - containerPort: 8060
        volumeMounts:
        - name: config
          mountPath: /etc/prometheus-webhook-dingtalk
      volumes:
      - name: config
        configMap:
          name: prometheus-webhook-dingtalk-config
```

### 8.3 编辑svc文件

```
[root@k8s-master01 prometheus]#  cat dingtalk_service.yml 
apiVersion: v1
kind: Service
metadata:
  name: dingtalk
  namespace: monitor-sa
  labels:
    app: dingtalk
spec:
  type: NodePort  # 关键修改：改为 NodePort
  selector:
    app: dingtalk
  ports:
    - name: dingtalk
      port: 8060    # Service 监听的端口（集群内访问）
      targetPort: 8060  # 容器端口
      nodePort: 30071   # （可选）手动指定 NodePort 范围（30000-32767）
```

## 九、验证告警

![image.png](http://www.hxy.bj.cn/usr/uploads/2025/05/897453137.png)

最后修改：2025 年 05 月 06 日