kube-prometheus-stack基础上部署domain-exporter监控域名注册过期时间

代码仓库地址

自定义Helm项目

[root@ip-172-31-26-146 domain-exporter]# tree
.
├── Chart.yaml
├── domain-values.yaml
├── templates
│   ├── _helpers.tpl
│   ├── configmap.yaml
│   ├── deployment.yaml
│   ├── service.yaml
│   └── servicemonitor.yaml
└── values.yaml

Chart.yaml文本

apiVersion: v2
name: domain-exporter
description: A Helm chart for Kubernetes to deploy domain_exporter
type: application
version: 0.1.0
appVersion: "1.24.1" # 对应 caarlos0/domain_exporter 的版本

domain-values.yaml文本

domains:
# 对于 parasial.net，改用对象格式，并指定 host
  #- name: parasial.network
  #  host: whois.godaddy.com  # <--- 这里填你的注册商 WHOIS 服务器
  - a.network
  - b.ventures 
  - c.io


serviceMonitor:
  enabled: true  # 如果你有 Prometheus Operator
  labels:
    release: kube-prometheus # 根据你的 Prometheus 实例标签进行调整

templates/_helpers.tpl文本

{{/*
Expand the name of the chart.
*/}}
{{- define "domain-exporter.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}

{{/*
Create a default fully qualified app name.
*/}}
{{- define "domain-exporter.fullname" -}}
{{- if .Values.fullnameOverride }}
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- if contains $name .Release.Name }}
{{- .Release.Name | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- end }}
{{- end }}

{{/*
Common labels
*/}}
{{- define "domain-exporter.labels" -}}
helm.sh/chart: {{ include "domain-exporter.chart" . }}
{{ include "domain-exporter.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}

{{/*
Selector labels
*/}}
{{- define "domain-exporter.selectorLabels" -}}
app.kubernetes.io/name: {{ include "domain-exporter.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}

{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "domain-exporter.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}

templates/configmap.yaml文本

apiVersion: v1
kind: ConfigMap
metadata:
  name: {{ include "domain-exporter.fullname" . }}
  labels:
    {{- include "domain-exporter.labels" . | nindent 4 }}
data:
  domain-exporter.yaml: |
    domains:
    {{- range .Values.domains }}
      {{- if kindIs "string" . }}
      - name: {{ . }}
      {{- else }}
      - name: {{ .name }}
        {{- if .host }}
        host: {{ .host }}
        {{- end }}
      {{- end }}
    {{- end }}

templates/deployment.yaml文本

apiVersion: apps/v1
kind: Deployment
metadata:
  name: {{ include "domain-exporter.fullname" . }}
  labels:
    {{- include "domain-exporter.labels" . | nindent 4 }}
spec:
  replicas: {{ .Values.replicaCount }}
  selector:
    matchLabels:
      {{- include "domain-exporter.selectorLabels" . | nindent 6 }}
  template:
    metadata:
      annotations:
        # 确保 ConfigMap 变更时 Pod 会重启
        checksum/config: {{ include (print $.Template.BasePath "/configmap.yaml") . | sha256sum }}
        # 为没有 ServiceMonitor 的 Prometheus 添加注解
        prometheus.io/scrape: "true"
        prometheus.io/port: "9222"
      labels:
        {{- include "domain-exporter.selectorLabels" . | nindent 8 }}
    spec:
      containers:
        - name: {{ .Chart.Name }}
          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
          imagePullPolicy: {{ .Values.image.pullPolicy }}
          args:
            - "--config"
            - "/etc/domain_exporter/domain-exporter.yaml" # <--- 修改这里：后缀改为 .yaml
            - "--bind"
            - ":9222"
            #- "--log-format" # 建议加上 json 格式日志，方便排查
            #- "json"
          ports:
            - name: http
              containerPort: 9222
              protocol: TCP
          livenessProbe:
            httpGet:
              path: /metrics
              port: http
          readinessProbe:
            httpGet:
              path: /metrics
              port: http
          resources:
            {{- toYaml .Values.resources | nindent 12 }}
          volumeMounts:
            - name: config
              mountPath: /etc/domain_exporter
              readOnly: true
      volumes:
        - name: config
          configMap:
            name: {{ include "domain-exporter.fullname" . }}

templates/service.yaml文本

apiVersion: v1
kind: Service
metadata:
  name: {{ include "domain-exporter.fullname" . }}
  labels:
    {{- include "domain-exporter.labels" . | nindent 4 }}
spec:
  type: {{ .Values.service.type }}
  ports:
    - port: {{ .Values.service.port }}
      targetPort: http
      protocol: TCP
      name: http
  selector:
    {{- include "domain-exporter.selectorLabels" . | nindent 4 }}

templates/servicemonitor.yaml文本

{{- if .Values.serviceMonitor.enabled }}
apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  name: {{ include "domain-exporter.fullname" . }}
  labels:
    {{- include "domain-exporter.labels" . | nindent 4 }}
    {{- if .Values.serviceMonitor.labels }}
    {{- toYaml .Values.serviceMonitor.labels | nindent 4 }}
    {{- end }}
spec:
  selector:
    matchLabels:
      {{- include "domain-exporter.selectorLabels" . | nindent 6 }}
  endpoints:
    - port: http
      interval: {{ .Values.serviceMonitor.interval }}
      scrapeTimeout: {{ .Values.serviceMonitor.scrapeTimeout }}
{{- end }}

values.yaml

# 镜像配置
image:
  repository: caarlos0/domain_exporter
  pullPolicy: IfNotPresent
  # Overrides the image tag whose default is the chart appVersion.
  tag: "v1.24.1"

# 副本数
replicaCount: 1

# 服务配置
service:
  type: ClusterIP
  port: 9222

# 要监控的域名列表 (在此处修改)
domains:
  - google.com
  - github.com
  - your-domain.com

# 资源限制
resources:
  limits:
    cpu: 100m
    memory: 128Mi
  requests:
    cpu: 10m
    memory: 32Mi

# Prometheus ServiceMonitor 配置 (如果你使用 Prometheus Operator)
serviceMonitor:
  enabled: false
  # namespace: monitoring
  labels: {}
  interval: 1m
  scrapeTimeout: 30s

2、部署domain-exporter

helm upgrade --install domain . -n monitoring -f domain-values.yaml

3、验证

[root@ip-172-31-26-146 domain-exporter]# helm list -n monitoring
NAME           	NAMESPACE 	REVISION	UPDATED                                  	STATUS  	CHART                                	APP VERSION  
domain         	monitoring	13      	2025-12-16 07:27:09.287695031 +0000 UTC  	deployed	domain-exporter-0.1.0                	1.24.1

4、创建alert rules

包括domain注册过期时间以及ssl证书过期时间

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: domain-monitoring-alerts
  namespace: monitoring
  labels:
    # 关键！这个 label 必须和你的 kube-prometheus-stack 的匹配规则一致
    # 也就是之前你在 ServiceMonitor 里用的那个 release 名称
    release: kube-prometheus
spec:
  groups:
    # ==============================
    # 组 1: SSL 证书监控 (Blackbox)
    # ==============================
    - name: ssl-expiry-alerts
      rules:
        # 告警级别：警告 (剩余时间 < 10 天)
        - alert: SslCertificateExpiringSoon
          expr: (probe_ssl_earliest_cert_expiry - time()) < 86400 * 10
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "SSL证书将在30天内过期: {{ $labels.instance }}"
            description: "域名 {{ $labels.instance }} 的 SSL 证书还有 {{ humanizeDuration (query (printf \"probe_ssl_earliest_cert_expiry{instance='%s'} - time()\" .Labels.instance)) }} 过期。"

        # 告警级别：严重 (剩余时间 < 7 天)
        - alert: SslCertificateExpiringCritical
          expr: (probe_ssl_earliest_cert_expiry - time()) < 86400 * 5
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "SSL证书将在7天内过期 (严重): {{ $labels.instance }}"
            description: "紧急！域名 {{ $labels.instance }} 的 SSL 证书将在 1 周内过期，请立即续费！"

    # ==============================
    # 组 2: 域名有效期监控 (Domain Exporter)
    # ==============================
    - name: domain-expiry-alerts
      rules:
        # 假设你的 domain-exporter 指标是 domain_expiry_days
        # 如果是时间戳，请参考上面 SSL 的写法：(metric - time()) < ...
        
        # 告警级别：警告 (剩余天数 < 10 天)
        - alert: DomainExpiringSoon
          expr: domain_expiry_days < 10
          for: 10m
          labels:
            severity: warning
          annotations:
            summary: "域名将在30天内过期: {{ $labels.domain }}"
            description: "域名 {{ $labels.domain }} 将在 {{ $value }} 天后过期，请安排续费。"

        # 告警级别：严重 (剩余天数 < 5 天)
        - alert: DomainExpiringCritical
          expr: domain_expiry_days < 5
          for: 5m
          labels:
            severity: critical
          annotations:
            summary: "域名将在7天内过期 (严重): {{ $labels.domain }}"
            description: "紧急！域名 {{ $labels.domain }} 只有 {{ $value }} 天有效期了，请立即处理！"

部署

[root@ip-172-31-26-146 prometheus-blackbox-exporter]# kubectl apply -f domain-ssl-rules.yaml