---

title: 8.6.在k8s中黑盒监控
order: 48

icon: lightbulb

一、环境

主机名	IP地址	系统	说明
k8s	192.168.11.65	Ubuntu 20.04	k8s版本：v1.23.10 单机版本

二、黑盒监控

1、安装blackbox-exporter

使用helm安装

通过 prometheus-community仓库下载

helm search repo prometheus-community|grep prometheus-blackbox-exporter
helm fetch prometheus-community/prometheus-blackbox-exporter
tar xf prometheus-blackbox-exporter-7.6.1.tgz

通过wget下载

wget https://github.com/prometheus-community/helm-charts/releases/download/prometheus-blackbox-exporter-7.6.1/prometheus-blackbox-exporter-7.6.1.tgz 

tar xf prometheus-blackbox-exporter-7.6.1.tgz 

grep -A 2 'image:' prometheus-blackbox-exporter/*

#不用替换

修改配置文件

vim prometheus-blackbox-exporter/values.yaml

```
config:
  modules:
    tcp_connect:
      prober: tcp
    icmp:
      prober: icmp
serviceMonitor:
  enabled: true
  defaults:
    labels:
      release: prometheus
  targets:
    - name: baidu.com
      url: https://baidu.com
    #- name: xxx
    #  url: xxxservice.namespace名称.svc.cluster.local:port/actuator/health
    - name: tcp-mysql
      url: mysql.default.svc.cluster.local:3306
      module: tcp_connect
    - name: icmp-localhost
      url: 127.0.0.1
      module: icmp
#告警规则（触发器）      
prometheusRule:
  enabled: true
  additionalLabels:
    release: prometheus
  namespace: ""
  rules:
  - alert: 黑盒子探测失败告警
    expr: probe_success == 0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "黑盒子探测失败{{ $labels.instance }}"
      description: "黑盒子检测失败，当前值：{{ $value }}"
  - alert: 请求慢告警
    expr: avg_over_time(probe_duration_seconds[1m]) > 1
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "请求慢{{ $labels.instance }}"
      description: "请求时间超过1秒，值为：{{ $value }}"
  - alert: http状态码检测失败
    expr: probe_http_status_code <= 199 OR probe_http_status_code >= 400
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "http状态码检测失败{{ $labels.instance }}"
      description: "HTTP状态码非 200-399，当前状态码为：{{ $value }}"
  - alert: ssl证书即将到期
    expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 30
    for: 1m
    labels:
      severity: warning
    annotations:
      summary: "证书即将到期{{ $labels.instance }}"
      description: "SSL 证书在 30 天后到期，值：{{ $value }}"

  - alert: ssl证书即将到期
    expr: probe_ssl_earliest_cert_expiry - time() < 86400 * 3
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "证书即将到期{{ $labels.instance }}"
      description: "SSL 证书在 3 天后到期，值：{{ $value }}"
  - alert: ssl证书已过期
    expr: probe_ssl_earliest_cert_expiry - time() <= 0
    for: 1m
    labels:
      severity: critical
    annotations:
      summary: "证书已过期{{ $labels.instance }}"
      description: "SSL 证书已经过期，请确认是否在使用"

安装blackbox-exporter

helm install -n monitoring --create-namespace prometheus-blackbox-exporter prometheus-blackbox-exporter

如果修改了配置文件

helm -n monitoring upgrade prometheus-blackbox-exporter prometheus-blackbox-exporter

检查

通过curl检查

curl http://10.233.55.233:9115/probe?target=https://www.baidu.com&module=http_2xx

检查配置

root@k8s:~# kubectl -n monitoring get cm prometheus-blackbox-exporter -o yaml
apiVersion: v1
data:
  blackbox.yaml: |
    modules:
      http_2xx:
        http:
          follow_redirects: true
          preferred_ip_protocol: ip4
          valid_http_versions:
          - HTTP/1.1
          - HTTP/2.0
        prober: http
        timeout: 5s
      icmp:
        prober: icmp
      tcp_connect:
        prober: tcp

```
root@k8s:~# kubectl get servicemonitors -n monitoring
NAME                                                 AGE
prometheus-blackbox-exporter-baidu.com               3m19s
prometheus-blackbox-exporter-icmp-localhost              3m19s
prometheus-blackbox-exporter-tcp-mysql               3m19s

检查配置

kubectl get prometheusrules prometheus-blackbox-exporter  -n monitoring -oyaml

检查targets

检查数据

检查触发器

http://192.168.11.65:9090/alerts?search=

3、grafama导入dashboard

id：13659

三、我的微信

如果碰到问题，可以随时加我微信，谢谢