【生产】钉钉告警安装 以及调试

​​前提条件Prometheus+Grafana+alertmanager+ 邮件​​

钉钉告警安装

下载

去官网下载​​prometheus-webhook-dingtalk-2.1.0.linux-amd64.tar.gz​​

wget https://github.com/timonwong/prometheus-webhook-dingtalk/releases/download/v2.1.0/prometheus-webhook-dingtalk-2.1.0.linux-amd64.tar.gz

上传

mkdir prometheus-webhook-dingtalk && cd prometheus-webhook-dingtalk && rz -be

tar zxvf prometheus-webhook-dingtalk-2.1.0.linux-amd64.tar.gz 
mv prometheus-webhook-dingtalk-2.1.0.linux-amd64 /usr/local/
ln -s /usr/local/prometheus-webhook-dingtalk-2.1.0.linux-amd64/ /usr/local/prometheus-webhook-dingtalk

配置config

拷贝个模板文件  

cp config.example.yml config.yml

url 和 secret 是我们创建告警机器人的 webook 和 "加签"

配置模板

[root@zcsmaster1 prometheus-webhook-dingtalk]# pwd
/usr/local/prometheus-webhook-dingtalk
[root@zcsmaster1 prometheus-webhook-dingtalk]# vim contrib/templates/legacy/template.tmpl

contrib/templates/legacy/template.tmpl

{{ define "default.__text_alert_list" }}{{ range . }}
#### \[{{ .Labels.severity | upper }}\] {{ .Annotations.summary }}

**Description:** {{ .Annotations.description }}

**Graph:** [<d83d><dcc8>]({{ .GeneratorURL }})

**Details:**
{{ range .Labels.SortedPairs }}{{ if and (ne (.Name) "severity") (ne (.Name) "summary") }}> - {{ .Name }}: {{ .Value | markdown | html }}
{{ end }}{{ end }}
{{ end }}{{ end }}

{{/* Default */}}
{{ define "default.title" }}{{ template "__subject" . }}{{ end }}
{{ define "default.content" }}#### \[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}\] **[{{ index .GroupLabels "alertname" }}]({{ template "__alertmanagerURL" . }})**
{{ if gt (len .Alerts.Firing) 0 -}}
**Alerts Firing**
{{ template "default.__text_alert_list" .Alerts.Firing }}
{{ range .AtMobiles }}@{{ . }}{{ end }}
{{- end }}
{{ if gt (len .Alerts.Resolved) 0 -}}
**Alerts Resolved**
{{ template "default.__text_alert_list" .Alerts.Resolved }}
{{ range .AtMobiles }}@{{ . }}{{ end }}
{{- end }}
{{- end }}

{{/* Legacy */}}
{{ define "legacy.title" }}{{ template "__subject" . }}{{ end }}
{{ define "legacy.content" }}#### \[{{ .Status | toUpper }}{{ if eq .Status "firing" }}:{{ .Alerts.Firing | len }}{{ end }}\] **[{{ index .GroupLabels "alertname" }}]({{ template "__alertmanagerURL" . }})**
{{ template "__text_alert_list" .Alerts.Firing }}
{{- end }}

{{/* Following names for compatibility */}}
{{ define "ding.link.title" }}{{ template "default.title" . }}{{ end }}
{{ define "ding.link.content" }}{{ template "default.content" . }}{{ end }}

配置启动服务

echo '
[Unit]
Description=prometheus-webhook-dingtalk
After=network.target
[Service]
Type=simple
User=prometheus
ExecStart=/usr/local/prometheus-webhook-dingtalk/prometheus-webhook-dingtalk  \
          --config.file='/usr/local/prometheus-webhook-dingtalk/config.yml'
Restart=on-failure
RestartSec=60s
[Install]
WantedBy=multi-user.target
' > /usr/lib/systemd/system/prometheus-webhook-dingtalk.service

赋权

useradd prometheus

chown prometheus.prometheus /usr/local/prometheus-webhook-dingtalk -R

启动

systemctl enable prometheus-webhook-dingtalk.service
systemctl start prometheus-webhook-dingtalk.service

确认开启了

 ps -aux|grep prometheus-webhook-dingtalk

观察日志

journalctl -u prometheus-webhook-dingtalk.service -f

测试告警

首先修改altermanger 配置

重启

kubectl  apply -f alertmanager-cm.yaml
kubectl  get pod -n ccse
kubectl  delete pod prometheus-server-6d8f4447dd-gfprw -n ccse

查看钉钉