Prometheus+Altermanager钉钉报警
一、添加钉钉机器人
参考钉钉官方文档：https://ding-doc.dingtalk.com/doc#/serverapi2/qf2nxq
二、在k8s上部署钉钉告警deployment，这里我们引用第三方的插件。
[root@cn-hongkong webhook-dingtalk]# cat webhook-dingtalk.yaml
apiVersion: apps/v1beta2
kind: Deployment
metadata:
labels:
app: webhook-dingtalk
name: webhook-dingtalk
namespace: monitoring
#需要和alertmanager在同一个namespace
spec:
replicas: 1
selector:
matchLabels:
app: webhook-dingtalk
template:
metadata:
labels:
app: webhook-dingtalk
spec:
containers:
- image: billy98/webhook-dingtalk:latest
name: webhook-dingtalk
args:
- "https://oapi.dingtalk.com/robot/send?access_token=1fd59067ab85bea575122a5e4f05cefd6609d9d3e41a725e46a90c2fad9b3"
#上面创建的钉钉机器人hook
ports:
- containerPort: 8080
protocol: TCP
resources:
requests:
cpu: 100m
memory: 100Mi
limits:
cpu: 500m
memory: 500Mi
livenessProbe:
failureThreshold: 3
initialDelaySeconds: 30
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 1
tcpSocket:
port: 8080
readinessProbe:
failureThreshold: 3
initialDelaySeconds: 30
periodSeconds: 10
successThreshold: 1
timeoutSeconds: 1
httpGet:
port: 8080
path: /
imagePullSecrets:
- name: IfNotPresent
---
apiVersion: v1
kind: Service
metadata:
labels:
app: webhook-dingtalk
name: webhook-dingtalk
namespace: monitoring
#需要和alertmanager在同一个namespace
spec:
ports:
- name: http
port: 80
protocol: TCP
targetPort: 8080
selector:
app: webhook-dingtalk
type: ClusterIP
三、alertmanager添加钉钉告警类型
config:
global:
resolve_timeout: 5m
route:
group_by: ['job','severity']
group_wait: 30s
group_interval: 5m
repeat_interval: 12h
receiver: default
receiver: webhook
routes:
- match:
filesystem: node
receiver: webhook
receivers:
- name: webhook
webhook_configs:
- url: http://webhook-dingtalk/dingtalk/send/
send_resolved: true