44713e4ca0
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018BAUeCFpDkRD6tU5wGsc1C
151 lines
4.1 KiB
YAML
151 lines
4.1 KiB
YAML
# =============================================================================
|
|
# Alertmanager -- routage des alertes vers Discord
|
|
# =============================================================================
|
|
# L'URL du webhook n'est PAS dans ce ConfigMap : elle est lue depuis un fichier
|
|
# monte depuis un Secret (webhook_url_file). Un ConfigMap est lisible par tout
|
|
# ce qui a un acces lecture au namespace, un webhook Discord permet de publier
|
|
# n'importe quoi dans votre canal d'exploitation.
|
|
---
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: alertmanager-config
|
|
namespace: monitoring
|
|
data:
|
|
alertmanager.yml: |
|
|
global:
|
|
resolve_timeout: 5m
|
|
|
|
route:
|
|
receiver: discord
|
|
group_by: ['alertname', 'severity']
|
|
group_wait: 30s
|
|
group_interval: 5m
|
|
# Une alerte critique non traitee est repetee toutes les heures : elle ne
|
|
# doit pas disparaitre du fil de discussion.
|
|
repeat_interval: 1h
|
|
routes:
|
|
- matchers:
|
|
- severity = "avertissement"
|
|
receiver: discord
|
|
repeat_interval: 12h
|
|
|
|
inhibit_rules:
|
|
# Si le backend est totalement indisponible, inutile d'inonder le canal
|
|
# avec les alertes de latence et de taux d'erreur qui en decoulent.
|
|
- source_matchers:
|
|
- alertname = "BackendIndisponible"
|
|
target_matchers:
|
|
- severity =~ "avertissement|critique"
|
|
equal: ['cluster']
|
|
|
|
receivers:
|
|
- name: discord
|
|
discord_configs:
|
|
- webhook_url_file: /etc/alertmanager/secrets/discord-webhook
|
|
send_resolved: true
|
|
title: '[{{ .Status | toUpper }}] {{ .CommonLabels.alertname }}'
|
|
message: |-
|
|
{{ range .Alerts }}{{ .Annotations.summary }}
|
|
{{ .Annotations.description }}
|
|
{{ end }}
|
|
---
|
|
apiVersion: v1
|
|
kind: PersistentVolumeClaim
|
|
metadata:
|
|
name: alertmanager-data
|
|
namespace: monitoring
|
|
spec:
|
|
accessModes: [ReadWriteOnce]
|
|
storageClassName: local-path
|
|
resources:
|
|
requests:
|
|
storage: 1Gi
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: alertmanager
|
|
namespace: monitoring
|
|
labels:
|
|
app.kubernetes.io/name: alertmanager
|
|
spec:
|
|
replicas: 1
|
|
strategy:
|
|
type: Recreate
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: alertmanager
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: alertmanager
|
|
spec:
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 65534
|
|
runAsGroup: 65534
|
|
fsGroup: 65534
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
containers:
|
|
- name: alertmanager
|
|
image: prom/alertmanager:v0.28.0
|
|
args:
|
|
- --config.file=/etc/alertmanager/alertmanager.yml
|
|
- --storage.path=/alertmanager
|
|
- --web.listen-address=:9093
|
|
ports:
|
|
- name: http
|
|
containerPort: 9093
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /-/ready
|
|
port: http
|
|
initialDelaySeconds: 10
|
|
resources:
|
|
requests:
|
|
cpu: 20m
|
|
memory: 64Mi
|
|
limits:
|
|
cpu: 200m
|
|
memory: 192Mi
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
readOnlyRootFilesystem: true
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
volumeMounts:
|
|
- name: config
|
|
mountPath: /etc/alertmanager/alertmanager.yml
|
|
subPath: alertmanager.yml
|
|
- name: secrets
|
|
mountPath: /etc/alertmanager/secrets
|
|
readOnly: true
|
|
- name: data
|
|
mountPath: /alertmanager
|
|
volumes:
|
|
- name: config
|
|
configMap:
|
|
name: alertmanager-config
|
|
- name: secrets
|
|
secret:
|
|
secretName: alertmanager-secrets
|
|
- name: data
|
|
persistentVolumeClaim:
|
|
claimName: alertmanager-data
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: alertmanager
|
|
namespace: monitoring
|
|
spec:
|
|
type: ClusterIP
|
|
selector:
|
|
app.kubernetes.io/name: alertmanager
|
|
ports:
|
|
- name: http
|
|
port: 9093
|
|
targetPort: http
|