mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-08 10:04:42 +02:00
18da44a89f
Dashboards (ConfigMaps, auto-importés par sidecar Grafana) : - dashboard-kubernetes : cluster overview, pods, PVCs, restarts - dashboard-infrastructure : compute/storage-01/gpu-01 CPU/RAM/disque/réseau + GPU ROCm - dashboard-ai : llama-server GPU/CPU tokens/s, requêtes, VRAM, température GPU Alertes (PrometheusRule) : - alerts-node : CPU>90%, RAM>90%, disque>80%, storage-01/gpu-01 down, load élevé - alerts-k8s : NodeNotReady, PodCrashLoop, PodPending, DeploymentUnavailable, PVCNotBound, ArgoCDOutOfSync - alerts-ai : llama-server GPU/system/monitor down, GPU temp>80°C, VRAM>95%, queue élevée Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
88 lines
3.1 KiB
YAML
88 lines
3.1 KiB
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: funk-k8s-alerts
|
|
namespace: monitoring
|
|
labels:
|
|
release: kube-prometheus-stack
|
|
spec:
|
|
groups:
|
|
- name: funk.kubernetes
|
|
interval: 1m
|
|
rules:
|
|
|
|
# --- Nœuds ---
|
|
- alert: KubeNodeNotReady
|
|
expr: |
|
|
kube_node_status_condition{condition="Ready",status="true"} == 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Nœud k8s NotReady : {{ $labels.node }}"
|
|
description: "Le nœud {{ $labels.node }} est NotReady depuis 5 min. Les workloads peuvent être impactés."
|
|
|
|
# --- Pods ---
|
|
- alert: PodCrashLooping
|
|
expr: |
|
|
increase(kube_pod_container_status_restarts_total[15m]) > 3
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Pod en CrashLoop : {{ $labels.namespace }}/{{ $labels.pod }}"
|
|
description: "{{ $labels.container }} a redémarré {{ $value | printf \"%.0f\" }} fois en 15 min."
|
|
|
|
- alert: PodFailedLong
|
|
expr: |
|
|
kube_pod_status_phase{phase=~"Failed|Unknown"} == 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Pod en échec : {{ $labels.namespace }}/{{ $labels.pod }}"
|
|
description: "Le pod est en phase {{ $labels.phase }} depuis 10 min."
|
|
|
|
- alert: PodPendingLong
|
|
expr: |
|
|
kube_pod_status_phase{phase="Pending"} == 1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Pod Pending depuis 15 min : {{ $labels.namespace }}/{{ $labels.pod }}"
|
|
description: "Vérifier les ressources disponibles, PVCs, et les événements du pod."
|
|
|
|
# --- Deployments ---
|
|
- alert: DeploymentUnavailable
|
|
expr: |
|
|
kube_deployment_status_replicas_available
|
|
< kube_deployment_spec_replicas
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Deployment dégradé : {{ $labels.namespace }}/{{ $labels.deployment }}"
|
|
description: "{{ $labels.deployment }} : {{ $value }} réplicas disponibles sur {{ $labels.replicas }} attendus."
|
|
|
|
# --- Stockage ---
|
|
- alert: PVCNotBound
|
|
expr: |
|
|
kube_persistentvolumeclaim_status_phase{phase!="Bound"} == 1
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "PVC non lié : {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }}"
|
|
description: "La PVC est en phase {{ $labels.phase }} depuis 10 min. Vérifier le NFS provisioner."
|
|
|
|
# --- ArgoCD ---
|
|
- alert: ArgoCDAppOutOfSync
|
|
expr: |
|
|
count(argocd_app_info{sync_status!="Synced"}) > 0
|
|
for: 30m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Application(s) ArgoCD OutOfSync depuis 30 min"
|
|
description: "{{ $value }} app(s) ne sont pas synchronisées. Vérifier http://argocd.lab.local"
|