mirror of
https://github.com/Alkatrazz24/Funk-lab.git
synced 2026-07-08 22:24:42 +02:00
d7b33bb34a
- k8s/argocd-bootstrap/values.yaml : ArgoCD Helm values (ingress Traefik,
resources limités, dex désactivé)
- k8s/apps-of-apps/ : root Application + monitoring Application
- k8s/infra/monitoring/ : kube-prometheus-stack v85.0.2 (Grafana, Prometheus,
AlertManager, node-exporter daemonset)
- Scrape additionnels : storage-01:9100, gpu-01:9100 (node), :9101 (ROCm),
llama-server :1234/:1236/:1237
- AlertManager webhook → http://192.168.10.1:9093/webhook (Hermes monitor)
- Ressources dimensionnées pour compute 8GB
- kubeEtcd/Scheduler/ControllerManager/Proxy désactivés (Talos)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
140 lines
2.9 KiB
YAML
140 lines
2.9 KiB
YAML
# kube-prometheus-stack — cluster Funk
|
|
# Ressources limitées pour compute-02/03 (8 GB RAM)
|
|
|
|
grafana:
|
|
ingress:
|
|
enabled: true
|
|
ingressClassName: traefik
|
|
hosts:
|
|
- grafana.lab.local
|
|
adminPassword: "funk-grafana"
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
memory: 256Mi
|
|
persistence:
|
|
enabled: false
|
|
|
|
prometheus:
|
|
prometheusSpec:
|
|
retention: 15d
|
|
retentionSize: "8GB"
|
|
resources:
|
|
requests:
|
|
cpu: 200m
|
|
memory: 512Mi
|
|
limits:
|
|
memory: 1Gi
|
|
storageSpec:
|
|
volumeClaimTemplate:
|
|
spec:
|
|
accessModes: ["ReadWriteOnce"]
|
|
resources:
|
|
requests:
|
|
storage: 20Gi
|
|
|
|
# Scrape des nœuds hors cluster (storage-01, gpu-01)
|
|
additionalScrapeConfigs:
|
|
- job_name: storage-01
|
|
static_configs:
|
|
- targets: ['192.168.10.1:9100']
|
|
labels:
|
|
instance: storage-01
|
|
role: gateway
|
|
|
|
- job_name: gpu-01-node
|
|
static_configs:
|
|
- targets: ['192.168.10.20:9100']
|
|
labels:
|
|
instance: gpu-01
|
|
role: gpu
|
|
|
|
- job_name: gpu-01-rocm
|
|
static_configs:
|
|
- targets: ['192.168.10.20:9101']
|
|
labels:
|
|
instance: gpu-01
|
|
role: gpu
|
|
|
|
- job_name: llama-server-gpu
|
|
static_configs:
|
|
- targets: ['192.168.10.20:1234']
|
|
labels:
|
|
instance: gpu-01
|
|
model: qwen3-8b
|
|
type: gpu
|
|
|
|
- job_name: llama-server-system
|
|
static_configs:
|
|
- targets: ['192.168.10.20:1236']
|
|
labels:
|
|
instance: gpu-01
|
|
model: qwen3-1.7b-system
|
|
type: cpu
|
|
|
|
- job_name: llama-server-monitor
|
|
static_configs:
|
|
- targets: ['192.168.10.20:1237']
|
|
labels:
|
|
instance: gpu-01
|
|
model: qwen3-1.7b-monitor
|
|
type: cpu
|
|
|
|
alertmanager:
|
|
alertmanagerSpec:
|
|
resources:
|
|
requests:
|
|
cpu: 50m
|
|
memory: 64Mi
|
|
limits:
|
|
memory: 128Mi
|
|
config:
|
|
global:
|
|
resolve_timeout: 5m
|
|
route:
|
|
group_by: ['alertname', 'instance']
|
|
group_wait: 30s
|
|
group_interval: 5m
|
|
repeat_interval: 4h
|
|
receiver: hermes-monitor
|
|
receivers:
|
|
- name: hermes-monitor
|
|
webhook_configs:
|
|
- url: 'http://192.168.10.1:9093/webhook'
|
|
send_resolved: true
|
|
|
|
prometheusOperator:
|
|
resources:
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
limits:
|
|
memory: 256Mi
|
|
|
|
kube-state-metrics:
|
|
resources:
|
|
requests:
|
|
cpu: 50m
|
|
memory: 64Mi
|
|
limits:
|
|
memory: 128Mi
|
|
|
|
nodeExporter:
|
|
resources:
|
|
requests:
|
|
cpu: 50m
|
|
memory: 32Mi
|
|
limits:
|
|
memory: 64Mi
|
|
|
|
# Désactiver etcd/scheduler monitoring (Talos — non accessible)
|
|
kubeEtcd:
|
|
enabled: false
|
|
kubeScheduler:
|
|
enabled: false
|
|
kubeControllerManager:
|
|
enabled: false
|
|
kubeProxy:
|
|
enabled: false
|