rock
605bc706e0
- cag-kv-cache-rules.yaml: recording rule vllm:prefix_cache_hit_rate (from cache_query_hit/miss counters), 3 alert rules: KVWarmupFailureHigh, KVWarmupMissHigh, VLLMPrefixCacheHitRateLow - api-latency-dashboard.yaml: 5 new panels (id 7-11): prefix cache hit rate, warmup hit/miss, warmup latency p50/p95, standing context tier hits, alert panel with fixed threshold 0.01/s
25 lines
936 B
YAML
25 lines
936 B
YAML
apiVersion: kustomize.config.k8s.io/v1beta1
|
|
kind: Kustomization
|
|
# Single source for cluster monitoring config (alerts, servicemonitors, dashboards).
|
|
# NO top-level `namespace:` transformer — PrometheusRules deliberately live in
|
|
# per-app namespaces (forgejo, iam, argocd, storage, ...); a transformer would
|
|
# wrongly rewrite them all to one ns.
|
|
resources:
|
|
- alerts/ingress-alerts.yaml
|
|
- alerts/svc-argocd-rules.yaml
|
|
- alerts/svc-authentik-rules.yaml
|
|
- alerts/svc-forgejo-rules.yaml
|
|
- alerts/svc-grafana-rules.yaml
|
|
- alerts/svc-minio-rules.yaml
|
|
- alerts/svc-vault-rules.yaml
|
|
- alerts/cluster-alerts.yaml
|
|
- alerts/api-gateway-alerts.yaml
|
|
- alerts/cag-kv-cache-rules.yaml
|
|
- servicemonitors/argocd.yaml
|
|
- servicemonitors/authentik.yaml
|
|
- servicemonitors/forgejo.yaml
|
|
- servicemonitors/minio.yaml
|
|
- servicemonitors/ingress-nginx.yaml
|
|
- dashboards/cluster-infrastructure.yaml
|
|
- dashboards/api-gateway.yaml
|