Add ServiceMonitor for llm-serving namespace. Wire prometheus.io annotations to all vLLM pods (reasoning, ornith, embeddings, reranker). Scrape /metrics@8080 every 30s with proper relabeling.
31 lines
821 B
YAML
31 lines
821 B
YAML
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: vllm
|
|
namespace: monitoring
|
|
labels:
|
|
app.kubernetes.io/name: vllm
|
|
app.kubernetes.io/part-of: llm-serving
|
|
spec:
|
|
namespaceSelector:
|
|
matchNames:
|
|
- llm-serving
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/part-of: llm-serving
|
|
endpoints:
|
|
- port: http
|
|
interval: 30s
|
|
scrapeTimeout: 10s
|
|
path: /metrics
|
|
scheme: http
|
|
relabelings:
|
|
- sourceLabels: [__meta_kubernetes_namespace]
|
|
targetLabel: namespace
|
|
- sourceLabels: [__meta_kubernetes_pod_name]
|
|
targetLabel: pod
|
|
- sourceLabels: [__meta_kubernetes_service_name]
|
|
targetLabel: service
|
|
- sourceLabels: [__meta_kubernetes_pod_label_app_kubernetes_io_name]
|
|
targetLabel: app
|