fix inference extension not correctly scrape pod metrics

Signed-off-by: Kuromesi <[email protected]>

Author: Kuromesi

pkg/ext-proc/backend/datastore.go

@@ -151,13 +151,16 @@ func (ds *datastore) PodDelete(namespacedName types.NamespacedName) {
 }
 
 func (ds *datastore) PodUpdateOrAddIfNotExist(pod *corev1.Pod) bool {
+	pool, _ := ds.PoolGet()
 	new := &PodMetrics{
 		Pod: Pod{
 			NamespacedName: types.NamespacedName{
 				Name:      pod.Name,
 				Namespace: pod.Namespace,
 			},
-			Address: pod.Status.PodIP,
+			Address:    pod.Status.PodIP,
+			ScrapePath: "/metrics",
+			ScrapePort: pool.Spec.TargetPortNumber,
 		},
 		Metrics: Metrics{
 			ActiveModels: make(map[string]int),

pkg/ext-proc/backend/types.go

@@ -10,6 +10,10 @@ import (
 type Pod struct {
 	NamespacedName types.NamespacedName
 	Address        string
+
+	// metrics scrape options
+	ScrapePort int32
+	ScrapePath string
 }
 
 type Metrics struct {
@@ -52,3 +56,7 @@ func (pm *PodMetrics) Clone() *PodMetrics {
 	}
 	return clone
 }
+
+func (pm *PodMetrics) BuildScrapeEndpoint() string {
+	return fmt.Sprintf("http://%s:%d%s", pm.Address, pm.ScrapePort, pm.ScrapePath)
+}

pkg/ext-proc/backend/vllm/metrics.go

@@ -45,7 +45,7 @@ func (p *PodMetricsClientImpl) FetchMetrics(
 
 	// Currently the metrics endpoint is hard-coded, which works with vLLM.
 	// TODO(https://github.com/kubernetes-sigs/gateway-api-inference-extension/issues/16): Consume this from InferencePool config.
-	url := fmt.Sprintf("http://%s/metrics", existing.Address)
+	url := existing.BuildScrapeEndpoint()
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, url, nil)
 	if err != nil {
 		loggerDefault.Error(err, "Failed create HTTP request", "method", http.MethodGet, "url", url)