Adding pprof endpoints to metrics port (kubernetes-sigs#1069)

Author: kfswain

cmd/epp/runner/runner.go

@@ -21,7 +21,6 @@ import (
 	"flag"
 	"fmt"
 	"net/http/pprof"
-	"os"
 
 	"github.com/go-logr/logr"
 	"github.com/prometheus/client_golang/prometheus"

site-src/guides/metrics-and-observability.md

@@ -172,6 +172,16 @@ We currently have 2 types of prometheus deployments documented:
 Please follow [grafana instructions](https://grafana.com/docs/grafana/latest/dashboards/build-dashboards/import-dashboards/) to load the dashboard json.
 The dashboard can be found here [Grafana Dashboard](https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/tools/dashboards/inference_gateway.json)
 
+### Pprof profiles
+
+Currently only the [predefined profiles](https://pkg.go.dev/runtime/pprof#Profile) are supported, CPU profiling will require code changes. Assuming the EPP has been port-forwarded as in the above example, to get the PGN display of the `heap` profile simply run:
+
+```
+PROFILE_NAME=heap
+curl -H "Authorization: Bearer $TOKEN" localhost:9090/debug/pprof/$PROFILE_NAME -o profile.out
+go tool pprof -png profile.out
+```
+
 ## Prometheus Alerts
 
 The section instructs how to configure prometheus alerts using collected metrics.