feat(datalayer): extend file-discovery to support cluster endpoints

Signed-off-by: Liav Weiss <lweiss@redhat.com>

Author: liavweiss

pkg/epp/framework/plugins/datalayer/discovery/file/README.md

@@ -18,10 +18,10 @@ datastore on each change.
 ## How It Works
 
 - **Initial load.** On `Start`, the file is read once. Each entry is
-  validated (address must be a parseable IP, port must be in `[1, 65535]`)
-  and applied via `notifier.Upsert`. Per-entry validation errors are logged
-  and the entry is skipped; file-level problems (open, parse, size > 1 MiB)
-  abort startup.
+  validated (address must be a valid IPv4 or RFC 1123 hostname, port must be
+  in `[1, 65535]`) and applied via `notifier.Upsert`. Per-entry validation
+  errors are logged and the entry is skipped; file-level problems (open,
+  parse, size > 1 MiB) abort startup.
 - **Reload (optional).** When `watchFile: true`, fsnotify Write / Create /
   Remove events trigger a reload. After an atomic rename or ConfigMap-style
   symlink swap (which destroys the inode being watched), the watcher is
@@ -42,12 +42,27 @@ plugin's `path` parameter.
 endpoints:
   - name: <string>              # required -- unique within the file
     namespace: <string>         # optional -- defaults to "default"
-    address: <IPv4>             # required -- must be a valid IPv4 address
+    address: <string>           # required -- IPv4 address or RFC 1123 hostname
     port: <string>              # required -- integer 1-65535 as a string
+    metricsPort: <string>       # optional -- metrics scrape port (defaults to port)
     labels:                     # optional -- arbitrary key/value labels
       <key>: <value>
 ```
 
+When `address` is an IPv4, the endpoint is treated as a pod (`PodName` is set
+to the entry name). When `address` is a hostname, the endpoint is treated as a
+cluster (`PodName` is empty).
+
+### Endpoint Type Label
+
+Each endpoint is tagged with the label `llm-d.ai/endpoint-type` so downstream
+plugins can distinguish pod endpoints from cluster endpoints explicitly. The
+label can be set in the endpoints file; when omitted, the plugin auto-detects
+it from the address format:
+
+- IPv4 address → `llm-d.ai/endpoint-type: pod`
+- Hostname → `llm-d.ai/endpoint-type: cluster`
+
 ## Configuration
 
 **Location:** `dataLayer.discovery.pluginRef` referencing a plugin entry of
@@ -75,7 +90,7 @@ dataLayer:
     pluginRef: file-discovery
 ```
 
-A two-endpoint file referenced by the config above:
+A two-endpoint file with pod IPs:
 
 ```yaml
 endpoints:
@@ -87,13 +102,32 @@ endpoints:
     port: "8000"
 ```
 
+A cluster endpoints file with host names instead of IP addresses:
+
+```yaml
+endpoints:
+  - name: cluster-us-east
+    address: spoke-us-east.example.com
+    port: "443"
+    metricsPort: "9090"
+    labels:
+      region: us-east
+  - name: cluster-eu-west
+    address: spoke-eu-west.example.com
+    port: "443"
+    metricsPort: "9090"
+    labels:
+      region: eu-west
+```
+
 ## Limitations
 
 - The endpoints file is capped at 1 MiB.
-- `address` must be a literal IPv4 address. Hostnames are not resolved;
-  IPv6 is not supported.
-- Metrics are scraped from `address:port` (same host and port that serves
-  inference); separate metrics endpoints are not supported.
+- `address` must be a valid IPv4 address or an RFC 1123 hostname. IPv6 is
+  not supported. Hostnames are not resolved by the plugin; DNS resolution
+  happens at scrape/connect time.
+- Metrics are scraped from `address:metricsPort` (or `address:port` when
+  `metricsPort` is not set).
 - File-discovery mode runs the EPP without a Kubernetes controller manager,
   so several K8s-only features are inactive: the `InferenceModelRewrite`
   and `InferenceObjective` reconcilers do not run, and any

pkg/epp/framework/plugins/datalayer/discovery/file/plugin.go

@@ -28,26 +28,36 @@ import (
 	"os"
 	"sort"
 	"strconv"
+	"strings"
 	"sync"
 
 	"github.com/fsnotify/fsnotify"
 	"k8s.io/apimachinery/pkg/types"
+	"k8s.io/apimachinery/pkg/util/validation"
 	"sigs.k8s.io/controller-runtime/pkg/log"
 	"sigs.k8s.io/yaml"
 
 	fwkdl "github.com/llm-d/llm-d-router/pkg/epp/framework/interface/datalayer"
 	fwkplugin "github.com/llm-d/llm-d-router/pkg/epp/framework/interface/plugin"
 )
 
-const PluginType = "file-discovery"
+const (
+	PluginType = "file-discovery"
+
+	// EndpointTypeLabel distinguishes pod from cluster endpoints.
+	EndpointTypeLabel   = "llm-d.ai/endpoint-type"
+	EndpointTypePod     = "pod"
+	EndpointTypeCluster = "cluster"
+)
 
 // EndpointEntry is the YAML/JSON representation of a single endpoint.
 type EndpointEntry struct {
-	Name      string            `json:"name"                yaml:"name"`
-	Namespace string            `json:"namespace,omitempty" yaml:"namespace,omitempty"`
-	Address   string            `json:"address"             yaml:"address"`
-	Port      string            `json:"port"                yaml:"port"`
-	Labels    map[string]string `json:"labels,omitempty"    yaml:"labels,omitempty"`
+	Name        string            `json:"name"                    yaml:"name"`
+	Namespace   string            `json:"namespace,omitempty"     yaml:"namespace,omitempty"`
+	Address     string            `json:"address"                 yaml:"address"`
+	Port        string            `json:"port"                    yaml:"port"`
+	MetricsPort string            `json:"metricsPort,omitempty"   yaml:"metricsPort,omitempty"`
+	Labels      map[string]string `json:"labels,omitempty"        yaml:"labels,omitempty"`
 }
 
 // EndpointsFile is the top-level structure of the endpoints YAML/JSON file.
@@ -238,9 +248,12 @@ func (f *FileDiscovery) load(notifier fwkdl.DiscoveryNotifier) error {
 	incoming := make(map[types.NamespacedName]struct{}, len(ef.Endpoints))
 	var errs []error
 	for _, e := range ef.Endpoints {
-		if ip := net.ParseIP(e.Address); ip == nil || ip.To4() == nil {
-			errs = append(errs, fmt.Errorf("endpoint %q: invalid IPv4 address %q", e.Name, e.Address))
-			continue
+		ip := net.ParseIP(e.Address)
+		if ip == nil || ip.To4() == nil {
+			if len(validation.IsDNS1123Subdomain(strings.ToLower(e.Address))) > 0 {
+				errs = append(errs, fmt.Errorf("endpoint %q: address %q is not a valid IPv4 or hostname", e.Name, e.Address))
+				continue
+			}
 		}
 		if portNum, err := strconv.Atoi(e.Port); err != nil || portNum < 1 || portNum > 65535 {
 			errs = append(errs, fmt.Errorf("endpoint %q: invalid port %q", e.Name, e.Port))
@@ -250,13 +263,32 @@ func (f *FileDiscovery) load(notifier fwkdl.DiscoveryNotifier) error {
 		if ns == "" {
 			ns = "default"
 		}
+		podName := e.Name
+		if ip == nil {
+			podName = ""
+		}
+		mPort := e.Port
+		if e.MetricsPort != "" {
+			mPort = e.MetricsPort
+		}
+		labels := e.Labels
+		if labels == nil {
+			labels = make(map[string]string)
+		}
+		if v := labels[EndpointTypeLabel]; v != EndpointTypePod && v != EndpointTypeCluster {
+			if ip == nil {
+				labels[EndpointTypeLabel] = EndpointTypeCluster
+			} else {
+				labels[EndpointTypeLabel] = EndpointTypePod
+			}
+		}
 		meta := &fwkdl.EndpointMetadata{
 			NamespacedName: types.NamespacedName{Name: e.Name, Namespace: ns},
-			PodName:        e.Name,
+			PodName:        podName,
 			Address:        e.Address,
 			Port:           e.Port,
-			MetricsHost:    net.JoinHostPort(e.Address, e.Port),
-			Labels:         e.Labels,
+			MetricsHost:    net.JoinHostPort(e.Address, mPort),
+			Labels:         labels,
 		}
 		incoming[meta.NamespacedName] = struct{}{}
 		notifier.Upsert(meta)