Fix LauncherConfig CRD to accept metadata in podTemplate

api/fma/v1alpha1/launcherconfig_types.go

@@ -21,11 +21,34 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 )
 
+// EmbeddedObjectMeta holds the subset of metav1.ObjectMeta fields that
+// we want in the CRD schema, so that strict decoding accepts them.
+type EmbeddedObjectMeta struct {
+	// Labels for organizing and categorizing objects.
+	// +optional
+	Labels map[string]string `json:"labels,omitempty"`
+
+	// Annotations for storing arbitrary non-identifying metadata.
+	// +optional
+	Annotations map[string]string `json:"annotations,omitempty"`
+}
+
+// EmbeddedPodTemplateSpec is a PodTemplateSpec whose metadata fields
+// are explicitly declared so that the CRD schema admits them.
+type EmbeddedPodTemplateSpec struct {
+	// +optional
+	Metadata EmbeddedObjectMeta `json:"metadata,omitempty"`
+
+	// Spec defines the behavior of pods created from this template.
+	// +optional
+	Spec corev1.PodSpec `json:"spec,omitempty"`
+}
+
 // LauncherConfigSpec defines the configuration to manage the nominal server-providing pod definition.
 type LauncherConfigSpec struct {
 	// PodTemplate defines the pod specification for the server-providing pod.
 	// +optional
-	PodTemplate corev1.PodTemplateSpec `json:"podTemplate,omitempty"`
+	PodTemplate EmbeddedPodTemplateSpec `json:"podTemplate,omitempty"`
 
 	// MaxSleepingInstances is the maximum number of sleeping inference engine instances allowed per launcher pod.
 	// +kubebuilder:validation:Required

config/crd/fma.llm-d.ai_launcherconfigs.yaml

@@ -54,13 +54,24 @@ spec:
                 properties:
                   metadata:
                     description: |-
-                      Standard object's metadata.
-                      More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#metadata
+                      EmbeddedObjectMeta holds the subset of metav1.ObjectMeta fields that
+                      we want in the CRD schema, so that strict decoding accepts them.
+                    properties:
+                      annotations:
+                        additionalProperties:
+                          type: string
+                        description: Annotations for storing arbitrary non-identifying
+                          metadata.
+                        type: object
+                      labels:
+                        additionalProperties:
+                          type: string
+                        description: Labels for organizing and categorizing objects.
+                        type: object
                     type: object
                   spec:
-                    description: |-
-                      Specification of the desired behavior of the pod.
-                      More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#spec-and-status
+                    description: Spec defines the behavior of pods created from this
+                      template.
                     properties:
                       activeDeadlineSeconds:
                         description: |-

docs/cluster-sharing.md

@@ -29,10 +29,13 @@ object.
 
 (One design goal is to minimize chores for administrators of shared clusters.)
 
-- As development progresses, we never change the definitions in an
-  existing version of the `fma.llm-d.ai` API group; we only add new
+- As development progresses, we almost never change the definitions in
+  an existing version of the `fma.llm-d.ai` API group; we only add new
   versions. Old versions may be deleted only once we are sure there is
   no further dev/test activity using them.
+  We can make a change in an existing definition if the change does not
+  affect any current usage (e.g., add a field, change an optional thing
+  that does not appear in any existing YAML).
 
 - During development of a PR that adds a version of the API group,
   successive revisions of the PR's head branch can change the

pkg/controller/utils/pod-helper.go

@@ -22,13 +22,16 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"maps"
 	"regexp"
 	"slices"
 
 	corev1 "k8s.io/api/core/v1"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/api/resource"
 	"k8s.io/apimachinery/pkg/util/intstr"
 
+	v1alpha1 "github.com/llm-d-incubation/llm-d-fast-model-actuation/api/fma/v1alpha1"
 	"github.com/llm-d-incubation/llm-d-fast-model-actuation/pkg/api"
 	"github.com/llm-d-incubation/llm-d-fast-model-actuation/pkg/controller/common"
 )
@@ -141,10 +144,13 @@ func IsPodReady(pod *corev1.Pod) bool {
 
 // BuildLauncherPodFromTemplate creates a launcher pod from a LauncherConfig object's
 // Spec.PodTemplate and assigns the built launcher pod to a node
-func BuildLauncherPodFromTemplate(template corev1.PodTemplateSpec, ns, nodeName, launcherConfigName string) (*corev1.Pod, error) {
+func BuildLauncherPodFromTemplate(template v1alpha1.EmbeddedPodTemplateSpec, ns, nodeName, launcherConfigName string) (*corev1.Pod, error) {
 	pod := &corev1.Pod{
-		ObjectMeta: template.ObjectMeta,
-		Spec:       *DeIndividualize(template.Spec.DeepCopy()),
+		ObjectMeta: metav1.ObjectMeta{
+			Labels:      maps.Clone(template.Metadata.Labels),
+			Annotations: maps.Clone(template.Metadata.Annotations),
+		},
+		Spec: *DeIndividualize(template.Spec.DeepCopy()),
 	}
 	pod.Namespace = ns
 	pod.GenerateName = "launcher-"

test/e2e/deploy_fma.sh

@@ -89,8 +89,15 @@ CRD_NAMES=""
 for crd_file in config/crd/*.yaml; do
     crd_name=$(kubectl apply --dry-run=client -f "$crd_file" -o jsonpath='{.metadata.name}')
     CRD_NAMES="$CRD_NAMES $crd_name"
-    if kubectl get crd "$crd_name" &>/dev/null; then
-        echo "  CRD $crd_name already exists, skipping"
+    live_spec=$(kubectl get crd "$crd_name" -o jsonpath='{.spec}' 2>/dev/null) || live_spec=""
+    if [ -n "$live_spec" ]; then
+        desired_spec=$(kubectl apply --dry-run=client -f "$crd_file" -o jsonpath='{.spec}')
+        if [ "$live_spec" = "$desired_spec" ]; then
+            echo "  CRD $crd_name already exists with matching spec, skipping"
+        else
+            echo "  CRD $crd_name exists but spec differs, updating"
+            kubectl apply --server-side -f "$crd_file"
+        fi
     else
         echo "  Applying $crd_file ($crd_name)"
         kubectl apply --server-side -f "$crd_file"
@@ -178,7 +185,7 @@ helm upgrade --install "$FMA_CHART_INSTANCE_NAME" charts/fma-controllers \
 
 step "Wait for controllers to be ready"
 
-kubectl wait --for=condition=available --timeout=120s \
+kubectl wait --for=condition=available --timeout=180s \
     deployment "${FMA_CHART_INSTANCE_NAME}-dual-pods-controller" -n "$FMA_NAMESPACE"
 kubectl wait --for=condition=available --timeout=120s \
     deployment "${FMA_CHART_INSTANCE_NAME}-launcher-populator" -n "$FMA_NAMESPACE"