bump NFD to v0.17.0

Signed-off-by: Tariq Ibrahim <[email protected]>
NVIDIA · Dec 24, 2024 · a2b3c24 · a2b3c24
1 parent 68c099f
commit a2b3c24
Show file tree

Hide file tree

Showing 16 changed files with 203 additions and 284 deletions.
diff --git a/deployments/gpu-operator/Chart.lock b/deployments/gpu-operator/Chart.lock
@@ -1,6 +1,6 @@
 dependencies:
 - name: node-feature-discovery
   repository: https://kubernetes-sigs.github.io/node-feature-discovery/charts
-  version: 0.16.6
-digest: sha256:e7b02cbdf9daff49892c0b74c50da2ed11e18eff2105a1b1abc9a8f2ebd8be47
-generated: "2024-10-31T07:12:50.141904-07:00"
+  version: 0.17.0
+digest: sha256:21baa50c4947a80eb075f1db42f9521672dbbcbbea309b0f2d6d9c05fbdd8a65
+generated: "2024-12-24T11:04:04.635377-08:00"
diff --git a/deployments/gpu-operator/Chart.yaml b/deployments/gpu-operator/Chart.yaml
@@ -19,6 +19,6 @@ keywords:
 
 dependencies:
   - name: node-feature-discovery
-    version: v0.16.6
+    version: v0.17.0
     repository: https://kubernetes-sigs.github.io/node-feature-discovery/charts
     condition: nfd.enabled
diff --git a/deployments/gpu-operator/charts/node-feature-discovery/Chart.yaml b/deployments/gpu-operator/charts/node-feature-discovery/Chart.yaml
@@ -1,5 +1,5 @@
 apiVersion: v2
-appVersion: v0.16.6
+appVersion: v0.17.0
 description: 'Detects hardware features available on each node in a Kubernetes cluster,
   and advertises those features using node labels. '
 home: https://github.com/kubernetes-sigs/node-feature-discovery
@@ -11,4 +11,4 @@ name: node-feature-discovery
 sources:
 - https://github.com/kubernetes-sigs/node-feature-discovery
 type: application
-version: 0.16.6
+version: 0.17.0
diff --git a/deployments/gpu-operator/charts/node-feature-discovery/README.md b/deployments/gpu-operator/charts/node-feature-discovery/README.md
@@ -6,5 +6,5 @@ labels. NFD provides flexible configuration and extension points for a wide
 range of vendor and application specific node labeling needs.
 
 See
-[NFD documentation](https://kubernetes-sigs.github.io/node-feature-discovery/v0.16/deployment/helm.html)
+[NFD documentation](https://kubernetes-sigs.github.io/node-feature-discovery/v0.17/deployment/helm.html)
 for deployment instructions.
diff --git a/deployments/gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml b/deployments/gpu-operator/charts/node-feature-discovery/crds/nfd-api-crds.yaml
@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.14.0
+    controller-gen.kubebuilder.io/version: v0.16.3
   name: nodefeatures.nfd.k8s-sigs.io
 spec:
   group: nfd.k8s-sigs.io
@@ -69,8 +69,9 @@ spec:
                       properties:
                         elements:
                           additionalProperties:
-                            description: Nil is a dummy empty struct for protobuf
-                              compatibility
+                            description: |-
+                              Nil is a dummy empty struct for protobuf compatibility.
+                              NOTE: protobuf definitions have been removed but this is kept for API compatibility.
                             type: object
                           description: Individual features of the feature set.
                           type: object
@@ -124,7 +125,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.14.0
+    controller-gen.kubebuilder.io/version: v0.16.3
   name: nodefeaturegroups.nfd.k8s-sigs.io
 spec:
   group: nfd.k8s-sigs.io
@@ -395,7 +396,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.14.0
+    controller-gen.kubebuilder.io/version: v0.16.3
   name: nodefeaturerules.nfd.k8s-sigs.io
 spec:
   group: nfd.k8s-sigs.io

diff --git a/deployments/gpu-operator/charts/node-feature-discovery/templates/cert-manager-certs.yaml b/deployments/gpu-operator/charts/node-feature-discovery/templates/cert-manager-certs.yaml
diff --git a/deployments/gpu-operator/charts/node-feature-discovery/templates/cert-manager-issuer.yaml b/deployments/gpu-operator/charts/node-feature-discovery/templates/cert-manager-issuer.yaml
diff --git a/deployments/gpu-operator/charts/node-feature-discovery/templates/clusterrole.yaml b/deployments/gpu-operator/charts/node-feature-discovery/templates/clusterrole.yaml
@@ -6,6 +6,13 @@ metadata:
   labels:
     {{- include "node-feature-discovery.labels" . | nindent 4 }}
 rules:
+- apiGroups:
+  - ""
+  resources:
+  - namespaces
+  verbs:
+  - watch
+  - list
 - apiGroups:
   - ""
   resources:
@@ -94,7 +101,7 @@ rules:
   - update
 {{- end }}
 
-{{- if and .Values.gc.enable .Values.gc.rbac.create (or (and .Values.featureGates.NodeFeatureAPI .Values.enableNodeFeatureApi) .Values.topologyUpdater.enable) }}
+{{- if and .Values.gc.enable .Values.gc.rbac.create }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRole

diff --git a/deployments/gpu-operator/charts/node-feature-discovery/templates/clusterrolebinding.yaml b/deployments/gpu-operator/charts/node-feature-discovery/templates/clusterrolebinding.yaml
@@ -33,7 +33,7 @@ subjects:
   namespace: {{ include "node-feature-discovery.namespace" .  }}
 {{- end }}
 
-{{- if and .Values.gc.enable .Values.gc.rbac.create (or (and .Values.featureGates.NodeFeatureAPI .Values.enableNodeFeatureApi) .Values.topologyUpdater.enable) }}
+{{- if and .Values.gc.enable .Values.gc.rbac.create }}
 ---
 apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding

diff --git a/deployments/gpu-operator/charts/node-feature-discovery/templates/master.yaml b/deployments/gpu-operator/charts/node-feature-discovery/templates/master.yaml
@@ -23,10 +23,11 @@ spec:
       labels:
         {{- include "node-feature-discovery.selectorLabels" . | nindent 8 }}
         role: master
-      {{- with .Values.master.annotations }}
       annotations:
+        checksum/config: {{ include (print $.Template.BasePath "/nfd-master-conf.yaml") . | sha256sum }}
+        {{- with .Values.master.annotations }}
         {{- toYaml . | nindent 8 }}
-      {{- end }}
+        {{- end }}
     spec:
     {{- with .Values.priorityClassName }}
       priorityClassName: {{ . }}
@@ -46,16 +47,58 @@ spec:
             {{- toYaml .Values.master.securityContext | nindent 12 }}
           image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
+          startupProbe:
+            grpc:
+              port: {{ .Values.master.healthPort | default "8082" }}
+          {{- with .Values.master.startupProbe.initialDelaySeconds }}
+            initialDelaySeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.startupProbe.failureThreshold }}
+            failureThreshold: {{ . }}
+          {{- end }}
+          {{- with .Values.master.startupProbe.periodSeconds }}
+            periodSeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.startupProbe.timeoutSeconds }}
+            timeoutSeconds: {{ . }}
+          {{- end }}
           livenessProbe:
-            {{- toYaml .Values.master.livenessProbe | nindent 12 }}
+            grpc:
+              port: {{ .Values.master.healthPort | default "8082" }}
+          {{- with .Values.master.livenessProbe.initialDelaySeconds }}
+            initialDelaySeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.livenessProbe.failureThreshold }}
+            failureThreshold: {{ . }}
+          {{- end }}
+          {{- with .Values.master.livenessProbe.periodSeconds }}
+            periodSeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.livenessProbe.timeoutSeconds }}
+            timeoutSeconds: {{ . }}
+          {{- end }}
           readinessProbe:
-            {{- toYaml .Values.master.readinessProbe | nindent 12 }}
+            grpc:
+              port: {{ .Values.master.healthPort | default "8082" }}
+          {{- with .Values.master.readinessProbe.initialDelaySeconds }}
+            initialDelaySeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.readinessProbe.failureThreshold }}
+            failureThreshold: {{ . }}
+          {{- end }}
+          {{- with .Values.master.readinessProbe.periodSeconds }}
+            periodSeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.readinessProbe.timeoutSeconds }}
+            timeoutSeconds: {{ . }}
+          {{- end }}
+          {{- with .Values.master.readinessProbe.successThreshold }}
+            successThreshold: {{ . }}
+          {{- end }}
           ports:
-          - containerPort: {{ .Values.master.port | default "8080" }}
-            name: grpc
           - containerPort: {{ .Values.master.metricsPort | default "8081" }}
             name: metrics
-          - containerPort: {{ .Values.master.healthPort  | default "8082" }}
+          - containerPort: {{ .Values.master.healthPort | default "8082" }}
             name: health
           env:
           - name: NODE_NAME
@@ -73,29 +116,16 @@ spec:
             {{- if .Values.master.instance | empty | not }}
             - "-instance={{ .Values.master.instance }}"
             {{- end }}
-            {{- if not (and .Values.featureGates.NodeFeatureAPI .Values.enableNodeFeatureApi) }}
-            - "-port={{ .Values.master.port | default "8080" }}"
-            {{- else if gt (int .Values.master.replicaCount) 1 }}
             - "-enable-leader-election"
-            {{- end }}
             {{- if .Values.master.extraLabelNs | empty | not }}
             - "-extra-label-ns={{- join "," .Values.master.extraLabelNs }}"
             {{- end }}
             {{- if .Values.master.denyLabelNs | empty | not }}
             - "-deny-label-ns={{- join "," .Values.master.denyLabelNs }}"
             {{- end }}
-            {{- if .Values.master.resourceLabels | empty | not }}
-            - "-resource-labels={{- join "," .Values.master.resourceLabels }}"
-            {{- end }}
             {{- if .Values.master.enableTaints }}
             - "-enable-taints"
             {{- end }}
-            {{- if .Values.master.crdController | kindIs "invalid" | not }}
-            - "-crd-controller={{ .Values.master.crdController }}"
-            {{- else }}
-            ## By default, disable crd controller for other than the default instances
-            - "-crd-controller={{ .Values.master.instance | empty }}"
-            {{- end }}
             {{- if .Values.master.featureRulesController | kindIs "invalid" | not }}
             - "-featurerules-controller={{ .Values.master.featureRulesController }}"
             {{- end }}
@@ -105,32 +135,20 @@ spec:
             {{- if .Values.master.nfdApiParallelism | empty | not }}
             - "-nfd-api-parallelism={{ .Values.master.nfdApiParallelism }}"
             {{- end }}
-            {{- if .Values.tls.enable }}
-            - "-ca-file=/etc/kubernetes/node-feature-discovery/certs/ca.crt"
-            - "-key-file=/etc/kubernetes/node-feature-discovery/certs/tls.key"
-            - "-cert-file=/etc/kubernetes/node-feature-discovery/certs/tls.crt"
-            {{- end }}
             # Go over featureGates and add the feature-gate flag
             {{- range $key, $value := .Values.featureGates }}
             - "-feature-gates={{ $key }}={{ $value }}"
             {{- end }}
             - "-metrics={{ .Values.master.metricsPort  | default "8081" }}"
-            - "-grpc-health={{ .Values.master.healthPort  | default "8082" }}"
-          volumeMounts:
-            {{- if .Values.tls.enable }}
-            - name: nfd-master-cert
-              mountPath: "/etc/kubernetes/node-feature-discovery/certs"
-              readOnly: true
+            - "-grpc-health={{ .Values.master.healthPort | default "8082" }}"
+            {{- with .Values.master.extraArgs }}
+            {{- toYaml . | nindent 12 }}
             {{- end }}
+          volumeMounts:
             - name: nfd-master-conf
               mountPath: "/etc/kubernetes/node-feature-discovery"
               readOnly: true
       volumes:
-        {{- if .Values.tls.enable }}
-        - name: nfd-master-cert
-          secret:
-            secretName: nfd-master-cert
-        {{- end }}
         - name: nfd-master-conf
           configMap:
             name: {{ include "node-feature-discovery.fullname" . }}-master-conf

diff --git a/deployments/gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml b/deployments/gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml
@@ -1,4 +1,4 @@
-{{- if and .Values.gc.enable (or (and .Values.featureGates.NodeFeatureAPI .Values.enableNodeFeatureApi) .Values.topologyUpdater.enable) -}}
+{{- if and .Values.gc.enable -}}
 apiVersion: apps/v1
 kind: Deployment
 metadata:
@@ -58,6 +58,9 @@ spec:
           {{- if .Values.gc.interval | empty | not }}
           - "-gc-interval={{ .Values.gc.interval }}"
           {{- end }}
+          {{- with .Values.gc.extraArgs }}
+          {{- toYaml . | nindent 10 }}
+          {{- end }}
         resources:
       {{- toYaml .Values.gc.resources | nindent 12 }}
         securityContext: