Merge pull request #1025 from NVIDIA/bump-nfd

Author: tariq1890

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: 0.16.3
-digest: sha256:afe2940cc8d0ec73ce509611270757da30cb81db960370c3d7ab8eda8b8a2829
-generated: "2024-07-17T15:23:43.364317-07:00"
+  version: 0.16.4
+digest: sha256:527fff3327048f6c749df93d105eddf3011ff1be4090e13c6455aedf472d259d
+generated: "2024-10-04T13:43:35.810538-07:00"

deployments/gpu-operator/Chart.yaml

@@ -19,6 +19,6 @@ keywords:
 
 dependencies:
   - name: node-feature-discovery
-    version: v0.16.3
+    version: v0.16.4
     repository: https://kubernetes-sigs.github.io/node-feature-discovery/charts
     condition: nfd.enabled

deployments/gpu-operator/charts/node-feature-discovery/Chart.yaml

@@ -1,5 +1,5 @@
 apiVersion: v2
-appVersion: v0.16.3
+appVersion: v0.16.4
 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: 0.16.3
+version: 0.16.4

deployments/gpu-operator/charts/node-feature-discovery/templates/master.yaml

@@ -46,16 +46,9 @@ spec:
           image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
           livenessProbe:
-            grpc:
-              port: 8082
-            initialDelaySeconds: 10
-            periodSeconds: 10
+            {{- toYaml .Values.master.livenessProbe | nindent 12 }}
           readinessProbe:
-            grpc:
-              port: 8082
-            initialDelaySeconds: 5
-            periodSeconds: 10
-            failureThreshold: 10
+            {{- toYaml .Values.master.readinessProbe | nindent 12 }}
           ports:
           - containerPort: {{ .Values.master.port | default "8080" }}
             name: grpc

deployments/gpu-operator/charts/node-feature-discovery/templates/topologyupdater.yaml

@@ -12,6 +12,7 @@ metadata:
     {{- toYaml . | nindent 4 }}
   {{- end }}
 spec:
+  revisionHistoryLimit: {{ .Values.topologyUpdater.revisionHistoryLimit }}
   selector:
     matchLabels:
       {{- include "node-feature-discovery.selectorLabels" . | nindent 6 }}
@@ -42,16 +43,9 @@ spec:
         image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
         imagePullPolicy: "{{ .Values.image.pullPolicy }}"
         livenessProbe:
-          grpc:
-            port: 8082
-          initialDelaySeconds: 10
-          periodSeconds: 10
+          {{- toYaml .Values.topologyUpdater.livenessProbe | nindent 10 }}
         readinessProbe:
-          grpc:
-            port: 8082
-          initialDelaySeconds: 5
-          periodSeconds: 10
-          failureThreshold: 10
+          {{- toYaml .Values.topologyUpdater.readinessProbe | nindent 10 }}
         env:
         - name: NODE_NAME
           valueFrom:

deployments/gpu-operator/charts/node-feature-discovery/templates/worker.yaml

@@ -12,6 +12,7 @@ metadata:
     {{- toYaml . | nindent 4 }}
   {{- end }}
 spec:
+  revisionHistoryLimit: {{ .Values.worker.revisionHistoryLimit }}
   selector:
     matchLabels:
       {{- include "node-feature-discovery.selectorLabels" . | nindent 6 }}
@@ -44,16 +45,9 @@ spec:
         image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
         imagePullPolicy: {{ .Values.image.pullPolicy }}
         livenessProbe:
-          grpc:
-            port: 8082
-          initialDelaySeconds: 10
-          periodSeconds: 10
+          {{- toYaml .Values.worker.livenessProbe | nindent 12 }}
         readinessProbe:
-          grpc:
-            port: 8082
-          initialDelaySeconds: 5
-          periodSeconds: 10
-          failureThreshold: 10
+          {{- toYaml .Values.worker.readinessProbe | nindent 12 }}
         env:
         - name: NODE_NAME
           valueFrom:

deployments/gpu-operator/charts/node-feature-discovery/values.yaml

@@ -141,6 +141,19 @@ master:
               - key: "node-role.kubernetes.io/control-plane"
                 operator: In
                 values: [""]
+                
+  livenessProbe:
+    grpc:
+      port: 8082
+    initialDelaySeconds: 10
+    # failureThreshold: 3
+    # periodSeconds: 10
+  readinessProbe:
+    grpc:
+      port: 8082
+    initialDelaySeconds: 5
+    failureThreshold: 10
+    # periodSeconds: 10
 
 worker:
   enable: true
@@ -401,19 +414,18 @@ worker:
     runAsNonRoot: true
     # runAsUser: 1000
 
-  # livenessProbe: {}
-    ## NOTE: Currently not configurable, defaults are provided for the sake of extra documentation.
-    # grpc:
-    #   port: 8082
-    # initialDelaySeconds: 10
+  livenessProbe:
+    grpc:
+      port: 8082
+    initialDelaySeconds: 10
+    # failureThreshold: 3
     # periodSeconds: 10
-  # readinessProbe: {}
-    ## NOTE: Currently not configurable, defaults are provided for the sake of extra documentation.
-    # grpc:
-    #   port: 8082
-    # initialDelaySeconds: 5
+  readinessProbe:
+    grpc:
+      port: 8082
+    initialDelaySeconds: 5
+    failureThreshold: 10
     # periodSeconds: 10
-    # failureThreshold: 10
 
   serviceAccount:
     # Specifies whether a service account should be created.
@@ -425,6 +437,9 @@ worker:
     # If not set and create is true, a name is generated using the fullname template
     name:
 
+  # specify how many old ControllerRevisions for the DaemonSet to retain.
+  revisionHistoryLimit:
+
   rbac:
     create: true
 
@@ -467,6 +482,10 @@ topologyUpdater:
     create: true
     annotations: {}
     name:
+
+  # specify how many old ControllerRevisions for the DaemonSet to retain.
+  revisionHistoryLimit:
+
   rbac:
     create: true
 
@@ -484,20 +503,19 @@ topologyUpdater:
       drop: [ "ALL" ]
     readOnlyRootFilesystem: true
     runAsUser: 0
-
-  # livenessProbe: {}
-    ## NOTE: Currently not configurable, defaults are provided for the sake of extra documentation.
-    # grpc:
-    #   port: 8082
-    # initialDelaySeconds: 10
+  
+  livenessProbe:
+    grpc:
+      port: 8082
+    initialDelaySeconds: 10
+    # failureThreshold: 3
     # periodSeconds: 10
-  # readinessProbe: {}
-    ## NOTE: Currently not configurable, defaults are provided for the sake of extra documentation.
-    # grpc:
-    #   port: 8082
-    # initialDelaySeconds: 5
+  readinessProbe:
+    grpc:
+      port: 8082
+    initialDelaySeconds: 5
+    failureThreshold: 10
     # periodSeconds: 10
-    # failureThreshold: 10
 
   resources:
     limits: