Fix helm charts - problems identified by linter

Signed-off-by: Davanum Srinivas <[email protected]>

Author: dims

distros/kubernetes/nvsentinel/charts/csp-health-monitor/templates/deployment.yaml

@@ -24,14 +24,14 @@ spec:
       {{- include "csp-health-monitor.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with (.Values.global.podAnnotations | default .Values.podAnnotations) }}
+      {{- with ((.Values.global).podAnnotations | default .Values.podAnnotations) }}
       annotations:
         {{- toYaml . | nindent 8 }}
       {{- end }}
       labels:
         {{- include "csp-health-monitor.selectorLabels" . | nindent 8 }}
     spec:
-      {{- with .Values.global.imagePullSecrets }}
+      {{- with ((.Values.global).imagePullSecrets | default .Values.imagePullSecrets) }}
       imagePullSecrets:
         {{- toYaml . | nindent 8 }}
       {{- end }}
@@ -53,19 +53,19 @@ spec:
           type: DirectoryOrCreate
       containers:
         - name: {{ .Chart.Name }}
-          image: "{{ .Values.global.cspHealthMonitor.image.repository }}:{{ .Values.global.image.tag | default .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.global.cspHealthMonitor.image.pullPolicy }}
+          image: "{{ ((.Values.global).cspHealthMonitor).image.repository | default "ghcr.io/nvidia/nvsentinel-csp-health-monitor" }}:{{ ((.Values.global).image).tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ ((.Values.global).cspHealthMonitor).image.pullPolicy | default "IfNotPresent" }}
           command: ["/app/csp-health-monitor"]
           args:
           - "--config=/etc/config/config.toml"
-          - "--metrics-port={{ .Values.global.metricsPort }}"
+          - "--metrics-port={{ ((.Values.global).metricsPort) | default 2112 }}"
           - "--mongo-client-cert-mount-path={{ .Values.clientCertMountPath }}"
           - "-v={{ .Values.logLevel }}"
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
           ports:
             - name: metrics
-              containerPort: {{ .Values.global.metricsPort }}
+              containerPort: {{ ((.Values.global).metricsPort) | default 2112 }}
               protocol: TCP
           volumeMounts:
           - name: config-volume
@@ -79,8 +79,8 @@ spec:
                 optional: true
 
         - name: maintenance-notifier
-          image: "{{ .Values.global.cspHealthMonitor.image.repository }}:{{ .Values.global.image.tag | default .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.global.cspHealthMonitor.image.pullPolicy }}
+          image: "{{ ((.Values.global).cspHealthMonitor).image.repository | default "ghcr.io/nvidia/nvsentinel-csp-health-monitor" }}:{{ ((.Values.global).image).tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ ((.Values.global).cspHealthMonitor).image.pullPolicy | default "IfNotPresent" }}
           securityContext:
             runAsUser: 0
           command: ["/app/maintenance-notifier"]
@@ -109,15 +109,15 @@ spec:
                 name: mongodb-config
                 optional: true
       restartPolicy: Always
-      {{- with (.Values.global.systemNodeSelector | default .Values.nodeSelector) }}
+      {{- with (((.Values.global).systemNodeSelector) | default .Values.nodeSelector) }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.global.affinity | default .Values.affinity) }}
+      {{- with (((.Values.global).affinity) | default .Values.affinity) }}
       affinity:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.global.systemNodeTolerations | default .Values.tolerations) }}
+      {{- with (((.Values.global).systemNodeTolerations) | default .Values.tolerations) }}
       tolerations:
         {{- toYaml . | nindent 8 }}
       {{- end }}

distros/kubernetes/nvsentinel/charts/csp-health-monitor/values.yaml

@@ -46,6 +46,17 @@ serviceAccount:
   annotations: {}
   name: ""
 
+# Scheduling configuration
+nodeSelector: {}
+affinity: {}
+tolerations: []
+
+# Optional image pull secrets (fallback if global not available)
+imagePullSecrets: []
+
+# Optional pod annotations (fallback if global not available)
+podAnnotations: {}
+
 # Klog verbosity level for the main CSP health monitor container (e.g., 1=Info, 2=Debug, etc.)
 logLevel: 1
 

distros/kubernetes/nvsentinel/charts/fault-quarantine/templates/deployment.yaml

@@ -24,35 +24,35 @@ spec:
       {{- include "fault-quarantine-module.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with (.Values.global.podAnnotations | default .Values.podAnnotations) }}
+      {{- with ((.Values.global).podAnnotations | default .Values.podAnnotations) }}
       annotations:
         {{- toYaml . | nindent 8 }}
       {{- end }}
       labels:
         {{- include "fault-quarantine-module.selectorLabels" . | nindent 8 }}
     spec:
-      {{- with .Values.global.imagePullSecrets }}
+      {{- with ((.Values.global).imagePullSecrets | default .Values.imagePullSecrets) }}
       imagePullSecrets:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      serviceAccountName: {{ include "nvsentinel.serviceAccountName" . }}
+      serviceAccountName: {{ include "fault-quarantine-module.serviceAccountName" . }}
       containers:
         - name: fault-quarantine
-          image: "{{ .Values.global.faultQuarantineModule.image.repository }}:{{ .Values.global.image.tag | default .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.global.faultQuarantineModule.image.pullPolicy }}
+          image: "{{ ((.Values.global).faultQuarantineModule).image.repository | default "ghcr.io/nvidia/nvsentinel-fault-quarantine-module" }}:{{ ((.Values.global).image).tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ ((.Values.global).faultQuarantineModule).image.pullPolicy | default "IfNotPresent" }}
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
           args:
-          - "--metrics-port={{ .Values.global.metricsPort }}"
+          - "--metrics-port={{ ((.Values.global).metricsPort) | default 2112 }}"
           - "--mongo-client-cert-mount-path={{ .Values.clientCertMountPath }}"
-          - "--dry-run={{ .Values.global.dryRun }}"
+          - "--dry-run={{ ((.Values.global).dryRun) | default false }}"
           - "--circuit-breaker-percentage={{ .Values.circuitBreaker.percentage }}"
           - "--circuit-breaker-duration={{ .Values.circuitBreaker.duration }}"
           - "--circuit-breaker-enabled={{ .Values.circuitBreaker.enabled }}"
           - "-v={{ .Values.logLevel }}"
           ports:
             - name: metrics
-              containerPort: {{ .Values.global.metricsPort }}
+              containerPort: {{ ((.Values.global).metricsPort) | default 2112 }}
           volumeMounts:
           - name: config-volume
             mountPath: /etc/config/config.toml
@@ -81,15 +81,15 @@ spec:
           secretName: mongo-app-client-cert-secret
           optional: true
       restartPolicy: Always
-      {{- with (.Values.global.systemNodeSelector | default .Values.nodeSelector) }}
+      {{- with (((.Values.global).systemNodeSelector) | default .Values.nodeSelector) }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.global.affinity | default .Values.affinity) }}
+      {{- with (((.Values.global).affinity) | default .Values.affinity) }}
       affinity:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.global.systemNodeTolerations | default .Values.tolerations) }}
+      {{- with (((.Values.global).systemNodeTolerations) | default .Values.tolerations) }}
       tolerations:
         {{- toYaml . | nindent 8 }}
       {{- end }}

distros/kubernetes/nvsentinel/charts/fault-quarantine/values.yaml

@@ -32,6 +32,17 @@ serviceAccount:
   annotations: {}
   name: ""
 
+# Scheduling configuration
+nodeSelector: {}
+affinity: {}
+tolerations: []
+
+# Optional image pull secrets (fallback if global not available)
+imagePullSecrets: []
+
+# Optional pod annotations (fallback if global not available)
+podAnnotations: {}
+
 # Log level for the fault quarantine module (klog verbosity)
 logLevel: 1
 

distros/kubernetes/nvsentinel/charts/fault-remediation/templates/deployment.yaml

@@ -24,18 +24,18 @@ spec:
       {{- include "fault-remediation-module.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with (.Values.global.podAnnotations | default .Values.podAnnotations) }}
+      {{- with ((.Values.global).podAnnotations | default .Values.podAnnotations) }}
       annotations:
         {{- toYaml . | nindent 8 }}
       {{- end }}
       labels:
         {{- include "fault-remediation-module.selectorLabels" . | nindent 8 }}
     spec:
-      {{- with .Values.global.imagePullSecrets }}
+      {{- with ((.Values.global).imagePullSecrets | default .Values.imagePullSecrets) }}
       imagePullSecrets:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      serviceAccountName: {{ include "nvsentinel.serviceAccountName" . }}
+      serviceAccountName: {{ include "fault-remediation-module.serviceAccountName" . }}
       containers:
         - name: fault-remediation
           env:
@@ -46,16 +46,16 @@ spec:
           - name: MAINTENANCE_API_GROUP
             value: {{ .Values.maintenanceResource.apiGroup }}
 
-          image: "{{ .Values.global.faultRemediationModule.image.repository }}:{{ .Values.global.image.tag | default .Chart.AppVersion }}"
-          imagePullPolicy: {{ .Values.global.faultRemediationModule.image.pullPolicy | default "IfNotPresent" }}
+          image: "{{ ((.Values.global).faultRemediationModule).image.repository | default "ghcr.io/nvidia/nvsentinel-fault-remediation-module" }}:{{ ((.Values.global).image).tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ ((.Values.global).faultRemediationModule).image.pullPolicy | default "IfNotPresent" }}
           resources:
             {{- toYaml .Values.resources | nindent 12 }}
           args:
           - "--mongo-client-cert-mount-path={{ .Values.clientCertMountPath }}"
-          - "--dry-run={{ .Values.global.dryRun }}"
+          - "--dry-run={{ ((.Values.global).dryRun) | default false }}"
           ports:
             - name: metrics
-              containerPort: {{ .Values.global.metricsPort }}
+              containerPort: {{ ((.Values.global).metricsPort) | default 2112 }}
           volumeMounts:
           - name: mongo-app-client-cert
             mountPath: {{ .Values.clientCertMountPath }}
@@ -99,15 +99,15 @@ spec:
               path: {{ .Values.logCollector.manifestFileName }}
             {{- end }}
       restartPolicy: Always
-      {{- with (.Values.global.systemNodeSelector | default .Values.nodeSelector) }}
+      {{- with (((.Values.global).systemNodeSelector) | default .Values.nodeSelector) }}
       nodeSelector:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.global.affinity | default .Values.affinity) }}
+      {{- with (((.Values.global).affinity) | default .Values.affinity) }}
       affinity:
         {{- toYaml . | nindent 8 }}
       {{- end }}
-      {{- with (.Values.global.systemNodeTolerations | default .Values.tolerations) }}
+      {{- with (((.Values.global).systemNodeTolerations) | default .Values.tolerations) }}
       tolerations:
         {{- toYaml . | nindent 8 }}
       {{- end }}

distros/kubernetes/nvsentinel/charts/fault-remediation/values.yaml

@@ -37,6 +37,16 @@ serviceAccount:
   annotations: {}
   name: ""
 
+# Scheduling configuration
+nodeSelector: {}
+affinity: {}
+
+# Optional image pull secrets (fallback if global not available)
+imagePullSecrets: []
+
+# Optional pod annotations (fallback if global not available)
+podAnnotations: {}
+
 # Special tolerations for fault remediation - allow running on nodes with any taints for log collection
 tolerations:
   - operator: "Exists"

distros/kubernetes/nvsentinel/charts/gpu-health-monitor/templates/daemonset-dcgm-4.x.yaml

@@ -29,14 +29,14 @@ spec:
       {{- include "gpu-health-monitor.selectorLabels" . | nindent 6 }}
   template:
     metadata:
-      {{- with (.Values.global.podAnnotations | default .Values.podAnnotations) }}
+      {{- with ((.Values.global).podAnnotations | default .Values.podAnnotations) }}
       annotations:
         {{- toYaml . | nindent 8 }}
       {{- end }}
       labels:
         {{- include "gpu-health-monitor.selectorLabels" . | nindent 8 }}
     spec:
-      {{- with .Values.global.imagePullSecrets }}
+      {{- with ((.Values.global).imagePullSecrets | default .Values.imagePullSecrets) }}
       imagePullSecrets:
         {{- toYaml . | nindent 8 }}
       {{- end }}

distros/kubernetes/nvsentinel/charts/gpu-health-monitor/values.yaml

@@ -23,11 +23,23 @@ podSecurityContext: {}
 securityContext:
   runAsUser: 0
 
-resources: 
+resources:
   limits:
     cpu: 500m
     memory: 512Mi
   requests:
     cpu: 100m
     memory: 128Mi
+
+# Scheduling configuration
+nodeSelector: {}
+affinity: {}
+tolerations: []
+
+# Optional image pull secrets (fallback if global not available)
+imagePullSecrets: []
+
+# Optional pod annotations (fallback if global not available)
+podAnnotations: {}
+
 stateFilePath: "/var/run/statefile"