chart for nvidia-driver-runtime

hostPID set for daemonset to ensure vgpu mgr works correctly

bump nvidia-driver-runtime to use official image

charts/nvidia-driver-runtime/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

charts/nvidia-driver-runtime/Chart.yaml

@@ -0,0 +1,27 @@
+apiVersion: v2
+name: nvidia-driver-runtime
+description: A Helm chart for Kubernetes
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.16.0"
+
+maintainers:
+  - name: harvester

charts/nvidia-driver-runtime/templates/_helpers.tpl

@@ -0,0 +1,63 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "nvidia-driver-runtime.name" -}}
+{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Create a default fully qualified app name.
+We truncate at 63 chars because some Kubernetes name fields are limited to this (by the DNS naming spec).
+If release name contains chart name it will be used as a full name.
+*/}}
+{{- define "nvidia-driver-runtime.fullname" -}}
+{{- if .Values.fullnameOverride }}
+{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- $name := default .Chart.Name .Values.nameOverride }}
+{{- if contains $name .Release.Name }}
+{{- .Release.Name | trunc 63 | trimSuffix "-" }}
+{{- else }}
+{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
+{{- end }}
+{{- end }}
+{{- end }}
+
+{{/*
+Create chart name and version as used by the chart label.
+*/}}
+{{- define "nvidia-driver-runtime.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "nvidia-driver-runtime.labels" -}}
+helm.sh/chart: {{ include "nvidia-driver-runtime.chart" . }}
+{{ include "nvidia-driver-runtime.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "nvidia-driver-runtime.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "nvidia-driver-runtime.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+app: nvidia-driver-daemonset
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "nvidia-driver-runtime.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "nvidia-driver-runtime.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

charts/nvidia-driver-runtime/templates/daemonset.yaml

@@ -0,0 +1,68 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: {{ include "nvidia-driver-runtime.fullname" . }}
+  labels:
+    {{- include "nvidia-driver-runtime.labels" . | nindent 4 }}
+spec:
+  updateStrategy:
+    type: RollingUpdate
+  selector:
+    matchLabels:
+      {{- include "nvidia-driver-runtime.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "nvidia-driver-runtime.selectorLabels" . | nindent 8 }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "nvidia-driver-runtime.serviceAccountName" . }}
+      hostPID: true
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: nvidia-driver-ctr
+          env:
+          - name: "DRIVER_LOCATION"
+            value: "{{ .Values.driverLocation }}"
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          volumeMounts:
+            - name: var-log
+              mountPath: /var/log
+            - name: dev-log
+              mountPath: /dev/log
+            - name: host-os-release
+              mountPath: "/host-etc/os-release"
+              readOnly: true
+            - name: host-sys
+              mountPath: /sys
+          resources:
+            {{- toYaml .Values.resources | nindent 12 }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      volumes:
+        - name: var-log
+          hostPath:
+            path: /var/log
+        - name: dev-log
+          hostPath:
+            path: /dev/log
+        - name: host-os-release
+          hostPath:
+            path: "/etc/os-release"
+        - name: host-sys
+          hostPath:
+            path: /sys
+            type: Directory

charts/nvidia-driver-runtime/templates/serviceaccount.yaml

@@ -0,0 +1,12 @@
+{{- if .Values.serviceAccount.create -}}
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: {{ include "nvidia-driver-runtime.serviceAccountName" . }}
+  labels:
+    {{- include "nvidia-driver-runtime.labels" . | nindent 4 }}
+  {{- with .Values.serviceAccount.annotations }}
+  annotations:
+    {{- toYaml . | nindent 4 }}
+  {{- end }}
+{{- end }}

charts/nvidia-driver-runtime/values.yaml

@@ -0,0 +1,56 @@
+# Default values for nvidia-driver-runtime.
+# This is a YAML-formatted file.
+# Declare variables to be passed into your templates.
+
+image:
+  repository: rancher/harvester-nvidia-driver-toolkit
+  pullPolicy: Always
+  # Overrides the image tag whose default is the chart appVersion.
+  tag: sle-micro-head
+
+imagePullSecrets: []
+nameOverride: ""
+fullnameOverride: "nvidia-driver-daemonset"
+
+serviceAccount:
+  # Specifies whether a service account should be created
+  create: true
+  # Annotations to add to the service account
+  annotations: {}
+  # The name of the service account to use.
+  # If not set and create is true, a name is generated using the fullname template
+  name: ""
+
+podAnnotations: {}
+
+podSecurityContext:
+  {}
+  # fsGroup: 2000
+
+securityContext:
+  privileged: true
+  # capabilities:
+  #   drop:
+  #   - ALL
+  # readOnlyRootFilesystem: true
+  # runAsNonRoot: true
+  # runAsUser: 1000
+
+resources:
+  {}
+  # We usually recommend not to specify default resources and to leave this as a conscious
+  # choice for the user. This also increases chances charts run on environments with little
+  # resources, such as Minikube. If you do want to specify resources, uncomment the following
+  # lines, adjust them as necessary, and remove the curly braces after 'resources:'.
+  # limits:
+  #   cpu: 100m
+  #   memory: 128Mi
+  # requests:
+  #   cpu: 100m
+  #   memory: 128Mi
+
+nodeSelector:
+  sriovgpu.harvesterhci.io/driver-needed: "true"
+# http endpoint where nvidia kvm driver is hosted
+# this will be pulled and installed by the daemonset on runtime
+driverLocation: "HTTPENDPOINT/NVIDIA-Linux-x86_64-525.60.12-vgpu-kvm.run"