1513 lines
39 KiB
YAML
1513 lines
39 KiB
YAML
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: node-feature-discovery
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
---
|
|
# Source: gpu-operator/templates/serviceaccount.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: gpu-operator
|
|
namespace: gpu-operator
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/nfd-master-conf.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: release-name-node-feature-discovery-master-conf
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
data:
|
|
nfd-master.conf: |-
|
|
extraLabelNs:
|
|
- nvidia.com
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/nfd-worker-conf.yaml
|
|
apiVersion: v1
|
|
kind: ConfigMap
|
|
metadata:
|
|
name: release-name-node-feature-discovery-worker-conf
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
data:
|
|
nfd-worker.conf: |-
|
|
sources:
|
|
pci:
|
|
deviceClassWhitelist:
|
|
- "02"
|
|
- "0200"
|
|
- "0207"
|
|
- "0300"
|
|
- "0302"
|
|
deviceLabelFields:
|
|
- vendor
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/clusterrole.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: release-name-node-feature-discovery
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- nodes
|
|
- nodes/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
- list
|
|
- apiGroups:
|
|
- nfd.k8s-sigs.io
|
|
resources:
|
|
- nodefeatures
|
|
- nodefeaturerules
|
|
- nodefeaturegroups
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- nfd.k8s-sigs.io
|
|
resources:
|
|
- nodefeaturegroups/status
|
|
verbs:
|
|
- patch
|
|
- update
|
|
- apiGroups:
|
|
- coordination.k8s.io
|
|
resources:
|
|
- leases
|
|
verbs:
|
|
- create
|
|
- apiGroups:
|
|
- coordination.k8s.io
|
|
resources:
|
|
- leases
|
|
resourceNames:
|
|
- "nfd-master.nfd.kubernetes.io"
|
|
verbs:
|
|
- get
|
|
- update
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/clusterrole.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: release-name-node-feature-discovery-gc
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- nodes
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- nodes/proxy
|
|
verbs:
|
|
- get
|
|
- apiGroups:
|
|
- topology.node.k8s.io
|
|
resources:
|
|
- noderesourcetopologies
|
|
verbs:
|
|
- delete
|
|
- list
|
|
- apiGroups:
|
|
- nfd.k8s-sigs.io
|
|
resources:
|
|
- nodefeatures
|
|
verbs:
|
|
- delete
|
|
- list
|
|
---
|
|
# Source: gpu-operator/templates/clusterrole.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: gpu-operator
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
rules:
|
|
- apiGroups:
|
|
- config.openshift.io
|
|
resources:
|
|
- clusterversions
|
|
- proxies
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- image.openshift.io
|
|
resources:
|
|
- imagestreams
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- security.openshift.io
|
|
resources:
|
|
- securitycontextconstraints
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- use
|
|
- apiGroups:
|
|
- rbac.authorization.k8s.io
|
|
resources:
|
|
- clusterroles
|
|
- clusterrolebindings
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- nodes
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- namespaces
|
|
verbs:
|
|
- get
|
|
- list
|
|
- create
|
|
- watch
|
|
- update
|
|
- patch
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- events
|
|
- pods
|
|
- pods/eviction
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- apps
|
|
resources:
|
|
- daemonsets
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- nvidia.com
|
|
resources:
|
|
- clusterpolicies
|
|
- clusterpolicies/finalizers
|
|
- clusterpolicies/status
|
|
- nvidiadrivers
|
|
- nvidiadrivers/finalizers
|
|
- nvidiadrivers/status
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- deletecollection
|
|
- apiGroups:
|
|
- scheduling.k8s.io
|
|
resources:
|
|
- priorityclasses
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- create
|
|
- apiGroups:
|
|
- node.k8s.io
|
|
resources:
|
|
- runtimeclasses
|
|
verbs:
|
|
- get
|
|
- list
|
|
- create
|
|
- update
|
|
- watch
|
|
- delete
|
|
- apiGroups:
|
|
- apiextensions.k8s.io
|
|
resources:
|
|
- customresourcedefinitions
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- create
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/clusterrolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: release-name-node-feature-discovery
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: release-name-node-feature-discovery
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: node-feature-discovery
|
|
namespace: gpu-operator
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/clusterrolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: release-name-node-feature-discovery-gc
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: release-name-node-feature-discovery-gc
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: node-feature-discovery
|
|
namespace: gpu-operator
|
|
---
|
|
# Source: gpu-operator/templates/clusterrolebinding.yaml
|
|
kind: ClusterRoleBinding
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
metadata:
|
|
name: gpu-operator
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: gpu-operator
|
|
namespace: gpu-operator
|
|
- kind: ServiceAccount
|
|
name: node-feature-discovery
|
|
namespace: gpu-operator
|
|
roleRef:
|
|
kind: ClusterRole
|
|
name: gpu-operator
|
|
apiGroup: rbac.authorization.k8s.io
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/role.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: Role
|
|
metadata:
|
|
name: release-name-node-feature-discovery-worker
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
rules:
|
|
- apiGroups:
|
|
- nfd.k8s-sigs.io
|
|
resources:
|
|
- nodefeatures
|
|
verbs:
|
|
- create
|
|
- get
|
|
- update
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- pods
|
|
verbs:
|
|
- get
|
|
---
|
|
# Source: gpu-operator/templates/role.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: Role
|
|
metadata:
|
|
name: gpu-operator
|
|
namespace: gpu-operator
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
rules:
|
|
- apiGroups:
|
|
- rbac.authorization.k8s.io
|
|
resources:
|
|
- roles
|
|
- rolebindings
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- apps
|
|
resources:
|
|
- controllerrevisions
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- apps
|
|
resources:
|
|
- daemonsets
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps
|
|
- endpoints
|
|
- pods
|
|
- pods/eviction
|
|
- secrets
|
|
- services
|
|
- services/finalizers
|
|
- serviceaccounts
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- coordination.k8s.io
|
|
resources:
|
|
- leases
|
|
verbs:
|
|
- get
|
|
- list
|
|
- watch
|
|
- create
|
|
- update
|
|
- patch
|
|
- delete
|
|
- apiGroups:
|
|
- monitoring.coreos.com
|
|
resources:
|
|
- servicemonitors
|
|
- prometheusrules
|
|
verbs:
|
|
- get
|
|
- list
|
|
- create
|
|
- watch
|
|
- update
|
|
- delete
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/rolebinding.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: RoleBinding
|
|
metadata:
|
|
name: release-name-node-feature-discovery-worker
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: Role
|
|
name: release-name-node-feature-discovery-worker
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: node-feature-discovery
|
|
namespace: gpu-operator
|
|
---
|
|
# Source: gpu-operator/templates/rolebinding.yaml
|
|
kind: RoleBinding
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
metadata:
|
|
name: gpu-operator
|
|
namespace: gpu-operator
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: gpu-operator
|
|
namespace: gpu-operator
|
|
roleRef:
|
|
kind: Role
|
|
name: gpu-operator
|
|
apiGroup: rbac.authorization.k8s.io
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/worker.yaml
|
|
apiVersion: apps/v1
|
|
kind: DaemonSet
|
|
metadata:
|
|
name: release-name-node-feature-discovery-worker
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
role: worker
|
|
spec:
|
|
revisionHistoryLimit:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
role: worker
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
role: worker
|
|
spec:
|
|
dnsPolicy: ClusterFirstWithHostNet
|
|
priorityClassName: system-node-critical
|
|
serviceAccountName: node-feature-discovery
|
|
securityContext:
|
|
{}
|
|
hostNetwork: false
|
|
containers:
|
|
- name: worker
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
runAsNonRoot: true
|
|
image: "harbor.cone-chain.com/highway/nfd/node-feature-discovery:v0.16.6"
|
|
imagePullPolicy: IfNotPresent
|
|
livenessProbe:
|
|
grpc:
|
|
port: 8082
|
|
initialDelaySeconds: 10
|
|
readinessProbe:
|
|
failureThreshold: 10
|
|
grpc:
|
|
port: 8082
|
|
initialDelaySeconds: 5
|
|
env:
|
|
- name: NODE_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: spec.nodeName
|
|
- name: POD_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.name
|
|
- name: POD_UID
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.uid
|
|
resources:
|
|
limits:
|
|
memory: 512Mi
|
|
requests:
|
|
cpu: 5m
|
|
memory: 64Mi
|
|
command:
|
|
- "nfd-worker"
|
|
args:
|
|
# Go over featureGate and add the feature-gate flag
|
|
- "-feature-gates=NodeFeatureAPI=true"
|
|
- "-feature-gates=NodeFeatureGroupAPI=false"
|
|
- "-metrics=8081"
|
|
- "-grpc-health=8082"
|
|
ports:
|
|
- containerPort: 8081
|
|
name: metrics
|
|
- containerPort: 8082
|
|
name: health
|
|
volumeMounts:
|
|
- name: host-boot
|
|
mountPath: "/host-boot"
|
|
readOnly: true
|
|
- name: host-os-release
|
|
mountPath: "/host-etc/os-release"
|
|
readOnly: true
|
|
- name: host-sys
|
|
mountPath: "/host-sys"
|
|
readOnly: true
|
|
- name: host-usr-lib
|
|
mountPath: "/host-usr/lib"
|
|
readOnly: true
|
|
- name: host-lib
|
|
mountPath: "/host-lib"
|
|
readOnly: true
|
|
- name: host-proc-swaps
|
|
mountPath: "/host-proc/swaps"
|
|
readOnly: true
|
|
- name: source-d
|
|
mountPath: "/etc/kubernetes/node-feature-discovery/source.d/"
|
|
readOnly: true
|
|
- name: features-d
|
|
mountPath: "/etc/kubernetes/node-feature-discovery/features.d/"
|
|
readOnly: true
|
|
- name: nfd-worker-conf
|
|
mountPath: "/etc/kubernetes/node-feature-discovery"
|
|
readOnly: true
|
|
volumes:
|
|
- name: host-boot
|
|
hostPath:
|
|
path: "/boot"
|
|
- name: host-os-release
|
|
hostPath:
|
|
path: "/etc/os-release"
|
|
- name: host-sys
|
|
hostPath:
|
|
path: "/sys"
|
|
- name: host-usr-lib
|
|
hostPath:
|
|
path: "/usr/lib"
|
|
- name: host-lib
|
|
hostPath:
|
|
path: "/lib"
|
|
- name: host-proc-swaps
|
|
hostPath:
|
|
path: "/proc/swaps"
|
|
- name: source-d
|
|
hostPath:
|
|
path: "/etc/kubernetes/node-feature-discovery/source.d/"
|
|
- name: features-d
|
|
hostPath:
|
|
path: "/etc/kubernetes/node-feature-discovery/features.d/"
|
|
- name: nfd-worker-conf
|
|
configMap:
|
|
name: release-name-node-feature-discovery-worker-conf
|
|
items:
|
|
- key: nfd-worker.conf
|
|
path: nfd-worker.conf
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/master
|
|
operator: Equal
|
|
value: ""
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/control-plane
|
|
operator: Equal
|
|
value: ""
|
|
- effect: NoSchedule
|
|
key: nvidia.com/gpu
|
|
operator: Exists
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/master.yaml
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: release-name-node-feature-discovery-master
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
role: master
|
|
spec:
|
|
replicas: 1
|
|
revisionHistoryLimit:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
role: master
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
role: master
|
|
spec:
|
|
priorityClassName: system-node-critical
|
|
serviceAccountName: node-feature-discovery
|
|
enableServiceLinks: false
|
|
securityContext:
|
|
{}
|
|
hostNetwork: false
|
|
containers:
|
|
- name: master
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
runAsNonRoot: true
|
|
image: "harbor.cone-chain.com/highway/nfd/node-feature-discovery:v0.16.6"
|
|
imagePullPolicy: IfNotPresent
|
|
livenessProbe:
|
|
grpc:
|
|
port: 8082
|
|
initialDelaySeconds: 10
|
|
readinessProbe:
|
|
failureThreshold: 10
|
|
grpc:
|
|
port: 8082
|
|
initialDelaySeconds: 5
|
|
ports:
|
|
- containerPort: 8080
|
|
name: grpc
|
|
- containerPort: 8081
|
|
name: metrics
|
|
- containerPort: 8082
|
|
name: health
|
|
env:
|
|
- name: NODE_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: spec.nodeName
|
|
command:
|
|
- "nfd-master"
|
|
resources:
|
|
limits:
|
|
memory: 4Gi
|
|
requests:
|
|
cpu: 100m
|
|
memory: 128Mi
|
|
args:
|
|
## By default, disable crd controller for other than the default instances
|
|
- "-crd-controller=true"
|
|
# Go over featureGates and add the feature-gate flag
|
|
- "-feature-gates=NodeFeatureAPI=true"
|
|
- "-feature-gates=NodeFeatureGroupAPI=false"
|
|
- "-metrics=8081"
|
|
- "-grpc-health=8082"
|
|
volumeMounts:
|
|
- name: nfd-master-conf
|
|
mountPath: "/etc/kubernetes/node-feature-discovery"
|
|
readOnly: true
|
|
volumes:
|
|
- name: nfd-master-conf
|
|
configMap:
|
|
name: release-name-node-feature-discovery-master-conf
|
|
items:
|
|
- key: nfd-master.conf
|
|
path: nfd-master.conf
|
|
affinity:
|
|
nodeAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- preference:
|
|
matchExpressions:
|
|
- key: node-role.kubernetes.io/master
|
|
operator: In
|
|
values:
|
|
- ""
|
|
weight: 1
|
|
- preference:
|
|
matchExpressions:
|
|
- key: node-role.kubernetes.io/control-plane
|
|
operator: In
|
|
values:
|
|
- ""
|
|
weight: 1
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/master
|
|
operator: Equal
|
|
value: ""
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/control-plane
|
|
operator: Equal
|
|
value: ""
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/nfd-gc.yaml
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: release-name-node-feature-discovery-gc
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
role: gc
|
|
spec:
|
|
replicas: 1
|
|
revisionHistoryLimit:
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
role: gc
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
role: gc
|
|
spec:
|
|
serviceAccountName: node-feature-discovery
|
|
dnsPolicy: ClusterFirstWithHostNet
|
|
priorityClassName: system-node-critical
|
|
securityContext:
|
|
{}
|
|
hostNetwork: false
|
|
tolerations:
|
|
- key: "nvidia.com/gpu"
|
|
operator: "Exists"
|
|
effect: "NoSchedule"
|
|
containers:
|
|
- name: gc
|
|
image: "harbor.cone-chain.com/highway/nfd/node-feature-discovery:v0.16.6"
|
|
imagePullPolicy: "IfNotPresent"
|
|
env:
|
|
- name: NODE_NAME
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: spec.nodeName
|
|
command:
|
|
- "nfd-gc"
|
|
args:
|
|
- "-gc-interval=1h"
|
|
resources:
|
|
limits:
|
|
memory: 1Gi
|
|
requests:
|
|
cpu: 10m
|
|
memory: 128Mi
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop: [ "ALL" ]
|
|
readOnlyRootFilesystem: true
|
|
runAsNonRoot: true
|
|
ports:
|
|
- name: metrics
|
|
containerPort: 8081
|
|
---
|
|
# Source: gpu-operator/templates/operator.yaml
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: gpu-operator
|
|
namespace: gpu-operator
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
nvidia.com/gpu-driver-upgrade-drain.skip: "true"
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
app: "gpu-operator"
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
app: "gpu-operator"
|
|
nvidia.com/gpu-driver-upgrade-drain.skip: "true"
|
|
annotations:
|
|
openshift.io/scc: restricted-readonly
|
|
spec:
|
|
serviceAccountName: gpu-operator
|
|
priorityClassName: system-node-critical
|
|
containers:
|
|
- name: gpu-operator
|
|
image: harbor.cone-chain.com/highway/nvidia/gpu-operator:v24.9.2
|
|
imagePullPolicy: IfNotPresent
|
|
command: ["gpu-operator"]
|
|
args:
|
|
- --leader-elect
|
|
- --zap-time-encoding=epoch
|
|
- --zap-log-level=info
|
|
env:
|
|
- name: WATCH_NAMESPACE
|
|
value: ""
|
|
- name: OPERATOR_NAMESPACE
|
|
valueFrom:
|
|
fieldRef:
|
|
fieldPath: metadata.namespace
|
|
- name: "DRIVER_MANAGER_IMAGE"
|
|
value: "harbor.cone-chain.com/highway/nvidia/cloud-native/k8s-driver-manager:v0.7.0"
|
|
volumeMounts:
|
|
- name: host-os-release
|
|
mountPath: "/host-etc/os-release"
|
|
readOnly: true
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: 8081
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 20
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /readyz
|
|
port: 8081
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 10
|
|
resources:
|
|
limits:
|
|
cpu: 500m
|
|
memory: 350Mi
|
|
requests:
|
|
cpu: 200m
|
|
memory: 100Mi
|
|
ports:
|
|
- name: metrics
|
|
containerPort: 8080
|
|
volumes:
|
|
- name: host-os-release
|
|
hostPath:
|
|
path: "/etc/os-release"
|
|
affinity:
|
|
nodeAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- preference:
|
|
matchExpressions:
|
|
- key: node-role.kubernetes.io/master
|
|
operator: In
|
|
values:
|
|
- ""
|
|
weight: 1
|
|
- preference:
|
|
matchExpressions:
|
|
- key: node-role.kubernetes.io/control-plane
|
|
operator: In
|
|
values:
|
|
- ""
|
|
weight: 1
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/master
|
|
operator: Equal
|
|
value: ""
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/control-plane
|
|
operator: Equal
|
|
value: ""
|
|
---
|
|
# Source: gpu-operator/templates/clusterpolicy.yaml
|
|
apiVersion: nvidia.com/v1
|
|
kind: ClusterPolicy
|
|
metadata:
|
|
name: cluster-policy
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
spec:
|
|
hostPaths:
|
|
rootFS: /
|
|
driverInstallDir: /run/nvidia/driver
|
|
operator:
|
|
defaultRuntime: docker
|
|
runtimeClass: nvidia
|
|
initContainer:
|
|
repository: harbor.cone-chain.com/highway/nvidia
|
|
image: cuda
|
|
version: "12.6.3-base-ubi9"
|
|
imagePullPolicy: IfNotPresent
|
|
daemonsets:
|
|
labels:
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/managed-by: gpu-operator
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: nvidia.com/gpu
|
|
operator: Exists
|
|
priorityClassName: system-node-critical
|
|
updateStrategy: RollingUpdate
|
|
rollingUpdate:
|
|
maxUnavailable: "1"
|
|
validator:
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: gpu-operator-validator
|
|
version: "v24.9.2"
|
|
imagePullPolicy: IfNotPresent
|
|
plugin:
|
|
env:
|
|
- name: WITH_WORKLOAD
|
|
value: "false"
|
|
|
|
mig:
|
|
strategy: single
|
|
psa:
|
|
enabled: false
|
|
cdi:
|
|
enabled: true
|
|
default: true
|
|
driver:
|
|
enabled: true
|
|
useNvidiaDriverCRD: false
|
|
useOpenKernelModules: false
|
|
usePrecompiled: false
|
|
repository: harbor.cone-chain.com/highway/nvidia
|
|
image: driver
|
|
version: "550.144.03"
|
|
imagePullPolicy: IfNotPresent
|
|
startupProbe:
|
|
failureThreshold: 120
|
|
initialDelaySeconds: 60
|
|
periodSeconds: 10
|
|
timeoutSeconds: 60
|
|
rdma:
|
|
enabled: false
|
|
useHostMofed: false
|
|
manager:
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: k8s-driver-manager
|
|
version: "v0.7.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: ENABLE_GPU_POD_EVICTION
|
|
value: "true"
|
|
- name: ENABLE_AUTO_DRAIN
|
|
value: "false"
|
|
- name: DRAIN_USE_FORCE
|
|
value: "false"
|
|
- name: DRAIN_POD_SELECTOR_LABEL
|
|
value: ""
|
|
- name: DRAIN_TIMEOUT_SECONDS
|
|
value: 0s
|
|
- name: DRAIN_DELETE_EMPTYDIR_DATA
|
|
value: "false"
|
|
repoConfig:
|
|
configMapName: ""
|
|
certConfig:
|
|
name: ""
|
|
licensingConfig:
|
|
configMapName: ""
|
|
nlsEnabled: true
|
|
virtualTopology:
|
|
config: ""
|
|
kernelModuleConfig:
|
|
name: ""
|
|
upgradePolicy:
|
|
autoUpgrade: true
|
|
maxParallelUpgrades: 1
|
|
maxUnavailable : 25%
|
|
waitForCompletion:
|
|
timeoutSeconds: 0
|
|
podDeletion:
|
|
force: false
|
|
timeoutSeconds: 300
|
|
deleteEmptyDir: false
|
|
drain:
|
|
enable: false
|
|
force: false
|
|
timeoutSeconds: 300
|
|
deleteEmptyDir: false
|
|
vgpuManager:
|
|
enabled: false
|
|
image: vgpu-manager
|
|
imagePullPolicy: IfNotPresent
|
|
driverManager:
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: k8s-driver-manager
|
|
version: "v0.7.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: ENABLE_GPU_POD_EVICTION
|
|
value: "false"
|
|
- name: ENABLE_AUTO_DRAIN
|
|
value: "false"
|
|
kataManager:
|
|
enabled: false
|
|
config:
|
|
artifactsDir: /opt/nvidia-gpu-operator/artifacts/runtimeclasses
|
|
runtimeClasses:
|
|
- artifacts:
|
|
pullSecret: ""
|
|
url: harbor.cone-chain.com/highway/nvidia/cloud-native/kata-gpu-artifacts:ubuntu22.04-535.54.03
|
|
name: kata-nvidia-gpu
|
|
nodeSelector: {}
|
|
- artifacts:
|
|
pullSecret: ""
|
|
url: harbor.cone-chain.com/highway/nvidia/cloud-native/kata-gpu-artifacts:ubuntu22.04-535.86.10-snp
|
|
name: kata-nvidia-gpu-snp
|
|
nodeSelector:
|
|
nvidia.com/cc.capable: "true"
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: k8s-kata-manager
|
|
version: "v0.2.2"
|
|
imagePullPolicy: IfNotPresent
|
|
vfioManager:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia
|
|
image: cuda
|
|
version: "12.6.3-base-ubi9"
|
|
imagePullPolicy: IfNotPresent
|
|
driverManager:
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: k8s-driver-manager
|
|
version: "v0.7.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: ENABLE_GPU_POD_EVICTION
|
|
value: "false"
|
|
- name: ENABLE_AUTO_DRAIN
|
|
value: "false"
|
|
vgpuDeviceManager:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: vgpu-device-manager
|
|
version: "v0.2.8"
|
|
imagePullPolicy: IfNotPresent
|
|
config:
|
|
default: default
|
|
name: ""
|
|
ccManager:
|
|
enabled: false
|
|
defaultMode: "off"
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: k8s-cc-manager
|
|
version: "v0.1.1"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
[]
|
|
toolkit:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia/k8s
|
|
image: container-toolkit
|
|
version: "v1.17.4-ubuntu20.04"
|
|
imagePullPolicy: IfNotPresent
|
|
installDir: /usr/local/nvidia
|
|
devicePlugin:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia
|
|
image: k8s-device-plugin
|
|
version: "v0.17.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: PASS_DEVICE_SPECS
|
|
value: "true"
|
|
- name: FAIL_ON_INIT_ERROR
|
|
value: "true"
|
|
- name: DEVICE_LIST_STRATEGY
|
|
value: envvar
|
|
- name: DEVICE_ID_STRATEGY
|
|
value: uuid
|
|
- name: NVIDIA_VISIBLE_DEVICES
|
|
value: all
|
|
- name: NVIDIA_DRIVER_CAPABILITIES
|
|
value: all
|
|
dcgm:
|
|
enabled: false
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: dcgm
|
|
version: "3.3.9-1-ubuntu22.04"
|
|
imagePullPolicy: IfNotPresent
|
|
dcgmExporter:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia/k8s
|
|
image: dcgm-exporter
|
|
version: "3.3.9-3.6.1-ubuntu22.04"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: DCGM_EXPORTER_LISTEN
|
|
value: :9400
|
|
- name: DCGM_EXPORTER_KUBERNETES
|
|
value: "true"
|
|
- name: DCGM_EXPORTER_COLLECTORS
|
|
value: /etc/dcgm-exporter/dcp-metrics-included.csv
|
|
serviceMonitor:
|
|
additionalLabels: {}
|
|
enabled: false
|
|
honorLabels: false
|
|
interval: 15s
|
|
relabelings: []
|
|
gfd:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia
|
|
image: k8s-device-plugin
|
|
version: "v0.17.0"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: GFD_SLEEP_INTERVAL
|
|
value: 60s
|
|
- name: GFD_FAIL_ON_INIT_ERROR
|
|
value: "true"
|
|
migManager:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: k8s-mig-manager
|
|
version: "v0.10.0-ubuntu20.04"
|
|
imagePullPolicy: IfNotPresent
|
|
env:
|
|
- name: WITH_REBOOT
|
|
value: "false"
|
|
config:
|
|
name:
|
|
default: all-disabled
|
|
gpuClientsConfig:
|
|
name: ""
|
|
nodeStatusExporter:
|
|
enabled: false
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: gpu-operator-validator
|
|
version: "v24.9.2"
|
|
imagePullPolicy: IfNotPresent
|
|
gdrcopy:
|
|
enabled: false
|
|
repository: harbor.cone-chain.com/highway/nvidia/cloud-native
|
|
image: gdrdrv
|
|
version: "v2.4.1-2"
|
|
imagePullPolicy: IfNotPresent
|
|
sandboxWorkloads:
|
|
enabled: false
|
|
defaultWorkload: container
|
|
sandboxDevicePlugin:
|
|
enabled: true
|
|
repository: harbor.cone-chain.com/highway/nvidia
|
|
image: kubevirt-gpu-device-plugin
|
|
version: "v1.2.10"
|
|
imagePullPolicy: IfNotPresent
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: release-name-node-feature-discovery-prune
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
annotations:
|
|
"helm.sh/hook": post-delete
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
---
|
|
# Source: gpu-operator/templates/upgrade_crd.yaml
|
|
apiVersion: v1
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: gpu-operator-upgrade-crd-hook-sa
|
|
namespace: gpu-operator
|
|
annotations:
|
|
helm.sh/hook: pre-upgrade
|
|
helm.sh/hook-delete-policy: hook-succeeded,before-hook-creation
|
|
helm.sh/hook-weight: "0"
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: release-name-node-feature-discovery-prune
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
annotations:
|
|
"helm.sh/hook": post-delete
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- nodes
|
|
- nodes/status
|
|
verbs:
|
|
- get
|
|
- patch
|
|
- update
|
|
- list
|
|
---
|
|
# Source: gpu-operator/templates/upgrade_crd.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: gpu-operator-upgrade-crd-hook-role
|
|
annotations:
|
|
helm.sh/hook: pre-upgrade
|
|
helm.sh/hook-delete-policy: hook-succeeded,before-hook-creation
|
|
helm.sh/hook-weight: "0"
|
|
rules:
|
|
- apiGroups:
|
|
- apiextensions.k8s.io
|
|
resources:
|
|
- customresourcedefinitions
|
|
verbs:
|
|
- create
|
|
- get
|
|
- list
|
|
- watch
|
|
- patch
|
|
- update
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: release-name-node-feature-discovery-prune
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
annotations:
|
|
"helm.sh/hook": post-delete
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: release-name-node-feature-discovery-prune
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: release-name-node-feature-discovery-prune
|
|
namespace: gpu-operator
|
|
---
|
|
# Source: gpu-operator/templates/upgrade_crd.yaml
|
|
kind: ClusterRoleBinding
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
metadata:
|
|
name: gpu-operator-upgrade-crd-hook-binding
|
|
annotations:
|
|
helm.sh/hook: pre-upgrade
|
|
helm.sh/hook-delete-policy: hook-succeeded,before-hook-creation
|
|
helm.sh/hook-weight: "0"
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: gpu-operator-upgrade-crd-hook-sa
|
|
namespace: gpu-operator
|
|
roleRef:
|
|
kind: ClusterRole
|
|
name: gpu-operator-upgrade-crd-hook-role
|
|
apiGroup: rbac.authorization.k8s.io
|
|
---
|
|
# Source: gpu-operator/charts/node-feature-discovery/templates/post-delete-job.yaml
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: release-name-node-feature-discovery-prune
|
|
namespace: gpu-operator
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
annotations:
|
|
"helm.sh/hook": post-delete
|
|
"helm.sh/hook-delete-policy": before-hook-creation,hook-succeeded
|
|
spec:
|
|
template:
|
|
metadata:
|
|
labels:
|
|
helm.sh/chart: node-feature-discovery-0.16.6
|
|
app.kubernetes.io/name: node-feature-discovery
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v0.16.6"
|
|
app.kubernetes.io/managed-by: Helm
|
|
role: prune
|
|
spec:
|
|
serviceAccountName: release-name-node-feature-discovery-prune
|
|
containers:
|
|
- name: nfd-master
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
runAsNonRoot: true
|
|
image: "harbor.cone-chain.com/highway/nfd/node-feature-discovery:v0.16.6"
|
|
imagePullPolicy: IfNotPresent
|
|
command:
|
|
- "nfd-master"
|
|
args:
|
|
- "-prune"
|
|
restartPolicy: Never
|
|
affinity:
|
|
nodeAffinity:
|
|
preferredDuringSchedulingIgnoredDuringExecution:
|
|
- preference:
|
|
matchExpressions:
|
|
- key: node-role.kubernetes.io/master
|
|
operator: In
|
|
values:
|
|
- ""
|
|
weight: 1
|
|
- preference:
|
|
matchExpressions:
|
|
- key: node-role.kubernetes.io/control-plane
|
|
operator: In
|
|
values:
|
|
- ""
|
|
weight: 1
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/master
|
|
operator: Equal
|
|
value: ""
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/control-plane
|
|
operator: Equal
|
|
value: ""
|
|
---
|
|
# Source: gpu-operator/templates/upgrade_crd.yaml
|
|
apiVersion: batch/v1
|
|
kind: Job
|
|
metadata:
|
|
name: gpu-operator-upgrade-crd
|
|
namespace: gpu-operator
|
|
annotations:
|
|
"helm.sh/hook": pre-upgrade
|
|
"helm.sh/hook-weight": "1"
|
|
"helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
spec:
|
|
template:
|
|
metadata:
|
|
name: gpu-operator-upgrade-crd
|
|
labels:
|
|
app.kubernetes.io/name: gpu-operator
|
|
helm.sh/chart: gpu-operator-v24.9.2
|
|
app.kubernetes.io/instance: release-name
|
|
app.kubernetes.io/version: "v24.9.2"
|
|
app.kubernetes.io/managed-by: Helm
|
|
app.kubernetes.io/component: "gpu-operator"
|
|
spec:
|
|
serviceAccountName: gpu-operator-upgrade-crd-hook-sa
|
|
tolerations:
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/master
|
|
operator: Equal
|
|
value: ""
|
|
- effect: NoSchedule
|
|
key: node-role.kubernetes.io/control-plane
|
|
operator: Equal
|
|
value: ""
|
|
containers:
|
|
- name: upgrade-crd
|
|
image: harbor.cone-chain.com/highway/nvidia/gpu-operator:v24.9.2
|
|
imagePullPolicy: IfNotPresent
|
|
command:
|
|
- /bin/sh
|
|
- -c
|
|
- >
|
|
kubectl apply -f /opt/gpu-operator/nvidia.com_clusterpolicies.yaml;
|
|
kubectl apply -f /opt/gpu-operator/nvidia.com_nvidiadrivers.yaml;
|
|
kubectl apply -f /opt/gpu-operator/nfd-api-crds.yaml;
|
|
restartPolicy: OnFailure
|