---
# Source: gpu-operator/templates/resources-namespace.yaml
apiVersion: v1
kind: Namespace
metadata:
name: gpu-operator-resources
labels:
app.kubernetes.io/component: "gpu-operator"
openshift.io/cluster-monitoring: "true"
---
# Source: gpu-operator/charts/node-feature-discovery/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: gpu-operator-node-feature-discovery
namespace: default
labels:
helm.sh/chart: node-feature-discovery-2.0.0
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/version: "0.6.0"
app.kubernetes.io/managed-by: Helm
---
# Source: gpu-operator/templates/serviceaccount.yaml
apiVersion: v1
kind: ServiceAccount
metadata:
name: gpu-operator
namespace: default
labels:
app.kubernetes.io/component: "gpu-operator"
---
# Source: gpu-operator/charts/node-feature-discovery/templates/configmap.yaml
apiVersion: v1
kind: ConfigMap
metadata:
name: gpu-operator-node-feature-discovery
namespace: default
labels:
helm.sh/chart: node-feature-discovery-2.0.0
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/version: "0.6.0"
app.kubernetes.io/managed-by: Helm
data:
nfd-worker.conf: |
sources:
pci:
deviceLabelFields:
- vendor
---
# Source: gpu-operator/charts/node-feature-discovery/templates/rbac.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: gpu-operator-node-feature-discovery-master
rules:
- apiGroups:
- ""
resources:
- nodes
# when using command line flag --resource-labels to create extended resources
# you will need to uncomment "- nodes/status"
# - nodes/status
verbs:
- get
- patch
- update
---
# Source: gpu-operator/templates/role.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
creationTimestamp: null
name: gpu-operator
labels:
app.kubernetes.io/component: "gpu-operator"
rules:
- apiGroups:
- config.openshift.io
resources:
- proxies
verbs:
- get
- apiGroups:
- rbac.authorization.k8s.io
resources:
- roles
- rolebindings
- clusterroles
- clusterrolebindings
verbs:
- '*'
- apiGroups:
- ""
resources:
- pods
- services
- endpoints
- persistentvolumeclaims
- events
- configmaps
- secrets
- serviceaccounts
- nodes
verbs:
- '*'
- apiGroups:
- ""
resources:
- namespaces
verbs:
- get
- apiGroups:
- apps
resources:
- deployments
- daemonsets
- replicasets
- statefulsets
verbs:
- '*'
- apiGroups:
- monitoring.coreos.com
resources:
- servicemonitors
verbs:
- get
- list
- create
- watch
- apiGroups:
- nvidia.com
resources:
- '*'
verbs:
- '*'
- apiGroups:
- scheduling.k8s.io
resources:
- priorityclasses
verbs:
- get
- list
- watch
- create
- apiGroups:
- security.openshift.io
resources:
- securitycontextconstraints
verbs:
- '*'
- apiGroups:
- config.openshift.io
resources:
- clusterversions
verbs:
- get
- list
- watch
---
# Source: gpu-operator/charts/node-feature-discovery/templates/rbac.yaml
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: gpu-operator-node-feature-discovery-master
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: gpu-operator-node-feature-discovery-master
subjects:
- kind: ServiceAccount
name: gpu-operator-node-feature-discovery
namespace: default
---
# Source: gpu-operator/templates/rolebinding.yaml
kind: ClusterRoleBinding
apiVersion: rbac.authorization.k8s.io/v1
metadata:
name: gpu-operator
labels:
app.kubernetes.io/component: "gpu-operator"
subjects:
- kind: ServiceAccount
name: gpu-operator
namespace: default
roleRef:
kind: ClusterRole
name: gpu-operator
apiGroup: rbac.authorization.k8s.io
---
# Source: gpu-operator/charts/node-feature-discovery/templates/service.yaml
apiVersion: v1
kind: Service
metadata:
name: gpu-operator-node-feature-discovery
namespace: default
labels:
helm.sh/chart: node-feature-discovery-2.0.0
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/version: "0.6.0"
app.kubernetes.io/managed-by: Helm
spec:
type: ClusterIP
ports:
- name: api
port: 8080
protocol: TCP
targetPort: api
selector:
app.kubernetes.io/component: master
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
---
# Source: gpu-operator/charts/node-feature-discovery/templates/daemonset-worker.yaml
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: gpu-operator-node-feature-discovery-worker
namespace: default
labels:
helm.sh/chart: node-feature-discovery-2.0.0
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/version: "0.6.0"
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: worker
spec:
selector:
matchLabels:
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/component: worker
template:
metadata:
labels:
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/component: worker
spec:
serviceAccountName: gpu-operator-node-feature-discovery
securityContext:
{}
dnsPolicy: ClusterFirstWithHostNet
containers:
- name: node-feature-discovery-master
securityContext:
{}
image: "quay.io/kubernetes_incubator/node-feature-discovery:v0.6.0"
imagePullPolicy: IfNotPresent
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
command:
- "nfd-worker"
args:
- "--sleep-interval=60s"
- "--server=gpu-operator-node-feature-discovery:8080"
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"
- name: source-d
mountPath: "/etc/kubernetes/node-feature-discovery/source.d/"
- name: features-d
mountPath: "/etc/kubernetes/node-feature-discovery/features.d/"
- name: nfd-worker-config
mountPath: "/etc/kubernetes/node-feature-discovery/"
resources:
{}
volumes:
- name: host-boot
hostPath:
path: "/boot"
- name: host-os-release
hostPath:
path: "/etc/os-release"
- name: host-sys
hostPath:
path: "/sys"
- 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-config
configMap:
name: gpu-operator-node-feature-discovery
tolerations:
- effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Equal
value: ""
- effect: NoSchedule
key: nvidia.com/gpu
operator: Equal
value: present
---
# Source: gpu-operator/charts/node-feature-discovery/templates/deployment-master.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: gpu-operator-node-feature-discovery-master
namespace: default
labels:
helm.sh/chart: node-feature-discovery-2.0.0
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/version: "0.6.0"
app.kubernetes.io/managed-by: Helm
app.kubernetes.io/component: master
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/component: master
template:
metadata:
labels:
app.kubernetes.io/name: node-feature-discovery
app.kubernetes.io/instance: gpu-operator
app.kubernetes.io/component: master
spec:
serviceAccountName: gpu-operator-node-feature-discovery
securityContext:
{}
containers:
- name: node-feature-discovery-master
securityContext:
{}
image: "quay.io/kubernetes_incubator/node-feature-discovery:v0.6.0"
imagePullPolicy: IfNotPresent
ports:
- name: api
containerPort: 8080
protocol: TCP
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
command:
- "nfd-master"
args:
- --extra-label-ns=nvidia.com
resources:
{}
affinity:
nodeAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- preference:
matchExpressions:
- key: node-role.kubernetes.io/master
operator: In
values:
- ""
weight: 1
tolerations:
- effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Equal
value: ""
---
# Source: gpu-operator/templates/operator.yaml
apiVersion: apps/v1
kind: Deployment
metadata:
name: gpu-operator
namespace: default
labels:
app.kubernetes.io/component: "gpu-operator"
spec:
replicas: 1
selector:
matchLabels:
app.kubernetes.io/component: "gpu-operator"
template:
metadata:
labels:
app.kubernetes.io/component: "gpu-operator"
annotations:
openshift.io/scc: restricted-readonly
spec:
serviceAccountName: gpu-operator
containers:
- name: gpu-operator
image: nvcr.io/nvidia/gpu-operator:1.6.2
imagePullPolicy: IfNotPresent
command: ["gpu-operator"]
args:
- "--zap-time-encoding=epoch"
env:
- name: WATCH_NAMESPACE
value: ""
- name: OPERATOR_NAME
value: "gpu-operator"
- name: POD_NAME
valueFrom:
fieldRef:
fieldPath: metadata.name
volumeMounts:
- name: host-os-release
mountPath: "/host-etc/os-release"
readOnly: true
readinessProbe:
exec:
command: ["stat", "/tmp/operator-sdk-ready"]
initialDelaySeconds: 4
periodSeconds: 10
failureThreshold: 1
ports:
- containerPort: 60000
name: metrics
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
tolerations:
- effect: NoSchedule
key: node-role.kubernetes.io/master
operator: Equal
value: ""
---
# Source: gpu-operator/templates/clusterpolicy.yaml
apiVersion: nvidia.com/v1
kind: ClusterPolicy
metadata:
name: cluster-policy
namespace: default
labels:
app.kubernetes.io/component: "gpu-operator"
spec:
operator:
defaultRuntime: containerd
validator:
repository: nvcr.io/nvidia/k8s
image: cuda-sample
version: vectoradd-cuda10.2
imagePullPolicy: IfNotPresent
driver:
repository: nvcr.io/nvidia
image: driver
version: 460.32.03
imagePullPolicy: IfNotPresent
repoConfig:
configMapName: ""
destinationDir: ""
licensingConfig:
configMapName: ""
tolerations:
- effect: NoSchedule
key: nvidia.com/gpu
operator: Exists
nodeSelector:
nvidia.com/gpu.present: "true"
securityContext:
privileged: true
seLinuxOptions:
level: s0
toolkit:
repository: nvcr.io/nvidia/k8s
image: container-toolkit
version: 1.4.7-ubuntu18.04
imagePullPolicy: IfNotPresent
tolerations:
- key: CriticalAddonsOnly
operator: Exists
- effect: NoSchedule
key: nvidia.com/gpu
operator: Exists
nodeSelector:
nvidia.com/gpu.present: "true"
securityContext:
privileged: true
seLinuxOptions:
level: s0
devicePlugin:
repository: nvcr.io/nvidia
image: k8s-device-plugin
version: v0.8.2-ubi8
imagePullPolicy: IfNotPresent
nodeSelector:
nvidia.com/gpu.present: "true"
securityContext:
privileged: true
args:
- --mig-strategy=single
- --pass-device-specs=true
- --fail-on-init-error=true
- --device-list-strategy=envvar
- --nvidia-driver-root=/run/nvidia/driver
dcgmExporter:
repository: nvcr.io/nvidia/k8s
image: dcgm-exporter
version: 2.1.4-2.2.0-ubuntu20.04
imagePullPolicy: IfNotPresent
args:
- -f
- /etc/dcgm-exporter/dcp-metrics-included.csv
gfd:
repository: nvcr.io/nvidia
image: gpu-feature-discovery
version: v0.4.1
imagePullPolicy: IfNotPresent
nodeSelector:
nvidia.com/gpu.present: "true"
migStrategy: single
discoveryIntervalSeconds: 60