Change chart directory structure
This commit is contained in:
wbsong111
@@ -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/
|
||||
@@ -0,0 +1,17 @@
|
||||
apiVersion: v2
|
||||
appVersion: 1.0.1
|
||||
description: NVIDIA NIM Operator creates/configures/manages NVIDIA NIM microservices
|
||||
in Kubernetes
|
||||
home: https://docs.nvidia.com/nim-operator/latest/index.html
|
||||
icon: https://assets.nvidiagrid.net/ngc/logos/NIMOperator.png
|
||||
keywords:
|
||||
- gpu
|
||||
- nim
|
||||
- nemo
|
||||
- operator
|
||||
- ai
|
||||
name: k8s-nim-operator
|
||||
sources:
|
||||
- https://github.com/NVIDIA/k8s-nim-operator
|
||||
type: application
|
||||
version: 1.0.1
|
||||
+500
@@ -0,0 +1,500 @@
|
||||
---
|
||||
apiVersion: apiextensions.k8s.io/v1
|
||||
kind: CustomResourceDefinition
|
||||
metadata:
|
||||
annotations:
|
||||
controller-gen.kubebuilder.io/version: v0.16.2
|
||||
name: nimcaches.apps.nvidia.com
|
||||
spec:
|
||||
group: apps.nvidia.com
|
||||
names:
|
||||
kind: NIMCache
|
||||
listKind: NIMCacheList
|
||||
plural: nimcaches
|
||||
singular: nimcache
|
||||
scope: Namespaced
|
||||
versions:
|
||||
- additionalPrinterColumns:
|
||||
- jsonPath: .status.state
|
||||
name: Status
|
||||
type: string
|
||||
- jsonPath: .status.pvc
|
||||
name: PVC
|
||||
type: string
|
||||
- format: date-time
|
||||
jsonPath: .metadata.creationTimestamp
|
||||
name: Age
|
||||
type: date
|
||||
name: v1alpha1
|
||||
schema:
|
||||
openAPIV3Schema:
|
||||
description: NIMCache is the Schema for the nimcaches API
|
||||
properties:
|
||||
apiVersion:
|
||||
description: |-
|
||||
APIVersion defines the versioned schema of this representation of an object.
|
||||
Servers should convert recognized schemas to the latest internal value, and
|
||||
may reject unrecognized values.
|
||||
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
|
||||
type: string
|
||||
kind:
|
||||
description: |-
|
||||
Kind is a string value representing the REST resource this object represents.
|
||||
Servers may infer this from the endpoint the client submits requests to.
|
||||
Cannot be updated.
|
||||
In CamelCase.
|
||||
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
|
||||
type: string
|
||||
metadata:
|
||||
type: object
|
||||
spec:
|
||||
description: NIMCacheSpec defines the desired state of NIMCache
|
||||
properties:
|
||||
certConfig:
|
||||
description: |-
|
||||
CertConfig is the name of the ConfigMap containing the custom certificates.
|
||||
for secure communication.
|
||||
properties:
|
||||
mountPath:
|
||||
description: MountPath is the path where the certificates should
|
||||
be mounted in the container.
|
||||
type: string
|
||||
name:
|
||||
description: Name of the ConfigMap containing the certificate
|
||||
data.
|
||||
type: string
|
||||
required:
|
||||
- mountPath
|
||||
- name
|
||||
type: object
|
||||
env:
|
||||
description: Env are the additional custom environment variabes for
|
||||
the caching job
|
||||
items:
|
||||
description: EnvVar represents an environment variable present in
|
||||
a Container.
|
||||
properties:
|
||||
name:
|
||||
description: Name of the environment variable. Must be a C_IDENTIFIER.
|
||||
type: string
|
||||
value:
|
||||
description: |-
|
||||
Variable references $(VAR_NAME) are expanded
|
||||
using the previously defined environment variables in the container and
|
||||
any service environment variables. If a variable cannot be resolved,
|
||||
the reference in the input string will be unchanged. Double $$ are reduced
|
||||
to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e.
|
||||
"$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)".
|
||||
Escaped references will never be expanded, regardless of whether the variable
|
||||
exists or not.
|
||||
Defaults to "".
|
||||
type: string
|
||||
valueFrom:
|
||||
description: Source for the environment variable's value. Cannot
|
||||
be used if value is not empty.
|
||||
properties:
|
||||
configMapKeyRef:
|
||||
description: Selects a key of a ConfigMap.
|
||||
properties:
|
||||
key:
|
||||
description: The key to select.
|
||||
type: string
|
||||
name:
|
||||
default: ""
|
||||
description: |-
|
||||
Name of the referent.
|
||||
This field is effectively required, but due to backwards compatibility is
|
||||
allowed to be empty. Instances of this type with an empty value here are
|
||||
almost certainly wrong.
|
||||
More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the ConfigMap or its key
|
||||
must be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
fieldRef:
|
||||
description: |-
|
||||
Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['<KEY>']`, `metadata.annotations['<KEY>']`,
|
||||
spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.
|
||||
properties:
|
||||
apiVersion:
|
||||
description: Version of the schema the FieldPath is
|
||||
written in terms of, defaults to "v1".
|
||||
type: string
|
||||
fieldPath:
|
||||
description: Path of the field to select in the specified
|
||||
API version.
|
||||
type: string
|
||||
required:
|
||||
- fieldPath
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
resourceFieldRef:
|
||||
description: |-
|
||||
Selects a resource of the container: only resources limits and requests
|
||||
(limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.
|
||||
properties:
|
||||
containerName:
|
||||
description: 'Container name: required for volumes,
|
||||
optional for env vars'
|
||||
type: string
|
||||
divisor:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: Specifies the output format of the exposed
|
||||
resources, defaults to "1"
|
||||
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
|
||||
x-kubernetes-int-or-string: true
|
||||
resource:
|
||||
description: 'Required: resource to select'
|
||||
type: string
|
||||
required:
|
||||
- resource
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
secretKeyRef:
|
||||
description: Selects a key of a secret in the pod's namespace
|
||||
properties:
|
||||
key:
|
||||
description: The key of the secret to select from. Must
|
||||
be a valid secret key.
|
||||
type: string
|
||||
name:
|
||||
default: ""
|
||||
description: |-
|
||||
Name of the referent.
|
||||
This field is effectively required, but due to backwards compatibility is
|
||||
allowed to be empty. Instances of this type with an empty value here are
|
||||
almost certainly wrong.
|
||||
More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names
|
||||
type: string
|
||||
optional:
|
||||
description: Specify whether the Secret or its key must
|
||||
be defined
|
||||
type: boolean
|
||||
required:
|
||||
- key
|
||||
type: object
|
||||
x-kubernetes-map-type: atomic
|
||||
type: object
|
||||
required:
|
||||
- name
|
||||
type: object
|
||||
type: array
|
||||
groupID:
|
||||
description: GroupID is the group ID for the caching job
|
||||
format: int64
|
||||
type: integer
|
||||
nodeSelector:
|
||||
additionalProperties:
|
||||
type: string
|
||||
description: NodeSelector is the node selector labels to schedule
|
||||
the caching job.
|
||||
type: object
|
||||
resources:
|
||||
description: Resources defines the minimum resources required for
|
||||
the caching job to run(cpu, memory, gpu).
|
||||
properties:
|
||||
cpu:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: CPU indicates the minimum number of CPUs to use while
|
||||
caching NIM
|
||||
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
|
||||
x-kubernetes-int-or-string: true
|
||||
memory:
|
||||
anyOf:
|
||||
- type: integer
|
||||
- type: string
|
||||
description: |-
|
||||
Memory indicates the minimum amount of memory to use while caching NIM
|
||||
Valid values are numbers followed by one of the suffixes Ki, Mi, Gi, or Ti (e.g. "4Gi", "4096Mi").
|
||||
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
|
||||
x-kubernetes-int-or-string: true
|
||||
type: object
|
||||
runtimeClassName:
|
||||
description: RuntimeClassName is the runtimeclass for the caching
|
||||
job
|
||||
type: string
|
||||
source:
|
||||
description: Source is the NIM model source to cache
|
||||
properties:
|
||||
dataStore:
|
||||
description: NGCSource represents models stored in NVIDIA DataStore
|
||||
service
|
||||
properties:
|
||||
authSecret:
|
||||
description: The name of an existing auth secret containing
|
||||
the AUTH_TOKEN"
|
||||
type: string
|
||||
checkpointName:
|
||||
type: string
|
||||
datasetName:
|
||||
type: string
|
||||
endpoint:
|
||||
description: The endpoint for datastore
|
||||
type: string
|
||||
modelName:
|
||||
description: Name of either model/checkpoint or dataset to
|
||||
download
|
||||
type: string
|
||||
modelPuller:
|
||||
description: ModelPuller is the container image that can pull
|
||||
the model
|
||||
type: string
|
||||
pullSecret:
|
||||
description: PullSecret for the model puller image
|
||||
type: string
|
||||
required:
|
||||
- authSecret
|
||||
- endpoint
|
||||
- modelPuller
|
||||
type: object
|
||||
ngc:
|
||||
description: NGCSource represents models stored in NGC
|
||||
properties:
|
||||
authSecret:
|
||||
description: The name of an existing pull secret containing
|
||||
the NGC_API_KEY
|
||||
type: string
|
||||
model:
|
||||
description: Model spec for caching
|
||||
properties:
|
||||
buildable:
|
||||
description: Buildable indicates generic model profiles
|
||||
that can be optimized with an NVIDIA engine for any
|
||||
GPUs
|
||||
type: boolean
|
||||
engine:
|
||||
description: Engine is the backend engine (tensort_llm,
|
||||
vllm)
|
||||
type: string
|
||||
gpus:
|
||||
description: GPU is the spec for matching GPUs for caching
|
||||
optimized models
|
||||
items:
|
||||
description: GPUSpec is the spec required to cache models
|
||||
for selected gpu type
|
||||
properties:
|
||||
ids:
|
||||
description: IDs are the device-ids for a specific
|
||||
GPU SKU
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
product:
|
||||
description: Product is the GPU product string (h100,
|
||||
a100, l40s)
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
lora:
|
||||
description: Lora indicates a finetuned model with LoRa
|
||||
adapters
|
||||
type: boolean
|
||||
precision:
|
||||
description: Precision is the precision for model quantization
|
||||
type: string
|
||||
profiles:
|
||||
description: Profiles are the specific model profiles
|
||||
to cache. When these are provided, rest of the model
|
||||
parameters for profile selection are ignored
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
qosProfile:
|
||||
description: QoSProfile is the supported QoS profile types
|
||||
for the models (throughput, latency)
|
||||
type: string
|
||||
tensorParallelism:
|
||||
description: TensorParallelism is the minimum GPUs required
|
||||
for the model computations
|
||||
type: string
|
||||
type: object
|
||||
modelPuller:
|
||||
description: ModelPuller is the container image that can pull
|
||||
the model
|
||||
type: string
|
||||
x-kubernetes-validations:
|
||||
- message: modelPuller is an immutable field. Please create
|
||||
a new NIMCache resource instead when you want to change
|
||||
this container.
|
||||
rule: self == oldSelf
|
||||
pullSecret:
|
||||
description: PullSecret to pull the model puller image
|
||||
type: string
|
||||
required:
|
||||
- authSecret
|
||||
- modelPuller
|
||||
type: object
|
||||
type: object
|
||||
storage:
|
||||
description: Storage is the target storage for caching NIM model
|
||||
properties:
|
||||
hostPath:
|
||||
description: HostPath is the host path volume for caching NIM
|
||||
type: string
|
||||
pvc:
|
||||
description: PersistentVolumeClaim is the pvc volume used for
|
||||
caching NIM
|
||||
properties:
|
||||
create:
|
||||
description: Create indicates to create a new PVC
|
||||
type: boolean
|
||||
name:
|
||||
description: Name is the name of the PVC
|
||||
type: string
|
||||
size:
|
||||
description: Size of the NIM cache in Gi, used during PVC
|
||||
creation
|
||||
type: string
|
||||
storageClass:
|
||||
description: StorageClass to be used for PVC creation. Leave
|
||||
it as empty if the PVC is already created.
|
||||
type: string
|
||||
subPath:
|
||||
type: string
|
||||
volumeAccessMode:
|
||||
description: VolumeAccessMode is the volume access mode of
|
||||
the PVC
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
tolerations:
|
||||
description: Tolerations for running the job to cache the NIM model
|
||||
items:
|
||||
description: |-
|
||||
The pod this Toleration is attached to tolerates any taint that matches
|
||||
the triple <key,value,effect> using the matching operator <operator>.
|
||||
properties:
|
||||
effect:
|
||||
description: |-
|
||||
Effect indicates the taint effect to match. Empty means match all taint effects.
|
||||
When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute.
|
||||
type: string
|
||||
key:
|
||||
description: |-
|
||||
Key is the taint key that the toleration applies to. Empty means match all taint keys.
|
||||
If the key is empty, operator must be Exists; this combination means to match all values and all keys.
|
||||
type: string
|
||||
operator:
|
||||
description: |-
|
||||
Operator represents a key's relationship to the value.
|
||||
Valid operators are Exists and Equal. Defaults to Equal.
|
||||
Exists is equivalent to wildcard for value, so that a pod can
|
||||
tolerate all taints of a particular category.
|
||||
type: string
|
||||
tolerationSeconds:
|
||||
description: |-
|
||||
TolerationSeconds represents the period of time the toleration (which must be
|
||||
of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default,
|
||||
it is not set, which means tolerate the taint forever (do not evict). Zero and
|
||||
negative values will be treated as 0 (evict immediately) by the system.
|
||||
format: int64
|
||||
type: integer
|
||||
value:
|
||||
description: |-
|
||||
Value is the taint value the toleration matches to.
|
||||
If the operator is Exists, the value should be empty, otherwise just a regular string.
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
userID:
|
||||
description: UserID is the user ID for the caching job
|
||||
format: int64
|
||||
type: integer
|
||||
required:
|
||||
- source
|
||||
- storage
|
||||
type: object
|
||||
status:
|
||||
description: NIMCacheStatus defines the observed state of NIMCache
|
||||
properties:
|
||||
conditions:
|
||||
items:
|
||||
description: Condition contains details for one aspect of the current
|
||||
state of this API Resource.
|
||||
properties:
|
||||
lastTransitionTime:
|
||||
description: |-
|
||||
lastTransitionTime is the last time the condition transitioned from one status to another.
|
||||
This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable.
|
||||
format: date-time
|
||||
type: string
|
||||
message:
|
||||
description: |-
|
||||
message is a human readable message indicating details about the transition.
|
||||
This may be an empty string.
|
||||
maxLength: 32768
|
||||
type: string
|
||||
observedGeneration:
|
||||
description: |-
|
||||
observedGeneration represents the .metadata.generation that the condition was set based upon.
|
||||
For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
|
||||
with respect to the current state of the instance.
|
||||
format: int64
|
||||
minimum: 0
|
||||
type: integer
|
||||
reason:
|
||||
description: |-
|
||||
reason contains a programmatic identifier indicating the reason for the condition's last transition.
|
||||
Producers of specific condition types may define expected values and meanings for this field,
|
||||
and whether the values are considered a guaranteed API.
|
||||
The value should be a CamelCase string.
|
||||
This field may not be empty.
|
||||
maxLength: 1024
|
||||
minLength: 1
|
||||
pattern: ^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$
|
||||
type: string
|
||||
status:
|
||||
description: status of the condition, one of True, False, Unknown.
|
||||
enum:
|
||||
- "True"
|
||||
- "False"
|
||||
- Unknown
|
||||
type: string
|
||||
type:
|
||||
description: type of condition in CamelCase or in foo.example.com/CamelCase.
|
||||
maxLength: 316
|
||||
pattern: ^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$
|
||||
type: string
|
||||
required:
|
||||
- lastTransitionTime
|
||||
- message
|
||||
- reason
|
||||
- status
|
||||
- type
|
||||
type: object
|
||||
type: array
|
||||
profiles:
|
||||
items:
|
||||
description: NIMProfile defines the profiles that were cached
|
||||
properties:
|
||||
config:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
model:
|
||||
type: string
|
||||
name:
|
||||
type: string
|
||||
release:
|
||||
type: string
|
||||
type: object
|
||||
type: array
|
||||
pvc:
|
||||
type: string
|
||||
state:
|
||||
type: string
|
||||
type: object
|
||||
type: object
|
||||
served: true
|
||||
storage: true
|
||||
subresources:
|
||||
status: {}
|
||||
+2309
File diff suppressed because it is too large
Load Diff
+2217
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,58 @@
|
||||
{{/*
|
||||
Expand the name of the chart.
|
||||
*/}}
|
||||
{{- define "k8s-nim-operator.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 "k8s-nim-operator.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 "k8s-nim-operator.chart" -}}
|
||||
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Common labels
|
||||
*/}}
|
||||
{{- define "k8s-nim-operator.labels" -}}
|
||||
helm.sh/chart: {{ include "k8s-nim-operator.chart" . }}
|
||||
{{ include "k8s-nim-operator.selectorLabels" . }}
|
||||
{{- if .Chart.AppVersion }}
|
||||
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
|
||||
{{- end }}
|
||||
app.kubernetes.io/managed-by: {{ .Release.Service }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Selector labels
|
||||
*/}}
|
||||
{{- define "k8s-nim-operator.selectorLabels" -}}
|
||||
app.kubernetes.io/name: {{ include "k8s-nim-operator.name" . }}
|
||||
app.kubernetes.io/instance: {{ .Release.Name }}
|
||||
{{- end }}
|
||||
|
||||
{{/*
|
||||
Full image name with tag
|
||||
*/}}
|
||||
{{- define "k8s-nim-operator.fullimage" -}}
|
||||
{{- .Values.operator.image.repository -}}:{{- .Values.operator.image.tag | default (printf "v%s" .Chart.AppVersion) -}}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,78 @@
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: {{ include "k8s-nim-operator.fullname" . }}
|
||||
labels:
|
||||
app.kubernetes.io/component: manager
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
control-plane: controller-manager
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
spec:
|
||||
replicas: {{ .Values.operator.replicas }}
|
||||
selector:
|
||||
matchLabels:
|
||||
control-plane: controller-manager
|
||||
{{- include "k8s-nim-operator.selectorLabels" . | nindent 6 }}
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
control-plane: controller-manager
|
||||
{{- include "k8s-nim-operator.selectorLabels" . | nindent 8 }}
|
||||
annotations:
|
||||
kubectl.kubernetes.io/default-container: manager
|
||||
spec:
|
||||
containers:
|
||||
- args: {{- toYaml .Values.operator.args | nindent 8 }}
|
||||
command:
|
||||
- /manager
|
||||
image: {{ include "k8s-nim-operator.fullimage" . }}
|
||||
imagePullPolicy: {{ .Values.operator.image.pullPolicy }}
|
||||
env:
|
||||
- name: WATCH_NAMESPACE
|
||||
value: ""
|
||||
- name: OPERATOR_NAMESPACE
|
||||
valueFrom:
|
||||
fieldRef:
|
||||
fieldPath: metadata.namespace
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /healthz
|
||||
port: 8081
|
||||
initialDelaySeconds: 15
|
||||
periodSeconds: 20
|
||||
name: manager
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /readyz
|
||||
port: 8081
|
||||
initialDelaySeconds: 5
|
||||
periodSeconds: 10
|
||||
resources: {{- toYaml .Values.operator.resources | nindent 10 }}
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
imagePullSecrets:
|
||||
{{- range .Values.operator.image.pullSecrets }}
|
||||
- name: {{ . }}
|
||||
{{- end }}
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
runAsNonRoot: true
|
||||
serviceAccountName: k8s-nim-operator
|
||||
terminationGracePeriodSeconds: 10
|
||||
{{- with .Values.operator.nodeSelector }}
|
||||
nodeSelector:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.operator.affinity }}
|
||||
affinity:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
{{- with .Values.operator.tolerations }}
|
||||
tolerations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
+59
@@ -0,0 +1,59 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: Role
|
||||
metadata:
|
||||
name: k8s-nim-operator-leader-election-role
|
||||
labels:
|
||||
app.kubernetes.io/component: rbac
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- configmaps
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- create
|
||||
- update
|
||||
- patch
|
||||
- delete
|
||||
- apiGroups:
|
||||
- coordination.k8s.io
|
||||
resources:
|
||||
- leases
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- create
|
||||
- update
|
||||
- patch
|
||||
- delete
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- events
|
||||
verbs:
|
||||
- create
|
||||
- patch
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: RoleBinding
|
||||
metadata:
|
||||
name: k8s-nim-operator-leader-election-rolebinding
|
||||
labels:
|
||||
app.kubernetes.io/component: rbac
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: Role
|
||||
name: k8s-nim-operator-leader-election-role
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: k8s-nim-operator
|
||||
namespace: '{{ .Release.Namespace }}'
|
||||
@@ -0,0 +1,315 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: k8s-nim-operator-role
|
||||
labels:
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
rules:
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- nodes
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- configmaps
|
||||
- persistentvolumeclaims
|
||||
- secrets
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- events
|
||||
verbs:
|
||||
- create
|
||||
- update
|
||||
- patch
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- endpoints
|
||||
- pods
|
||||
- pods/log
|
||||
- pods/eviction
|
||||
- serviceaccounts
|
||||
- services
|
||||
- services/finalizers
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- pods
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps
|
||||
resources:
|
||||
- deployments
|
||||
- statefulsets
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimcaches
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimcaches/finalizers
|
||||
verbs:
|
||||
- update
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimcaches/status
|
||||
verbs:
|
||||
- get
|
||||
- patch
|
||||
- update
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimpipelines
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimpipelines/finalizers
|
||||
verbs:
|
||||
- update
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimpipelines/status
|
||||
verbs:
|
||||
- get
|
||||
- patch
|
||||
- update
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimservices
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimservices/finalizers
|
||||
verbs:
|
||||
- update
|
||||
- apiGroups:
|
||||
- apps.nvidia.com
|
||||
resources:
|
||||
- nimservices/status
|
||||
verbs:
|
||||
- get
|
||||
- patch
|
||||
- update
|
||||
- apiGroups:
|
||||
- batch
|
||||
resources:
|
||||
- jobs
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- config.openshift.io
|
||||
resources:
|
||||
- clusterversions
|
||||
- proxies
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- ""
|
||||
resources:
|
||||
- persistentvolumeclaims
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- apiGroups:
|
||||
- monitoring.coreos.com
|
||||
resources:
|
||||
- prometheusrules
|
||||
- servicemonitors
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- rbac.authorization.k8s.io
|
||||
resources:
|
||||
- rolebindings
|
||||
- roles
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- route.openshift.io
|
||||
resources:
|
||||
- routes
|
||||
verbs:
|
||||
- create
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- networking.k8s.io
|
||||
resources:
|
||||
- ingresses
|
||||
verbs:
|
||||
- create
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- delete
|
||||
- apiGroups:
|
||||
- autoscaling
|
||||
resources:
|
||||
- horizontalpodautoscalers
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- scheduling.k8s.io
|
||||
resources:
|
||||
- priorityclasses
|
||||
verbs:
|
||||
- create
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- security.openshift.io
|
||||
resourceNames:
|
||||
- nonroot
|
||||
resources:
|
||||
- securitycontextconstraints
|
||||
verbs:
|
||||
- use
|
||||
- apiGroups:
|
||||
- security.openshift.io
|
||||
resources:
|
||||
- securitycontextconstraints
|
||||
verbs:
|
||||
- create
|
||||
- delete
|
||||
- get
|
||||
- list
|
||||
- patch
|
||||
- update
|
||||
- watch
|
||||
- apiGroups:
|
||||
- storage.k8s.io
|
||||
resources:
|
||||
- storageclasses
|
||||
verbs:
|
||||
- get
|
||||
- list
|
||||
- watch
|
||||
- apiGroups:
|
||||
- authentication.k8s.io
|
||||
resources:
|
||||
- tokenreviews
|
||||
verbs:
|
||||
- create
|
||||
- apiGroups:
|
||||
- authorization.k8s.io
|
||||
resources:
|
||||
- subjectaccessreviews
|
||||
verbs:
|
||||
- create
|
||||
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRoleBinding
|
||||
metadata:
|
||||
name: k8s-nim-operator-rolebinding
|
||||
labels:
|
||||
app.kubernetes.io/component: rbac
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
roleRef:
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
kind: ClusterRole
|
||||
name: k8s-nim-operator-role
|
||||
subjects:
|
||||
- kind: ServiceAccount
|
||||
name: k8s-nim-operator
|
||||
namespace: {{ .Release.Namespace }}
|
||||
@@ -0,0 +1,14 @@
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: k8s-nim-operator-metrics-reader
|
||||
labels:
|
||||
app.kubernetes.io/component: kube-rbac-proxy
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
rules:
|
||||
- nonResourceURLs:
|
||||
- /metrics
|
||||
verbs:
|
||||
- get
|
||||
@@ -0,0 +1,17 @@
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: k8s-nim-operator-metrics-service
|
||||
labels:
|
||||
app.kubernetes.io/component: kube-rbac-proxy
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
control-plane: controller-manager
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
spec:
|
||||
type: {{ .Values.metricsService.type }}
|
||||
selector:
|
||||
control-plane: controller-manager
|
||||
{{- include "k8s-nim-operator.selectorLabels" . | nindent 4 }}
|
||||
ports:
|
||||
{{- .Values.metricsService.ports | toYaml | nindent 2 -}}
|
||||
@@ -0,0 +1,17 @@
|
||||
{{- if .Values.nfd.nodeFeatureRules.deviceID }}
|
||||
kind: NodeFeatureRule
|
||||
apiVersion: nfd.k8s-sigs.io/v1alpha1
|
||||
metadata:
|
||||
name: nfd-pci-device-rule
|
||||
spec:
|
||||
rules:
|
||||
- name: "NVIDIA PCIe Device Label"
|
||||
labelsTemplate: |
|
||||
{{`{{ range .pci.device }}pci-{{ .vendor }}-{{ .device }}.present=true`}}
|
||||
{{`{{ end }}`}}
|
||||
matchFeatures:
|
||||
- feature: pci.device
|
||||
matchExpressions:
|
||||
vendor: {op: In, value: ["10de"]}
|
||||
class: {op: In, value: ["0300", "0302"]}
|
||||
{{- end }}
|
||||
@@ -0,0 +1,11 @@
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: k8s-nim-operator
|
||||
labels:
|
||||
app.kubernetes.io/component: rbac
|
||||
app.kubernetes.io/created-by: k8s-nim-operator
|
||||
app.kubernetes.io/part-of: k8s-nim-operator
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
annotations:
|
||||
{{- toYaml .Values.operator.annotations | nindent 4 }}
|
||||
@@ -0,0 +1,100 @@
|
||||
{{- if .Values.operator.upgradeCRD }}
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: ServiceAccount
|
||||
metadata:
|
||||
name: nim-operator-upgrade-crd-hook-sa
|
||||
annotations:
|
||||
helm.sh/hook: pre-upgrade
|
||||
helm.sh/hook-delete-policy: hook-succeeded,before-hook-creation
|
||||
helm.sh/hook-weight: "0"
|
||||
---
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
kind: ClusterRole
|
||||
metadata:
|
||||
name: nim-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
|
||||
---
|
||||
kind: ClusterRoleBinding
|
||||
apiVersion: rbac.authorization.k8s.io/v1
|
||||
metadata:
|
||||
name: nim-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: nim-operator-upgrade-crd-hook-sa
|
||||
namespace: {{ .Release.Namespace }}
|
||||
roleRef:
|
||||
kind: ClusterRole
|
||||
name: nim-operator-upgrade-crd-hook-role
|
||||
apiGroup: rbac.authorization.k8s.io
|
||||
---
|
||||
apiVersion: batch/v1
|
||||
kind: Job
|
||||
metadata:
|
||||
name: nim-operator-upgrade-crd
|
||||
namespace: {{ .Release.Namespace }}
|
||||
annotations:
|
||||
"helm.sh/hook": pre-upgrade
|
||||
"helm.sh/hook-weight": "1"
|
||||
"helm.sh/hook-delete-policy": hook-succeeded,before-hook-creation
|
||||
labels:
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 4 }}
|
||||
app.kubernetes.io/component: "nim-operator"
|
||||
spec:
|
||||
template:
|
||||
metadata:
|
||||
name: nim-operator-upgrade-crd
|
||||
labels:
|
||||
{{- include "k8s-nim-operator.labels" . | nindent 8 }}
|
||||
app.kubernetes.io/component: "nim-operator"
|
||||
spec:
|
||||
serviceAccountName: nim-operator-upgrade-crd-hook-sa
|
||||
{{- if .Values.operator.image.pullSecrets }}
|
||||
imagePullSecrets:
|
||||
{{- range .Values.operator.image.pullSecrets }}
|
||||
- name: {{ . }}
|
||||
{{- end }}
|
||||
{{- end }}
|
||||
{{- with .Values.operator.tolerations }}
|
||||
securityContext:
|
||||
seccompProfile:
|
||||
type: RuntimeDefault
|
||||
runAsNonRoot: true
|
||||
tolerations:
|
||||
{{- toYaml . | nindent 8 }}
|
||||
{{- end }}
|
||||
containers:
|
||||
- name: upgrade-crd
|
||||
image: {{ include "k8s-nim-operator.fullimage" . }}
|
||||
imagePullPolicy: {{ .Values.operator.image.pullPolicy }}
|
||||
securityContext:
|
||||
allowPrivilegeEscalation: false
|
||||
capabilities:
|
||||
drop:
|
||||
- ALL
|
||||
command: ["kubectl"]
|
||||
args:
|
||||
- "apply"
|
||||
- "-f"
|
||||
- "/opt/nim-operator/crds/*.yaml"
|
||||
restartPolicy: OnFailure
|
||||
{{- end }}
|
||||
@@ -0,0 +1,46 @@
|
||||
operator:
|
||||
replicas: 1
|
||||
upgradeCRD: true
|
||||
image:
|
||||
repository: nvcr.io/nvidia/cloud-native/k8s-nim-operator
|
||||
tag: v1.0.1
|
||||
pullSecrets: []
|
||||
pullPolicy: Always
|
||||
args:
|
||||
- --health-probe-bind-address=:8081
|
||||
- --metrics-bind-address=:8080
|
||||
- --leader-elect
|
||||
resources:
|
||||
limits:
|
||||
cpu: "1"
|
||||
memory: 256Mi
|
||||
requests:
|
||||
cpu: 500m
|
||||
memory: 128Mi
|
||||
nodeSelector: {}
|
||||
annotations: {}
|
||||
tolerations:
|
||||
- key: "node-role.kubernetes.io/control-plane"
|
||||
operator: "Equal"
|
||||
value: ""
|
||||
effect: "NoSchedule"
|
||||
affinity:
|
||||
nodeAffinity:
|
||||
preferredDuringSchedulingIgnoredDuringExecution:
|
||||
- weight: 1
|
||||
preference:
|
||||
matchExpressions:
|
||||
- key: "node-role.kubernetes.io/control-plane"
|
||||
operator: In
|
||||
values: [""]
|
||||
|
||||
metricsService:
|
||||
ports:
|
||||
- name: metrics
|
||||
port: 8080
|
||||
protocol: TCP
|
||||
type: ClusterIP
|
||||
|
||||
nfd:
|
||||
nodeFeatureRules:
|
||||
deviceID: true
|
||||
Reference in New Issue
Block a user