Make the gpus selectable

Signed-off-by: Martyn Ranyard <m@rtyn.berlin>
This commit is contained in:
Martyn 2024-02-21 14:45:29 +00:00
parent 353c5c4171
commit 9ce01b80d7
24 changed files with 2305 additions and 4 deletions

View File

@ -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/

View File

@ -0,0 +1,14 @@
apiVersion: v2
appVersion: v0.14.3
description: 'Detects hardware features available on each node in a Kubernetes cluster,
and advertises those features using node labels. '
home: https://github.com/kubernetes-sigs/node-feature-discovery
keywords:
- feature-discovery
- feature-detection
- node-labels
name: node-feature-discovery
sources:
- https://github.com/kubernetes-sigs/node-feature-discovery
type: application
version: 0.14.3

View File

@ -0,0 +1,10 @@
# Node Feature Discovery
Node Feature Discovery (NFD) is a Kubernetes add-on for detecting hardware
features and system configuration. Detected features are advertised as node
labels. NFD provides flexible configuration and extension points for a wide
range of vendor and application specific node labeling needs.
See
[NFD documentation](https://kubernetes-sigs.github.io/node-feature-discovery/v0.14/deployment/helm.html)
for deployment instructions.

View File

@ -0,0 +1,361 @@
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.12.1
name: nodefeatures.nfd.k8s-sigs.io
spec:
group: nfd.k8s-sigs.io
names:
kind: NodeFeature
listKind: NodeFeatureList
plural: nodefeatures
singular: nodefeature
scope: Namespaced
versions:
- name: v1alpha1
schema:
openAPIV3Schema:
description: NodeFeature resource holds the features discovered for one node
in the cluster.
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: NodeFeatureSpec describes a NodeFeature object.
properties:
features:
description: Features is the full "raw" features data that has been
discovered.
properties:
attributes:
additionalProperties:
description: AttributeFeatureSet is a set of features having
string value.
properties:
elements:
additionalProperties:
type: string
type: object
required:
- elements
type: object
description: Attributes contains all the attribute-type features
of the node.
type: object
flags:
additionalProperties:
description: FlagFeatureSet is a set of simple features only
containing names without values.
properties:
elements:
additionalProperties:
description: Nil is a dummy empty struct for protobuf
compatibility
type: object
type: object
required:
- elements
type: object
description: Flags contains all the flag-type features of the
node.
type: object
instances:
additionalProperties:
description: InstanceFeatureSet is a set of features each of
which is an instance having multiple attributes.
properties:
elements:
items:
description: InstanceFeature represents one instance of
a complex features, e.g. a device.
properties:
attributes:
additionalProperties:
type: string
type: object
required:
- attributes
type: object
type: array
required:
- elements
type: object
description: Instances contains all the instance-type features
of the node.
type: object
type: object
labels:
additionalProperties:
type: string
description: Labels is the set of node labels that are requested to
be created.
type: object
type: object
required:
- spec
type: object
served: true
storage: true
---
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
controller-gen.kubebuilder.io/version: v0.12.1
name: nodefeaturerules.nfd.k8s-sigs.io
spec:
group: nfd.k8s-sigs.io
names:
kind: NodeFeatureRule
listKind: NodeFeatureRuleList
plural: nodefeaturerules
shortNames:
- nfr
singular: nodefeaturerule
scope: Cluster
versions:
- name: v1alpha1
schema:
openAPIV3Schema:
description: NodeFeatureRule resource specifies a configuration for feature-based
customization of node objects, such as node labeling.
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: NodeFeatureRuleSpec describes a NodeFeatureRule.
properties:
rules:
description: Rules is a list of node customization rules.
items:
description: Rule defines a rule for node customization such as
labeling.
properties:
extendedResources:
additionalProperties:
type: string
description: ExtendedResources to create if the rule matches.
type: object
labels:
additionalProperties:
type: string
description: Labels to create if the rule matches.
type: object
labelsTemplate:
description: LabelsTemplate specifies a template to expand for
dynamically generating multiple labels. Data (after template
expansion) must be keys with an optional value (<key>[=<value>])
separated by newlines.
type: string
matchAny:
description: MatchAny specifies a list of matchers one of which
must match.
items:
description: MatchAnyElem specifies one sub-matcher of MatchAny.
properties:
matchFeatures:
description: MatchFeatures specifies a set of matcher
terms all of which must match.
items:
description: FeatureMatcherTerm defines requirements
against one feature set. All requirements (specified
as MatchExpressions) are evaluated against each element
in the feature set.
properties:
feature:
type: string
matchExpressions:
additionalProperties:
description: "MatchExpression specifies an expression
to evaluate against a set of input values. It
contains an operator that is applied when matching
the input and an array of values that the operator
evaluates the input against. \n NB: CreateMatchExpression
or MustCreateMatchExpression() should be used
for creating new instances. \n NB: Validate()
must be called if Op or Value fields are modified
or if a new instance is created from scratch
without using the helper functions."
properties:
op:
description: Op is the operator to be applied.
enum:
- In
- NotIn
- InRegexp
- Exists
- DoesNotExist
- Gt
- Lt
- GtLt
- IsTrue
- IsFalse
type: string
value:
description: Value is the list of values that
the operand evaluates the input against.
Value should be empty if the operator is
Exists, DoesNotExist, IsTrue or IsFalse.
Value should contain exactly one element
if the operator is Gt or Lt and exactly
two elements if the operator is GtLt. In
other cases Value should contain at least
one element.
items:
type: string
type: array
required:
- op
type: object
description: MatchExpressionSet contains a set of
MatchExpressions, each of which is evaluated against
a set of input values.
type: object
required:
- feature
- matchExpressions
type: object
type: array
required:
- matchFeatures
type: object
type: array
matchFeatures:
description: MatchFeatures specifies a set of matcher terms
all of which must match.
items:
description: FeatureMatcherTerm defines requirements against
one feature set. All requirements (specified as MatchExpressions)
are evaluated against each element in the feature set.
properties:
feature:
type: string
matchExpressions:
additionalProperties:
description: "MatchExpression specifies an expression
to evaluate against a set of input values. It contains
an operator that is applied when matching the input
and an array of values that the operator evaluates
the input against. \n NB: CreateMatchExpression or
MustCreateMatchExpression() should be used for creating
new instances. \n NB: Validate() must be called if
Op or Value fields are modified or if a new instance
is created from scratch without using the helper functions."
properties:
op:
description: Op is the operator to be applied.
enum:
- In
- NotIn
- InRegexp
- Exists
- DoesNotExist
- Gt
- Lt
- GtLt
- IsTrue
- IsFalse
type: string
value:
description: Value is the list of values that the
operand evaluates the input against. Value should
be empty if the operator is Exists, DoesNotExist,
IsTrue or IsFalse. Value should contain exactly
one element if the operator is Gt or Lt and exactly
two elements if the operator is GtLt. In other
cases Value should contain at least one element.
items:
type: string
type: array
required:
- op
type: object
description: MatchExpressionSet contains a set of MatchExpressions,
each of which is evaluated against a set of input values.
type: object
required:
- feature
- matchExpressions
type: object
type: array
name:
description: Name of the rule.
type: string
taints:
description: Taints to create if the rule matches.
items:
description: The node this Taint is attached to has the "effect"
on any pod that does not tolerate the Taint.
properties:
effect:
description: Required. The effect of the taint on pods
that do not tolerate the taint. Valid effects are NoSchedule,
PreferNoSchedule and NoExecute.
type: string
key:
description: Required. The taint key to be applied to
a node.
type: string
timeAdded:
description: TimeAdded represents the time at which the
taint was added. It is only written for NoExecute taints.
format: date-time
type: string
value:
description: The taint value corresponding to the taint
key.
type: string
required:
- effect
- key
type: object
type: array
vars:
additionalProperties:
type: string
description: Vars is the variables to store if the rule matches.
Variables do not directly inflict any changes in the node
object. However, they can be referenced from other rules enabling
more complex rule hierarchies, without exposing intermediary
output values as labels.
type: object
varsTemplate:
description: VarsTemplate specifies a template to expand for
dynamically generating multiple variables. Data (after template
expansion) must be keys with an optional value (<key>[=<value>])
separated by newlines.
type: string
required:
- name
type: object
type: array
required:
- rules
type: object
required:
- spec
type: object
served: true
storage: true

View File

@ -0,0 +1,107 @@
{{/* vim: set filetype=mustache: */}}
{{/*
Expand the name of the chart.
*/}}
{{- define "node-feature-discovery.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 "node-feature-discovery.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 -}}
{{/*
Allow the release namespace to be overridden for multi-namespace deployments in combined charts
*/}}
{{- define "node-feature-discovery.namespace" -}}
{{- if .Values.namespaceOverride -}}
{{- .Values.namespaceOverride -}}
{{- else -}}
{{- .Release.Namespace -}}
{{- end -}}
{{- end -}}
{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "node-feature-discovery.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" -}}
{{- end -}}
{{/*
Common labels
*/}}
{{- define "node-feature-discovery.labels" -}}
helm.sh/chart: {{ include "node-feature-discovery.chart" . }}
{{ include "node-feature-discovery.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end -}}
{{/*
Selector labels
*/}}
{{- define "node-feature-discovery.selectorLabels" -}}
app.kubernetes.io/name: {{ include "node-feature-discovery.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end -}}
{{/*
Create the name of the service account which the nfd master will use
*/}}
{{- define "node-feature-discovery.master.serviceAccountName" -}}
{{- if .Values.master.serviceAccount.create -}}
{{ default (include "node-feature-discovery.fullname" .) .Values.master.serviceAccount.name }}
{{- else -}}
{{ default "default" .Values.master.serviceAccount.name }}
{{- end -}}
{{- end -}}
{{/*
Create the name of the service account which the nfd worker will use
*/}}
{{- define "node-feature-discovery.worker.serviceAccountName" -}}
{{- if .Values.worker.serviceAccount.create -}}
{{ default (printf "%s-worker" (include "node-feature-discovery.fullname" .)) .Values.worker.serviceAccount.name }}
{{- else -}}
{{ default "default" .Values.worker.serviceAccount.name }}
{{- end -}}
{{- end -}}
{{/*
Create the name of the service account which topologyUpdater will use
*/}}
{{- define "node-feature-discovery.topologyUpdater.serviceAccountName" -}}
{{- if .Values.topologyUpdater.serviceAccount.create -}}
{{ default (printf "%s-topology-updater" (include "node-feature-discovery.fullname" .)) .Values.topologyUpdater.serviceAccount.name }}
{{- else -}}
{{ default "default" .Values.topologyUpdater.serviceAccount.name }}
{{- end -}}
{{- end -}}
{{/*
Create the name of the service account which nfd-gc will use
*/}}
{{- define "node-feature-discovery.gc.serviceAccountName" -}}
{{- if .Values.gc.serviceAccount.create -}}
{{ default (printf "%s-gc" (include "node-feature-discovery.fullname" .)) .Values.gc.serviceAccount.name }}
{{- else -}}
{{ default "default" .Values.gc.serviceAccount.name }}
{{- end -}}
{{- end -}}

View File

@ -0,0 +1,67 @@
{{- if .Values.tls.certManager }}
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: nfd-master-cert
namespace: {{ include "node-feature-discovery.namespace" . }}
spec:
secretName: nfd-master-cert
subject:
organizations:
- node-feature-discovery
commonName: nfd-master
dnsNames:
# must match the service name
- {{ include "node-feature-discovery.fullname" . }}-master
# first one is configured for use by the worker; below are for completeness
- {{ include "node-feature-discovery.fullname" . }}-master.{{ include "node-feature-discovery.namespace" . }}.svc
- {{ include "node-feature-discovery.fullname" . }}-master.{{ include "node-feature-discovery.namespace" . }}.svc.cluster.local
# localhost needed for grpc_health_probe
- localhost
issuerRef:
name: nfd-ca-issuer
kind: Issuer
group: cert-manager.io
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: nfd-worker-cert
namespace: {{ include "node-feature-discovery.namespace" . }}
spec:
secretName: nfd-worker-cert
subject:
organizations:
- node-feature-discovery
commonName: nfd-worker
dnsNames:
- {{ include "node-feature-discovery.fullname" . }}-worker.{{ include "node-feature-discovery.namespace" . }}.svc.cluster.local
issuerRef:
name: nfd-ca-issuer
kind: Issuer
group: cert-manager.io
{{- if .Values.topologyUpdater.enable }}
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: nfd-topology-updater-cert
namespace: {{ include "node-feature-discovery.namespace" . }}
spec:
secretName: nfd-topology-updater-cert
subject:
organizations:
- node-feature-discovery
commonName: nfd-topology-updater
dnsNames:
- {{ include "node-feature-discovery.fullname" . }}-topology-updater.{{ include "node-feature-discovery.namespace" . }}.svc.cluster.local
issuerRef:
name: nfd-ca-issuer
kind: Issuer
group: cert-manager.io
{{- end }}
{{- end }}

View File

@ -0,0 +1,42 @@
{{- if .Values.tls.certManager }}
# See https://cert-manager.io/docs/configuration/selfsigned/#bootstrapping-ca-issuers
# - Create a self signed issuer
# - Use this to create a CA cert
# - Use this to now create a CA issuer
---
apiVersion: cert-manager.io/v1
kind: Issuer
metadata:
name: nfd-ca-bootstrap
namespace: {{ include "node-feature-discovery.namespace" . }}
spec:
selfSigned: {}
---
apiVersion: cert-manager.io/v1
kind: Certificate
metadata:
name: nfd-ca-cert
namespace: {{ include "node-feature-discovery.namespace" . }}
spec:
isCA: true
secretName: nfd-ca-cert
subject:
organizations:
- node-feature-discovery
commonName: nfd-ca-cert
issuerRef:
name: nfd-ca-bootstrap
kind: Issuer
group: cert-manager.io
---
apiVersion: cert-manager.io/v1
kind: Issuer
metadata:
name: nfd-ca-issuer
namespace: {{ include "node-feature-discovery.namespace" . }}
spec:
ca:
secretName: nfd-ca-cert
{{- end }}

View File

@ -0,0 +1,119 @@
{{- if .Values.master.rbac.create }}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: {{ include "node-feature-discovery.fullname" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
rules:
- apiGroups:
- ""
resources:
- nodes
- nodes/status
verbs:
- get
- patch
- update
- list
- apiGroups:
- nfd.k8s-sigs.io
resources:
- nodefeatures
- nodefeaturerules
verbs:
- get
- list
- watch
- apiGroups:
- coordination.k8s.io
resources:
- leases
verbs:
- create
- apiGroups:
- coordination.k8s.io
resources:
- leases
resourceNames:
- "nfd-master.nfd.kubernetes.io"
verbs:
- get
- update
{{- end }}
{{- if and .Values.topologyUpdater.enable .Values.topologyUpdater.rbac.create }}
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-topology-updater
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
rules:
- apiGroups:
- ""
resources:
- nodes
verbs:
- get
- list
- apiGroups:
- ""
resources:
- nodes/proxy
verbs:
- get
- apiGroups:
- ""
resources:
- pods
verbs:
- get
- apiGroups:
- topology.node.k8s.io
resources:
- noderesourcetopologies
verbs:
- create
- get
- update
{{- end }}
{{- if and .Values.gc.enable .Values.gc.rbac.create (or .Values.enableNodeFeatureApi .Values.topologyUpdater.enable) }}
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRole
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-gc
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
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
{{- end }}

View File

@ -0,0 +1,52 @@
{{- if .Values.master.rbac.create }}
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: {{ include "node-feature-discovery.fullname" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: {{ include "node-feature-discovery.fullname" . }}
subjects:
- kind: ServiceAccount
name: {{ include "node-feature-discovery.master.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
{{- end }}
{{- if and .Values.topologyUpdater.enable .Values.topologyUpdater.rbac.create }}
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-topology-updater
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: {{ include "node-feature-discovery.fullname" . }}-topology-updater
subjects:
- kind: ServiceAccount
name: {{ include "node-feature-discovery.topologyUpdater.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
{{- end }}
{{- if and .Values.gc.enable .Values.gc.rbac.create (or .Values.enableNodeFeatureApi .Values.topologyUpdater.enable) }}
---
apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-gc
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: {{ include "node-feature-discovery.fullname" . }}-gc
subjects:
- kind: ServiceAccount
name: {{ include "node-feature-discovery.gc.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
{{- end }}

View File

@ -0,0 +1,159 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-master
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
role: master
{{- with .Values.master.deploymentAnnotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
replicas: {{ .Values.master.replicaCount }}
selector:
matchLabels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 6 }}
role: master
template:
metadata:
labels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 8 }}
role: master
{{- with .Values.master.annotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "node-feature-discovery.master.serviceAccountName" . }}
enableServiceLinks: false
securityContext:
{{- toYaml .Values.master.podSecurityContext | nindent 8 }}
containers:
- name: master
securityContext:
{{- toYaml .Values.master.securityContext | nindent 12 }}
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
livenessProbe:
exec:
command:
- "/usr/bin/grpc_health_probe"
- "-addr=:{{ .Values.master.port | default "8080" }}"
{{- if .Values.tls.enable }}
- "-tls"
- "-tls-ca-cert=/etc/kubernetes/node-feature-discovery/certs/ca.crt"
- "-tls-client-key=/etc/kubernetes/node-feature-discovery/certs/tls.key"
- "-tls-client-cert=/etc/kubernetes/node-feature-discovery/certs/tls.crt"
{{- end }}
initialDelaySeconds: 10
periodSeconds: 10
readinessProbe:
exec:
command:
- "/usr/bin/grpc_health_probe"
- "-addr=:{{ .Values.master.port | default "8080" }}"
{{- if .Values.tls.enable }}
- "-tls"
- "-tls-ca-cert=/etc/kubernetes/node-feature-discovery/certs/ca.crt"
- "-tls-client-key=/etc/kubernetes/node-feature-discovery/certs/tls.key"
- "-tls-client-cert=/etc/kubernetes/node-feature-discovery/certs/tls.crt"
{{- end }}
initialDelaySeconds: 5
periodSeconds: 10
failureThreshold: 10
ports:
- containerPort: {{ .Values.master.port | default "8080" }}
name: grpc
- containerPort: {{ .Values.master.metricsPort | default "8081" }}
name: metrics
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
command:
- "nfd-master"
resources:
{{- toYaml .Values.master.resources | nindent 12 }}
args:
{{- if .Values.master.instance | empty | not }}
- "-instance={{ .Values.master.instance }}"
{{- end }}
- "-port={{ .Values.master.port | default "8080" }}"
{{- if not .Values.enableNodeFeatureApi }}
- "-enable-nodefeature-api=false"
{{- else if gt (int .Values.master.replicaCount) 1 }}
- "-enable-leader-election"
{{- end }}
{{- if .Values.master.extraLabelNs | empty | not }}
- "-extra-label-ns={{- join "," .Values.master.extraLabelNs }}"
{{- end }}
{{- if .Values.master.denyLabelNs | empty | not }}
- "-deny-label-ns={{- join "," .Values.master.denyLabelNs }}"
{{- end }}
{{- if .Values.master.resourceLabels | empty | not }}
- "-resource-labels={{- join "," .Values.master.resourceLabels }}"
{{- end }}
{{- if .Values.master.enableTaints }}
- "-enable-taints"
{{- end }}
{{- if .Values.master.crdController | kindIs "invalid" | not }}
- "-crd-controller={{ .Values.master.crdController }}"
{{- else }}
## By default, disable crd controller for other than the default instances
- "-crd-controller={{ .Values.master.instance | empty }}"
{{- end }}
{{- if .Values.master.featureRulesController | kindIs "invalid" | not }}
- "-featurerules-controller={{ .Values.master.featureRulesController }}"
{{- end }}
{{- if .Values.master.resyncPeriod }}
- "-resync-period={{ .Values.master.resyncPeriod }}"
{{- end }}
{{- if .Values.master.nfdApiParallelism | empty | not }}
- "-nfd-api-parallelism={{ .Values.master.nfdApiParallelism }}"
{{- end }}
{{- if .Values.tls.enable }}
- "-ca-file=/etc/kubernetes/node-feature-discovery/certs/ca.crt"
- "-key-file=/etc/kubernetes/node-feature-discovery/certs/tls.key"
- "-cert-file=/etc/kubernetes/node-feature-discovery/certs/tls.crt"
{{- end }}
- "-metrics={{ .Values.master.metricsPort | default "8081" }}"
volumeMounts:
{{- if .Values.tls.enable }}
- name: nfd-master-cert
mountPath: "/etc/kubernetes/node-feature-discovery/certs"
readOnly: true
{{- end }}
- name: nfd-master-conf
mountPath: "/etc/kubernetes/node-feature-discovery"
readOnly: true
volumes:
{{- if .Values.tls.enable }}
- name: nfd-master-cert
secret:
secretName: nfd-master-cert
{{- end }}
- name: nfd-master-conf
configMap:
name: {{ include "node-feature-discovery.fullname" . }}-master-conf
items:
- key: nfd-master.conf
path: nfd-master.conf
{{- with .Values.master.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.master.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.master.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}

View File

@ -0,0 +1,74 @@
{{- if and .Values.gc.enable (or .Values.enableNodeFeatureApi .Values.topologyUpdater.enable) -}}
apiVersion: apps/v1
kind: Deployment
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-gc
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
role: gc
{{- with .Values.gc.deploymentAnnotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
replicas: {{ .Values.gc.replicaCount | default 1 }}
selector:
matchLabels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 6 }}
role: gc
template:
metadata:
labels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 8 }}
role: gc
{{- with .Values.gc.annotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
serviceAccountName: {{ include "node-feature-discovery.gc.serviceAccountName" . }}
dnsPolicy: ClusterFirstWithHostNet
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
securityContext:
{{- toYaml .Values.gc.podSecurityContext | nindent 8 }}
containers:
- name: gc
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: "{{ .Values.image.pullPolicy }}"
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
command:
- "nfd-gc"
args:
{{- if .Values.gc.interval | empty | not }}
- "-gc-interval={{ .Values.gc.interval }}"
{{- end }}
resources:
{{- toYaml .Values.gc.resources | nindent 12 }}
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: [ "ALL" ]
readOnlyRootFilesystem: true
runAsNonRoot: true
{{- with .Values.gc.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.gc.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.gc.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,10 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-master-conf
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
data:
nfd-master.conf: |-
{{- .Values.master.config | toYaml | nindent 4 }}

View File

@ -0,0 +1,10 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-topology-updater-conf
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
data:
nfd-topology-updater.conf: |-
{{- .Values.topologyUpdater.config | toYaml | nindent 4 }}

View File

@ -0,0 +1,10 @@
apiVersion: v1
kind: ConfigMap
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-worker-conf
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
data:
nfd-worker.conf: |-
{{- .Values.worker.config | toYaml | nindent 4 }}

View File

@ -0,0 +1,26 @@
{{- if .Values.prometheus.enable }}
# Prometheus Monitor Service (Metrics)
apiVersion: monitoring.coreos.com/v1
kind: PodMonitor
metadata:
name: {{ include "node-feature-discovery.fullname" . }}
labels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 4 }}
{{- with .Values.prometheus.labels }}
{{ toYaml . | nindent 4 }}
{{- end }}
spec:
podMetricsEndpoints:
- honorLabels: true
interval: 10s
path: /metrics
port: metrics
scheme: http
namespaceSelector:
matchNames:
- {{ include "node-feature-discovery.namespace" . }}
selector:
matchExpressions:
- {key: app.kubernetes.io/instance, operator: In, values: ["{{ .Release.Name }}"]}
- {key: app.kubernetes.io/name, operator: In, values: ["{{ include "node-feature-discovery.name" . }}"]}
{{- end }}

View File

@ -0,0 +1,19 @@
{{- if .Values.worker.rbac.create }}
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-worker
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
rules:
- apiGroups:
- nfd.k8s-sigs.io
resources:
- nodefeatures
verbs:
- create
- get
- update
{{- end }}

View File

@ -0,0 +1,18 @@
{{- if .Values.worker.rbac.create }}
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-worker
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: {{ include "node-feature-discovery.fullname" . }}-worker
subjects:
- kind: ServiceAccount
name: {{ include "node-feature-discovery.worker.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
{{- end }}

View File

@ -0,0 +1,18 @@
apiVersion: v1
kind: Service
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-master
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
role: master
spec:
type: {{ .Values.master.service.type }}
ports:
- port: {{ .Values.master.service.port | default "8080" }}
targetPort: grpc
protocol: TCP
name: grpc
selector:
{{- include "node-feature-discovery.selectorLabels" . | nindent 4 }}
role: master

View File

@ -0,0 +1,58 @@
{{- if .Values.master.serviceAccount.create -}}
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "node-feature-discovery.master.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
{{- with .Values.master.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- end }}
{{- if and .Values.topologyUpdater.enable .Values.topologyUpdater.serviceAccount.create }}
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "node-feature-discovery.topologyUpdater.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
{{- with .Values.topologyUpdater.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- end }}
{{- if and .Values.gc.enable .Values.gc.serviceAccount.create (or .Values.enableNodeFeatureApi .Values.topologyUpdater.enable) }}
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "node-feature-discovery.gc.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
{{- with .Values.gc.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- end }}
{{- if .Values.worker.serviceAccount.create }}
---
apiVersion: v1
kind: ServiceAccount
metadata:
name: {{ include "node-feature-discovery.worker.serviceAccountName" . }}
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
{{- with .Values.worker.serviceAccount.annotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,278 @@
{{- if and .Values.topologyUpdater.enable .Values.topologyUpdater.createCRDs -}}
apiVersion: apiextensions.k8s.io/v1
kind: CustomResourceDefinition
metadata:
annotations:
api-approved.kubernetes.io: https://github.com/kubernetes/enhancements/pull/1870
controller-gen.kubebuilder.io/version: v0.11.2
creationTimestamp: null
name: noderesourcetopologies.topology.node.k8s.io
spec:
group: topology.node.k8s.io
names:
kind: NodeResourceTopology
listKind: NodeResourceTopologyList
plural: noderesourcetopologies
shortNames:
- node-res-topo
singular: noderesourcetopology
scope: Cluster
versions:
- name: v1alpha1
schema:
openAPIV3Schema:
description: NodeResourceTopology describes node resources and their topology.
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
topologyPolicies:
items:
type: string
type: array
zones:
description: ZoneList contains an array of Zone objects.
items:
description: Zone represents a resource topology zone, e.g. socket,
node, die or core.
properties:
attributes:
description: AttributeList contains an array of AttributeInfo objects.
items:
description: AttributeInfo contains one attribute of a Zone.
properties:
name:
type: string
value:
type: string
required:
- name
- value
type: object
type: array
costs:
description: CostList contains an array of CostInfo objects.
items:
description: CostInfo describes the cost (or distance) between
two Zones.
properties:
name:
type: string
value:
format: int64
type: integer
required:
- name
- value
type: object
type: array
name:
type: string
parent:
type: string
resources:
description: ResourceInfoList contains an array of ResourceInfo
objects.
items:
description: ResourceInfo contains information about one resource
type.
properties:
allocatable:
anyOf:
- type: integer
- type: string
description: Allocatable quantity of the resource, corresponding
to allocatable in node status, i.e. total amount of this
resource available to be used by pods.
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
available:
anyOf:
- type: integer
- type: string
description: Available is the amount of this resource currently
available for new (to be scheduled) pods, i.e. Allocatable
minus the resources reserved by currently running pods.
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
capacity:
anyOf:
- type: integer
- type: string
description: Capacity of the resource, corresponding to capacity
in node status, i.e. total amount of this resource that
the node has.
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
name:
description: Name of the resource.
type: string
required:
- allocatable
- available
- capacity
- name
type: object
type: array
type:
type: string
required:
- name
- type
type: object
type: array
required:
- topologyPolicies
- zones
type: object
served: true
storage: false
- name: v1alpha2
schema:
openAPIV3Schema:
description: NodeResourceTopology describes node resources and their topology.
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
attributes:
description: AttributeList contains an array of AttributeInfo objects.
items:
description: AttributeInfo contains one attribute of a Zone.
properties:
name:
type: string
value:
type: string
required:
- name
- value
type: object
type: array
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
topologyPolicies:
description: 'DEPRECATED (to be removed in v1beta1): use top level attributes
if needed'
items:
type: string
type: array
zones:
description: ZoneList contains an array of Zone objects.
items:
description: Zone represents a resource topology zone, e.g. socket,
node, die or core.
properties:
attributes:
description: AttributeList contains an array of AttributeInfo objects.
items:
description: AttributeInfo contains one attribute of a Zone.
properties:
name:
type: string
value:
type: string
required:
- name
- value
type: object
type: array
costs:
description: CostList contains an array of CostInfo objects.
items:
description: CostInfo describes the cost (or distance) between
two Zones.
properties:
name:
type: string
value:
format: int64
type: integer
required:
- name
- value
type: object
type: array
name:
type: string
parent:
type: string
resources:
description: ResourceInfoList contains an array of ResourceInfo
objects.
items:
description: ResourceInfo contains information about one resource
type.
properties:
allocatable:
anyOf:
- type: integer
- type: string
description: Allocatable quantity of the resource, corresponding
to allocatable in node status, i.e. total amount of this
resource available to be used by pods.
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
available:
anyOf:
- type: integer
- type: string
description: Available is the amount of this resource currently
available for new (to be scheduled) pods, i.e. Allocatable
minus the resources reserved by currently running pods.
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
capacity:
anyOf:
- type: integer
- type: string
description: Capacity of the resource, corresponding to capacity
in node status, i.e. total amount of this resource that
the node has.
pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
x-kubernetes-int-or-string: true
name:
description: Name of the resource.
type: string
required:
- allocatable
- available
- capacity
- name
type: object
type: array
type:
type: string
required:
- name
- type
type: object
type: array
required:
- zones
type: object
served: true
storage: true
status:
acceptedNames:
kind: ""
plural: ""
conditions: []
storedVersions: []
{{- end }}

View File

@ -0,0 +1,156 @@
{{- if .Values.topologyUpdater.enable -}}
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-topology-updater
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
role: topology-updater
{{- with .Values.topologyUpdater.daemonsetAnnotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
selector:
matchLabels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 6 }}
role: topology-updater
template:
metadata:
labels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 8 }}
role: topology-updater
{{- with .Values.topologyUpdater.annotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
serviceAccountName: {{ include "node-feature-discovery.topologyUpdater.serviceAccountName" . }}
dnsPolicy: ClusterFirstWithHostNet
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
securityContext:
{{- toYaml .Values.topologyUpdater.podSecurityContext | nindent 8 }}
containers:
- name: topology-updater
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: "{{ .Values.image.pullPolicy }}"
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
- name: NODE_ADDRESS
valueFrom:
fieldRef:
fieldPath: status.hostIP
command:
- "nfd-topology-updater"
args:
- "-podresources-socket=/host-var/lib/kubelet-podresources/kubelet.sock"
{{- if .Values.topologyUpdater.updateInterval | empty | not }}
- "-sleep-interval={{ .Values.topologyUpdater.updateInterval }}"
{{- else }}
- "-sleep-interval=3s"
{{- end }}
{{- if .Values.topologyUpdater.watchNamespace | empty | not }}
- "-watch-namespace={{ .Values.topologyUpdater.watchNamespace }}"
{{- else }}
- "-watch-namespace=*"
{{- end }}
{{- if .Values.tls.enable }}
- "-ca-file=/etc/kubernetes/node-feature-discovery/certs/ca.crt"
- "-key-file=/etc/kubernetes/node-feature-discovery/certs/tls.key"
- "-cert-file=/etc/kubernetes/node-feature-discovery/certs/tls.crt"
{{- end }}
{{- if .Values.topologyUpdater.podSetFingerprint }}
- "-pods-fingerprint"
{{- end }}
{{- if .Values.topologyUpdater.kubeletConfigPath | empty | not }}
- "-kubelet-config-uri=file:///host-var/kubelet-config"
{{- end }}
{{- if .Values.topologyUpdater.kubeletStateDir | empty }}
# Disable kubelet state tracking by giving an empty path
- "-kubelet-state-dir="
{{- end }}
- -metrics={{ .Values.topologyUpdater.metricsPort | default "8081"}}
ports:
- name: metrics
containerPort: {{ .Values.topologyUpdater.metricsPort | default "8081"}}
volumeMounts:
{{- if .Values.topologyUpdater.kubeletConfigPath | empty | not }}
- name: kubelet-config
mountPath: /host-var/kubelet-config
{{- end }}
- name: kubelet-podresources-sock
mountPath: /host-var/lib/kubelet-podresources/kubelet.sock
- name: host-sys
mountPath: /host-sys
{{- if .Values.topologyUpdater.kubeletStateDir | empty | not }}
- name: kubelet-state-files
mountPath: /host-var/lib/kubelet
readOnly: true
{{- end }}
{{- if .Values.tls.enable }}
- name: nfd-topology-updater-cert
mountPath: "/etc/kubernetes/node-feature-discovery/certs"
readOnly: true
{{- end }}
- name: nfd-topology-updater-conf
mountPath: "/etc/kubernetes/node-feature-discovery"
readOnly: true
resources:
{{- toYaml .Values.topologyUpdater.resources | nindent 12 }}
securityContext:
{{- toYaml .Values.topologyUpdater.securityContext | nindent 12 }}
volumes:
- name: host-sys
hostPath:
path: "/sys"
{{- if .Values.topologyUpdater.kubeletConfigPath | empty | not }}
- name: kubelet-config
hostPath:
path: {{ .Values.topologyUpdater.kubeletConfigPath }}
{{- end }}
- name: kubelet-podresources-sock
hostPath:
{{- if .Values.topologyUpdater.kubeletPodResourcesSockPath | empty | not }}
path: {{ .Values.topologyUpdater.kubeletPodResourcesSockPath }}
{{- else }}
path: /var/lib/kubelet/pod-resources/kubelet.sock
{{- end }}
{{- if .Values.topologyUpdater.kubeletStateDir | empty | not }}
- name: kubelet-state-files
hostPath:
path: {{ .Values.topologyUpdater.kubeletStateDir }}
{{- end }}
- name: nfd-topology-updater-conf
configMap:
name: {{ include "node-feature-discovery.fullname" . }}-topology-updater-conf
items:
- key: nfd-topology-updater.conf
path: nfd-topology-updater.conf
{{- if .Values.tls.enable }}
- name: nfd-topology-updater-cert
secret:
secretName: nfd-topology-updater-cert
{{- end }}
{{- with .Values.topologyUpdater.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.topologyUpdater.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.topologyUpdater.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- end }}

View File

@ -0,0 +1,152 @@
apiVersion: apps/v1
kind: DaemonSet
metadata:
name: {{ include "node-feature-discovery.fullname" . }}-worker
namespace: {{ include "node-feature-discovery.namespace" . }}
labels:
{{- include "node-feature-discovery.labels" . | nindent 4 }}
role: worker
{{- with .Values.worker.daemonsetAnnotations }}
annotations:
{{- toYaml . | nindent 4 }}
{{- end }}
spec:
selector:
matchLabels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 6 }}
role: worker
template:
metadata:
labels:
{{- include "node-feature-discovery.selectorLabels" . | nindent 8 }}
role: worker
{{- with .Values.worker.annotations }}
annotations:
{{- toYaml . | nindent 8 }}
{{- end }}
spec:
dnsPolicy: ClusterFirstWithHostNet
{{- with .Values.imagePullSecrets }}
imagePullSecrets:
{{- toYaml . | nindent 8 }}
{{- end }}
serviceAccountName: {{ include "node-feature-discovery.worker.serviceAccountName" . }}
securityContext:
{{- toYaml .Values.worker.podSecurityContext | nindent 8 }}
containers:
- name: worker
securityContext:
{{- toYaml .Values.worker.securityContext | nindent 12 }}
image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
imagePullPolicy: {{ .Values.image.pullPolicy }}
env:
- name: NODE_NAME
valueFrom:
fieldRef:
fieldPath: spec.nodeName
resources:
{{- toYaml .Values.worker.resources | nindent 12 }}
command:
- "nfd-worker"
args:
- "-server={{ include "node-feature-discovery.fullname" . }}-master:{{ .Values.master.service.port }}"
{{- if not .Values.enableNodeFeatureApi }}
- "-enable-nodefeature-api=false"
{{- end }}
{{- if .Values.tls.enable }}
- "-ca-file=/etc/kubernetes/node-feature-discovery/certs/ca.crt"
- "-key-file=/etc/kubernetes/node-feature-discovery/certs/tls.key"
- "-cert-file=/etc/kubernetes/node-feature-discovery/certs/tls.crt"
{{- end }}
- "-metrics={{ .Values.worker.metricsPort | default "8081"}}"
ports:
- name: metrics
containerPort: {{ .Values.worker.metricsPort | default "8081"}}
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
{{- if .Values.worker.mountUsrSrc }}
- name: host-usr-src
mountPath: "/host-usr/src"
readOnly: true
{{- end }}
- 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
{{- if .Values.tls.enable }}
- name: nfd-worker-cert
mountPath: "/etc/kubernetes/node-feature-discovery/certs"
readOnly: true
{{- end }}
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"
{{- if .Values.worker.mountUsrSrc }}
- name: host-usr-src
hostPath:
path: "/usr/src"
{{- end }}
- 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: {{ include "node-feature-discovery.fullname" . }}-worker-conf
items:
- key: nfd-worker.conf
path: nfd-worker.conf
{{- if .Values.tls.enable }}
- name: nfd-worker-cert
secret:
secretName: nfd-worker-cert
{{- end }}
{{- with .Values.worker.nodeSelector }}
nodeSelector:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.worker.affinity }}
affinity:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.worker.tolerations }}
tolerations:
{{- toYaml . | nindent 8 }}
{{- end }}
{{- with .Values.worker.priorityClassName }}
priorityClassName: {{ . | quote }}
{{- end }}

View File

@ -0,0 +1,513 @@
image:
repository: registry.k8s.io/nfd/node-feature-discovery
# This should be set to 'IfNotPresent' for released version
pullPolicy: IfNotPresent
# tag, if defined will use the given image tag, else Chart.AppVersion will be used
# tag
imagePullSecrets: []
nameOverride: ""
fullnameOverride: ""
namespaceOverride: ""
enableNodeFeatureApi: true
master:
config: ### <NFD-MASTER-CONF-START-DO-NOT-REMOVE>
# noPublish: false
# extraLabelNs: ["added.ns.io","added.kubernets.io"]
# denyLabelNs: ["denied.ns.io","denied.kubernetes.io"]
# resourceLabels: ["vendor-1.com/feature-1","vendor-2.io/feature-2"]
# enableTaints: false
# labelWhiteList: "foo"
# resyncPeriod: "2h"
# klog:
# addDirHeader: false
# alsologtostderr: false
# logBacktraceAt:
# logtostderr: true
# skipHeaders: false
# stderrthreshold: 2
# v: 0
# vmodule:
## NOTE: the following options are not dynamically run-time configurable
## and require a nfd-master restart to take effect after being changed
# logDir:
# logFile:
# logFileMaxSize: 1800
# skipLogHeaders: false
# leaderElection:
# leaseDuration: 15s
# # this value has to be lower than leaseDuration and greater than retryPeriod*1.2
# renewDeadline: 10s
# # this value has to be greater than 0
# retryPeriod: 2s
# nfdApiParallelism: 10
### <NFD-MASTER-CONF-END-DO-NOT-REMOVE>
# The TCP port that nfd-master listens for incoming requests. Default: 8080
port: 8080
metricsPort: 8081
instance:
featureApi:
resyncPeriod:
denyLabelNs: []
extraLabelNs: []
resourceLabels: []
enableTaints: false
crdController: null
featureRulesController: null
nfdApiParallelism: null
deploymentAnnotations: {}
replicaCount: 1
podSecurityContext: {}
# fsGroup: 2000
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: [ "ALL" ]
readOnlyRootFilesystem: true
runAsNonRoot: true
# runAsUser: 1000
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:
rbac:
create: true
service:
type: ClusterIP
port: 8080
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: {}
tolerations:
- key: "node-role.kubernetes.io/master"
operator: "Equal"
value: ""
effect: "NoSchedule"
- key: "node-role.kubernetes.io/control-plane"
operator: "Equal"
value: ""
effect: "NoSchedule"
annotations: {}
affinity:
nodeAffinity:
preferredDuringSchedulingIgnoredDuringExecution:
- weight: 1
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: [""]
worker:
config: ### <NFD-WORKER-CONF-START-DO-NOT-REMOVE>
#core:
# labelWhiteList:
# noPublish: false
# sleepInterval: 60s
# featureSources: [all]
# labelSources: [all]
# klog:
# addDirHeader: false
# alsologtostderr: false
# logBacktraceAt:
# logtostderr: true
# skipHeaders: false
# stderrthreshold: 2
# v: 0
# vmodule:
## NOTE: the following options are not dynamically run-time configurable
## and require a nfd-worker restart to take effect after being changed
# logDir:
# logFile:
# logFileMaxSize: 1800
# skipLogHeaders: false
#sources:
# cpu:
# cpuid:
## NOTE: whitelist has priority over blacklist
# attributeBlacklist:
# - "BMI1"
# - "BMI2"
# - "CLMUL"
# - "CMOV"
# - "CX16"
# - "ERMS"
# - "F16C"
# - "HTT"
# - "LZCNT"
# - "MMX"
# - "MMXEXT"
# - "NX"
# - "POPCNT"
# - "RDRAND"
# - "RDSEED"
# - "RDTSCP"
# - "SGX"
# - "SSE"
# - "SSE2"
# - "SSE3"
# - "SSE4"
# - "SSE42"
# - "SSSE3"
# - "TDX_GUEST"
# attributeWhitelist:
# kernel:
# kconfigFile: "/path/to/kconfig"
# configOpts:
# - "NO_HZ"
# - "X86"
# - "DMI"
# pci:
# deviceClassWhitelist:
# - "0200"
# - "03"
# - "12"
# deviceLabelFields:
# - "class"
# - "vendor"
# - "device"
# - "subsystem_vendor"
# - "subsystem_device"
# usb:
# deviceClassWhitelist:
# - "0e"
# - "ef"
# - "fe"
# - "ff"
# deviceLabelFields:
# - "class"
# - "vendor"
# - "device"
# local:
# hooksEnabled: false
# custom:
# # The following feature demonstrates the capabilities of the matchFeatures
# - name: "my custom rule"
# labels:
# my-ng-feature: "true"
# # matchFeatures implements a logical AND over all matcher terms in the
# # list (i.e. all of the terms, or per-feature matchers, must match)
# matchFeatures:
# - feature: cpu.cpuid
# matchExpressions:
# AVX512F: {op: Exists}
# - feature: cpu.cstate
# matchExpressions:
# enabled: {op: IsTrue}
# - feature: cpu.pstate
# matchExpressions:
# no_turbo: {op: IsFalse}
# scaling_governor: {op: In, value: ["performance"]}
# - feature: cpu.rdt
# matchExpressions:
# RDTL3CA: {op: Exists}
# - feature: cpu.sst
# matchExpressions:
# bf.enabled: {op: IsTrue}
# - feature: cpu.topology
# matchExpressions:
# hardware_multithreading: {op: IsFalse}
#
# - feature: kernel.config
# matchExpressions:
# X86: {op: Exists}
# LSM: {op: InRegexp, value: ["apparmor"]}
# - feature: kernel.loadedmodule
# matchExpressions:
# e1000e: {op: Exists}
# - feature: kernel.selinux
# matchExpressions:
# enabled: {op: IsFalse}
# - feature: kernel.version
# matchExpressions:
# major: {op: In, value: ["5"]}
# minor: {op: Gt, value: ["10"]}
#
# - feature: storage.block
# matchExpressions:
# rotational: {op: In, value: ["0"]}
# dax: {op: In, value: ["0"]}
#
# - feature: network.device
# matchExpressions:
# operstate: {op: In, value: ["up"]}
# speed: {op: Gt, value: ["100"]}
#
# - feature: memory.numa
# matchExpressions:
# node_count: {op: Gt, value: ["2"]}
# - feature: memory.nv
# matchExpressions:
# devtype: {op: In, value: ["nd_dax"]}
# mode: {op: In, value: ["memory"]}
#
# - feature: system.osrelease
# matchExpressions:
# ID: {op: In, value: ["fedora", "centos"]}
# - feature: system.name
# matchExpressions:
# nodename: {op: InRegexp, value: ["^worker-X"]}
#
# - feature: local.label
# matchExpressions:
# custom-feature-knob: {op: Gt, value: ["100"]}
#
# # The following feature demonstrates the capabilities of the matchAny
# - name: "my matchAny rule"
# labels:
# my-ng-feature-2: "my-value"
# # matchAny implements a logical IF over all elements (sub-matchers) in
# # the list (i.e. at least one feature matcher must match)
# matchAny:
# - matchFeatures:
# - feature: kernel.loadedmodule
# matchExpressions:
# driver-module-X: {op: Exists}
# - feature: pci.device
# matchExpressions:
# vendor: {op: In, value: ["8086"]}
# class: {op: In, value: ["0200"]}
# - matchFeatures:
# - feature: kernel.loadedmodule
# matchExpressions:
# driver-module-Y: {op: Exists}
# - feature: usb.device
# matchExpressions:
# vendor: {op: In, value: ["8086"]}
# class: {op: In, value: ["02"]}
#
# # The following features demonstreate label templating capabilities
# - name: "my template rule"
# labelsTemplate: |
# {{ range .system.osrelease }}my-system-feature.{{ .Name }}={{ .Value }}
# {{ end }}
# matchFeatures:
# - feature: system.osrelease
# matchExpressions:
# ID: {op: InRegexp, value: ["^open.*"]}
# VERSION_ID.major: {op: In, value: ["13", "15"]}
#
# - name: "my template rule 2"
# labelsTemplate: |
# {{ range .pci.device }}my-pci-device.{{ .class }}-{{ .device }}=with-cpuid
# {{ end }}
# matchFeatures:
# - feature: pci.device
# matchExpressions:
# class: {op: InRegexp, value: ["^06"]}
# vendor: ["8086"]
# - feature: cpu.cpuid
# matchExpressions:
# AVX: {op: Exists}
#
# # The following examples demonstrate vars field and back-referencing
# # previous labels and vars
# - name: "my dummy kernel rule"
# labels:
# "my.kernel.feature": "true"
# matchFeatures:
# - feature: kernel.version
# matchExpressions:
# major: {op: Gt, value: ["2"]}
#
# - name: "my dummy rule with no labels"
# vars:
# "my.dummy.var": "1"
# matchFeatures:
# - feature: cpu.cpuid
# matchExpressions: {}
#
# - name: "my rule using backrefs"
# labels:
# "my.backref.feature": "true"
# matchFeatures:
# - feature: rule.matched
# matchExpressions:
# my.kernel.feature: {op: IsTrue}
# my.dummy.var: {op: Gt, value: ["0"]}
#
### <NFD-WORKER-CONF-END-DO-NOT-REMOVE>
metricsPort: 8081
daemonsetAnnotations: {}
podSecurityContext: {}
# fsGroup: 2000
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: [ "ALL" ]
readOnlyRootFilesystem: true
runAsNonRoot: true
# runAsUser: 1000
serviceAccount:
# Specifies whether a service account should be created.
# We create this by default to make it easier for downstream users to apply PodSecurityPolicies.
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:
rbac:
create: true
# Allow users to mount the hostPath /usr/src, useful for RHCOS on s390x
# Does not work on systems without /usr/src AND a read-only /usr, such as Talos
mountUsrSrc: false
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: {}
tolerations: []
annotations: {}
affinity: {}
priorityClassName: ""
topologyUpdater:
config: ### <NFD-TOPOLOGY-UPDATER-CONF-START-DO-NOT-REMOVE>
## key = node name, value = list of resources to be excluded.
## use * to exclude from all nodes.
## an example for how the exclude list should looks like
#excludeList:
# node1: [cpu]
# node2: [memory, example/deviceA]
# *: [hugepages-2Mi]
### <NFD-TOPOLOGY-UPDATER-CONF-END-DO-NOT-REMOVE>
enable: false
createCRDs: false
serviceAccount:
create: true
annotations: {}
name:
rbac:
create: true
metricsPort: 8081
kubeletConfigPath:
kubeletPodResourcesSockPath:
updateInterval: 60s
watchNamespace: "*"
kubeletStateDir: /var/lib/kubelet
podSecurityContext: {}
securityContext:
allowPrivilegeEscalation: false
capabilities:
drop: [ "ALL" ]
readOnlyRootFilesystem: true
runAsUser: 0
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: {}
tolerations: []
annotations: {}
daemonsetAnnotations: {}
affinity: {}
podSetFingerprint: true
gc:
enable: true
replicaCount: 1
serviceAccount:
create: true
annotations: {}
name:
rbac:
create: true
interval: 1h
podSecurityContext: {}
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: {}
tolerations: []
annotations: {}
deploymentAnnotations: {}
affinity: {}
# Optionally use encryption for worker <--> master comms
# TODO: verify hostname is not yet supported
#
# If you do not enable certManager (and have it installed) you will
# need to manually, or otherwise, provision the TLS certs as secrets
tls:
enable: false
certManager: false
prometheus:
enable: false
labels: {}

View File

@ -25,7 +25,8 @@ patches:
path: /data/nfd-worker.conf path: /data/nfd-worker.conf
value: |- value: |-
core: core:
sources: ["custom", "pci", "usb"] sources:
- "all"
sources: sources:
usb: usb:
deviceClassWhitelist: deviceClassWhitelist:
@ -48,6 +49,10 @@ patches:
- "subsystem_device" - "subsystem_device"
custom: custom:
- name: "intel-gpu" # Intel integrated GPU - name: "intel-gpu" # Intel integrated GPU
matchOn: labels:
- pciId: "intel.feature.node.kubernetes.io/gpu": "true"
class: ["0300"] matchFeatures:
- feature: pci.device
matchExpressions:
class: {op: In, value: ["0300"]}
vendor: {op: In, value: ["8086"]}