Add helm charts for mldiagnostics injection webhook and connection operator

ai-ml/mldiagnostics-webhook-and-operator/READMDE.md

@@ -0,0 +1,44 @@
+## mldiagnostics-webhook-and-operator
+
+It provide helm charts for mldiagnostics webhook and operator, which is needed for integrating mldiagnostics SDK in GKE.
+
+
+
+### Install cert-manager if not already installed
+
+Cert-manager is a prerequisite for the injection-webhook. If it’s not installed, follow this to install. After installing cert-manager, it may take up to two minutes for the certificate to become ready.
+
+```bash
+helm repo add jetstack https://charts.jetstack.io
+helm repo update
+
+helm install \
+  cert-manager jetstack/cert-manager \
+  --namespace cert-manager \
+  --create-namespace \
+  --version v1.13.0 \
+  --set installCRDs=true \
+  --set global.leaderElection.namespace=cert-manager \
+  --timeout 10m
+```
+
+### Install injection-webhook
+
+```bash
+helm install mldiagnostics-injection-webhook \
+   --namespace=gke-diagon\
+   --create-namespace \
+  ./injection-webhook/chart
+
+```
+
+
+### Install connection-operator
+
+```bash
+helm install mldiagnostics-connection-operator \
+   --namespace=gke-diagon\
+   --create-namespace \
+  ./connection-operator/chart
+```
+

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/.helmignore

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

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/Chart.yaml

@@ -0,0 +1,21 @@
+apiVersion: v2
+name: mldiagnostics-connection-operator
+description: A Helm chart to capture profiler traces based on MLDiagnosticsConnection Custom Resource in frameworks JAX, Pytorch XLA and TensorFlow.
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "0.1.0"

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/_helpers.tpl

@@ -0,0 +1,62 @@
+{{/*
+Expand the name of the chart.
+*/}}
+{{- define "chart.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 "chart.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 "chart.chart" -}}
+{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
+{{- end }}
+
+{{/*
+Common labels
+*/}}
+{{- define "chart.labels" -}}
+helm.sh/chart: {{ include "chart.chart" . }}
+{{ include "chart.selectorLabels" . }}
+{{- if .Chart.AppVersion }}
+app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
+{{- end }}
+app.kubernetes.io/managed-by: {{ .Release.Service }}
+{{- end }}
+
+{{/*
+Selector labels
+*/}}
+{{- define "chart.selectorLabels" -}}
+app.kubernetes.io/name: {{ include "chart.name" . }}
+app.kubernetes.io/instance: {{ .Release.Name }}
+{{- end }}
+
+{{/*
+Create the name of the service account to use
+*/}}
+{{- define "chart.serviceAccountName" -}}
+{{- if .Values.serviceAccount.create }}
+{{- default (include "chart.fullname" .) .Values.serviceAccount.name }}
+{{- else }}
+{{- default "default" .Values.serviceAccount.name }}
+{{- end }}
+{{- end }}

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/deployment.yaml

@@ -0,0 +1,71 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: {{ include "chart.fullname" . }}
+  labels:
+    control-plane: diagon-connection-operator
+  {{- include "chart.labels" . | nindent 4 }}
+spec:
+  replicas: {{ .Values.diagonConnectionOperator.replicas }}
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: connection-operator
+      control-plane: diagon-connection-operator
+    {{- include "chart.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: connection-operator
+        control-plane: diagon-connection-operator
+      {{- include "chart.selectorLabels" . | nindent 8 }}
+      annotations:
+        kubectl.kubernetes.io/default-container: controller
+    spec:
+      containers:
+      - args: {{- toYaml .Values.diagonConnectionOperator.controller.args | nindent 8 }}
+        command:
+        - /manager
+        env:
+        - name: KUBERNETES_CLUSTER_DOMAIN
+          value: {{ quote .Values.kubernetesClusterDomain }}
+        image: {{ .Values.diagonConnectionOperator.controller.image.repository }}:{{ .Values.diagonConnectionOperator.controller.image.tag
+          | default .Chart.AppVersion }}
+        livenessProbe:
+          httpGet:
+            path: /healthz
+            port: 8081
+          initialDelaySeconds: 15
+          periodSeconds: 20
+        name: controller
+        readinessProbe:
+          httpGet:
+            path: /readyz
+            port: 8081
+          initialDelaySeconds: 5
+          periodSeconds: 10
+        resources: {{- toYaml .Values.diagonConnectionOperator.controller.resources | nindent
+          10 }}
+        securityContext: {{- toYaml .Values.diagonConnectionOperator.controller.containerSecurityContext
+          | nindent 10 }}
+      - env:
+        - name: KUBERNETES_CLUSTER_DOMAIN
+          value: {{ quote .Values.kubernetesClusterDomain }}
+        image: '{{ .Values.diagonConnectionOperator.googleCloudMldiagnosticsProfiler.image.repository
+          }}:{{ .Values.diagonConnectionOperator.googleCloudMldiagnosticsProfiler.image.tag
+          | default .Chart.AppVersion }}'
+        name: google-cloud-mldiagnostics-profiler
+        ports:
+        - containerPort: 5001
+        resources: {}
+        securityContext: {{- toYaml .Values.diagonConnectionOperator.googleCloudMldiagnosticsProfiler.containerSecurityContext
+          | nindent 10 }}
+        volumeMounts:
+        - mountPath: /tmp
+          name: tmp-volume
+      securityContext: {{- toYaml .Values.diagonConnectionOperator.podSecurityContext |
+        nindent 8 }}
+      serviceAccountName: {{ include "chart.fullname" . }}
+      terminationGracePeriodSeconds: 10
+      volumes:
+      - emptyDir: {}
+        name: tmp-volume

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/leader-election-rbac.yaml

@@ -0,0 +1,53 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: Role
+metadata:
+  name: {{ include "chart.fullname" . }}-leader-election-role
+  labels:
+  {{- include "chart.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: {{ include "chart.fullname" . }}-leader-election-rolebinding
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: Role
+  name: '{{ include "chart.fullname" . }}-leader-election-role'
+subjects:
+- kind: ServiceAccount
+  name: '{{ include "chart.fullname" . }}'
+  namespace: '{{ .Release.Namespace }}'

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/manager-rbac.yaml

@@ -0,0 +1,56 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: {{ include "chart.fullname" . }}-manager-role
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - pods
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - diagon.gke.io
+  resources:
+  - mldiagnosticsconnections
+  verbs:
+  - create
+  - delete
+  - get
+  - list
+  - patch
+  - update
+  - watch
+- apiGroups:
+  - diagon.gke.io
+  resources:
+  - mldiagnosticsconnections/finalizers
+  verbs:
+  - update
+- apiGroups:
+  - diagon.gke.io
+  resources:
+  - mldiagnosticsconnections/status
+  verbs:
+  - get
+  - patch
+  - update
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: {{ include "chart.fullname" . }}-manager-rolebinding
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: '{{ include "chart.fullname" . }}-manager-role'
+subjects:
+- kind: ServiceAccount
+  name: '{{ include "chart.fullname" . }}'
+  namespace: '{{ .Release.Namespace }}'

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/metrics-auth-rbac.yaml

@@ -0,0 +1,34 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: {{ include "chart.fullname" . }}-metrics-auth-role
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+rules:
+- 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: {{ include "chart.fullname" . }}-metrics-auth-rolebinding
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: '{{ include "chart.fullname" . }}-metrics-auth-role'
+subjects:
+- kind: ServiceAccount
+  name: controller-manager
+  namespace: '{{ .Release.Namespace }}'

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/metrics-reader-rbac.yaml

@@ -0,0 +1,11 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: {{ include "chart.fullname" . }}-metrics-reader
+  labels:
+  {{- include "chart.labels" . | nindent 4 }}
+rules:
+- nonResourceURLs:
+  - /metrics
+  verbs:
+  - get

ai-ml/mldiagnostics-webhook-and-operator/connection-operator/chart/templates/metrics-service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: {{ include "chart.fullname" . }}-controller-manager-metrics
+  labels:
+    control-plane: controller-manager
+  {{- include "chart.labels" . | nindent 4 }}
+spec:
+  type: {{ .Values.metricsService.type }}
+  selector:
+    app.kubernetes.io/name: connection-operator
+    control-plane: controller-manager
+    {{- include "chart.selectorLabels" . | nindent 4 }}
+  ports:
+  {{- .Values.metricsService.ports | toYaml | nindent 2 }}