add metax addon

.gitignore

@@ -3,4 +3,7 @@
 /build/
 /test/.config
 /charts/harbor-operator/chart-harbor-operator
-*pycache*
+*pycache*
+charts/metax-exporter/data
+charts/metax-gpu-extensions/data
+charts/metax-operator/data

charts/metax-exporter/config

@@ -0,0 +1,17 @@
+export USE_OPENSOURCE_CHART=false
+export BUILD_SELF=custom.sh
+export MX_VERSION=0.9.0
+export MX_HELM_VERSION=0.5.0
+
+# pr, issue, none
+export UPGRADE_METHOD=pr
+export UPGRADE_REVIWER=lengrongfu
+export TEST_ASSIGNER=lengrongfu
+
+# push to daocloud repo
+export DAOCLOUD_REPO_PROJECT=addon
+
+# optional, for wrapper chart
+# gpu-operator version
+export CUSTOM_VERSION=${VERSION}+1
+

charts/metax-exporter/custom.sh

@@ -0,0 +1,42 @@
+#!/usr/bin/env bash
+
+if [ -z "${LOCAL+x}" ]; then
+  echo "LOCAL is not defined, skipping..."
+  exit 0
+fi
+
+bash ./script/upload.sh ./data/mx-exporter.${MX_VERSION}.tgz release.daocloud.io dc-image
+echo "Upload image complete"
+
+CHART_DIR=./mx-exporter/deployment/mx-exporter/helm/mx-exporter
+
+rm -rf metax-exporter/
+cp -rf ./mx-exporter/deployment/mx-exporter/helm/mx-exporter metax-exporter
+rm -rf mx-exporter
+
+yq -i '
+  .name = "metax-exporter"
+' metax-exporter/Chart.yaml
+
+yq -i "
+  .image.registry=\"release.daocloud.io\" |
+  .image.repository = \"metax/mx-exporter\" |
+  .image.tag= \"${MX_VERSION}\"
+" metax-exporter/values.yaml
+
+os=$(uname)
+echo $os
+if [ $os == "Darwin" ];then
+   sed -i "" "s/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}/{{ .Values.image.registry }}\/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}/g" ./metax-exporter/templates/daemonset.yaml
+elif [ $os == "Linux" ]; then
+   sed -i  "s/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}/{{ .Values.image.registry }}\/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}/g" ./metax-exporter/templates/daemonset.yaml
+fi
+
+
+helm schema-gen metax-exporter/values.yaml > metax-exporter/values.schema.json
+cp -rf parent/ metax-exporter/
+
+
+bash ./script/upload.sh ./data/mx-exporter.${MX_VERSION}.tgz release.daocloud.io helm-push
+rm -rf metax-exporter-${MX_HELM_VERSION}.tgz
+echo "Push helm chart complete"

charts/metax-exporter/example/README-custom.md

@@ -0,0 +1,61 @@
+# This project is offline gpu-operator helm chart
+
+## How To Test
+
+1. make build_chart
+```shell
+$ cd github.com/daocloud/dce-charts-repackage
+$ make build_chart -e PROJECT=gpu-operator
+```
+
+2. package helm chart
+```shell
+$ cd github.com/daocloud/dce-charts-repackage/charts/gpu-operator
+$ helm package gpu-operator
+```
+
+3. upload to harbor
+```shell
+$ helm repo add harbor-test-helm-repo --username=xxx --password=xxx http://harbor-test.demo.com.cn:8086/chartrepo/helm-repo
+$ helm push gpu-operator-v23.6.1.tgz harbor-test-helm-repo
+```
+
+4. download charts-syncer
+```shell
+https://github.com/DaoCloud/charts-syncer
+```
+
+5. sync to local
+```shell
+$ vim config-save-bundles.yaml
+# sync to local
+$ charts-syncer sync --config config-save-bundles.yaml --v 5
+```
+
+6. sync offline addon to harbor
+```shell
+$ vim config-write-bundles.yaml
+source:
+    intermediateBundlesPath: addon # chart tar 包所在的目录，需把 relok8s 生成的 tar 包放到此目录下
+target:
+    containerRegistry: 10.6.232.5:30727  # 目标镜像仓库地址
+    containerRepository: kangaroo # laod 镜像时 project 如果不需要修改可不填写
+    repo:
+        kind: HARBOR # or as any other supported Helm Chart repository kinds
+        url: http://10.6.232.5:30727/chartrepo/kangaroo  #load charts 的目标地址，改为需要的地址即可
+        auth:   ## charts仓库用户名密码
+            username: admin
+            password: Harbor12345
+    containers:
+        auth:
+           username: admin
+           password: Harbor12345
+
+$ charts-syncer sync --config config-write-bundles.yaml --insecure=true
+```
+
+6. schema-gen
+```
+$ helm schema-gen values-schema.yaml > values.schema.json
+```
+

charts/metax-exporter/example/config-save-bundles.yaml

@@ -0,0 +1,19 @@
+source:
+  repo:
+    kind: HARBOR # or as any other supported Helm Chart repository kinds
+    url: https://release.daocloud.io/chartrepo/addon
+    auth: ## charts仓库用户名密码
+      username: admin
+      password: x3OFzuW0tpGYFDAr63wRx81dqms=
+  containers:
+#    url: https://release.daocloud.io
+    auth:
+      registry: release.daocloud.io
+      username: "admin"
+      password: ""
+target:
+  # The important bit. This instructs charts-syncer to store intermediate bundles in the given directory
+  intermediateBundlesPath: addon
+
+charts:
+  - name: metax-exporter

charts/metax-exporter/metax-exporter/.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/

charts/metax-exporter/metax-exporter/.relok8s-images.yaml

@@ -0,0 +1 @@
+- "{{ .image.registry }}/{{ .image.repository }}:{{ .image.tag }}"

charts/metax-exporter/metax-exporter/Chart.yaml

@@ -0,0 +1,26 @@
+apiVersion: v2
+name: metax-exporter
+description: A Helm chart for MetaX GPU metrics exporter
+# 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: 0.5.0
+# 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: "2.1.10"
+keywords:
+  - gpu
+  - compute
+  - monitoring
+  - telemetry

charts/metax-exporter/metax-exporter/templates/NOTES.txt

@@ -0,0 +1,22 @@
+1. Get the application URL by running these commands:
+{{- if .Values.ingress.enabled }}
+{{- range $host := .Values.ingress.hosts }}
+  {{- range .paths }}
+  http{{ if $.Values.ingress.tls }}s{{ end }}://{{ $host.host }}{{ .path }}
+  {{- end }}
+{{- end }}
+{{- else if contains "NodePort" .Values.service.type }}
+  export NODE_PORT=$(kubectl get --namespace {{ .Release.Namespace }} -o jsonpath="{.spec.ports[0].nodePort}" services {{ include "mx-exporter.fullname" . }})
+  export NODE_IP=$(kubectl get nodes --namespace {{ .Release.Namespace }} -o jsonpath="{.items[0].status.addresses[0].address}")
+  echo http://$NODE_IP:$NODE_PORT
+{{- else if contains "LoadBalancer" .Values.service.type }}
+     NOTE: It may take a few minutes for the LoadBalancer IP to be available.
+           You can watch the status of by running 'kubectl get --namespace {{ .Release.Namespace }} svc -w {{ include "mx-exporter.fullname" . }}'
+  export SERVICE_IP=$(kubectl get svc --namespace {{ .Release.Namespace }} {{ include "mx-exporter.fullname" . }} --template "{{"{{ range (index .status.loadBalancer.ingress 0) }}{{.}}{{ end }}"}}")
+  echo http://$SERVICE_IP:{{ .Values.service.port }}
+{{- else if contains "ClusterIP" .Values.service.type }}
+  export POD_NAME=$(kubectl get pods --namespace {{ .Release.Namespace }} -l "app.kubernetes.io/name={{ include "mx-exporter.name" . }},app.kubernetes.io/instance={{ .Release.Name }}" -o jsonpath="{.items[0].metadata.name}")
+  export CONTAINER_PORT=$(kubectl get pod --namespace {{ .Release.Namespace }} $POD_NAME -o jsonpath="{.spec.containers[0].ports[0].containerPort}")
+  echo "Visit http://127.0.0.1:8080 to use your application"
+  kubectl --namespace {{ .Release.Namespace }} port-forward $POD_NAME 8080:$CONTAINER_PORT
+{{- end }}

charts/metax-exporter/metax-exporter/templates/_helpers.tpl

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

charts/metax-exporter/metax-exporter/templates/daemonset.yaml

@@ -0,0 +1,94 @@
+apiVersion: apps/v1
+kind: DaemonSet
+metadata:
+  name: {{ include "mx-exporter.fullname" . }}
+  namespace: {{ .Release.Namespace }}
+  labels:
+    {{- include "mx-exporter.labels" . | nindent 4 }}
+spec:
+  selector:
+    matchLabels:
+      {{- include "mx-exporter.selectorLabels" . | nindent 6 }}
+  template:
+    metadata:
+      {{- with .Values.podAnnotations }}
+      annotations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      labels:
+        {{- include "mx-exporter.labels" . | nindent 8 }}
+        {{- with .Values.podLabels }}
+        {{- toYaml . | nindent 8 }}
+        {{- end }}
+    spec:
+      {{- with .Values.imagePullSecrets }}
+      imagePullSecrets:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      serviceAccountName: {{ include "mx-exporter.serviceAccountName" . }}
+      securityContext:
+        {{- toYaml .Values.podSecurityContext | nindent 8 }}
+      containers:
+        - name: {{ .Chart.Name }}
+          securityContext:
+            {{- toYaml .Values.securityContext | nindent 12 }}
+          image: "{{ .Values.image.registry }}/{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
+          imagePullPolicy: {{ .Values.image.pullPolicy }}
+          args:
+            - "-c=/etc/config/metrics"
+            - "-p={{.Values.service.port}}"
+            - "-i={{.Values.gatherInterval}}"
+            - "-lm={{.Values.logMonitor}}"
+          env:
+            - name: "NODE_NAME"
+              valueFrom:
+                fieldRef:
+                  fieldPath: spec.nodeName
+          ports:
+            - name: "metrics"
+              containerPort: {{ .Values.service.port }}
+              protocol: TCP
+          volumeMounts:
+            - name: "pod-gpu-resources"
+              readOnly: true
+              mountPath: "/var/lib/kubelet/pod-resources"
+            - name: "all-devices"
+              mountPath: "/dev/dri"
+            - name: "config-vol"
+              mountPath: "/etc/config"
+            {{- if .Values.logMonitor }}
+            - name: "var-log"
+              readOnly: true
+              mountPath: "/var/log"
+            {{- end }}
+            {{- with .Values.volumeMounts }}
+              {{- toYaml . | nindent 12 }}
+            {{- end }}
+      volumes:
+        - name: "pod-gpu-resources"
+          hostPath:
+            path: {{ .Values.kubeletPath }}
+        - name: "var-log"
+          hostPath:
+            path: "/var/log"
+        - name: "all-devices"
+          hostPath:
+            path: {{ .Values.devicePath }}
+        - name: "config-vol"
+          configMap:
+            name: "exporter-metrics-config-map"
+        {{- with .Values.volumes }}
+          {{- toYaml . | nindent 8 }}
+        {{- end }}
+      {{- with .Values.nodeSelector }}
+      nodeSelector:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.affinity }}
+      affinity:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}
+      {{- with .Values.tolerations }}
+      tolerations:
+        {{- toYaml . | nindent 8 }}
+      {{- end }}