fix: rm kubesphere-monitoring-federated ns

* fix(files): external delete

* login & system-frontend: update login and system-frontend new version

---------

Co-authored-by: qq815776412 <815776412@qq.com>

.github/workflows/check.yaml

@@ -65,6 +65,7 @@ jobs:
     with:
       version: ${{ needs.test-version.outputs.version }}
       ref: ${{ github.event.pull_request.head.ref }}
+      repository: ${{ github.event.pull_request.head.repo.full_name }}
 
   upload-daemon:
     needs: test-version
@@ -73,6 +74,7 @@ jobs:
     with:
       version: ${{ needs.test-version.outputs.version }}
       ref: ${{ github.event.pull_request.head.ref }}
+      repository: ${{ github.event.pull_request.head.repo.full_name }}
 
   push-image:
     runs-on: ubuntu-latest
@@ -132,6 +134,7 @@ jobs:
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           AWS_DEFAULT_REGION: "us-east-1"
           VERSION: ${{ needs.test-version.outputs.version }}
+          REPO_PATH: '${{ secrets.REPO_PATH }}'
         run: |
           bash build/deps-manifest.sh && bash build/upload-deps.sh
 
@@ -156,6 +159,7 @@ jobs:
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           AWS_DEFAULT_REGION: "us-east-1"
           VERSION: ${{ needs.test-version.outputs.version }}
+          REPO_PATH: '${{ secrets.REPO_PATH }}'
         run: |
           export PATH=$PATH:/usr/local/bin:/home/ubuntu/.local/bin
           bash build/deps-manifest.sh linux/arm64 && bash build/upload-deps.sh linux/arm64

.github/workflows/push-deps-to-s3.yml

@@ -11,27 +11,13 @@ jobs:
       - name: "Checkout source code"
         uses: actions/checkout@v3
 
-      - name: Install coscmd
-        run: pip install coscmd        
-
-      - name: Configure coscmd
-        env:
-          TENCENT_SECRET_ID: ${{ secrets.TENCENT_SECRET_ID }}
-          TENCENT_SECRET_KEY: ${{ secrets.TENCENT_SECRET_KEY }}
-          COS_BUCKET: ${{ secrets.COS_BUCKET }}
-          COS_REGION: ${{ secrets.COS_REGION }}
-          END_POINT: ${{ secrets.END_POINT }}
-        run: |
-          coscmd config -a $TENCENT_SECRET_ID \
-                        -s $TENCENT_SECRET_KEY \
-                        -b $COS_BUCKET \
-                        -r $COS_REGION 
 
       # test
       - env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           AWS_DEFAULT_REGION: "us-east-1"
+          REPO_PATH: '${{ secrets.REPO_PATH }}'
         run: |
           bash build/deps-manifest.sh && bash build/upload-deps.sh
 
@@ -42,28 +28,12 @@ jobs:
       - name: "Checkout source code"
         uses: actions/checkout@v3
 
-      - name: Install coscmd
-        run: pip install coscmd        
-
-      - name: Configure coscmd
-        env:
-          TENCENT_SECRET_ID: ${{ secrets.TENCENT_SECRET_ID }}
-          TENCENT_SECRET_KEY: ${{ secrets.TENCENT_SECRET_KEY }}
-          COS_BUCKET: ${{ secrets.COS_BUCKET }}
-          COS_REGION: ${{ secrets.COS_REGION }}
-          END_POINT: ${{ secrets.END_POINT }}
-        run: |
-          export PATH=$PATH:/usr/local/bin:/home/ubuntu/.local/bin
-          coscmd config -m 10 -p 10 -a $TENCENT_SECRET_ID \
-                        -s $TENCENT_SECRET_KEY \
-                        -b $COS_BUCKET \
-                        -r $COS_REGION 
-
       # test
       - env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           AWS_DEFAULT_REGION: "us-east-1"
+          REPO_PATH: '${{ secrets.REPO_PATH }}'
         run: |
           export PATH=$PATH:/usr/local/bin:/home/ubuntu/.local/bin
           bash build/deps-manifest.sh linux/arm64 && bash build/upload-deps.sh linux/arm64

.github/workflows/push-to-s3.yaml

@@ -11,22 +11,6 @@ jobs:
       - name: "Checkout source code"
         uses: actions/checkout@v3
 
-      - name: Install coscmd
-        run: pip install coscmd        
-
-      - name: Configure coscmd
-        env:
-          TENCENT_SECRET_ID: ${{ secrets.TENCENT_SECRET_ID }}
-          TENCENT_SECRET_KEY: ${{ secrets.TENCENT_SECRET_KEY }}
-          COS_BUCKET: ${{ secrets.COS_BUCKET }}
-          COS_REGION: ${{ secrets.COS_REGION }}
-          END_POINT: ${{ secrets.END_POINT }}
-        run: |
-          coscmd config -a $TENCENT_SECRET_ID \
-                        -s $TENCENT_SECRET_KEY \
-                        -b $COS_BUCKET \
-                        -r $COS_REGION 
-
       # test
       - env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
@@ -42,23 +26,6 @@ jobs:
       - name: "Checkout source code"
         uses: actions/checkout@v3
 
-      - name: Install coscmd
-        run: pip install coscmd        
-
-      - name: Configure coscmd
-        env:
-          TENCENT_SECRET_ID: ${{ secrets.TENCENT_SECRET_ID }}
-          TENCENT_SECRET_KEY: ${{ secrets.TENCENT_SECRET_KEY }}
-          COS_BUCKET: ${{ secrets.COS_BUCKET }}
-          COS_REGION: ${{ secrets.COS_REGION }}
-          END_POINT: ${{ secrets.END_POINT }}
-        run: |
-          export PATH=$PATH:/usr/local/bin:/home/ubuntu/.local/bin
-          coscmd config -m 10 -p 10 -a $TENCENT_SECRET_ID \
-                        -s $TENCENT_SECRET_KEY \
-                        -b $COS_BUCKET \
-                        -r $COS_REGION 
-
       - env:
           AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}

.github/workflows/release-cli.yaml

@@ -8,7 +8,17 @@ on:
         required: true
       ref:
         type: string
+      repository:
+        type: string
   workflow_dispatch:
+    inputs:
+      version:
+        type: string
+        required: true
+      ref:
+        type: string
+      repository:
+        type: string
 jobs:
   goreleaser:
     runs-on: ubuntu-22.04
@@ -18,6 +28,7 @@ jobs:
         with:
           fetch-depth: 1
           ref: ${{ inputs.ref }}
+          repository: ${{ inputs.repository }}
 
       - name: Add Local Git Tag For GoReleaser
         run: git tag ${{ inputs.version }}
@@ -51,6 +62,5 @@ jobs:
           AWS_DEFAULT_REGION: "us-east-1"
         run: |
           cd cli/output && for file in *.tar.gz; do
-            aws s3 cp "$file" s3://terminus-os-install/$file --acl=public-read
-            # coscmd upload $file /$file
+            aws s3 cp "$file" s3://terminus-os-install${{ secrets.REPO_PATH }}${file} --acl=public-read
           done

.github/workflows/release-daemon.yaml

@@ -8,7 +8,17 @@ on:
         required: true
       ref:
         type: string
+      repository:
+        type: string
   workflow_dispatch:
+    inputs:
+      version:
+        type: string
+        required: true
+      ref:
+        type: string
+      repository:
+        type: string
 
 jobs:
   goreleaser:
@@ -19,6 +29,7 @@ jobs:
         with:
           fetch-depth: 1
           ref: ${{ inputs.ref }}
+          repository: ${{ inputs.repository }}
 
       - name: Add Local Git Tag For GoReleaser
         run: git tag ${{ inputs.version }}
@@ -54,5 +65,5 @@ jobs:
           AWS_DEFAULT_REGION: 'us-east-1'
         run: |
           cd daemon/output && for file in *.tar.gz; do
-            aws s3 cp "$file" s3://terminus-os-install/$file --acl=public-read
+            aws s3 cp "$file" s3://terminus-os-install${{ secrets.REPO_PATH }}${file} --acl=public-read
           done

.github/workflows/release-daily.yaml

@@ -77,6 +77,7 @@ jobs:
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           AWS_DEFAULT_REGION: "us-east-1"
           VERSION: ${{ needs.daily-version.outputs.version }}
+          REPO_PATH: '${{ secrets.REPO_PATH }}'
         run: |
           bash build/deps-manifest.sh && bash build/upload-deps.sh
 
@@ -94,6 +95,7 @@ jobs:
           AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
           AWS_DEFAULT_REGION: "us-east-1"
           VERSION: ${{ needs.daily-version.outputs.version }}
+          REPO_PATH: '${{ secrets.REPO_PATH }}'
         run: |
           export PATH=$PATH:/usr/local/bin:/home/ubuntu/.local/bin
           bash build/deps-manifest.sh linux/arm64 && bash build/upload-deps.sh linux/arm64
@@ -121,8 +123,8 @@ jobs:
           AWS_DEFAULT_REGION: 'us-east-1'
         run: |
           md5sum install-wizard-v${{ needs.daily-version.outputs.version }}.tar.gz > install-wizard-v${{ needs.daily-version.outputs.version }}.md5sum.txt && \
-          aws s3 cp install-wizard-v${{ needs.daily-version.outputs.version }}.md5sum.txt s3://terminus-os-install/install-wizard-v${{ needs.daily-version.outputs.version }}.md5sum.txt --acl=public-read && \
-          aws s3 cp install-wizard-v${{ needs.daily-version.outputs.version }}.tar.gz s3://terminus-os-install/install-wizard-v${{ needs.daily-version.outputs.version }}.tar.gz --acl=public-read && \
+          aws s3 cp install-wizard-v${{ needs.daily-version.outputs.version }}.md5sum.txt s3://terminus-os-install${{ secrets.REPO_PATH }}install-wizard-v${{ needs.daily-version.outputs.version }}.md5sum.txt --acl=public-read && \
+          aws s3 cp install-wizard-v${{ needs.daily-version.outputs.version }}.tar.gz s3://terminus-os-install${{ secrets.REPO_PATH }}install-wizard-v${{ needs.daily-version.outputs.version }}.tar.gz --acl=public-read && \
           echo "md5sum=$(awk '{print $1}' install-wizard-v${{ needs.daily-version.outputs.version }}.md5sum.txt)" >> "$GITHUB_OUTPUT"
 
 

.github/workflows/release.yaml

@@ -80,8 +80,8 @@ jobs:
           AWS_DEFAULT_REGION: 'us-east-1'
         run: |
           md5sum install-wizard-v${{ github.event.inputs.tags }}.tar.gz > install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt && \
-          aws s3 cp install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt s3://terminus-os-install/install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt --acl=public-read && \
-          aws s3 cp install-wizard-v${{ github.event.inputs.tags }}.tar.gz s3://terminus-os-install/install-wizard-v${{ github.event.inputs.tags }}.tar.gz --acl=public-read
+          aws s3 cp install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt s3://terminus-os-install${{ secrets.REPO_PATH }}install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt --acl=public-read && \
+          aws s3 cp install-wizard-v${{ github.event.inputs.tags }}.tar.gz s3://terminus-os-install${{ secrets.REPO_PATH }}install-wizard-v${{ github.event.inputs.tags }}.tar.gz --acl=public-read
 
   release:
     runs-on: ubuntu-latest
@@ -101,7 +101,7 @@ jobs:
       - name: Get checksum
         id: vars
         run: |
-          echo "version_md5sum=$(curl -sSfL https://dc3p1870nn3cj.cloudfront.net/install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt|awk '{print $1}')" >> $GITHUB_OUTPUT
+          echo "version_md5sum=$(curl -sSfL https://dc3p1870nn3cj.cloudfront.net${{ secrets.REPO_PATH }}install-wizard-v${{ github.event.inputs.tags }}.md5sum.txt|awk '{print $1}')" >> $GITHUB_OUTPUT
 
       - name: Update checksum
         uses: eball/write-tag-to-version-file@latest

README.md

@@ -108,20 +108,15 @@ Olares has been tested and verified on the following Linux platforms:
 To get started with Olares on your own device, follow the [Getting Started Guide](https://docs.olares.com/manual/get-started/) for step-by-step instructions.
 
 ## Project navigation
-
-> [!NOTE]  
-> We are currently consolidating Olares subproject code into this repository. This process may take a few months. Once finished, you will get a comprehensive view of the entire Olares system here.
-
-
 This section lists the main directories in the Olares repository:
 
-* **`apps`**: Contains the code for system applications, primarily for `larepass`.
-* **`cli`**: Contains the code for `olares-cli`, the command-line interface tool for Olares.
-* **`daemon`**: Contains the code for `olaresd`, the system daemon process.
+* **[`apps`](./apps)**: Contains the code for system applications, primarily for `larepass`.
+* **[`cli`](./cli)**: Contains the code for `olares-cli`, the command-line interface tool for Olares.
+* **[`daemon`](./daemon)**: Contains the code for `olaresd`, the system daemon process.
 * **`docs`**: Contains documentation for the project.
-* **`framework`**: Contains the Olares system services.
-* **`infrastructure`**: Contains code related to infrastructure components such as computing, storage, networking, and GPUs.
-* **`platform`**: Contains code for cloud-native components like databases and message queues.
+* **[`framework`](./framework)**: Contains the Olares system services.
+* **[`infrastructure`](./infrastructure)**: Contains code related to infrastructure components such as computing, storage, networking, and GPUs.
+* **[`platform`](./platform)**: Contains code for cloud-native components like databases and message queues.
 * **`vendor`**: Contains code from third-party hardware vendors.
 
 ## Contributing to Olares

README_CN.md

@@ -110,19 +110,15 @@ Olares 已在以下 Linux 平台完成测试与验证：
 参考[快速上手指南](https://docs.olares.cn/zh/manual/get-started/)安装并激活 Olares。
 
 ## 项目目录
-
-> [!NOTE]
-> 我们正将 Olares 子项目的代码移动到当前仓库。此过程可能会持续数月。届时您就可以通过本仓库了解 Olares 系统的全貌。
-
 Olares 代码库中的主要目录如下：
 
-* **`apps`**: 用于存放系统应用，主要是 `larepass` 的代码。
-* **`cli`**: 用于存放 `olares-cli`（Olares 的命令行界面工具）的代码。
-* **`daemon`**: 用于存放 `olaresd`（系统守护进程）的代码。
+* **[`apps`](./apps)**: 用于存放系统应用，主要是 `larepass` 的代码。
+* **[`cli`](./cli)**: 用于存放 `olares-cli`（Olares 的命令行界面工具）的代码。
+* **[`daemon`](./daemon)**: 用于存放 `olaresd`（系统守护进程）的代码。
 * **`docs`**: 用于存放 Olares 项目的文档。
-* **`framework`**: 用来存放 Olares 系统服务代码。
-* **`infrastructure`**: 用于存放计算，存储，网络，GPU 等基础设施的代码。
-* **`platform`**: 用于存放数据库、消息队列等云原生组件的代码。
+* **[`framework`](./framework)**: 用来存放 Olares 系统服务代码。
+* **[`infrastructure`](./infrastructure)**: 用于存放计算，存储，网络，GPU 等基础设施的代码。
+* **[`platform`](./platform)**: 用于存放数据库、消息队列等云原生组件的代码。
 * **`vendor`**: 用于存放来自第三方硬件供应商的代码。
 
 ## 社区贡献

README_JP.md

@@ -110,18 +110,15 @@ Olaresは以下のLinuxプラットフォームで動作検証を完了してい
 
 ## プロジェクトナビゲーション
 
-> [!NOTE]
-> 現在、Olaresのサブプロジェクトのコードを当リポジトリへ移行する作業を進めています。この作業が完了するまでには数ヶ月を要する見込みです。完了後には、当リポジトリを通じてOlaresシステムの全貌をご覧いただけるようになります。
-
 このセクションでは、Olares リポジトリ内の主要なディレクトリをリストアップしています：
 
-* **`apps`**: システムアプリケーションのコードが含まれており、主に `larepass` 用です。
-* **`cli`**: Olares のコマンドラインインターフェースツールである `olares-cli` のコードが含まれています。
-* **`daemon`**: システムデーモンプロセスである `olaresd` のコードが含まれています。
+* **[`apps`](./apps)**: システムアプリケーションのコードが含まれており、主に `larepass` 用です。
+* **[`cli`](./cli)**: Olares のコマンドラインインターフェースツールである `olares-cli` のコードが含まれています。
+* **[`daemon`](./daemon)**: システムデーモンプロセスである `olaresd` のコードが含まれています。
 * **`docs`**: プロジェクトのドキュメントが含まれています。
-* **`framework`**: Olares システムサービスが含まれています。
-* **`infrastructure`**: コンピューティング、ストレージ、ネットワーキング、GPU などのインフラストラクチャコンポーネントに関連するコードが含まれています。
-* **`platform`**: データベースやメッセージキューなどのクラウドネイティブコンポーネントのコードが含まれています。
+* **[`framework`](./framework)**: Olares システムサービスが含まれています。
+* **[`infrastructure`](./infrastructure)**: コンピューティング、ストレージ、ネットワーキング、GPU などのインフラストラクチャコンポーネントに関連するコードが含まれています。
+* **[`platform`](./platform)**: データベースやメッセージキューなどのクラウドネイティブコンポーネントのコードが含まれています。
 * **`vendor`**: サードパーティのハードウェアベンダーからのコードが含まれています。
 
 ## Olaresへの貢献

apps/.olares/config/user/helm-charts/market/.helmignore

@@ -1,23 +0,0 @@
-# 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/

apps/.olares/config/user/helm-charts/market/Chart.yaml

@@ -1,26 +0,0 @@
-apiVersion: v2
-name: appstore
-description: A Helm chart for Kubernetes
-maintainers:
-- name: bytetrade
-
-# 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: 0.0.1
-
-# 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: "1.16.0"

apps/.olares/config/user/helm-charts/market/templates/_helpers.tpl

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

apps/.olares/config/user/helm-charts/market/templates/market_deploy.yaml

@@ -1,353 +0,0 @@
-{{- $market_secret := (lookup "v1" "Secret" .Release.Namespace "market-secrets") -}}
-
-{{- $redis_password := "" -}}
-{{ if $market_secret -}}
-{{ $redis_password = (index $market_secret "data" "redis-passwords") }}
-{{ else -}}
-{{ $redis_password = randAlphaNum 16 | b64enc }}
-{{- end -}}
-
-{{- $market_backend_nats_secret := (lookup "v1" "Secret" .Release.Namespace "market-backend-nats-secret") -}}
-{{- $nats_password := "" -}}
-{{ if $market_backend_nats_secret -}}
-{{ $nats_password = (index $market_backend_nats_secret "data" "nats_password") }}
-{{ else -}}
-{{ $nats_password = randAlphaNum 16 | b64enc }}
-{{- end -}}
-
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: market-backend-nats-secret
-  namespace: {{ .Release.Namespace }}
-type: Opaque
-data:
-  nats_password: {{ $nats_password }}
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: market-secrets
-  namespace: {{ .Release.Namespace }}
-type: Opaque
-data:
-  redis-passwords: {{ $redis_password }}
-
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: market-deployment
-  namespace: {{ .Release.Namespace }}
-  labels:
-    app: appstore
-    applications.app.bytetrade.io/author: bytetrade.io
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: appstore
-  template:
-    metadata:
-      labels:
-        app: appstore
-        io.bytetrade.app: "true"
-      annotations:
-        instrumentation.opentelemetry.io/inject-go: "olares-instrumentation"
-        instrumentation.opentelemetry.io/go-container-names: "appstore-backend"    
-        instrumentation.opentelemetry.io/otel-go-auto-target-exe: "/opt/app/market"
-    spec:
-      priorityClassName: "system-cluster-critical"
-      initContainers:
-        - args:
-          - -it
-          - authelia-backend.os-framework:9091
-          image: owncloudci/wait-for:latest
-          imagePullPolicy: IfNotPresent
-          name: check-auth
-        - name: terminus-sidecar-init
-          image: openservicemesh/init:v1.2.3
-          imagePullPolicy: IfNotPresent
-          securityContext:
-            privileged: true
-            capabilities: 
-              add:
-              - NET_ADMIN
-            runAsNonRoot: false
-            runAsUser: 0
-          command:
-          - /bin/sh
-          - -c
-          - |
-            iptables-restore --noflush <<EOF
-            # sidecar interception rules
-            *nat
-            :PROXY_IN_REDIRECT - [0:0]
-            :PROXY_INBOUND - [0:0]
-            -A PROXY_IN_REDIRECT -p tcp -j REDIRECT --to-port 15003
-            -A PROXY_INBOUND -p tcp --dport 15000 -j RETURN
-            -A PROXY_INBOUND -p tcp -j PROXY_IN_REDIRECT
-            -A PREROUTING -p tcp -j PROXY_INBOUND
-            COMMIT
-            EOF
-          
-          env:
-          - name: POD_IP
-            valueFrom:
-              fieldRef:
-                apiVersion: v1
-                fieldPath: status.podIP         
-      containers:
-      - name: appstore-backend
-        image: beclab/market-backend:v0.3.12
-        imagePullPolicy: IfNotPresent
-        ports:
-          - containerPort: 81
-        env:
-          - name: OS_SYSTEM_SERVER
-            value: system-server.user-system-{{ .Values.bfl.username }}
-          - name: OS_APP_SECRET
-            value: '{{ .Values.os.appstore.appSecret }}'
-          - name: OS_APP_KEY
-            value: {{ .Values.os.appstore.appKey }}
-          - name: APP_SOTRE_SERVICE_SERVICE_HOST
-            value: appstore-server-prod.bttcdn.com
-          - name: MARKET_PROVIDER
-            value: '{{ .Values.os.appstore.marketProvider }}'
-          - name: APP_SOTRE_SERVICE_SERVICE_PORT
-            value: '443'
-          - name: APP_SERVICE_SERVICE_HOST
-            value: app-service.os-framework
-          - name: APP_SERVICE_SERVICE_PORT
-            value: '6755'
-          - name: REPO_URL_PORT
-            value: "82"
-          - name: REDIS_ADDRESS
-            value: 'redis-cluster-proxy.user-system-{{ .Values.bfl.username }}:6379'
-          - name: REDIS_PASSWORD
-            valueFrom:
-              secretKeyRef:
-                name: market-secrets
-                key: redis-passwords
-          - name: REDIS_DB_NUMBER
-            value: '0'
-          - name: REPO_URL_HOST
-            valueFrom:
-              fieldRef:
-                fieldPath: status.podIP
-          - name: NATS_HOST
-            value: nats.user-system-{{ .Values.bfl.username }}
-          - name: NATS_PORT
-            value: '4222'
-          - name: NATS_USERNAME
-            value: os-market-backend
-          - name: NATS_PASSWORD
-            valueFrom:
-              secretKeyRef:
-                name: market-backend-nats-secret
-                key: nats_password
-          - name: NATS_SUBJECT_USER_APPLICATION
-            value: terminus.user.application.{{ .Values.bfl.username}}
-        volumeMounts:
-          - name: opt-data
-            mountPath: /opt/app/data
-      - name: terminus-envoy-sidecar
-        image: bytetrade/envoy:v1.25.11
-        imagePullPolicy: IfNotPresent
-        securityContext:
-          allowPrivilegeEscalation: false
-          runAsUser: 1000
-        ports:
-        - name: proxy-admin
-          containerPort: 15000
-        - name: proxy-inbound
-          containerPort: 15003
-        volumeMounts:
-        - name: terminus-sidecar-config
-          readOnly: true
-          mountPath: /etc/envoy/envoy.yaml
-          subPath: envoy.yaml
-        command:
-        - /usr/local/bin/envoy
-        - --log-level
-        - debug
-        - -c
-        - /etc/envoy/envoy.yaml
-        env:
-        - name: POD_UID
-          valueFrom:
-            fieldRef:
-              fieldPath: metadata.uid
-        - name: POD_NAME
-          valueFrom:
-            fieldRef:
-              fieldPath: metadata.name
-        - name: POD_NAMESPACE
-          valueFrom:
-            fieldRef:
-              fieldPath: metadata.namespace
-        - name: POD_IP
-          valueFrom:
-            fieldRef:
-              fieldPath: status.podIP
-      - name: terminus-ws-sidecar
-        image: 'beclab/ws-gateway:v1.0.5'
-        command:
-          - /ws-gateway
-        env:
-          - name: WS_PORT
-            value: '81'
-          - name: WS_URL
-            value: /app-store/v1/websocket/message
-        resources: { }
-        terminationMessagePath: /dev/termination-log
-        terminationMessagePolicy: File
-        imagePullPolicy: IfNotPresent
-      volumes:
-      - name: terminus-sidecar-config
-        configMap:
-          name: sidecar-ws-configs
-          items:
-          - key: envoy.yaml
-            path: envoy.yaml
-      - name: opt-data
-        hostPath:
-          path: '{{ .Values.userspace.appData}}/appstore/data'
-          type: DirectoryOrCreate
-      - name: app
-        emptyDir: {}
-      - name: nginx-confd
-        emptyDir: {}
-
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: appstore-service
-  namespace: {{ .Release.Namespace }}
-spec:
-  selector:
-    app: appstore
-  type: ClusterIP
-  ports:
-    - protocol: TCP
-      name: appstore-backend
-      port: 81
-      targetPort: 81
-
----
-apiVersion: sys.bytetrade.io/v1alpha1
-kind: ApplicationPermission
-metadata:
-  name: appstore
-  namespace: user-system-{{ .Values.bfl.username }}
-spec:
-  app: appstore
-  appid: appstore
-  key: {{ .Values.os.appstore.appKey }}
-  secret: {{ .Values.os.appstore.appSecret }}
-  permissions:
-  - dataType: event
-    group: message-disptahcer.system-server
-    ops:
-      - Create
-    version: v1
-  - dataType: app
-    group: service.bfl
-    ops:
-      - UserApps
-    version: v1
-status:
-  state: active
-
----
-apiVersion: sys.bytetrade.io/v1alpha1
-kind: ProviderRegistry
-metadata:
-  name: appstore-backend-provider
-  namespace: user-system-{{ .Values.bfl.username }}
-spec:
-  dataType: app
-  deployment: market
-  description: app store provider
-  endpoint: appstore-service.{{ .Release.Namespace }}:81
-  group: service.appstore
-  kind: provider
-  namespace: {{ .Release.Namespace }}
-  opApis:
-    - name: InstallDevApp
-      uri: /app-store/v1/applications/provider/installdev
-    - name: UninstallDevApp
-      uri: /app-store/v1/applications/provider/uninstalldev
-  version: v1
-status:
-  state: active
----
-apiVersion: apr.bytetrade.io/v1alpha1
-kind: MiddlewareRequest
-metadata:
-  name: market-redis
-  namespace: {{ .Release.Namespace }}
-spec:
-  app: market
-  appNamespace: {{ .Release.Namespace }}
-  middleware: redis
-  redis:
-    password:
-      valueFrom:
-        secretKeyRef:
-          key: redis-passwords
-          name: market-secrets
-    namespace: market
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: appstore-svc
-  namespace: {{ .Release.Namespace }}
-spec:
-  type: ClusterIP
-  selector:
-    app: appstore
-  ports:
-    - name: "appstore-backend"
-      protocol: TCP
-      port: 81
-      targetPort: 81
-    - name: "appstore-websocket"
-      protocol: TCP
-      port: 40010
-      targetPort: 40010
----
-apiVersion: apr.bytetrade.io/v1alpha1
-kind: MiddlewareRequest
-metadata:
-  name: market-backend-nats
-  namespace: {{ .Release.Namespace }}
-spec:
-  app: market-backend
-  appNamespace: os
-  middleware: nats
-  nats:
-    password:
-      valueFrom:
-        secretKeyRef:
-          key: nats_password
-          name: market-backend-nats-secret
-    refs:
-      - appName: user-service
-        appNamespace: os
-        subjects:
-          - name: "application.*"
-            perm:
-              - pub
-              - sub
-      - appName: user-service
-        appNamespace: os
-        subjects:
-          - name: "market.*"
-            perm:
-              - pub
-              - sub
-    user: os-market-backend

apps/.olares/config/user/helm-charts/market/values.yaml

@@ -1,44 +0,0 @@
-bfl:
-  nodeport: 30883
-  nodeport_ingress_http: 30083
-  nodeport_ingress_https: 30082
-  username: 'test'
-  url: 'test'
-  nodeName: test
-pvc:
-  userspace: test
-userspace:
-  userData: test/Home
-  appData: test/Data
-  appCache: test
-  dbdata: test
-docs:
-  nodeport: 30881
-desktop:
-  nodeport: 30180
-os:
-  portfolio:
-    appKey: '${ks[0]}'
-    appSecret: test
-  vault:
-    appKey: '${ks[0]}'
-    appSecret: test
-  desktop:
-    appKey: '${ks[0]}'
-    appSecret: test
-  message:
-    appKey: '${ks[0]}'
-    appSecret: test
-  rss:
-    appKey: '${ks[0]}'
-    appSecret: test
-  search:
-    appKey: '${ks[0]}'
-    appSecret: test
-  search2:
-    appKey: '${ks[0]}'
-    appSecret: test
-  appstore:
-    marketProvider: ''
-kubesphere:
-  redis_password: ""

apps/.olares/config/user/helm-charts/studio/templates/deployment.yaml

@@ -1,294 +1,13 @@
-{{- $namespace := printf "%s%s" "user-system-" .Values.bfl.username -}}
-{{- $studio_secret := (lookup "v1" "Secret" $namespace "studio-secrets") -}}
-
-{{- $pg_password := "" -}}
-{{ if $studio_secret -}}
-{{ $pg_password = (index $studio_secret "data" "pg_password") }}
-{{ else -}}
-{{ $pg_password = randAlphaNum 16 | b64enc }}
-{{- end -}}
-
----
-apiVersion: v1
-kind: Secret
-metadata:
-  name: studio-secrets
-  namespace: user-system-{{ .Values.bfl.username }}
-type: Opaque
-data:
-  pg_password: {{ $pg_password }}
-
----
-apiVersion: apr.bytetrade.io/v1alpha1
-kind: MiddlewareRequest
-metadata:
-  name: studio-pg
-  namespace: user-system-{{ .Values.bfl.username }}
-spec:
-  app: studio
-  appNamespace: {{ .Release.Namespace }}
-  middleware: postgres
-  postgreSQL:
-    user: studio_{{ .Values.bfl.username }}
-    password:
-      valueFrom:
-        secretKeyRef:
-          key: pg_password
-          name: studio-secrets
-    databases:
-      - name: studio
----
 apiVersion: v1
 kind: Service
 metadata:
   name: studio-server
-  namespace: {{ .Release.Namespace }}
+  namespace: user-space-{{ .Values.bfl.username }}
 spec:
-  selector:
-    app: studio-server
+  type: ExternalName
+  externalName: studio-server.os-framework.svc.cluster.local
   ports:
     - protocol: TCP
+      name: studio-server
       port: 8080
-      targetPort: 8088
-      name: http
-    - protocol: TCP
-      port: 8083
-      targetPort: 8083
-      name: https
-
----
-kind: Service
-apiVersion: v1
-metadata:
-  name: chartmuseum-studio
-  namespace: {{ .Release.Namespace }}
-spec:
-  ports:
-    - name: http
-      protocol: TCP
-      port: 8080
-      targetPort: 8888
-  selector:
-    app: studio-server
-
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  name: studio-san-cnf
-  namespace: {{ .Release.Namespace }}
-data:
-  san.cnf: |
-    [req]
-    distinguished_name = req_distinguished_name
-    req_extensions = v3_req
-    prompt = no
-
-    [req_distinguished_name]
-    countryName = CN
-    stateOrProvinceName = Beijing
-    localityName = Beijing
-    0.organizationName = bytetrade
-    commonName = studio-server.{{ .Release.Namespace }}.svc
-
-    [v3_req]
-    basicConstraints = CA:FALSE
-    keyUsage = nonRepudiation, digitalSignature, keyEncipherment
-    subjectAltName = @bytetrade
-
-    [bytetrade]
-    DNS.1 = studio-server.{{ .Release.Namespace }}.svc
-
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: studio-server
-  namespace: {{ .Release.Namespace }}
-  labels:
-    app: studio-server
-    applications.app.bytetrade.io/author: bytetrade.io
-spec:
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app: studio-server
-  template:
-    metadata:
-      labels:
-        app: studio-server
-    spec:
-      serviceAccountName: bytetrade-controller
-      volumes:
-        - name: chart
-          hostPath:
-            type: DirectoryOrCreate
-            path: '{{ .Values.userspace.appData}}/studio/Chart'
-        - name: data
-          hostPath:
-            type: DirectoryOrCreate
-            path: '{{ .Values.userspace.appData }}/studio/Data'
-        - name: storage-volume
-          hostPath:
-            path: '{{ .Values.userspace.appData }}/studio/helm-repo-dev'
-            type: DirectoryOrCreate
-        - name: config-san
-          configMap:
-            name: studio-san-cnf
-            items:
-              - key: san.cnf
-                path: san.cnf
-        - name: certs
-          emptyDir: {}
-      initContainers:
-        - name: init-chmod-data
-          image: busybox:1.28
-          imagePullPolicy: IfNotPresent
-          command:
-            - sh
-            - '-c'
-            - |
-              chown -R 1000:1000 /home/coder
-              chown -R 65532:65532 /charts
-              chown -R 65532:65532 /data
-          securityContext:
-            runAsUser: 0
-          resources: { }
-          volumeMounts:
-            - name: storage-volume
-              mountPath: /home/coder
-            - name: chart
-              mountPath: /charts
-            - name: data
-              mountPath: /data
-        - name: generate-certs
-          image: beclab/openssl:v3
-          imagePullPolicy: IfNotPresent
-          command: [ "/bin/sh", "-c" ]
-          args:
-            - |
-              openssl genrsa -out /etc/certs/ca.key 2048
-              openssl req -new -x509 -days 3650 -key /etc/certs/ca.key -out /etc/certs/ca.crt \
-                -subj "/CN=bytetrade CA/O=bytetrade/C=CN"
-              openssl req -new -newkey rsa:2048 -nodes \
-                -keyout /etc/certs/server.key -out /etc/certs/server.csr \
-                -config /etc/san/san.cnf
-              openssl x509 -req -days 3650 -in /etc/certs/server.csr \
-                -CA /etc/certs/ca.crt -CAkey /etc/certs/ca.key \
-                -CAcreateserial -out /etc/certs/server.crt \
-                -extensions v3_req -extfile /etc/san/san.cnf
-              chown -R 65532 /etc/certs/*
-          volumeMounts:
-            - name: config-san
-              mountPath: /etc/san
-            - name: certs
-              mountPath: /etc/certs
-
-      containers:
-        - name: studio
-          image: beclab/studio-server:v0.1.51
-          imagePullPolicy: IfNotPresent
-          args:
-            - server
-          ports:
-            - name: port
-              containerPort: 8088
-              protocol: TCP
-            - name: ssl-port
-              containerPort: 8083
-              protocol: TCP
-          volumeMounts:
-            - name: chart
-              mountPath: /charts
-            - name: data
-              mountPath: /data
-            - mountPath: /etc/certs
-              name: certs
-          lifecycle:
-            preStop:
-              exec:
-                command:
-                  - "/studio"
-                  - "clean"
-          env:
-            - name: BASE_DIR
-              value: /charts
-            - name: OS_API_KEY
-              value: {{ .Values.os.studio.appKey }}
-            - name: OS_API_SECRET
-              value: {{ .Values.os.studio.appSecret }}
-            - name: OS_SYSTEM_SERVER
-              value: system-server.user-system-{{ .Values.bfl.username }}
-            - name: NAME_SPACE
-              value: {{ .Release.Namespace }}
-            - name: OWNER
-              value: '{{ .Values.bfl.username }}'
-            - name: DB_HOST
-              value: citus-master-svc.user-system-{{ .Values.bfl.username }}
-            - name: DB_USERNAME
-              value: studio_{{ .Values.bfl.username }}
-            - name: DB_PASSWORD
-              value: "{{ $pg_password | b64dec }}"
-            - name: DB_NAME
-              value: user_space_{{ .Values.bfl.username }}_studio
-            - name: DB_PORT
-              value: "5432"
-          resources:
-            requests:
-              cpu: "50m"
-              memory: 100Mi
-            limits:
-              cpu: "0.5"
-              memory: 1000Mi
-        - name: chartmuseum
-          image: aboveos/helm-chartmuseum:v0.15.0
-          args:
-            - '--port=8888'
-            - '--storage-local-rootdir=/storage'
-          ports:
-            - name: http
-              containerPort: 8888
-              protocol: TCP
-          env:
-            - name: CHART_POST_FORM_FIELD_NAME
-              value: chart
-            - name: DISABLE_API
-              value: 'false'
-            - name: LOG_JSON
-              value: 'true'
-            - name: PROV_POST_FORM_FIELD_NAME
-              value: prov
-            - name: STORAGE
-              value: local
-          resources:
-            requests:
-              cpu: "50m"
-              memory: 100Mi
-            limits:
-              cpu: 1000m
-              memory: 512Mi
-          volumeMounts:
-            - name: storage-volume
-              mountPath: /storage
-          livenessProbe:
-            httpGet:
-              path: /health
-              port: http
-              scheme: HTTP
-            initialDelaySeconds: 5
-            timeoutSeconds: 1
-            periodSeconds: 10
-            successThreshold: 1
-            failureThreshold: 3
-          readinessProbe:
-            httpGet:
-              path: /health
-              port: http
-              scheme: HTTP
-            initialDelaySeconds: 5
-            timeoutSeconds: 1
-            periodSeconds: 10
-            successThreshold: 1
-            failureThreshold: 3
+      targetPort: 8080

apps/README.md

@@ -0,0 +1,20 @@
+# Olares Apps
+
+## Overview
+
+This directory contains the code for system applications, primarily for LarePass. The following are the pre-installed system applications that offer tools for managing files, knowledge, passwords, and the system itself.
+
+## System Applications Overview
+
+| Application | Description |
+| --- | --- |
+| Files | A file management app that manages and synchronizes files across devices and sources, enabling seamless sharing and access. |
+| Wise | A local-first and AI-native modern reader that helps to collect, read, and manage information from various platforms. Users can run self-hosted recommendation algorithms to filter and sort online content. |
+| Vault | A secure password manager for storing and managing sensitive information across devices. |
+| Market | A decentralized and permissionless app store for installing, uninstalling, and updating applications and recommendation algorithms. |
+| Desktop | A hub for managing and interacting with installed applications. File and application searching are also supported. |
+| Profile | An app to customize the user's profile page. |
+| Settings | A system configuration application. |
+| Dashboard | An app for monitoring system resource usage. |
+| Control Hub | The console for Olares, providing precise and autonomous control over the system and its environment. |
+| DevBox | A development tool for building and deploying Olares applications. |

build/base-package/wizard/config/account/templates/account.yaml

@@ -6,7 +6,7 @@ metadata:
   annotations:
     iam.kubesphere.io/uninitialized: "true"
     helm.sh/resource-policy: keep
-    bytetrade.io/owner-role: platform-admin
+    bytetrade.io/owner-role: owner
     bytetrade.io/terminus-name: "{{.Values.user.terminus_name}}"
     bytetrade.io/launcher-auth-policy: two_factor
     bytetrade.io/launcher-access-level: "1"
@@ -23,4 +23,4 @@ spec:
   groups:
   - lldap_admin
 status:
-  state: Active
+  state: Created

build/build-full.sh

@@ -24,6 +24,7 @@ cp ${BASE_DIR}/.dependencies/components ${BASE_DIR}/.manifest/.
 cp ${BASE_DIR}/.dependencies/components ${BASE_DIR}/.manifest/.
 pushd ${BASE_DIR}.manifest
 bash ${BASE_DIR}/build-manifest.sh ${BASE_DIR}/../.manifest/installation.manifest
+python3 ${BASE_DIR}/build-manifest.py ${BASE_DIR}/../.manifest/installation.manifest
 popd
 
 

build/build-manifest.py

@@ -0,0 +1,162 @@
+#!/usr/bin/env python3
+
+import argparse
+import hashlib
+import os
+import requests
+import sys
+import json
+
+CDN_URL = "https://dc3p1870nn3cj.cloudfront.net"
+
+def download_checksum(name):
+    """Downloads the checksum for a given name."""
+    url = f"{CDN_URL}/{name}.checksum.txt"
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        return response.text.split()[0]
+    except requests.exceptions.RequestException as e:
+        print(f"Error getting checksum for {name} from {url}: {e}", file=sys.stderr)
+        sys.exit(1)
+
+def get_image_manifest(name):
+    """Downloads the image manifest for a given name."""
+    url = f"{CDN_URL}/{name}.manifest.json"
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        print(f"Error getting manifest for {name} from {url}: {e}", file=sys.stderr)
+        sys.exit(1)        
+
+def main():
+    """Main function."""
+    parser = argparse.ArgumentParser()
+    parser.add_argument("manifest_file", help="The manifest file to write to.")
+    args = parser.parse_args()
+
+    manifest_file = args.manifest_file
+    version = os.environ.get("VERSION", "")
+    repo_path = os.environ.get("REPO_PATH", "/")
+    manifest_amd64_data = {}
+    manifest_arm64_data = {}
+
+    # Process components
+    try:
+        with open("components", "r") as f:
+            for line in f:
+                line = line.strip()
+                if not line:
+                    continue
+
+                # Replace version
+                if version:
+                    line = line.replace("#__VERSION__", version)
+
+                # Replace repo path
+                if repo_path:
+                    line = line.replace("#__REPO_PATH__", repo_path)
+
+                fields = line.split(",")
+                if len(fields) < 5:
+                    print(f"Format error in components file: {line}", file=sys.stderr)
+                    sys.exit(1)
+
+                filename, path, deps, _, fileid = fields[:5]
+                print(f"Downloading file checksum for {filename}")
+
+                name = hashlib.md5(filename.encode()).hexdigest()
+                url_amd64 = name
+                url_arm64 = f"arm64/{name}"
+
+                checksum_amd64 = download_checksum(url_amd64)
+                checksum_arm64 = download_checksum(url_arm64)
+
+                manifest_amd64_data[filename] = {
+                    "type": "component",
+                    "path": path,
+                    "deps": deps,
+                    "url_amd64": url_amd64,
+                    "checksum_amd64": checksum_amd64,
+                    "fileid": fileid
+                }
+
+
+                manifest_arm64_data[filename] = {
+                    "type": "component",
+                    "path": path,
+                    "deps": deps,
+                    "url_arm64": url_arm64,
+                    "checksum_arm64": checksum_arm64,
+                    "fileid": fileid
+                }
+
+    except FileNotFoundError:
+        print("Error: 'components' file not found.", file=sys.stderr)
+        sys.exit(1)
+
+    # Process images
+    path = "images"
+    for deps_file in ["images.mf"]:
+        try:
+            with open(deps_file, "r") as f:
+                for line in f:
+                    line = line.strip()
+                    if not line:
+                        continue
+
+                    print(f"Downloading file checksum for {line}")
+                    name = hashlib.md5(line.encode()).hexdigest()
+                    url_amd64 = f"{name}.tar.gz"
+                    url_arm64 = f"arm64/{name}.tar.gz"
+
+                    checksum_amd64 = download_checksum(name)
+                    checksum_arm64 = download_checksum(f"arm64/{name}")
+
+                    # Get the image manifest
+                    image_manifest_amd64 = get_image_manifest(name)
+                    image_manifest_arm64 = get_image_manifest(f"arm64/{name}")
+
+                    filename = f"{name}.tar.gz"
+                    manifest_amd64_data[filename] = {
+                        "type": "image",
+                        "path": path,
+                        "deps": deps_file,
+                        "url_amd64": url_amd64,
+                        "checksum_amd64": checksum_amd64,
+                        "fileid": line,
+                        "manifest": image_manifest_amd64
+                    }
+
+                    manifest_arm64_data[filename] = {
+                        "type": "image",
+                        "path": path,
+                        "deps": deps_file,
+                        "url_arm64": url_arm64,
+                        "checksum_arm64": checksum_arm64,
+                        "fileid": line,
+                        "manifest": image_manifest_arm64
+                    }
+                    
+
+        except FileNotFoundError:
+            print(f"Warning: '{deps_file}' not found, skipping.", file=sys.stderr)
+            sys.exit(1)
+
+
+    # Write the manifest file
+    amd64_manifest_file = f"{manifest_file}.amd64"
+    with open(amd64_manifest_file, "w") as mf:
+        json.dump(manifest_amd64_data, mf, indent=2)
+    
+    arm64_manifest_file = f"{manifest_file}.arm64"
+    with open(arm64_manifest_file, "w") as mf:
+        json.dump(manifest_arm64_data, mf, indent=2)
+
+
+    # TODO: compress the manifest files
+
+if __name__ == "__main__":
+    main()

build/build-manifest.sh

@@ -46,6 +46,9 @@ while read line; do
 done < components
 sed -i "s/#__VERSION__/${VERSION}/g" $manifest_file
 
+path="${REPO_PATH:-/}"
+sed -i "s|#__REPO_PATH__|${path}|g" $manifest_file
+
 path="images"
 for deps in "images.mf"; do
     while read line; do

build/build.sh

@@ -16,6 +16,7 @@ rm -rf ${BASE_DIR}/../.dependencies
 set -e
 pushd ${BASE_DIR}/../.manifest
 bash ${BASE_DIR}/build-manifest.sh ${BASE_DIR}/../.manifest/installation.manifest
+python3 ${BASE_DIR}/build-manifest.py ${BASE_DIR}/../.manifest/installation.manifest
 popd
 
 pushd $DIST_PATH

build/deps-manifest.sh

@@ -77,3 +77,5 @@ find $BASE_DIR/../ -type f -name Olares.yaml | while read f; do
 done
 
 sed -i "s/#__VERSION__/${VERSION}/g" ${manifest}
+path="${REPO_PATH:-/}"
+sed -i "s|#__REPO_PATH__|${path}|g" ${manifest}

build/get-manifest.py

@@ -0,0 +1,200 @@
+#!/usr/bin/env python3
+
+import requests
+import json
+import argparse
+import re
+import sys
+import platform
+
+def parse_image_name(image_name):
+    """
+    Parses a full image name into registry, repository, and reference (tag/digest).
+    Handles defaults for Docker Hub.
+    """
+    # Default to 'latest' tag if no tag or digest is specified
+    if ":" not in image_name and "@" not in image_name:
+        image_name += ":latest"
+    
+    # Split repository from reference (tag or digest)
+    if "@" in image_name:
+        repo_part, reference = image_name.rsplit("@", 1)
+    else:
+        repo_part, reference = image_name.rsplit(":", 1)
+
+    # Determine registry and repository
+    if "/" not in repo_part:
+        # This is an official Docker Hub image, e.g., "ubuntu"
+        registry = "registry-1.docker.io"
+        repository = f"library/{repo_part}"
+    else:
+        parts = repo_part.split("/")
+        # If the first part looks like a domain name, it's the registry
+        if "." in parts[0] or ":" in parts[0]:
+            registry = parts[0]
+            repository = "/".join(parts[1:])
+        else:
+            # A scoped Docker Hub image, e.g., "bitnami/nginx"
+            registry = "registry-1.docker.io"
+            repository = repo_part
+            
+    return registry, repository, reference
+
+def get_auth_token(registry, repository):
+    """
+    Gets an authentication token from the registry's auth service.
+    """
+    # First, probe the registry to get the auth challenge
+    try:
+        probe_url = f"https://{registry}/v2/"
+        response = requests.get(probe_url, timeout=10)
+    except requests.exceptions.RequestException as e:
+        print(f"Error: Could not connect to registry at {probe_url}. Details: {e}", file=sys.stderr)
+        sys.exit(1)
+
+    if response.status_code != 401:
+        # Either public or something is wrong, we can try without a token
+        return None
+
+    auth_header = response.headers.get("Www-Authenticate")
+    if not auth_header:
+        print(f"Error: Registry {registry} returned 401 but did not provide Www-Authenticate header.", file=sys.stderr)
+        sys.exit(1)
+
+    # Parse the Www-Authenticate header to find realm, service, and scope
+    try:
+        realm = re.search('realm="([^"]+)"', auth_header).group(1)
+        service = re.search('service="([^"]+)"', auth_header).group(1)
+        # Scope for the specific repository is needed
+        scope = f"repository:{repository}:pull"
+    except AttributeError:
+        print(f"Error: Could not parse Www-Authenticate header: {auth_header}", file=sys.stderr)
+        sys.exit(1)
+
+    # Request the actual token from the auth realm
+    auth_params = {
+        "service": service,
+        "scope": scope
+    }
+    
+    try:
+        auth_response = requests.get(realm, params=auth_params, timeout=10)
+        auth_response.raise_for_status()
+        return auth_response.json().get("token")
+    except requests.exceptions.RequestException as e:
+        print(f"Error: Failed to get auth token from {realm}. Details: {e}", file=sys.stderr)
+        sys.exit(1)
+    except json.JSONDecodeError:
+        print(f"Error: Failed to decode JSON response from auth server: {auth_response.text}", file=sys.stderr)
+        sys.exit(1)
+
+
+def get_manifest(registry, repository, reference, token):
+    """
+    Fetches the image manifest from the registry.
+    """
+    manifest_url = f"https://{registry}/v2/{repository}/manifests/{reference}"
+    
+    headers = {
+        # Request multiple manifest types, the registry will return the correct one
+        "Accept": "application/vnd.oci.image.index.v1+json, application/vnd.oci.image.manifest.v1+json, application/vnd.docker.distribution.manifest.v2+json, application/vnd.docker.distribution.manifest.list.v2+json"
+    }
+
+    if token:
+        headers["Authorization"] = f"Bearer {token}"
+
+    try:
+        response = requests.get(manifest_url, headers=headers, timeout=10)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.HTTPError as e:
+        if e.response.status_code == 401 and not token:
+             print("Error: Received 401 Unauthorized. Attempting to get a token...", file=sys.stderr)
+             # The initial probe might have passed, but manifest access requires auth.
+             # We re-run the token acquisition logic.
+             new_token = get_auth_token(registry, repository)
+             if new_token:
+                 return get_manifest(registry, repository, reference, new_token)
+        print(f"Error: Failed to fetch manifest from {manifest_url}. Status: {e.response.status_code}", file=sys.stderr)
+        print(f"Response: {e.response.text}", file=sys.stderr)
+        sys.exit(1)
+    except requests.exceptions.RequestException as e:
+        print(f"Error: A network error occurred. Details: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Fetch an OCI/Docker image manifest from a container registry.",
+        epilog="""Examples:
+  python get_manifest.py ubuntu:22.04
+  python get_manifest.py quay.io/brancz/kube-rbac-proxy:v0.18.1 -o manifest.json
+  python get_manifest.py gcr.io/google-containers/pause:3.9""",
+        formatter_class=argparse.RawTextHelpFormatter
+    )
+    parser.add_argument("image_name", help="Full name of the container image (e.g., 'ubuntu:latest' or 'quay.io/prometheus/node-exporter:v1.7.0')")
+    parser.add_argument("-o", "--output-file", help="Optional. Path to write the final manifest JSON to. If not provided, prints to stdout.")
+    args = parser.parse_args()
+
+    registry, repository, reference = parse_image_name(args.image_name)
+
+    # Suppress informational prints if writing to a file
+    verbose_print = print if not args.output_file else lambda *a, **k: None
+
+    verbose_print(f"Registry:   {registry}")
+    verbose_print(f"Repository: {repository}")
+    verbose_print(f"Reference:  {reference}", end='\n\n', flush=True)
+
+    token = get_auth_token(registry, repository)
+
+    if not token and not args.output_file:
+        print("No authentication token needed or could be retrieved. Proceeding without token...", file=sys.stderr)
+
+    manifest = get_manifest(registry, repository, reference, token)
+    final_manifest = None
+
+    media_type = manifest.get("mediaType", "")
+    if "manifest.list" in media_type or "image.index" in media_type:
+        verbose_print("Detected a multi-platform image index. Finding manifest for current architecture...")
+
+        system_arch = platform.machine()
+        arch_map = {"x86_64": "amd64", "aarch64": "arm64"}
+        target_arch = arch_map.get(system_arch, system_arch)
+
+        verbose_print(f"System architecture: {system_arch} -> Target: linux/{target_arch}")
+
+        target_digest = None
+        for m in manifest.get("manifests", []):
+            plat = m.get("platform", {})
+            if plat.get("os") == "linux" and plat.get("architecture") == target_arch:
+                target_digest = m.get("digest")
+                break
+
+        if target_digest:
+            verbose_print(f"Found manifest for linux/{target_arch} with digest: {target_digest}\n")
+            final_manifest = get_manifest(registry, repository, target_digest, token)
+        else:
+            print(f"Error: Could not find a manifest for 'linux/{target_arch}' in the index.", file=sys.stderr)
+            if not args.output_file:
+                print("Available platforms:", file=sys.stderr)
+                for m in manifest.get("manifests", []):
+                    print(f"  - {m.get('platform', {}).get('os')}/{m.get('platform', {}).get('architecture')}", file=sys.stderr)
+            sys.exit(1)
+    else:
+        final_manifest = manifest
+
+    if final_manifest:
+        if args.output_file:
+            try:
+                with open(args.output_file, 'w') as f:
+                    json.dump(final_manifest, f, indent=2)
+                print(f"Successfully wrote manifest to {args.output_file}")
+            except IOError as e:
+                print(f"Error: Could not write to file {args.output_file}. Details: {e}", file=sys.stderr)
+                sys.exit(1)
+        else:
+            print(json.dumps(final_manifest, indent=2))
+
+
+if __name__ == "__main__":
+    main()

build/package.sh

@@ -74,6 +74,6 @@ echo "packaging launcher ..."
 run_cmd "cp -rf framework/bfl/.olares/config/launcher ${DIST}/wizard/config/"
 
 echo "packaging gpu ..."
-run_cmd "cp -rf framework/gpu/.olares/config/gpu ${DIST}/wizard/config/"
+run_cmd "cp -rf infrastructure/gpu/.olares/config/gpu ${DIST}/wizard/config/"
 
 echo "packaging completed"

build/upload-deps.sh

@@ -23,26 +23,28 @@ while read line; do
         continue
     fi
     
-    bash ${BASE_DIR}/download-deps.sh $PLATFORM $line
-    if [ $? -ne 0 ]; then
-        exit -1
-    fi
-
     filename=$(echo "$line"|awk -F"," '{print $1}')
-    echo "if exists $filename ... "
     name=$(echo -n "$filename"|md5sum|awk '{print $1}')
     checksum="$name.checksum.txt"
-    md5sum $name > $checksum
-    backup_file=$(awk '{print $1}' $checksum)
-    if [ x"$backup_file"  == x""  ]; then
-        echo  "invalid checksum"
-        exit 1
-    fi
 
+    echo "if exists $filename ... "
     curl -fsSLI https://dc3p1870nn3cj.cloudfront.net/$path$name > /dev/null
     if [ $? -ne 0 ]; then
-        code=$(curl -o /dev/null -fsSLI -w "%{http_code}" https://dc3p1870nn3cj.cloudfront.net/$path$name.tar.gz)
+        code=$(curl -o /dev/null -fsSLI -w "%{http_code}" https://dc3p1870nn3cj.cloudfront.net/$path$name)
         if [ $code -eq 403 ]; then
+
+            bash ${BASE_DIR}/download-deps.sh $PLATFORM $line
+            if [ $? -ne 0 ]; then
+                exit -1
+            fi
+
+            md5sum $name > $checksum
+            backup_file=$(awk '{print $1}' $checksum)
+            if [ x"$backup_file"  == x""  ]; then
+                echo  "invalid checksum"
+                exit 1
+            fi
+
             set -ex
             aws s3 cp $name s3://terminus-os-install/$path$name --acl=public-read
             aws s3 cp $name s3://terminus-os-install/backup/$path$backup_file --acl=public-read

build/upload-images.sh

@@ -10,6 +10,7 @@ cat $1|while read image; do
     echo "if exists $image ... "
     name=$(echo -n "$image"|md5sum|awk '{print $1}')
     checksum="$name.checksum.txt"
+    manifest="$name.manifest.json"
 
     curl -fsSLI https://dc3p1870nn3cj.cloudfront.net/$path$name.tar.gz > /dev/null
     if [ $? -ne 0 ]; then
@@ -68,48 +69,29 @@ cat $1|while read image; do
             set +ex
         else
             if [ $code -ne 200  ]; then
-                echo  "failed to check image"
+                echo  "failed to check image checksum"
                 exit -1
             fi
         fi
     fi
 
-    # upload to tencent cloud cos
-
-    # curl -fsSLI https://cdn.joinolares.cn/$path$name.tar.gz > /dev/null
-    # if [ $? -ne 0 ]; then
-    #     set -e
-    #     docker pull $image
-    #     docker save $image -o $name.tar
-    #     gzip $name.tar
-
-    #     md5sum $name.tar.gz > $checksum
-
-    #     coscmd upload ./$name.tar.gz /$path$name.tar.gz
-    #     coscmd upload ./$checksum /$path$checksum
-    #     echo "upload $name to cos completed"
-
-    #     set +e
-    # fi
-
-    
-
-    # # re-upload checksum.txt
-    # curl -fsSLI https://cdn.joinolares.cn/$path$checksum > /dev/null
-    # if [ $? -ne 0 ]; then
-    #     set -e
-    #     docker pull $image
-    #     docker save $image -o $name.tar
-    #     gzip $name.tar
-
-    #     md5sum $name.tar.gz > $checksum
-
-    #     coscmd upload ./$name.tar.gz /$path$name.tar.gz
-    #     coscmd upload ./$checksum /$path$checksum
-    #     echo "upload $name to cos completed"
-
-    #     set +e
-    # fi
-    
+    # upload manifest.json
+    curl -fsSLI https://dc3p1870nn3cj.cloudfront.net/$path$manifest > /dev/null
+    if [ $? -ne 0 ]; then   
+        code=$(curl -o /dev/null -fsSLI -w "%{http_code}" https://dc3p1870nn3cj.cloudfront.net/$path$manifest)
+        if [ $code -eq 403 ]; then
+            set -ex
+            BASE_DIR=$(dirname $(realpath -s $0))
+            python3 $BASE_DIR/get-manifest.py $image -o $manifest
 
+            aws s3 cp $manifest s3://terminus-os-install/$path$manifest --acl=public-read
+            echo "upload $name manifest completed"
+            set +ex
+        else
+            if [ $code -ne 200  ]; then
+                echo  "failed to check image manifest"
+                exit -1
+            fi
+        fi
+    fi
 done

cli/.goreleaser.yaml

@@ -17,8 +17,12 @@ builds:
     ignore:
       - goos: darwin
         goarch: arm
+      - goos: darwin
+        goarch: amd64
       - goos: windows
         goarch: arm
+      - goos: windows
+        goarch: arm64
     ldflags:
       - -s
       - -w

cli/README.md

@@ -1 +1,92 @@
-# installer
+# Olares CLI
+
+This directory contains the code for **olares-cli**, the official command-line interface for administering an **Olares** cluster. It provides a modular, pipeline-based architecture for orchestrating complex system operations. See the full [Olares CLI Documentation](https://docs.olares.com/developer/install/cli-1.12/olares-cli.html) for command reference and tutorials.
+
+Key responsibilities include: 
+- **Cluster management**: Installing, upgrading, restarting, and maintaining an Olares cluster.
+- **Node management**: Adding to or removing nodes from an Olares cluster.
+
+
+## Execution Model
+
+For most of the commands, `olares-cli` is executed through a four-tier hierarchy:
+
+```
+Pipeline ➜ Module ➜ Task ➜ Action
+````
+
+### Example: `install-olares` Pipeline
+
+```text
+Pipeline: Install Olares
+├── ...other modules
+└── Module: Bootstrap OS
+    ├── ...other tasks
+    ├── Task: Check Prerequisites
+    │   └── Action: run-precheck.sh
+    └── Task: Configure System
+        └── Action: apply-sysctl
+````
+
+
+## Repository layout
+
+```text
+cli/
+├── cmd/                  # Cobra command definitions
+│   ├── main.go           # CLI entry point
+│   └── ctl/
+│       ├── root.go
+│       ├── os/           # OS-level maintenance commands
+│       ├── node/         # Cluster node operations
+│       └── gpu/          # GPU management
+└── pkg/
+    ├── core/
+    │   ├── action/       # Re-usable action primitives
+    │   ├── module/       # Module abstractions
+    │   ├── pipeline/     # Pipeline abstractions
+    │   └── task/         # Task abstractions
+    └── pipelines/        # Pre-built pipelines
+    │   ├── ...           # actual modules and tasks for various commands and components
+```
+
+
+## Build from source
+
+### Prerequisites
+
+* **Go 1.24+**
+* **GoReleaser** (optional, for cross-compiling and packaging)
+
+### Sample commands
+
+```bash
+# Clone the repo and enter the CLI folder
+cd cli
+
+# 1) Build for the host OS/ARCH
+go build -o olares-cli ./cmd/main.go
+
+# 2) Cross-compile for Linux amd64 (from macOS, for example)
+GOOS=linux GOARCH=amd64 go build -o olares-cli ./cmd/main.go
+
+# 3) Produce multi-platform artifacts (tar.gz, checksums, etc.)
+goreleaser release --snapshot --clean
+```
+
+---
+
+## Development workflow
+
+### Add a new command
+
+1. Create the command file in `cmd/ctl/<category>/`.
+2. Define a pipeline in `pkg/pipelines/`.
+3. Implement modules & tasks inside the relevant `pkg/` sub-packages.
+
+
+### Test your build
+
+1. Upload the self-built `olares-cli` binary to a machine that's running Olares.
+2. Replace the existing `olares-cli` binary on the machine using `sudo cp -f olares-cli /usr/local/bin`.
+3. Execute arbitrary commands using `olares-cli`

cli/pkg/bootstrap/os/templates/init_script.go

@@ -60,7 +60,7 @@ echo 'net.ipv4.ip_forward = 1' >> /etc/sysctl.conf
 echo 'net.bridge.bridge-nf-call-arptables = 1' >> /etc/sysctl.conf
 echo 'net.bridge.bridge-nf-call-ip6tables = 1' >> /etc/sysctl.conf
 echo 'net.bridge.bridge-nf-call-iptables = 1' >> /etc/sysctl.conf
-echo 'net.ipv4.ip_local_reserved_ports = 30000-32767' >> /etc/sysctl.conf
+echo 'net.ipv4.ip_local_reserved_ports = 30000-32767,46800-50000' >> /etc/sysctl.conf
 echo 'vm.max_map_count = 262144' >> /etc/sysctl.conf
 echo 'fs.inotify.max_user_instances = 524288' >> /etc/sysctl.conf
 echo 'kernel.pid_max = 65535' >> /etc/sysctl.conf
@@ -84,7 +84,7 @@ sed -r -i  "s@#{0,}?net.ipv4.ip_forward ?= ?(0|1)@net.ipv4.ip_forward = 1@g" /et
 sed -r -i  "s@#{0,}?net.bridge.bridge-nf-call-arptables ?= ?(0|1)@net.bridge.bridge-nf-call-arptables = 1@g" /etc/sysctl.conf
 sed -r -i  "s@#{0,}?net.bridge.bridge-nf-call-ip6tables ?= ?(0|1)@net.bridge.bridge-nf-call-ip6tables = 1@g" /etc/sysctl.conf
 sed -r -i  "s@#{0,}?net.bridge.bridge-nf-call-iptables ?= ?(0|1)@net.bridge.bridge-nf-call-iptables = 1@g" /etc/sysctl.conf
-sed -r -i  "s@#{0,}?net.ipv4.ip_local_reserved_ports ?= ?([0-9]{1,}-{0,1},{0,1}){1,}@net.ipv4.ip_local_reserved_ports = 30000-32767@g" /etc/sysctl.conf
+sed -r -i  "s@#{0,}?net.ipv4.ip_local_reserved_ports ?= ?([0-9]{1,}-{0,1},{0,1}){1,}@net.ipv4.ip_local_reserved_ports = 30000-32767,46800-50000@g" /etc/sysctl.conf
 sed -r -i  "s@#{0,}?vm.max_map_count ?= ?([0-9]{1,})@vm.max_map_count = 262144@g" /etc/sysctl.conf
 sed -r -i  "s@#{0,}?fs.inotify.max_user_instances ?= ?([0-9]{1,})@fs.inotify.max_user_instances = 524288@g" /etc/sysctl.conf
 sed -r -i  "s@#{0,}?kernel.pid_max ?= ?([0-9]{1,})@kernel.pid_max = 65535@g" /etc/sysctl.conf

cli/pkg/common/common.go

@@ -265,7 +265,7 @@ const (
 	CacheAppServicePod = "app_service_pod_name"
 	CacheAppValues     = "app_built_in_values"
 
-	CacheCountPodsUsingHostIP = "count_pods_using_host_ip"
+	CacheCountPodsWaitForRecreation = "count_pods_wait_for_recreation"
 
 	CacheUpgradeUsers     = "upgrade_users"
 	CacheUpgradeAdminUser = "upgrade_admin_user"

cli/pkg/common/kube_runtime.go

@@ -73,7 +73,6 @@ type Argument struct {
 	ImagesDir        string `json:"images_dir"`
 	Namespace        string `json:"namespace"`
 	DeleteCRI        bool   `json:"delete_cri"`
-	DeleteCache      bool   `json:"delete_cache"`
 	Role             string `json:"role"`
 	Type             string `json:"type"`
 	Kubetype         string `json:"kube_type"`
@@ -322,10 +321,26 @@ func (a *Argument) SaveReleaseInfo() error {
 	if a.OlaresVersion == "" {
 		return errors.New("invalid: empty olares version")
 	}
+
 	releaseInfoMap := map[string]string{
 		ENV_OLARES_BASE_DIR: a.BaseDir,
 		ENV_OLARES_VERSION:  a.OlaresVersion,
 	}
+
+	if a.User != nil {
+		releaseInfoMap["OLARES_NAME"] = fmt.Sprintf("%s@%s", a.User.UserName, a.User.DomainName)
+	} else {
+		if util.IsExist(OlaresReleaseFile) {
+			// if the user is not set, try to load the user name from the release file
+			envs, err := godotenv.Read(OlaresReleaseFile)
+			if err == nil {
+				if userName, ok := envs["OLARES_NAME"]; ok {
+					releaseInfoMap["OLARES_NAME"] = userName
+				}
+			}
+		}
+	}
+
 	if !util.IsExist(filepath.Dir(OlaresReleaseFile)) {
 		if err := os.MkdirAll(filepath.Dir(OlaresReleaseFile), 0755); err != nil {
 			return fmt.Errorf("failed to create directory %s: %v", filepath.Dir(OlaresReleaseFile), err)
@@ -395,10 +410,6 @@ func (a *Argument) SetRegistryMirrors(registryMirrors string) {
 	a.RegistryMirrors = registryMirrors
 }
 
-func (a *Argument) SetDeleteCache(deleteCache bool) {
-	a.DeleteCache = deleteCache
-}
-
 func (a *Argument) SetDeleteCRI(deleteCRI bool) {
 	a.DeleteCRI = deleteCRI
 }

cli/pkg/common/plugins.go

@@ -1,17 +1,16 @@
 package common
 
 const (
-	NamespaceDefault                       = "default"
-	NamespaceKubeNodeLease                 = "kube-node-lease"
-	NamespaceKubePublic                    = "kube-public"
-	NamespaceKubeSystem                    = "kube-system"
-	NamespaceKubekeySystem                 = "kubekey-system"
-	NamespaceKubesphereControlsSystem      = "kubesphere-controls-system"
-	NamespaceKubesphereMonitoringFederated = "kubesphere-monitoring-federated"
-	NamespaceKubesphereMonitoringSystem    = "kubesphere-monitoring-system"
-	NamespaceKubesphereSystem              = "kubesphere-system"
-	NamespaceOsFramework                   = "os-framework"
-	NamespaceOsPlatform                    = "os-platform"
+	NamespaceDefault                    = "default"
+	NamespaceKubeNodeLease              = "kube-node-lease"
+	NamespaceKubePublic                 = "kube-public"
+	NamespaceKubeSystem                 = "kube-system"
+	NamespaceKubekeySystem              = "kubekey-system"
+	NamespaceKubesphereControlsSystem   = "kubesphere-controls-system"
+	NamespaceKubesphereMonitoringSystem = "kubesphere-monitoring-system"
+	NamespaceKubesphereSystem           = "kubesphere-system"
+	NamespaceOsFramework                = "os-framework"
+	NamespaceOsPlatform                 = "os-platform"
 
 	ChartNameRedis               = "redis"
 	ChartNameSnapshotController  = "snapshot-controller"

cli/pkg/daemon/task.go

@@ -133,8 +133,11 @@ type DisableTerminusdService struct {
 }
 
 func (s *DisableTerminusdService) Execute(runtime connector.Runtime) error {
-	if _, err := runtime.GetRunner().SudoCmd("systemctl disable --now olaresd", false, true); err != nil {
-		return errors.Wrap(errors.WithStack(err), "disable olaresd failed")
+	stdout, _ := runtime.GetRunner().SudoCmd("systemctl is-active olaresd", false, false)
+	if stdout == "active" {
+		if _, err := runtime.GetRunner().SudoCmd("systemctl disable --now olaresd", false, true); err != nil {
+			return errors.Wrap(errors.WithStack(err), "disable olaresd failed")
+		}
 	}
 	return nil
 }
@@ -144,10 +147,18 @@ type UninstallTerminusd struct {
 }
 
 func (r *UninstallTerminusd) Execute(runtime connector.Runtime) error {
+	var olaresdFiles []string
 	svcpath := filepath.Join("/etc/systemd/system", templates.TerminusdService.Name())
 	svcenvpath := filepath.Join("/etc/systemd/system", templates.TerminusdEnv.Name())
-	if _, err := runtime.GetRunner().SudoCmd(fmt.Sprintf("rm -rf %s && rm -rf %s && rm -rf /usr/local/bin/olaresd", svcpath, svcenvpath), false, false); err != nil {
-		return errors.Wrap(errors.WithStack(err), "remove olaresd failed")
+	binPath := "/usr/local/bin/olaresd"
+	olaresdFiles = append(olaresdFiles, svcpath, svcenvpath, binPath)
+	for _, pidFile := range []string{"installing.pid", "changingip.pid"} {
+		olaresdFiles = append(olaresdFiles, filepath.Join(runtime.GetBaseDir(), pidFile))
+	}
+	for _, f := range olaresdFiles {
+		if _, err := runtime.GetRunner().SudoCmd(fmt.Sprintf("rm -rf %s", f), false, false); err != nil {
+			return errors.Wrap(errors.WithStack(err), "remove olaresd failed")
+		}
 	}
 	return nil
 }

cli/pkg/gpu/module.go

@@ -263,30 +263,25 @@ type NodeLabelingModule struct {
 func (l *NodeLabelingModule) Init() {
 	l.Name = "NodeLabeling"
 
-	updateNode := &task.RemoteTask{
-		Name:  "UpdateNode",
-		Hosts: l.Runtime.GetHostsByRole(common.Master),
+	updateNode := &task.LocalTask{
+		Name: "UpdateNode",
 		Prepare: &prepare.PrepareCollection{
-			new(common.OnlyFirstMaster),
 			new(CudaInstalled),
 			new(K8sNodeInstalled),
 		},
-		Action:   new(UpdateNodeLabels),
-		Parallel: false,
-		Retry:    1,
+		Action: new(UpdateNodeLabels),
+		Retry:  1,
 	}
 
-	restartPlugin := &task.RemoteTask{
-		Name:  "RestartPlugin",
-		Hosts: l.Runtime.GetHostsByRole(common.Master),
+	restartPlugin := &task.LocalTask{
+		Name: "RestartPlugin",
 		Prepare: &prepare.PrepareCollection{
 			new(common.OnlyFirstMaster),
 			new(CudaInstalled),
 			new(K8sNodeInstalled),
 		},
-		Action:   new(RestartPlugin),
-		Parallel: false,
-		Retry:    1,
+		Action: new(RestartPlugin),
+		Retry:  1,
 	}
 
 	l.Tasks = []task.Interface{

cli/pkg/k3s/tasks.go

@@ -195,11 +195,13 @@ func (g *GenerateK3sService) Execute(runtime connector.Runtime) error {
 	defaultKubeletArs := map[string]string{
 		"kube-reserved":           "cpu=200m,memory=250Mi,ephemeral-storage=1Gi",
 		"system-reserved":         "cpu=200m,memory=250Mi,ephemeral-storage=1Gi",
-		"eviction-hard":           "memory.available<5%,nodefs.available<10%",
+		"eviction-hard":           "memory.available<5%,nodefs.available<10%,imagefs.available<10%",
 		"config":                  "/etc/rancher/k3s/kubelet.config",
 		"containerd":              container.DefaultContainerdCRISocket,
 		"cgroup-driver":           "systemd",
 		"runtime-request-timeout": "5m",
+		"image-gc-high-threshold": "91",
+		"image-gc-low-threshold":  "90",
 	}
 	defaultKubeProxyArgs := map[string]string{
 		"proxy-mode": "ipvs",

cli/pkg/kubernetes/templates/v1beta2/kubeadm_config.go

@@ -307,6 +307,8 @@ func GetKubeletConfiguration(runtime connector.Runtime, kubeConf *common.KubeCon
 		"evictionPressureTransitionPeriod": "30s",
 		"featureGates":                     FeatureGatesDefaultConfiguration,
 		"runtimeRequestTimeout":            "5m",
+		"imageGCHighThresholdPercent":      91,
+		"imageGCLowThresholdPercent":       90,
 	}
 
 	if securityEnhancement {

cli/pkg/kubesphere/module.go

@@ -47,24 +47,6 @@ func (m *DeleteKubeSphereCachesModule) Init() {
 	}
 }
 
-type DeleteCacheModule struct {
-	common.KubeModule
-}
-
-func (m *DeleteCacheModule) Init() {
-	m.Name = "DeleteCache"
-
-	deleteCache := &task.LocalTask{
-		Name:    "DeleteCache",
-		Prepare: new(ShouldDeleteCache),
-		Action:  new(DeleteCache),
-	}
-
-	m.Tasks = []task.Interface{
-		deleteCache,
-	}
-}
-
 type DeployModule struct {
 	common.KubeModule
 	Skip bool

cli/pkg/kubesphere/plugins/files/build/ks-core-config/values.yaml

@@ -4,8 +4,6 @@
 
 image:
   # Overrides the image tag whose default is the chart appVersion.
-  ks_controller_manager_repo: kubesphere/ks-controller-manager
-  ks_controller_manager_tag: "v3.3.0"
 
   ks_apiserver_repo: beclab/ks-apiserver
   ks_apiserver_tag: "v3.3.0-ext-3"

cli/pkg/kubesphere/plugins/files/build/ks-core/templates/ks-apiserver.yml

@@ -32,7 +32,7 @@ spec:
       - command:
         - ks-apiserver
         - --logtostderr=true
-        image: beclab/ks-apiserver:0.0.20
+        image: beclab/ks-apiserver:0.0.21
         imagePullPolicy: {{ .Values.image.pullPolicy }}
         name: ks-apiserver
         ports:

cli/pkg/kubesphere/plugins/files/build/ks-core/templates/ks-controller-manager.yaml

@@ -1,121 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  labels:
-    app: ks-controller-manager
-    tier: backend
-    version: {{ .Chart.AppVersion }}
-  name: ks-controller-manager
-spec:
-  strategy:
-    rollingUpdate:
-      maxSurge: 0
-    type: RollingUpdate
-  progressDeadlineSeconds: 600
-  replicas: 1
-  revisionHistoryLimit: 10
-  selector:
-    matchLabels:
-      app: ks-controller-manager
-      tier: backend
-      # version: {{ .Chart.AppVersion }}
-  template:
-    metadata:
-      labels:
-        app: ks-controller-manager
-        tier: backend
-        # version: {{ .Chart.AppVersion }}
-    spec:
-      {{- with .Values.imagePullSecrets }}
-      imagePullSecrets:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      containers:
-      - command:
-        - controller-manager
-        - --logtostderr=true
-        - --leader-elect=false
-        image: beclab/ks-controller-manager:0.0.20
-        imagePullPolicy: {{ .Values.image.pullPolicy }}
-        name: ks-controller-manager
-        ports:
-        - containerPort: 8080
-          protocol: TCP
-        resources:
-          {{- toYaml .Values.controller.resources | nindent 12 }}
-        volumeMounts:
-        - mountPath: /etc/kubesphere/
-          name: kubesphere-config
-        - mountPath: /etc/localtime
-          name: host-time
-          readOnly: true
-        {{- if .Values.controller.extraVolumeMounts }}
-          {{- toYaml .Values.controller.extraVolumeMounts | nindent 8 }}
-        {{- end }}
-        env:
-        {{- if .Values.env }}
-        {{- toYaml .Values.env | nindent 8 }}
-        {{- end }}
-      dnsPolicy: ClusterFirst
-      restartPolicy: Always
-      schedulerName: default-scheduler
-      serviceAccountName: {{ include "ks-core.serviceAccountName" . }}
-      terminationGracePeriodSeconds: 30
-      volumes:
-      - name: kubesphere-config
-        configMap:
-          name: kubesphere-config
-          defaultMode: 420
-      - hostPath:
-          path: /etc/localtime
-          type: ""
-        name: host-time
-      {{- if .Values.controller.extraVolumes }}
-        {{ toYaml .Values.controller.extraVolumes | nindent 6 }}
-      {{- end }}
-      {{- with .Values.tolerations }}
-      tolerations:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      {{- with .Values.nodeSelector }}
-      nodeSelector:
-        {{- toYaml . | nindent 8 }}
-      {{- end }}
-      affinity:
-        podAntiAffinity:
-          requiredDuringSchedulingIgnoredDuringExecution:
-          - topologyKey: kubernetes.io/hostname
-            labelSelector:
-              matchExpressions:
-              - key: app
-                operator: In
-                values:
-                - ks-controller-manager
-            namespaces:
-            - kubesphere-system
-{{- with .Values.nodeAffinity }}
-        nodeAffinity:
-{{ toYaml . | indent 10 }}
-{{- end }}
-
----
-
-apiVersion: v1
-kind: Service
-metadata:
-  labels:
-    app: ks-controller-manager
-    tier: backend
-    version: {{ .Chart.AppVersion }}
-  name: ks-controller-manager
-spec:
-  ports:
-  - port: 443
-    protocol: TCP
-    targetPort: 8443
-  selector:
-    app: ks-controller-manager
-    tier: backend
-    # version: {{ .Chart.AppVersion }}
-  sessionAffinity: None
-  type: ClusterIP

cli/pkg/kubesphere/plugins/files/build/ks-core/values.yaml

@@ -4,8 +4,6 @@
 
 image:
   # Overrides the image tag whose default is the chart appVersion.
-  ks_controller_manager_repo: kubesphere/ks-controller-manager
-  ks_controller_manager_tag: "v3.3.0"
 
   ks_apiserver_repo: beclab/ks-apiserver
   ks_apiserver_tag: "v3.3.0-ext-3"

cli/pkg/kubesphere/plugins/files/build/prometheus/kubernetes/kubernetes-prometheusRule.yaml

@@ -748,12 +748,12 @@ spec:
             sum (node_cpu_seconds_total{job="node-exporter", mode=~"user|nice|system|iowait|irq|softirq"}) by (cpu, instance, job, namespace, pod)
           record: node_cpu_used_seconds_total
         - expr: |
-            max(kube_pod_info{job="kube-state-metrics"} * on(node) group_left(role) kube_node_role{job="kube-state-metrics", role="master"} or on(pod, namespace) kube_pod_info{job="kube-state-metrics"}) by (node, namespace, host_ip, role, pod)
+            max(kube_pod_info{job="kube-state-metrics"} * on(node) group_left(role) kube_node_role{job="kube-state-metrics", role="master"} or on(pod, namespace) kube_pod_info{job="kube-state-metrics"}) by (node, namespace, role, pod)
           record: 'node_namespace_pod:kube_pod_info:'
         - expr: |
-            count by (node, host_ip, role) (sum by (node, cpu, host_ip, role) (
+            count by (node, role) (sum by (node, cpu, role) (
               node_cpu_seconds_total{job="node-exporter"}
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             ))
           record: node:node_num_cpu:sum
@@ -761,27 +761,27 @@ spec:
             avg(irate(node_cpu_used_seconds_total{job="node-exporter"}[5m]))
           record: :node_cpu_utilisation:avg1m
         - expr: |
-            avg by (node, host_ip, role) (
+            avg by (node, role) (
               irate(node_cpu_used_seconds_total{job="node-exporter"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:)
           record: node:node_cpu_utilisation:avg1m
         - expr: |
-            avg by (node, host_ip, role) (
+            avg by (node, role) (
               irate(node_cpu_seconds_total{job="node-exporter",mode=~"user"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
             node_namespace_pod:kube_pod_info:)
           record: node:node_user_cpu_utilisation:avg1m
         - expr: |
-            avg by (node, host_ip, role) (
+            avg by (node, role) (
               irate(node_cpu_seconds_total{job="node-exporter",mode=~"system"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
             node_namespace_pod:kube_pod_info:)
           record: node:node_system_cpu_utilisation:avg1m
         - expr: |
-            avg by (node, host_ip, role) (
+            avg by (node, role) (
               irate(node_cpu_seconds_total{job="node-exporter",mode=~"iowait"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
             node_namespace_pod:kube_pod_info:)
           record: node:node_iowait_cpu_utilisation:avg1m
         - expr: |
@@ -806,9 +806,9 @@ spec:
             label_replace(node_memory_Cached_bytes, "node", "$1", "instance", "(.*)")
           record: node:node_memory_Cached_bytes
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               (node_memory_Slab_bytes{job="node-exporter"} + node_memory_KernelStack_bytes{job="node-exporter"} + node_memory_PageTables_bytes{job="node-exporter"}+ node_memory_HardwareCorrupted_bytes{job="node-exporter"}+node_memory_Bounce_bytes{job="node-exporter"}-node_memory_SReclaimable_bytes{job="node-exporter"})
-              * on (namespace, pod) group_left(node, host_ip, role)
+              * on (namespace, pod) group_left(node, role)
                 node_namespace_pod:kube_pod_info:
             )
           record: node:node_memory_system_reserved
@@ -825,16 +825,16 @@ spec:
             sum(node_memory_MemTotal_bytes{job="node-exporter"})
           record: ':node_memory_utilisation:'
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               (node_memory_MemFree_bytes{job="node-exporter"} + node_memory_Cached_bytes{job="node-exporter"} + node_memory_Buffers_bytes{job="node-exporter"} + node_memory_SReclaimable_bytes{job="node-exporter"})
-              * on (namespace, pod) group_left(node, host_ip, role)
+              * on (namespace, pod) group_left(node, role)
                 node_namespace_pod:kube_pod_info:
             )
           record: node:node_memory_bytes_available:sum
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               node_memory_MemTotal_bytes{job="node-exporter"}
-              * on (namespace, pod) group_left(node, host_ip, role)
+              * on (namespace, pod) group_left(node, role)
                 node_namespace_pod:kube_pod_info:
             )
           record: node:node_memory_bytes_total:sum
@@ -842,30 +842,30 @@ spec:
             1 - (node:node_memory_bytes_available:sum / node:node_memory_bytes_total:sum)
           record: 'node:node_memory_utilisation:'
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               irate(node_disk_reads_completed_total{job="node-exporter"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:data_volume_iops_reads:sum
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               irate(node_disk_writes_completed_total{job="node-exporter"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:data_volume_iops_writes:sum
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               irate(node_disk_read_bytes_total{job="node-exporter"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:data_volume_throughput_bytes_read:sum
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               irate(node_disk_written_bytes_total{job="node-exporter"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:data_volume_throughput_bytes_written:sum
@@ -874,74 +874,74 @@ spec:
             sum(irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[5m]))
           record: :node_net_utilisation:sum_irate
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               (irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[5m]) +
               irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[5m]))
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:node_net_utilisation:sum_irate
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               irate(node_network_transmit_bytes_total{job="node-exporter",device!~"veth.+"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:node_net_bytes_transmitted:sum_irate
         - expr: |
-            sum by (node, host_ip, role) (
+            sum by (node, role) (
               irate(node_network_receive_bytes_total{job="node-exporter",device!~"veth.+"}[5m])
-            * on (namespace, pod) group_left(node, host_ip, role)
+            * on (namespace, pod) group_left(node, role)
               node_namespace_pod:kube_pod_info:
             )
           record: node:node_net_bytes_received:sum_irate
         - expr: |
-            sum by(node, host_ip, role) (sum(max(node_filesystem_files{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"}) by (device, pod, namespace)) by (pod, namespace) * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:)
+            sum by(node, role) (sum(max(node_filesystem_files{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"}) by (device, pod, namespace)) by (pod, namespace) * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:)
           record: 'node:node_inodes_total:'
         - expr: |
-            sum by(node, host_ip, role) (sum(max(node_filesystem_files_free{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"}) by (device, pod, namespace)) by (pod, namespace) * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:)
+            sum by(node, role) (sum(max(node_filesystem_files_free{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"}) by (device, pod, namespace)) by (pod, namespace) * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:)
           record: 'node:node_inodes_free:'
         - expr: |
-            sum by (node, host_ip, role) (node_load1{job="node-exporter"} * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:) / node:node_num_cpu:sum
+            sum by (node, role) (node_load1{job="node-exporter"} * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:) / node:node_num_cpu:sum
           record: node:load1:ratio
         - expr: |
-            sum by (node, host_ip, role) (node_load5{job="node-exporter"} * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:) / node:node_num_cpu:sum
+            sum by (node, role) (node_load5{job="node-exporter"} * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:) / node:node_num_cpu:sum
           record: node:load5:ratio
         - expr: |
-            sum by (node, host_ip, role) (node_load15{job="node-exporter"} * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:) / node:node_num_cpu:sum
+            sum by (node, role) (node_load15{job="node-exporter"} * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:) / node:node_num_cpu:sum
           record: node:load15:ratio
         - expr: |
-            sum by (node, host_ip, role) ((kube_pod_status_scheduled{job="kube-state-metrics", condition="true"} > 0)  * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:)
+            sum by (node, role) ((kube_pod_status_scheduled{job="kube-state-metrics", condition="true"} > 0)  * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:)
           record: node:pod_count:sum
         - expr: |
-            (sum(kube_node_status_capacity{resource="pods", job="kube-state-metrics"}) by (node) * on(node) group_left(host_ip, role) max by(node, host_ip, role) (node_namespace_pod:kube_pod_info:{node!="",host_ip!=""}))
+            (sum(kube_node_status_capacity{resource="pods", job="kube-state-metrics"}) by (node) * on(node) group_left(role) max by(node, role) (node_namespace_pod:kube_pod_info:{node!=""}))
           record: node:pod_capacity:sum
         - expr: |
             node:pod_running:count / node:pod_capacity:sum
           record: node:pod_utilization:ratio
         - expr: |
-            count(node_namespace_pod:kube_pod_info: unless on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown|Succeeded"} > 0)) by (node, host_ip, role)
+            count(node_namespace_pod:kube_pod_info: unless on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown|Succeeded"} > 0)) by (node, role)
           record: node:pod_running:count
         - expr: |
-            count(node_namespace_pod:kube_pod_info: unless on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown|Running"} > 0)) by (node, host_ip, role)
+            count(node_namespace_pod:kube_pod_info: unless on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Failed|Pending|Unknown|Running"} > 0)) by (node, role)
           record: node:pod_succeeded:count
         - expr: |
-            count(node_namespace_pod:kube_pod_info:{node!="",host_ip!=""} unless on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase="Succeeded"}>0) unless on (pod, namespace) ((kube_pod_status_ready{job="kube-state-metrics", condition="true"}>0) and on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase="Running"}>0)) unless on (pod, namespace) kube_pod_container_status_waiting_reason{job="kube-state-metrics", reason="ContainerCreating"}>0) by (node, host_ip, role)
+            count(node_namespace_pod:kube_pod_info:{node!=""} unless on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase="Succeeded"}>0) unless on (pod, namespace) ((kube_pod_status_ready{job="kube-state-metrics", condition="true"}>0) and on (pod, namespace) (kube_pod_status_phase{job="kube-state-metrics", phase="Running"}>0)) unless on (pod, namespace) kube_pod_container_status_waiting_reason{job="kube-state-metrics", reason="ContainerCreating"}>0) by (node, role)
           record: node:pod_abnormal:count
         - expr: |
             (count by(namespace, cluster) (kube_pod_info{job="kube-state-metrics"} unless on(pod, namespace, cluster) (kube_pod_status_phase{job="kube-state-metrics",phase="Succeeded"} > 0) unless on(pod, namespace, cluster) ((kube_pod_status_ready{condition="true",job="kube-state-metrics"} > 0) and on(pod, namespace, cluster) (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} > 0)) unless on(pod, namespace, cluster) kube_pod_container_status_waiting_reason{job="kube-state-metrics",reason="ContainerCreating"} > 0) or on(namespace, cluster) (group by(namespace, cluster) (kube_pod_info{job="kube-state-metrics"}) * 0)) * on(namespace, cluster) group_left(user) (kube_namespace_labels{job="kube-state-metrics"}) > 0
           record: user:pod_abnormal:count
         - expr: |
-            node:pod_abnormal:count / count(node_namespace_pod:kube_pod_info:{node!="",host_ip!=""} unless on (pod, namespace) kube_pod_status_phase{job="kube-state-metrics", phase="Succeeded"}>0) by (node, host_ip, role)
+            node:pod_abnormal:count / count(node_namespace_pod:kube_pod_info:{node!=""} unless on (pod, namespace) kube_pod_status_phase{job="kube-state-metrics", phase="Succeeded"}>0) by (node, role)
           record: node:pod_abnormal:ratio
         - expr: |
-            user:pod_abnormal:count / count(node_namespace_pod:kube_pod_info:{node!="",host_ip!=""} unless on (pod, namespace) kube_pod_status_phase{job="kube-state-metrics", phase="Succeeded"}>0) by (node, host_ip, role)
+            user:pod_abnormal:count / count(node_namespace_pod:kube_pod_info:{node!=""} unless on (pod, namespace) kube_pod_status_phase{job="kube-state-metrics", phase="Succeeded"}>0) by (node, role)
           record: user:pod_abnormal:ratio
         - expr: |
-            sum(max(node_filesystem_avail_bytes{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"} * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:) by (device, node, host_ip, role)) by (node, host_ip, role)
+            sum(max(node_filesystem_avail_bytes{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"} * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:) by (device, node, role)) by (node, role)
           record: 'node:disk_space_available:'
         - expr: |
-            1- sum(max(node_filesystem_avail_bytes{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"} * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:) by (device, node, host_ip, role)) by (node, host_ip, role) / sum(max(node_filesystem_size_bytes{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"} * on (namespace, pod) group_left(node, host_ip, role) node_namespace_pod:kube_pod_info:) by (device, node, host_ip, role)) by (node, host_ip, role)
+            1- sum(max(node_filesystem_avail_bytes{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"} * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:) by (device, node, role)) by (node, role) / sum(max(node_filesystem_size_bytes{device=~"/dev/.*", device!~"/dev/loop\\d+", job="node-exporter"} * on (namespace, pod) group_left(node, role) node_namespace_pod:kube_pod_info:) by (device, node, role)) by (node, role)
           record: node:disk_space_utilization:ratio
         - expr: |
             (1 - (node:node_inodes_free: / node:node_inodes_total:))

cli/pkg/kubesphere/plugins/files/build/prometheus/node-exporter/node-exporter-daemonset.yaml

@@ -42,7 +42,7 @@ spec:
         - --collector.netdev.address-info
         - --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+)($|/)
         - --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$
-        image: beclab/node-exporter:0.0.2
+        image: beclab/node-exporter:0.0.3
         name: node-exporter
         securityContext:
           privileged: true

cli/pkg/kubesphere/plugins/kscore_config.go

@@ -58,12 +58,12 @@ var kscorecrds = []map[string]string{
 		"resource": "default-http-backend",
 		"release":  "ks-core",
 	},
-	{
-		"ns":       "kubesphere-system",
-		"kind":     "secrets",
-		"resource": "ks-controller-manager-webhook-cert",
-		"release":  "ks-core",
-	},
+	//{
+	//	"ns":       "kubesphere-system",
+	//	"kind":     "secrets",
+	//	"resource": "ks-controller-manager-webhook-cert",
+	//	"release":  "ks-core",
+	//},
 	{
 		"ns":       "kubesphere-system",
 		"kind":     "serviceaccounts",
@@ -100,24 +100,24 @@ var kscorecrds = []map[string]string{
 		"resource": "ks-apiserver",
 		"release":  "ks-core",
 	},
-	{
-		"ns":       "kubesphere-system",
-		"kind":     "services",
-		"resource": "ks-controller-manager",
-		"release":  "ks-core",
-	},
+	//{
+	//	"ns":       "kubesphere-system",
+	//	"kind":     "services",
+	//	"resource": "ks-controller-manager",
+	//	"release":  "ks-core",
+	//},
 	{
 		"ns":       "kubesphere-system",
 		"kind":     "deployments",
 		"resource": "ks-apiserver",
 		"release":  "ks-core",
 	},
-	{
-		"ns":       "kubesphere-system",
-		"kind":     "deployments",
-		"resource": "ks-controller-manager",
-		"release":  "ks-core",
-	},
+	//{
+	//	"ns":       "kubesphere-system",
+	//	"kind":     "deployments",
+	//	"resource": "ks-controller-manager",
+	//	"release":  "ks-core",
+	//},
 	//{
 	//	"ns":       "kubesphere-system",
 	//	"kind":     "validatingwebhookconfigurations",

cli/pkg/kubesphere/plugins/tasks.go

@@ -65,7 +65,7 @@ func (t *InitNamespace) Execute(runtime connector.Runtime) error {
 		kubectlpath = path.Join(common.BinDir, common.CommandKubectl)
 	}
 
-	for _, ns := range []string{common.NamespaceKubesphereControlsSystem, common.NamespaceKubesphereMonitoringFederated} {
+	for _, ns := range []string{common.NamespaceKubesphereControlsSystem} {
 		if stdout, err := runtime.GetRunner().Cmd(fmt.Sprintf("%s create ns %s", kubectlpath, ns), false, true); err != nil {
 			if !strings.Contains(stdout, "already exists") {
 				logger.Errorf("create ns %s failed: %v", ns, err)
@@ -98,8 +98,6 @@ func (t *InitNamespace) Execute(runtime connector.Runtime) error {
 		common.NamespaceKubeSystem,
 		common.NamespaceKubekeySystem,
 		common.NamespaceKubesphereControlsSystem,
-		common.NamespaceKubesphereMonitoringFederated,
-		common.NamespaceKubesphereMonitoringSystem,
 		common.NamespaceKubesphereSystem,
 	}
 

cli/pkg/kubesphere/prepares.go

@@ -23,17 +23,6 @@ import (
 	versionutil "k8s.io/apimachinery/pkg/util/version"
 )
 
-type ShouldDeleteCache struct {
-	common.KubePrepare
-}
-
-func (p *ShouldDeleteCache) PreCheck(runtime connector.Runtime) (bool, error) {
-	if p.KubeConf.Arg.DeleteCache {
-		return true, nil
-	}
-	return false, nil
-}
-
 type VersionBelowV3 struct {
 	common.KubePrepare
 }

cli/pkg/kubesphere/tasks.go

@@ -52,19 +52,6 @@ func (d *DeleteKubeSphereCaches) Execute(runtime connector.Runtime) error {
 	return nil
 }
 
-type DeleteCache struct {
-	common.KubeAction
-}
-
-func (t *DeleteCache) Execute(runtime connector.Runtime) error {
-	// var cacheDir = path.Join(runtime.GetBaseDir(), cc.ImagesDir)
-	// if err := util.RemoveDir(cacheDir); err != nil {
-	// 	return err
-	// }
-	// logger.Debugf("delete caches success")
-	return nil
-}
-
 type AddInstallerConfig struct {
 	common.KubeAction
 }
@@ -368,7 +355,7 @@ func (c *Check) Execute(runtime connector.Runtime) error {
 		return fmt.Errorf("kubectl not found")
 	}
 
-	var labels = []string{"app=ks-apiserver", "app=ks-controller-manager"}
+	var labels = []string{"app=ks-apiserver"}
 
 	for _, label := range labels {
 		var cmd = fmt.Sprintf("%s get pod -n %s -l '%s' -o jsonpath='{.items[0].status.phase}'", kubectlpath, common.NamespaceKubesphereSystem, label)

cli/pkg/phase/cluster/add_node.go

@@ -6,6 +6,7 @@ import (
 	"github.com/beclab/Olares/cli/pkg/core/logger"
 	"github.com/beclab/Olares/cli/pkg/core/module"
 	"github.com/beclab/Olares/cli/pkg/core/pipeline"
+	"github.com/beclab/Olares/cli/pkg/gpu"
 	"github.com/beclab/Olares/cli/pkg/k3s"
 	"github.com/beclab/Olares/cli/pkg/kubernetes"
 	"github.com/beclab/Olares/cli/pkg/manifest"
@@ -75,6 +76,7 @@ func (m *AddNodeModule) Init() {
 			&k3s.JoinNodesModule{},
 		}
 	}
+	m.underlyingModules = append(m.underlyingModules, &gpu.NodeLabelingModule{})
 	for _, underlyingModule := range m.underlyingModules {
 		underlyingModule.Default(m.Runtime, m.PipelineCache, m.ModuleCache)
 		underlyingModule.AutoAssert()

cli/pkg/phase/cluster/delete_cluster.go

@@ -105,6 +105,7 @@ func (p *phaseBuilder) phaseInstall() *phaseBuilder {
 			&certs.UninstallCertsFilesModule{},
 			&storage.DeleteUserDataModule{},
 			&terminus.DeleteWizardFilesModule{},
+			&terminus.DeleteUpgradeFilesModule{},
 			&storage.RemoveJuiceFSModule{},
 			&storage.DeletePhaseFlagModule{
 				PhaseFile: common.TerminusStateFileInstalled,
@@ -132,33 +133,13 @@ func (p *phaseBuilder) phasePrepare() *phaseBuilder {
 				PhaseFile: common.TerminusStateFilePrepared,
 				BaseDir:   p.runtime.GetBaseDir(),
 			},
+			&daemon.UninstallTerminusdModule{},
 			&terminus.RemoveReleaseFileModule{},
 		)
 	}
 	return p
 }
 
-func (p *phaseBuilder) phaseDownload() *phaseBuilder {
-	terminusdAction := &daemon.CheckTerminusdService{}
-	err := terminusdAction.Execute()
-
-	if p.convert() >= PhaseDownload {
-		if err == nil {
-			p.modules = append(p.modules, &daemon.UninstallTerminusdModule{})
-		}
-		p.modules = append(p.modules,
-			&kubesphere.DeleteCacheModule{},
-		)
-
-		if p.runtime.Arg.DeleteCache {
-			p.modules = append(p.modules, &storage.DeleteCacheModule{
-				BaseDir: p.runtime.GetBaseDir(),
-			})
-		}
-	}
-	return p
-}
-
 func (p *phaseBuilder) phaseMacos() {
 	p.modules = []module.Module{
 		&precheck.GreetingsModule{},
@@ -168,9 +149,6 @@ func (p *phaseBuilder) phaseMacos() {
 	}
 	if p.convert() >= PhaseDownload {
 		p.modules = append(p.modules, &kubesphere.DeleteKubeSphereCachesModule{})
-		if p.runtime.Arg.DeleteCache {
-			p.modules = append(p.modules, &kubesphere.DeleteCacheModule{})
-		}
 	}
 }
 
@@ -189,8 +167,7 @@ func UninstallTerminus(phase string, runtime *common.KubeRuntime) pipeline.Pipel
 		builder.
 			phaseInstall().
 			phaseStorage().
-			phasePrepare().
-			phaseDownload()
+			phasePrepare()
 	}
 
 	return pipeline.Pipeline{

cli/pkg/plugins/dns/templates/coredns_service.go

@@ -65,6 +65,7 @@ data:
         health
         ready
         kubernetes {{ .DNSDomain }} in-addr.arpa ip6.arpa {
+          endpoint_pod_names
           pods insecure
           fallthrough in-addr.arpa ip6.arpa
         }

cli/pkg/plugins/network/templates/calico_v1.16+.go

@@ -5993,6 +5993,8 @@ spec:
             # Enable or Disable VXLAN on the default IPv6 IP pool.
             - name: CALICO_IPV6POOL_VXLAN
               value: "Never"
+            - name: FELIX_HEALTHHOST
+              value: 127.0.0.1
             # Set MTU for tunnel device used if ipip is enabled
             - name: FELIX_IPINIPMTU
               valueFrom:

cli/pkg/release/app/app.go

@@ -117,7 +117,7 @@ func (m *Manager) packageLauncher() error {
 func (m *Manager) packageGPU() error {
 	fmt.Println("packaging gpu ...")
 	return util.CopyDirectory(
-		filepath.Join(m.olaresRepoRoot, "framework/gpu/.olares/config/gpu"),
+		filepath.Join(m.olaresRepoRoot, "infrastructure/gpu/.olares/config/gpu"),
 		filepath.Join(m.distPath, "wizard/config/gpu"),
 	)
 }

cli/pkg/release/builder/builder.go

@@ -11,6 +11,7 @@ import (
 
 type Builder struct {
 	olaresRepoRoot  string
+	vendorRepoPath  string
 	distPath        string
 	version         string
 	manifestManager *manifest.Manager
@@ -19,8 +20,13 @@ type Builder struct {
 
 func NewBuilder(olaresRepoRoot, version, cdnURL string, ignoreMissingImages bool) *Builder {
 	distPath := filepath.Join(olaresRepoRoot, ".dist/install-wizard")
+	vendorRepoPath := os.Getenv("OLARES_VENDOR_REPO_PATH")
+	if vendorRepoPath == "" {
+		vendorRepoPath = "/"
+	}
 	return &Builder{
 		olaresRepoRoot:  olaresRepoRoot,
+		vendorRepoPath:  vendorRepoPath,
 		distPath:        distPath,
 		version:         version,
 		manifestManager: manifest.NewManager(olaresRepoRoot, distPath, cdnURL, ignoreMissingImages),
@@ -68,6 +74,9 @@ func (b *Builder) archive() (string, error) {
 		if err := util.ReplaceInFile(file, "#__VERSION__", b.version); err != nil {
 			return "", err
 		}
+		if err := util.ReplaceInFile(file, "#__REPO_PATH__", b.vendorRepoPath); err != nil {
+			return "", err
+		}
 	}
 
 	tarFile := filepath.Join(b.olaresRepoRoot, fmt.Sprintf("install-wizard-%s.tar.gz", versionStr))

cli/pkg/storage/module.go

@@ -214,29 +214,6 @@ func (m *DeletePhaseFlagModule) Init() {
 	}
 }
 
-type DeleteCacheModule struct {
-	common.KubeModule
-	BaseDir string
-}
-
-func (m *DeleteCacheModule) Init() {
-	m.Name = "DeleteCaches"
-
-	deleteCaches := &task.RemoteTask{
-		Name:  "DeleteCaches",
-		Hosts: m.Runtime.GetHostsByRole(common.Master),
-		Action: &DeleteCaches{
-			BaseDir: m.BaseDir,
-		},
-		Parallel: false,
-		Retry:    1,
-	}
-
-	m.Tasks = []task.Interface{
-		deleteCaches,
-	}
-}
-
 type DeleteUserDataModule struct {
 	common.KubeModule
 }

cli/pkg/storage/tasks.go

@@ -325,38 +325,6 @@ func (t *DeletePhaseFlagFile) Execute(runtime connector.Runtime) error {
 	return nil
 }
 
-type DeleteCaches struct {
-	common.KubeAction
-	BaseDir string
-}
-
-func (t *DeleteCaches) Execute(runtime connector.Runtime) error {
-	var cachesDirs []string
-
-	filepath.WalkDir(t.BaseDir, func(path string, d fs.DirEntry, err error) error {
-		if path != t.BaseDir {
-			if d.IsDir() {
-				cachesDirs = append(cachesDirs, path)
-				return filepath.SkipDir
-			}
-		}
-		return nil
-	},
-	)
-
-	if cachesDirs != nil && len(cachesDirs) > 0 {
-		for _, cachesDir := range cachesDirs {
-			if util.IsExist(cachesDir) {
-				if err := util.RemoveDir(cachesDir); err != nil {
-					logger.Errorf("remove %s failed %v", cachesDir, err)
-				}
-			}
-		}
-	}
-
-	return nil
-}
-
 type DeleteTerminusUserData struct {
 	common.KubeAction
 }

cli/pkg/terminus/modules.go

@@ -199,6 +199,23 @@ func (m *InstalledModule) Init() {
 	}
 }
 
+type DeleteUpgradeFilesModule struct {
+	common.KubeModule
+}
+
+func (d *DeleteUpgradeFilesModule) Init() {
+	d.Name = "DeleteUpgradeFiles"
+
+	deleteUpgradeFiles := &task.LocalTask{
+		Name:   "DeleteUpgradeFiles",
+		Action: &DeleteUpgradeFiles{},
+	}
+
+	d.Tasks = []task.Interface{
+		deleteUpgradeFiles,
+	}
+}
+
 type DeleteWizardFilesModule struct {
 	common.KubeModule
 }

cli/pkg/terminus/ossystem.go

@@ -86,6 +86,12 @@ func (t *InstallOsSystem) Execute(runtime connector.Runtime) error {
 
 	// TODO: wait for the platform to be ready
 
+	actionConfig, settings, err = utils.InitConfig(config, common.NamespaceOsFramework)
+	if err != nil {
+		return err
+	}
+	ctx, cancel = context.WithTimeout(context.Background(), 3*time.Minute)
+	defer cancel()
 	var frameworkPath = path.Join(runtime.GetInstallerDir(), "wizard", "config", "os-framework")
 	if err := utils.UpgradeCharts(ctx, actionConfig, settings, common.ChartNameOSFramework, frameworkPath, "", common.NamespaceOsFramework, vals, false); err != nil {
 		return err

cli/pkg/terminus/tasks.go

@@ -296,6 +296,30 @@ func (t *InstallFinished) Execute(runtime connector.Runtime) error {
 	return nil
 }
 
+type DeleteUpgradeFiles struct {
+	common.KubeAction
+}
+
+func (d *DeleteUpgradeFiles) Execute(runtime connector.Runtime) error {
+	baseDir := runtime.GetBaseDir()
+
+	files, err := os.ReadDir(baseDir)
+	if err != nil {
+		return errors.Wrapf(err, "failed to read directory %s", baseDir)
+	}
+
+	for _, file := range files {
+		if strings.HasPrefix(file.Name(), "upgrade.") {
+			filePath := path.Join(baseDir, file.Name())
+			if err := os.RemoveAll(filePath); err != nil && !os.IsNotExist(err) {
+				logger.Warnf("failed to delete %s: %v", filePath, err)
+			}
+		}
+	}
+
+	return nil
+}
+
 type DeleteWizardFiles struct {
 	common.KubeAction
 }
@@ -453,14 +477,21 @@ func (a *DeletePodsUsingHostIP) Execute(runtime connector.Runtime) error {
 	if err != nil {
 		return errors.Wrap(err, "failed to get pods using host IP")
 	}
-	a.PipelineCache.Set(common.CacheCountPodsUsingHostIP, len(targetPods))
+	var waitRecreationPodsCount int
 	for _, pod := range targetPods {
 		logger.Infof("restarting pod %s/%s that's using host IP", pod.Namespace, pod.Name)
 		err = kubeClient.CoreV1().Pods(pod.Namespace).Delete(context.Background(), pod.Name, metav1.DeleteOptions{})
 		if err != nil && !kerrors.IsNotFound(err) {
 			return errors.Wrap(err, "failed to delete pod")
 		}
+
+		// pods not created by any owner resource
+		// may not be recreated immediately and should not be waited
+		if len(pod.OwnerReferences) > 0 {
+			waitRecreationPodsCount++
+		}
 	}
+	a.PipelineCache.Set(common.CacheCountPodsWaitForRecreation, waitRecreationPodsCount)
 
 	// try our best to wait for the pods to be actually deleted
 	// to avoid the next module getting the pods with a still running phase
@@ -479,7 +510,7 @@ type WaitForPodsUsingHostIPRecreate struct {
 }
 
 func (a *WaitForPodsUsingHostIPRecreate) Execute(runtime connector.Runtime) error {
-	count, ok := a.PipelineCache.GetMustInt(common.CacheCountPodsUsingHostIP)
+	count, ok := a.PipelineCache.GetMustInt(common.CacheCountPodsWaitForRecreation)
 	if !ok {
 		return errors.New("failed to get the count of pods using host IP")
 	}

cli/pkg/upgrade/task.go

@@ -5,6 +5,7 @@ import (
 	"fmt"
 	"os"
 	"path"
+	"strings"
 	"time"
 
 	"github.com/beclab/Olares/cli/pkg/common"
@@ -197,7 +198,7 @@ func (u *UpgradeSystemComponents) Execute(runtime connector.Runtime) error {
 		return err
 	}
 
-	actionConfig, settings, err = utils.InitConfig(config, common.NamespaceOsPlatform)
+	actionConfig, settings, err = utils.InitConfig(config, common.NamespaceOsFramework)
 	if err != nil {
 		return err
 	}
@@ -221,3 +222,67 @@ func (u *UpgradeSystemComponents) Execute(runtime connector.Runtime) error {
 	}
 	return nil
 }
+
+type UpdateSysctlReservedPorts struct {
+	common.KubeAction
+}
+
+func (u *UpdateSysctlReservedPorts) Execute(runtime connector.Runtime) error {
+	const sysctlFile = "/etc/sysctl.conf"
+	const reservedPortsKey = "net.ipv4.ip_local_reserved_ports"
+	const expectedValue = "30000-32767,46800-50000"
+
+	content, err := os.ReadFile(sysctlFile)
+	if err != nil {
+		return fmt.Errorf("failed to read sysctl.conf: %v", err)
+	}
+
+	lines := strings.Split(string(content), "\n")
+	var foundKey bool
+	var needUpdate bool
+	var updatedLines []string
+
+	for _, line := range lines {
+		trimmedLine := strings.TrimSpace(line)
+		if strings.HasPrefix(trimmedLine, reservedPortsKey) {
+			foundKey = true
+			parts := strings.SplitN(trimmedLine, "=", 2)
+			if len(parts) == 2 {
+				currentValue := strings.TrimSpace(parts[1])
+				if currentValue != expectedValue {
+					logger.Infof("updating %s from %s to %s", reservedPortsKey, currentValue, expectedValue)
+					updatedLines = append(updatedLines, fmt.Sprintf("%s=%s", reservedPortsKey, expectedValue))
+					needUpdate = true
+				} else {
+					updatedLines = append(updatedLines, line)
+				}
+			} else {
+				updatedLines = append(updatedLines, line)
+			}
+		} else {
+			updatedLines = append(updatedLines, line)
+		}
+	}
+
+	if !foundKey {
+		logger.Infof("key %s not found in sysctl.conf, adding it", reservedPortsKey)
+		updatedLines = append(updatedLines, fmt.Sprintf("%s=%s", reservedPortsKey, expectedValue))
+		needUpdate = true
+	}
+
+	if needUpdate {
+		updatedContent := strings.Join(updatedLines, "\n")
+		if err := os.WriteFile(sysctlFile, []byte(updatedContent), 0644); err != nil {
+			return fmt.Errorf("failed to write updated sysctl.conf: %v", err)
+		}
+
+		if _, err := runtime.GetRunner().SudoCmd("sysctl -p", false, false); err != nil {
+			return fmt.Errorf("failed to reload sysctl: %v", err)
+		}
+		logger.Infof("updated and reloaded sysctl configuration")
+	} else {
+		logger.Debugf("%s already has the expected value: %s", reservedPortsKey, expectedValue)
+	}
+
+	return nil
+}

cli/pkg/upgrade/upgrade.go

@@ -18,7 +18,16 @@ type UpgradeModule struct {
 }
 
 var (
-	preTasks []*upgradeTask
+	preTasks = []*upgradeTask{
+		{
+			Task: &task.LocalTask{
+				Name:   "UpdateSysctlReservedPorts",
+				Action: new(UpdateSysctlReservedPorts),
+			},
+			Current: &explicitVersionMatcher{max: semver.New(1, 12, 0, "20250701", "")},
+			Target:  anyVersion,
+		},
+	}
 
 	coreTasks = []*upgradeTask{
 		{

daemon/.olares/Olares.yaml

@@ -5,5 +5,5 @@ output:
     - 
       id: olaresd
       name: olaresd-v#__VERSION__.tar.gz
-      amd64: https://dc3p1870nn3cj.cloudfront.net/olaresd-v#__VERSION__-linux-amd64.tar.gz
-      arm64: https://dc3p1870nn3cj.cloudfront.net/olaresd-v#__VERSION__-linux-arm64.tar.gz
+      amd64: https://dc3p1870nn3cj.cloudfront.net#__REPO_PATH__olaresd-v#__VERSION__-linux-amd64.tar.gz
+      arm64: https://dc3p1870nn3cj.cloudfront.net#__REPO_PATH__olaresd-v#__VERSION__-linux-arm64.tar.gz

daemon/Makefile

@@ -1,4 +1,6 @@
 
+current_dir := $(dir $(abspath $(firstword $(MAKEFILE_LIST))))
+
 .PHONY: all tidy fmt vet build
 
 all: tidy build
@@ -17,3 +19,11 @@ build: fmt vet ;$(info $(M)...Begin to build terminusd.) @
 
 build-linux: fmt vet ;$(info $(M)...Begin to build terminusd (linux version).) @
 	CGO_ENABLED=1 GOOS=linux GOARCH=amd64 go build -o bin/olaresd cmd/terminusd/main.go
+
+build-linux-in-docker:
+	docker run -it --platform linux/amd64 --rm \
+		-v $(current_dir):/olaresd \
+		-w /olaresd \
+		-e DEBIAN_FRONTEND=noninteractive \
+		golang:1.24 \
+		sh -c "apt-get -y update; apt-get -y install libudev-dev; make build-linux"

daemon/README.md

@@ -0,0 +1,170 @@
+
+# Olares System Daemon (`olaresd`)
+
+`olaresd` is the foundational process that boots on every Olares node. It runs as a `systemd` service on port `18088`, exposing a secure REST API for hardware abstraction, network orchestration, storage management, and turnkey cluster operations—all before Kubernetes starts. 
+
+Olaresd is installed as a systemd service in `/etc/systemd/system/olaresd.service`.
+
+## Key features
+
+- **System monitoring**: Continuous health checks of cluster and node status.
+- **Cluster lifecycle management**: Automated install, upgrade, IP-switching, restart, and maintenance operations.
+- **Hardware Abstraction**: USB auto-mounting, storage provisioning, and management.
+- **Network Management**: mDNS service discovery, WiFi onboarding, and network interface control.
+
+## REST API reference
+
+The daemon provides an authenticated REST API (using signature-based auth):
+
+**Base URL**: `http://<node-ip>:18088`
+
+### System commands `/command/`
+
+**Lifecycle operations**
+
+| Method | Endpoint                    | Description                  |
+|--------|-----------------------------|------------------------------|
+| POST   | `/command/install`          | Install Olares               |
+| POST   | `/command/uninstall`        | Uninstall Olares             |
+| POST   | `/command/upgrade`          | Upgrade Olares               |
+| DELETE | `/command/upgrade`          | Cancel upgrade               |
+| POST   | `/command/reboot`           | Reboot node                  |
+| POST   | `/command/shutdown`         | Shutdown node                |
+
+**Network configuration**
+
+| Method | Endpoint                    | Description                  |
+|--------|-----------------------------|------------------------------|
+| POST   | `/command/connect-wifi`     | Connect to WiFi              |
+| POST   | `/command/change-host`      | Change Olares IP binding     |
+
+**Storage management**
+
+| Method | Endpoint                          | Description                        |
+|--------|-----------------------------------|------------------------------------|
+| POST   | `/command/mount-samba`            | Mount SMB shares                   |
+| POST   | `/command/v2/mount-samba`         | Enhanced SMB mounting              |
+| POST   | `/command/umount-samba`           | Unmount SMB shares                 |
+| POST   | `/command/umount-samba-incluster` | Cluster-wide SMB unmount           |
+| POST   | `/command/umount-usb`             | Unmount USB device                 |
+| POST   | `/command/umount-usb-incluster`   | Cluster-wide USB unmount           |
+
+**System Maintenance**
+
+| Method | Endpoint                    | Description                         |
+|--------|-----------------------------|-------------------------------------|
+| POST   | `/command/collect-logs`     | Collect system logs for diagnostics |
+
+---
+
+### System information (`/system/`)
+
+**System status**
+
+| Method | Endpoint                 | Description                 |
+|--------|--------------------------|-----------------------------|
+| GET    | `/system/status`         | Get full system status      |
+| GET    | `/system/ifs`            | List network interfaces     |
+| GET    | `/system/hosts-file`     | View `/etc/hosts`           |
+| POST   | `/system/hosts-file`     | Update `/etc/hosts`         |
+
+**Mount information**
+
+| Method | Endpoint                        | Description                    |
+|--------|---------------------------------|--------------------------------|
+| GET    | `/system/mounted-usb`           | Mounted USB devices            |
+| GET    | `/system/mounted-hdd`           | Mounted hard drives            |
+| GET    | `/system/mounted-smb`           | Mounted SMB shares             |
+| GET    | `/system/mounted-path`          | All mount points               |
+
+**Cluster-wide mounts**
+
+| Method | Endpoint                             | Description                      |
+|--------|--------------------------------------|----------------------------------|
+| GET    | `/system/mounted-usb-incluster`      | USB mounts in cluster            |
+| GET    | `/system/mounted-hdd-incluster`      | HDD mounts in cluster            |
+| GET    | `/system/mounted-smb-incluster`      | SMB mounts in cluster            |
+| GET    | `/system/mounted-path-incluster`     | All cluster mounts               |
+
+---
+
+### Container management (`/containerd/`)
+
+**Registry Management**
+
+| Method | Endpoint                                  | Description                         |
+|--------|-------------------------------------------|-------------------------------------|
+| GET    | `/containerd/registries`                  | List registries                     |
+| GET    | `/containerd/registry/mirrors/`           | List registry mirrors               |
+| GET    | `/containerd/registry/mirrors/:registry`  | Get specific registry mirror        |
+| PUT    | `/containerd/registry/mirrors/:registry`  | Update registry mirror              |
+| DELETE | `/containerd/registry/mirrors/:registry`  | Delete registry mirror              |
+
+**Image Management**
+
+| Method | Endpoint                         | Description                    |
+|--------|----------------------------------|--------------------------------|
+| GET    | `/containerd/images/`            | List container images          |
+| DELETE | `/containerd/images/:image`      | Delete specific image          |
+| POST   | `/containerd/images/prune`       | Remove unused images           |
+
+
+## Build from source
+
+### Prerequisites
+
+* Go 1.24+
+* GoReleaser (Optional, for creating release artifacts)
+
+### Steps
+
+1.  **Navigate to the daemon directory:**
+
+    ```bash
+    cd daemon
+    ```
+
+2.  **Build for your host OS/architecture:**
+
+    ```bash
+    go build -o olaresd ./cmd/olaresd/main.go
+    ```
+
+3.  **Cross-compile for another target (e.g., Linux AMD64):**
+
+    ```bash
+    GOOS=linux GOARCH=amd64 go build -o olaresd ./cmd/olaresd/main.go
+    ```
+
+4.  **Produce release artifacts (optional):**
+
+    ```bash
+    goreleaser release --snapshot --clean
+    ```
+
+## Extend `olaresd`
+
+To add a new command API:
+
+1.  **Define command**: Add a new command struct in `pkg/commands/`.
+2.  **Implement handler**: Create the corresponding HTTP handler logic in `internal/apiserver/handlers/`.
+3.  **Register route**: Register the new API route in `internal/apiserver/server.go`.
+4.  **Update state**: If the command modifies the cluster's state, ensure you update the logic in `pkg/cluster/state/`.
+5.  **Validate**: Run `go vet ./... && go test ./...` to check for issues and ensure all tests pass before opening a pull request.
+
+
+### Test a custom build
+
+1.  Copy the binary to your Olares node.
+
+2.  On the node, replace the existing binary:
+
+    ```bash
+    # Move the new binary into place
+    sudo cp -f /tmp/olaresd /usr/local/bin/
+
+3. Restart the daemon to apply changes:
+    
+   ``` 
+   sudo systemctl restart olaresd
+   ```

daemon/cmd/terminusd/main.go

@@ -14,6 +14,7 @@ import (
 	"github.com/beclab/Olares/daemon/internel/ble"
 	"github.com/beclab/Olares/daemon/internel/mdns"
 	"github.com/beclab/Olares/daemon/internel/watcher"
+	"github.com/beclab/Olares/daemon/internel/watcher/cert"
 	"github.com/beclab/Olares/daemon/internel/watcher/system"
 	"github.com/beclab/Olares/daemon/internel/watcher/upgrade"
 	"github.com/beclab/Olares/daemon/internel/watcher/usb"
@@ -96,6 +97,7 @@ func main() {
 		// usb.NewUsbWatcher(),
 		usb.NewUmountWatcher(),
 		upgrade.NewUpgradeWatcher(),
+		cert.NewCertWatcher(),
 	}, func() {
 		if s != nil {
 			if err := s.Restart(); err != nil {

daemon/go.mod

@@ -6,6 +6,7 @@ toolchain go1.24.4
 
 replace (
 	bytetrade.io/web3os/app-service => github.com/beclab/app-service v0.2.33
+	bytetrade.io/web3os/backups-sdk => github.com/Above-Os/backups-sdk v0.1.17
 	bytetrade.io/web3os/bfl => github.com/beclab/bfl v0.3.36
 	k8s.io/api => k8s.io/api v0.31.0
 	k8s.io/apimachinery => k8s.io/apimachinery v0.31.0
@@ -79,7 +80,6 @@ require (
 	github.com/containerd/platforms v0.2.1 // indirect
 	github.com/containerd/ttrpc v1.2.7 // indirect
 	github.com/containerd/typeurl/v2 v2.1.1 // indirect
-	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/decred/dcrd/dcrec/secp256k1/v4 v4.2.0 // indirect
 	github.com/distribution/reference v0.6.0 // indirect
@@ -123,7 +123,7 @@ require (
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/moby/locker v1.0.1 // indirect
 	github.com/moby/spdystream v0.5.0 // indirect
-	github.com/moby/sys/mountinfo v0.7.1 // indirect
+	github.com/moby/sys/mountinfo v0.7.2 // indirect
 	github.com/moby/sys/sequential v0.5.0 // indirect
 	github.com/moby/sys/signal v0.7.0 // indirect
 	github.com/moby/sys/user v0.3.0 // indirect
@@ -134,9 +134,9 @@ require (
 	github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
 	github.com/opencontainers/image-spec v1.1.1 // indirect
-	github.com/opencontainers/runc v1.1.13 // indirect
-	github.com/opencontainers/runtime-spec v1.1.0 // indirect
-	github.com/opencontainers/selinux v1.11.0 // indirect
+	github.com/opencontainers/runc v1.3.0 // indirect
+	github.com/opencontainers/runtime-spec v1.2.1 // indirect
+	github.com/opencontainers/selinux v1.11.1 // indirect
 	github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c // indirect
 	github.com/prometheus/client_golang v1.22.0 // indirect
 	github.com/prometheus/client_model v0.6.1 // indirect

daemon/go.sum

@@ -63,8 +63,6 @@ github.com/containerd/ttrpc v1.2.7 h1:qIrroQvuOL9HQ1X6KHe2ohc7p+HP/0VE6XPU7elJRq
 github.com/containerd/ttrpc v1.2.7/go.mod h1:YCXHsb32f+Sq5/72xHubdiJRQY9inL4a4ZQrAbN1q9o=
 github.com/containerd/typeurl/v2 v2.1.1 h1:3Q4Pt7i8nYwy2KmQWIw2+1hTvwTE/6w9FqcttATPO/4=
 github.com/containerd/typeurl/v2 v2.1.1/go.mod h1:IDp2JFvbwZ31H8dQbEIY7sDl2L3o3HZj1hsSQlywkQ0=
-github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs=
-github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
@@ -120,7 +118,6 @@ github.com/go-openapi/swag v0.23.0/go.mod h1:esZ8ITTYEsH1V2trKHjAN8Ai7xHb8RV+YSZ
 github.com/go-task/slim-sprig/v3 v3.0.0 h1:sUs3vkvUymDpBKi3qH1YSqBQk9+9D/8M2mN1vB6EwHI=
 github.com/go-task/slim-sprig/v3 v3.0.0/go.mod h1:W848ghGpv3Qj3dhTPRyJypKRiqCdHZiAzKg9hl15HA8=
 github.com/godbus/dbus/v5 v5.0.3/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
-github.com/godbus/dbus/v5 v5.0.4/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/godbus/dbus/v5 v5.1.0 h1:4KLkAxT3aOY8Li4FRJe/KvhoNFFxo0m6fNuFUO8QJUk=
 github.com/godbus/dbus/v5 v5.1.0/go.mod h1:xhWf0FNVPg57R7Z0UbKHbJfkEywrmjJnf7w5xrFpKfA=
 github.com/gofiber/fiber/v2 v2.52.5 h1:tWoP1MJQjGEe4GB5TUGOi7P2E0ZMMRx5ZTG4rT+yGMo=
@@ -233,8 +230,8 @@ github.com/moby/locker v1.0.1 h1:fOXqR41zeveg4fFODix+1Ch4mj/gT0NE1XJbp/epuBg=
 github.com/moby/locker v1.0.1/go.mod h1:S7SDdo5zpBK84bzzVlKr2V0hz+7x9hWbYC/kq7oQppc=
 github.com/moby/spdystream v0.5.0 h1:7r0J1Si3QO/kjRitvSLVVFUjxMEb/YLj6S9FF62JBCU=
 github.com/moby/spdystream v0.5.0/go.mod h1:xBAYlnt/ay+11ShkdFKNAG7LsyK/tmNBVvVOwrfMgdI=
-github.com/moby/sys/mountinfo v0.7.1 h1:/tTvQaSJRr2FshkhXiIpux6fQ2Zvc4j7tAhMTStAG2g=
-github.com/moby/sys/mountinfo v0.7.1/go.mod h1:IJb6JQeOklcdMU9F5xQ8ZALD+CUr5VlGpwtX+VE0rpI=
+github.com/moby/sys/mountinfo v0.7.2 h1:1shs6aH5s4o5H2zQLn796ADW1wMrIwHsyJ2v9KouLrg=
+github.com/moby/sys/mountinfo v0.7.2/go.mod h1:1YOa8w8Ih7uW0wALDUgT1dTTSBrZ+HiBLGws92L2RU4=
 github.com/moby/sys/sequential v0.5.0 h1:OPvI35Lzn9K04PBbCLW0g4LcFAJgHsvXsRyewg5lXtc=
 github.com/moby/sys/sequential v0.5.0/go.mod h1:tH2cOOs5V9MlPiXcQzRC+eEyab644PWKGRYaaV5ZZlo=
 github.com/moby/sys/signal v0.7.0 h1:25RW3d5TnQEoKvRbEKUGay6DCQ46IxAVTT9CUMgmsSI=
@@ -273,12 +270,12 @@ github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8
 github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
 github.com/opencontainers/image-spec v1.1.1 h1:y0fUlFfIZhPF1W537XOLg0/fcx6zcHCJwooC2xJA040=
 github.com/opencontainers/image-spec v1.1.1/go.mod h1:qpqAh3Dmcf36wStyyWU+kCeDgrGnAve2nCC8+7h8Q0M=
-github.com/opencontainers/runc v1.1.13 h1:98S2srgG9vw0zWcDpFMn5TRrh8kLxa/5OFUstuUhmRs=
-github.com/opencontainers/runc v1.1.13/go.mod h1:R016aXacfp/gwQBYw2FDGa9m+n6atbLWrYY8hNMT/sA=
-github.com/opencontainers/runtime-spec v1.1.0 h1:HHUyrt9mwHUjtasSbXSMvs4cyFxh+Bll4AjJ9odEGpg=
-github.com/opencontainers/runtime-spec v1.1.0/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
-github.com/opencontainers/selinux v1.11.0 h1:+5Zbo97w3Lbmb3PeqQtpmTkMwsW5nRI3YaLpt7tQ7oU=
-github.com/opencontainers/selinux v1.11.0/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
+github.com/opencontainers/runc v1.3.0 h1:cvP7xbEvD0QQAs0nZKLzkVog2OPZhI/V2w3WmTmUSXI=
+github.com/opencontainers/runc v1.3.0/go.mod h1:9wbWt42gV+KRxKRVVugNP6D5+PQciRbenB4fLVsqGPs=
+github.com/opencontainers/runtime-spec v1.2.1 h1:S4k4ryNgEpxW1dzyqffOmhI1BHYcjzU8lpJfSlR0xww=
+github.com/opencontainers/runtime-spec v1.2.1/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
+github.com/opencontainers/selinux v1.11.1 h1:nHFvthhM0qY8/m+vfhJylliSshm8G1jJ2jDMcgULaH8=
+github.com/opencontainers/selinux v1.11.1/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 h1:onHthvaw9LFnH4t2DcNVpwGmV9E1BkGknEliJkfwQj0=
 github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58/go.mod h1:DXv8WO4yhMYhSNPKjeNKa5WY9YCIEBRbNzFFPJbWO6Y=
 github.com/pelletier/go-toml v1.9.5 h1:4yBQzkHv+7BHq2PQUZF3Mx0IYxG7LsP222s7Agd3ve8=
@@ -440,7 +437,6 @@ golang.org/x/sys v0.0.0-20210303074136-134d130e1a04/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210426080607-c94f62235c83/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20211025201205-69cdffdb9359/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220908164124-27713097b956/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

daemon/internel/apiserver/handler_ifs.go

@@ -80,22 +80,32 @@ func (h *handlers) GetNetIfs(ctx *fiber.Ctx) error {
 			}
 		}
 
-		if test == "true" {
-			r.InternetConnected = ptr.To(utils.CheckInterfaceIPv4Connectivity(ctx.Context(), i.Iface.Name))
-			devices, err := utils.GetAllDevice(ctx.Context())
-			if err != nil {
-				klog.Error("get all devices error, ", err)
-				return h.ErrJSON(ctx, http.StatusServiceUnavailable, err.Error())
-			}
+		devices, err := utils.GetAllDevice(ctx.Context())
+		if err != nil {
+			klog.Error("get all devices error, ", err)
+			return h.ErrJSON(ctx, http.StatusServiceUnavailable, err.Error())
+		}
 
-			if d, ok := devices[r.Iface]; ok {
-				r.Ipv4Gateway = &d.Ipv4Gateway
-				r.Ipv6Gateway = &d.Ipv6Gateway
-				r.Ipv4DNS = &d.Ipv4DNS
-				r.Ipv6DNS = &d.Ipv6DNS
-				r.Ipv6Address = &d.Ipv6Address
-				r.Ipv4Mask = &d.Ipv4Mask
-				r.Method = &d.Method
+		if d, ok := devices[r.Iface]; ok {
+			r.Ipv4Gateway = &d.Ipv4Gateway
+			r.Ipv6Gateway = &d.Ipv6Gateway
+			r.Ipv4DNS = &d.Ipv4DNS
+			r.Ipv6DNS = &d.Ipv6DNS
+			r.Ipv6Address = &d.Ipv6Address
+			r.Ipv4Mask = &d.Ipv4Mask
+			r.Method = &d.Method
+		}
+
+		if rx, tx, err := utils.GetInterfaceTraffic(r.Iface); err == nil {
+			r.RxRate = ptr.To(rx)
+			r.TxRate = ptr.To(tx)
+		} else {
+			klog.Error("get interface rx/tx rate error, ", err)
+		}
+
+		if test == "true" {
+			if r.IP != "" {
+				r.InternetConnected = ptr.To(utils.CheckInterfaceIPv4Connectivity(ctx.Context(), i.Iface.Name))
 			}
 
 			if r.Ipv6Address != nil && *r.Ipv6Address != "" {
@@ -104,12 +114,6 @@ func (h *handlers) GetNetIfs(ctx *fiber.Ctx) error {
 				r.Ipv6Connectivity = &connected
 			}
 
-			if rx, tx, err := utils.GetInterfaceTraffic(r.Iface); err == nil {
-				r.RxRate = ptr.To(rx)
-				r.TxRate = ptr.To(tx)
-			} else {
-				klog.Error("get interface rx/tx rate error, ", err)
-			}
 		}
 
 		res = append(res, r)

daemon/internel/apiserver/handler_olares_upgrade.go

@@ -8,12 +8,14 @@ import (
 	"github.com/beclab/Olares/daemon/pkg/cluster/state"
 
 	"github.com/beclab/Olares/daemon/pkg/commands"
+	"github.com/beclab/Olares/daemon/pkg/commands/upgrade"
 	"github.com/gofiber/fiber/v2"
 	"k8s.io/klog/v2"
 )
 
 type UpgradeReq struct {
-	Version string `json:"version"`
+	Version      string `json:"version"`
+	DownloadOnly bool   `json:"downloadOnly,omitempty"` // false means download-and-upgrade
 }
 
 func (r *UpgradeReq) Check() error {
@@ -43,10 +45,18 @@ func (h *handlers) RequestOlaresUpgrade(ctx *fiber.Ctx, cmd commands.Interface)
 		return h.ErrJSON(ctx, http.StatusBadRequest, err.Error())
 	}
 
-	if _, err := cmd.Execute(ctx.Context(), req.Version); err != nil {
+	upgradeReq := upgrade.UpgradeRequest{
+		Version:      req.Version,
+		DownloadOnly: req.DownloadOnly,
+	}
+
+	if _, err := cmd.Execute(ctx.Context(), upgradeReq); err != nil {
 		return h.ErrJSON(ctx, http.StatusBadRequest, err.Error())
 	}
 
+	if req.DownloadOnly {
+		return h.OkJSON(ctx, "successfully created download target")
+	}
 	return h.OkJSON(ctx, "successfully created upgrade target")
 }
 
@@ -55,5 +65,5 @@ func (h *handlers) CancelOlaresUpgrade(ctx *fiber.Ctx, cmd commands.Interface) e
 		return h.ErrJSON(ctx, http.StatusBadRequest, err.Error())
 	}
 
-	return h.OkJSON(ctx, "successfully removed upgrade target")
+	return h.OkJSON(ctx, "successfully cancelled upgrade/download")
 }

daemon/internel/apiserver/server.go

@@ -50,10 +50,10 @@ func (s *server) Start() error {
 
 	cmd.Post("/upgrade", s.handlers.RequireSignature(
 		s.handlers.WaitServerRunning(
-			s.handlers.RunCommand(s.handlers.RequestOlaresUpgrade, upgrade.NewCreateTarget))))
+			s.handlers.RunCommand(s.handlers.RequestOlaresUpgrade, upgrade.NewCreateUpgradeTarget))))
 
 	cmd.Delete("/upgrade", s.handlers.RequireSignature(
-		s.handlers.RunCommand(s.handlers.CancelOlaresUpgrade, upgrade.NewRemoveTarget)))
+		s.handlers.RunCommand(s.handlers.CancelOlaresUpgrade, upgrade.NewRemoveUpgradeTarget)))
 
 	cmd.Post("/reboot", s.handlers.RequireSignature(
 		s.handlers.WaitServerRunning(

daemon/internel/mdns/server.go

@@ -43,6 +43,7 @@ func (s *server) Close() {
 	if s.server != nil {
 		klog.Info("mDNS server shutdown ")
 		s.server.Shutdown()
+		s.registeredIP = "" // clear the registered IP
 	}
 }
 
@@ -88,11 +89,11 @@ func (s *server) Restart() error {
 	}
 
 	if s.registeredIP != ip {
-		s.registeredIP = ip
 		if s.server != nil {
 			s.Close()
 		}
 
+		s.registeredIP = ip
 		instanceName := s.name
 		if instanceName == "" {
 			instanceName = hostname

daemon/internel/watcher/cert/user_cert_watcher.go

@@ -0,0 +1,141 @@
+package cert
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"github.com/beclab/Olares/daemon/internel/watcher"
+	"github.com/beclab/Olares/daemon/pkg/cluster/state"
+	"github.com/beclab/Olares/daemon/pkg/utils"
+	batchv1 "k8s.io/api/batch/v1"
+	corev1 "k8s.io/api/core/v1"
+	kubeErr "k8s.io/apimachinery/pkg/api/errors"
+	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
+	"k8s.io/client-go/kubernetes"
+	"k8s.io/klog/v2"
+	"k8s.io/utils/ptr"
+)
+
+var _ watcher.Watcher = &userCertWatcher{}
+
+type userCertWatcher struct {
+}
+
+func NewCertWatcher() *userCertWatcher {
+	return &userCertWatcher{}
+}
+
+// Watch implements watcher.Watcher.
+func (u *userCertWatcher) Watch(ctx context.Context) {
+
+	if state.CurrentState.TerminusState != state.TerminusRunning {
+		return
+	}
+
+	kubeClient, err := utils.GetKubeClient()
+	if err != nil {
+		klog.Error("failed to get kube client, ", err)
+		return
+	}
+
+	dynamicClient, err := utils.GetDynamicClient()
+	if err != nil {
+		klog.Error("failed to get dynamic client, ", err)
+		return
+	}
+
+	users, err := utils.ListUsers(ctx, dynamicClient)
+	if err != nil {
+		klog.Error("failed to list users, ", err)
+		return
+	}
+
+	for _, user := range users {
+		namespace := fmt.Sprintf("user-space-%s", user.GetName())
+		config, err := kubeClient.CoreV1().ConfigMaps(namespace).Get(ctx, "zone-ssl-config", metav1.GetOptions{})
+		if err != nil {
+			klog.Error("failed to get user config map, ", err, ", namespace: ", namespace)
+			continue
+		}
+
+		if expired, ok := config.Data["expired_at"]; ok {
+			expiredTime, err := time.Parse("2006-01-02T15:04:05Z", expired)
+			if err != nil {
+				klog.Error("failed to parse expired_at, ", err)
+				continue
+			}
+
+			// Check if the certificate will expire within 10 days
+			if expiredTime.Before(time.Now().Add(10 * 24 * time.Hour)) {
+				klog.Info("user cert expired, ", user.GetName())
+				err = createOrUpdateJob(ctx, kubeClient, namespace)
+				if err != nil {
+					klog.Error("failed to create or update job for user cert, ", err, ", namespace: ", namespace)
+				} else {
+					klog.Info("job created for user cert download, ", user.GetName(), ", namespace: ", namespace)
+				}
+			}
+		}
+	}
+}
+
+func createOrUpdateJob(ctx context.Context, kubeClient kubernetes.Interface, namespace string) error {
+	currentJob, err := kubeClient.BatchV1().Jobs(namespace).Get(ctx, jobDownloadUserCert.Name, metav1.GetOptions{})
+	if err != nil {
+		if kubeErr.IsNotFound(err) {
+			// Create the job if it does not exist
+		} else {
+			return fmt.Errorf("failed to get job: %w", err)
+		}
+	} else {
+		// check the existing job
+		if currentJob.Status.Succeeded == 0 || currentJob.Status.Failed > 0 {
+			klog.Info("job is still running, skip creating a new one")
+			return nil
+		}
+
+		// If the job exists and has completed, delete it before creating a new one
+		klog.Info("delete existing job: ", currentJob.Name)
+		err = kubeClient.BatchV1().Jobs(namespace).Delete(ctx, currentJob.Name, metav1.DeleteOptions{})
+		if err != nil {
+			return fmt.Errorf("failed to delete job: %w", err)
+		}
+	}
+
+	job := jobDownloadUserCert.DeepCopy()
+	job.Namespace = namespace
+	_, err = kubeClient.BatchV1().Jobs(job.Namespace).Create(ctx, job, metav1.CreateOptions{})
+	if err != nil {
+		return fmt.Errorf("failed to create job: %w", err)
+	}
+
+	klog.Info("Job created: ", job.Name)
+	return nil
+}
+
+var jobDownloadUserCert = batchv1.Job{
+	ObjectMeta: metav1.ObjectMeta{
+		Name: "download-user-cert",
+	},
+	Spec: batchv1.JobSpec{
+		BackoffLimit: ptr.To[int32](5),
+		Template: corev1.PodTemplateSpec{
+			Spec: corev1.PodSpec{
+				RestartPolicy: corev1.RestartPolicyOnFailure,
+				Containers: []corev1.Container{
+					{
+						Name:  "download-user-cert",
+						Image: "busybox:1.28",
+						Command: []string{"wget",
+							"--header",
+							"X-FROM-CRONJOB: true",
+							"-qSO -",
+							"http://bfl.user-space-pengpeng9/bfl/backend/v1/re-download-cert",
+						},
+					},
+				},
+			},
+		},
+	},
+}

daemon/internel/watcher/upgrade/upgrade_watcher.go

@@ -3,10 +3,13 @@ package upgrade
 import (
 	"context"
 	"fmt"
+	"github.com/Masterminds/semver/v3"
+	"github.com/beclab/Olares/daemon/pkg/utils"
 	"math"
 	"os"
 	"path/filepath"
 	"sync"
+	"time"
 
 	"github.com/beclab/Olares/daemon/internel/watcher"
 	"github.com/beclab/Olares/daemon/pkg/cluster/state"
@@ -19,6 +22,9 @@ type upgradeWatcher struct {
 	watcher.Watcher
 	sync.Mutex
 	upgrading bool
+	// Internal retry state
+	retryCount    int
+	nextRetryTime *time.Time
 }
 
 func NewUpgradeWatcher() watcher.Watcher {
@@ -27,19 +33,72 @@ func NewUpgradeWatcher() watcher.Watcher {
 }
 
 func (w *upgradeWatcher) Watch(ctx context.Context) {
-	switch state.CurrentState.TerminusState {
-	// indicates an upgrade target exists
-	case state.Upgrading:
-		// if the upgrade process is running, just wait for it to finish
-		if !w.isUpgrading() {
-			go func() {
-				w.startUpgrading()
-				defer w.stopUpgrading()
-				if err := doUpgrade(ctx); err != nil {
-					klog.Errorf("upgrading error: %v", err)
-				}
-			}()
+	targetVersion, err := state.GetOlaresUpgradeTarget()
+	if err != nil {
+		klog.Errorf("failed to check upgrade target: %v", err)
+		return
+	}
+
+	if targetVersion == nil {
+		w.resetRetryState()
+
+		state.TerminusStateMu.Lock()
+		state.CurrentState.UpgradingState = ""
+		state.CurrentState.UpgradingTarget = ""
+		state.CurrentState.UpgradingRetryNum = 0
+		state.CurrentState.UpgradingNextRetryAt = nil
+		state.CurrentState.UpgradingStep = ""
+		state.CurrentState.UpgradingProgressNum = 0
+		state.CurrentState.UpgradingProgress = ""
+		state.CurrentState.UpgradingError = ""
+
+		state.CurrentState.UpgradingDownloadState = ""
+		state.CurrentState.UpgradingDownloadStep = ""
+		state.CurrentState.UpgradingDownloadProgressNum = 0
+		state.CurrentState.UpgradingDownloadProgress = ""
+		state.CurrentState.UpgradingDownloadError = ""
+		state.TerminusStateMu.Unlock()
+
+		return
+	}
+
+	dynamicClient, err := utils.GetDynamicClient()
+	if err != nil {
+		return
+	}
+
+	currentVersionStr, err := utils.GetTerminusVersion(ctx, dynamicClient)
+	if err != nil {
+		klog.Error("failed to get current version, skip upgrading check: ", err)
+		return
+	}
+	if currentVersionStr == nil {
+		klog.Error("current version is nil, skip upgrading check")
+		return
+	}
+	currentVersion, err := semver.NewVersion(*currentVersionStr)
+	if err != nil || currentVersion.LessThan(targetVersion) {
+		state.CurrentState.UpgradingTarget = targetVersion.Original()
+	} else {
+		err = upgrade.RemoveUpgradeFiles()
+		if err != nil {
+			klog.Error("failed to remove upgrade files: ", err)
 		}
+		return
+	}
+
+	if !w.isUpgrading() {
+		if !w.isTimeToRetry() {
+			return
+		}
+
+		go func() {
+			w.startUpgrading()
+			defer w.stopUpgrading()
+			if err := w.doUpgradeWithRetry(ctx); err != nil {
+				klog.Errorf("upgrading error: %v", err)
+			}
+		}()
 	}
 }
 
@@ -61,52 +120,195 @@ func (w *upgradeWatcher) stopUpgrading() {
 	w.upgrading = false
 }
 
+func (w *upgradeWatcher) isTimeToRetry() bool {
+	w.Lock()
+	defer w.Unlock()
+
+	if w.nextRetryTime == nil {
+		return true
+	}
+
+	now := time.Now()
+	if now.Before(*w.nextRetryTime) {
+		klog.V(2).Infof("upgrade retry scheduled for %v (in %v)",
+			*w.nextRetryTime,
+			w.nextRetryTime.Sub(now))
+		return false
+	}
+
+	return true
+}
+
+func (w *upgradeWatcher) resetRetryState() {
+	w.Lock()
+	defer w.Unlock()
+	w.retryCount = 0
+	w.nextRetryTime = nil
+}
+
+func (w *upgradeWatcher) incrementRetry() {
+	w.Lock()
+	defer w.Unlock()
+	w.retryCount++
+	nextRetry := state.CalculateNextRetryTime(w.retryCount)
+	w.nextRetryTime = &nextRetry
+}
+
+func (w *upgradeWatcher) getRetryCount() int {
+	w.Lock()
+	defer w.Unlock()
+	return w.retryCount
+}
+
+func (w *upgradeWatcher) doUpgradeWithRetry(ctx context.Context) error {
+	err := doUpgrade(ctx)
+	if err != nil {
+		w.incrementRetry()
+
+		state.CurrentState.UpgradingRetryNum = w.getRetryCount()
+		state.CurrentState.UpgradingNextRetryAt = w.nextRetryTime
+
+		klog.Errorf("upgrade attempt %d failed: %v. Next retry scheduled for %v",
+			w.getRetryCount(), err, *w.nextRetryTime)
+
+		targetVersionDir := filepath.Join(commands.TERMINUS_BASE_DIR, "versions", "v"+state.CurrentState.UpgradingTarget)
+		prepareLogFile := filepath.Join(targetVersionDir, "install.log")
+		upgradeLogFile := filepath.Join(targetVersionDir, "upgrade.log")
+		for _, logFile := range []string{prepareLogFile, upgradeLogFile} {
+			if err := os.Remove(logFile); err != nil && !os.IsNotExist(err) {
+				klog.Errorf("failed to clear log file %s: %v", logFile, err)
+			}
+		}
+	}
+	return err
+}
+
 type upgradePhase struct {
 	newCMD         func() commands.Interface
 	progressOffset int
 	progressSpan   int
 }
 
-// todo: add a phase to upgrade olares-cli after the version of olares-cli and olares has been unified
+var downloadPhases = []upgradePhase{
+	{upgrade.NewDownloadCLI, 0, 10},
+	{upgrade.NewDownloadWizard, 10, 20},
+	{upgrade.NewDownloadComponent, 30, 40},
+}
+
 var upgradePhases = []upgradePhase{
-	{upgrade.NewUpgradeCli, 0, 5},
-	{upgrade.NewDownloadWizard, 5, 10},
-	{upgrade.NewVersionCompatibilityCheck, 15, 0},
-	{upgrade.NewHealthCheck, 15, 0},
-	{upgrade.NewDownloadComponent, 15, 30},
-	{upgrade.NewPrepareImages, 45, 30},
-	{upgrade.NewPrepareOlaresd, 75, 5},
-	{upgrade.NewUpgrade, 80, 15},
+	{upgrade.NewVersionCompatibilityCheck, 0, 5},
+	{upgrade.NewHealthCheck, 5, 5},
+	{upgrade.NewInstallCLI, 10, 10},
+	{upgrade.NewImportImages, 20, 30},
+	{upgrade.NewInstallOlaresd, 50, 10},
+	{upgrade.NewUpgrade, 60, 35},
 	{upgrade.NewRemoveTarget, 95, 5},
 }
 
 func doUpgrade(ctx context.Context) (err error) {
+	downloadCompleted, err := state.IsUpgradeDownloadCompleted()
+	if err != nil {
+		return fmt.Errorf("failed to check download status: %v", err)
+	}
+
+	if !downloadCompleted {
+		// Execute download phases
+		if err := doDownloadPhases(ctx); err != nil {
+			return err
+		}
+	} else {
+		klog.Info("download already completed, skipping download phases")
+		state.CurrentState.UpgradingDownloadState = state.Completed
+		state.CurrentState.UpgradingDownloadProgress = "100%"
+		state.CurrentState.UpgradingDownloadProgressNum = 100
+	}
+
+	downloadOnly, err := state.IsUpgradeDownloadOnly()
+	if err != nil {
+		return fmt.Errorf("failed to check download-only status: %v", err)
+	}
+
+	if downloadOnly {
+		state.CurrentState.UpgradingState = "WaitingForUserConfirm"
+		klog.Info("download completed, waiting for user request to remove upgrade.downloadonly file to proceed with upgrade")
+		return nil
+	}
+
+	return doUpgradePhases(ctx)
+}
+
+func doDownloadPhases(ctx context.Context) (err error) {
+	defer func() {
+		if err != nil {
+			state.CurrentState.UpgradingDownloadState = state.Failed
+			state.CurrentState.UpgradingDownloadError = err.Error()
+			klog.Errorf("download phases failed: %v", err)
+		} else {
+			state.CurrentState.UpgradingDownloadState = state.Completed
+			state.CurrentState.UpgradingDownloadError = ""
+			if err := createUpgradeDownloadedFile(); err != nil {
+				klog.Errorf("failed to create upgrade.downloaded file: %v", err)
+			}
+			klog.Info("download phases completed successfully")
+		}
+	}()
+
+	state.CurrentState.UpgradingDownloadState = state.InProgress
+	state.CurrentState.UpgradingDownloadError = ""
+
+	for _, phase := range downloadPhases {
+		phaseCMD := phase.newCMD()
+		state.CurrentState.UpgradingDownloadStep = string(phaseCMD.OperationName())
+
+		res, err := phaseCMD.Execute(ctx, state.CurrentState.UpgradingTarget)
+		if err != nil {
+			return fmt.Errorf("error: download phase %s: %v", phaseCMD.OperationName(), err)
+		}
+		executionRes, ok := res.(upgrade.ExecutionRes)
+		if !ok {
+			return fmt.Errorf("unexpected result type for download phase %s", phaseCMD.OperationName())
+		}
+		if executionRes.Finished() {
+			continue
+		}
+		var phaseProgress int
+		for phaseProgress < 100 {
+			select {
+			case <-ctx.Done():
+				return nil
+			case p, ok := <-executionRes.Progress():
+				if !ok {
+					if phaseProgress != commands.ProgressNumFinished {
+						return fmt.Errorf("error: download phase %s: command execution did not succeed", phaseCMD.OperationName())
+					}
+				} else if p > phaseProgress {
+					klog.Infof("refreshing download phase %s, progress: %d", phaseCMD.OperationName(), phaseProgress)
+					phaseProgress = p
+				}
+			}
+			refreshDownloadProgressFromPhase(phase, phaseProgress)
+		}
+	}
+	return nil
+}
+
+func doUpgradePhases(ctx context.Context) (err error) {
 	defer func() {
 		if err != nil {
 			state.CurrentState.UpgradingState = state.Failed
 			state.CurrentState.UpgradingError = err.Error()
-
-			// clear logs after every failed attempt
-			// in case any under layer change that bypassed olaresd, e.g., manual removal of files
-			// is causing the upgrade retry to stuck forever
-			targetVersionDir := filepath.Join(commands.TERMINUS_BASE_DIR, "versions", "v"+state.CurrentState.UpgradingTarget)
-			prepareLogFile := filepath.Join(targetVersionDir, "install.log")
-			upgradeLogFile := filepath.Join(targetVersionDir, "upgrade.log")
-			for _, logFile := range []string{prepareLogFile, upgradeLogFile} {
-				if err := os.Remove(logFile); err != nil && !os.IsNotExist(err) {
-					klog.Errorf("failed to clear log file %s of current upgrade attempt (%d): %v", logFile, state.CurrentState.UpgradingRetryNum, err)
-				}
-			}
 		}
 	}()
 
 	state.CurrentState.UpgradingState = state.InProgress
 	state.CurrentState.UpgradingError = ""
-	state.CurrentState.UpgradingRetryNum += 1
+
+	state.StateTrigger <- struct{}{}
 
 	for _, phase := range upgradePhases {
 		phaseCMD := phase.newCMD()
 		state.CurrentState.UpgradingStep = string(phaseCMD.OperationName())
+
 		res, err := phaseCMD.Execute(ctx, state.CurrentState.UpgradingTarget)
 		if err != nil {
 			return fmt.Errorf("error: upgrade phase %s: %v", phaseCMD.OperationName(), err)
@@ -116,9 +318,6 @@ func doUpgrade(ctx context.Context) (err error) {
 			return fmt.Errorf("unexpected result type for upgrade phase %s", phaseCMD.OperationName())
 		}
 		if executionRes.Finished() {
-			// for now, do not update progress here
-			// as it may revert back the progress
-			// todo: if the retry num will be presented by the frontend to user, maybe we can update progress here
 			continue
 		}
 		var phaseProgress int
@@ -127,7 +326,6 @@ func doUpgrade(ctx context.Context) (err error) {
 			case <-ctx.Done():
 				return nil
 			case p, ok := <-executionRes.Progress():
-				// the command completed and the progress channel is closed
 				if !ok {
 					if phaseProgress != commands.ProgressNumFinished {
 						return fmt.Errorf("error: upgrade phase %s: command execution did not succeed", phaseCMD.OperationName())
@@ -140,8 +338,6 @@ func doUpgrade(ctx context.Context) (err error) {
 			refreshUpgradeProgressFromPhase(phase, phaseProgress)
 		}
 	}
-	// if the upgrade succeeded, the upgrade target will be removed
-	// and the upgrade status cleared
 	return nil
 }
 
@@ -154,3 +350,17 @@ func refreshUpgradeProgressFromPhase(phase upgradePhase, phaseProgress int) {
 	state.CurrentState.UpgradingProgressNum = newProgress
 	state.CurrentState.UpgradingProgress = fmt.Sprintf("%d%%", state.CurrentState.UpgradingProgressNum)
 }
+
+func refreshDownloadProgressFromPhase(phase upgradePhase, phaseProgress int) {
+	spanProgress := math.Min(float64(phaseProgress)*float64(phase.progressSpan)/float64(commands.ProgressNumFinished), float64(phase.progressSpan))
+	newProgress := phase.progressOffset + int(math.Round(spanProgress))
+	if state.CurrentState.UpgradingDownloadProgressNum >= newProgress {
+		return
+	}
+	state.CurrentState.UpgradingDownloadProgressNum = newProgress
+	state.CurrentState.UpgradingDownloadProgress = fmt.Sprintf("%d%%", state.CurrentState.UpgradingDownloadProgressNum)
+}
+
+func createUpgradeDownloadedFile() error {
+	return os.WriteFile(commands.UPGRADE_DOWNLOADED_FILE, []byte(""), 0644)
+}

daemon/pkg/cluster/state/current.go

@@ -16,7 +16,6 @@ import (
 	"k8s.io/klog/v2"
 	"k8s.io/utils/pointer"
 
-	"github.com/Masterminds/semver/v3"
 	cpu "github.com/klauspost/cpuid/v2"
 	"github.com/pbnjay/memory"
 )
@@ -59,12 +58,19 @@ type state struct {
 	UninstallingProgressNum int             `json:"-"`
 	UpgradingTarget         string          `json:"upgradingTarget"`
 	UpgradingRetryNum       int             `json:"upgradingRetryNum"`
+	UpgradingNextRetryAt    *time.Time      `json:"upgradingNextRetryAt,omitempty"`
 	UpgradingState          ProcessingState `json:"upgradingState"`
 	UpgradingStep           string          `json:"upgradingStep"`
 	UpgradingProgress       string          `json:"upgradingProgress"`
 	UpgradingProgressNum    int             `json:"-"`
 	UpgradingError          string          `json:"upgradingError"`
 
+	UpgradingDownloadState       ProcessingState `json:"upgradingDownloadState"`
+	UpgradingDownloadStep        string          `json:"upgradingDownloadStep"`
+	UpgradingDownloadProgress    string          `json:"upgradingDownloadProgress"`
+	UpgradingDownloadProgressNum int             `json:"-"`
+	UpgradingDownloadError       string          `json:"upgradingDownloadError"`
+
 	CollectingLogsState ProcessingState `json:"collectingLogsState"`
 	CollectingLogsError string          `json:"collectingLogsError"`
 
@@ -97,6 +103,13 @@ func bToGb(b uint64) string {
 
 func CheckCurrentStatus(ctx context.Context) error {
 	TerminusStateMu.Lock()
+	name, err := utils.GetOlaresNameFromReleaseFile()
+	if err != nil {
+		klog.Error("get olares name from release file error, ", err)
+	} else {
+		CurrentState.TerminusName = &name
+	}
+
 	var currentTerminusState TerminusState = CurrentState.TerminusState
 	defer func() {
 		CurrentState.TerminusState = currentTerminusState
@@ -151,6 +164,7 @@ func CheckCurrentStatus(ctx context.Context) error {
 	// get network info
 	ips, err := nets.GetInternalIpv4Addr()
 	if err != nil {
+		currentTerminusState = NetworkNotReady
 		return err
 	}
 
@@ -293,7 +307,6 @@ func CheckCurrentStatus(ctx context.Context) error {
 		currentTerminusState = NotInstalled
 		CurrentState.InstallingProgress = ""
 		CurrentState.InstallingState = ""
-		CurrentState.TerminusName = nil
 		CurrentState.InstalledTime = nil
 		CurrentState.InitializedTime = nil
 
@@ -332,33 +345,24 @@ func CheckCurrentStatus(ctx context.Context) error {
 		}
 	}
 
-	targetVersion, err := GetOlaresUpgradeTarget()
+	// only set system state to Upgrading if actual upgrade should be in progress
+	// (not during download phase)
+	upgradeTarget, err := GetOlaresUpgradeTarget()
 	if err != nil {
-		return err
+		return fmt.Errorf("error getting Olares upgrade target: %v", err.Error())
 	}
-	if targetVersion != nil {
-		// get current version and compare with target version
-		currentVersionStr, err := utils.GetTerminusVersion(ctx, dynamicClient)
-		if err != nil {
-			klog.Error("failed to get current version: ", err)
-			return err
-		}
-		currentVersion, err := semver.NewVersion(*currentVersionStr)
-		if err != nil || currentVersion.LessThan(targetVersion) {
-			CurrentState.UpgradingTarget = targetVersion.Original()
-			currentTerminusState = Upgrading
-			return nil
-		}
+	upgradeDownloadCompleted, err := IsUpgradeDownloadCompleted()
+	if err != nil {
+		return fmt.Errorf("error checking if upgrade download completed: %v", err.Error())
+	}
+	upgradeDownloadOnly, err := IsUpgradeDownloadOnly()
+	if err != nil {
+		return fmt.Errorf("error checking if upgrade download only: %v", err.Error())
+	}
+	if upgradeTarget != nil && upgradeDownloadCompleted && !upgradeDownloadOnly {
+		currentTerminusState = Upgrading
+		return nil
 	}
-
-	// not upgrading, reset upgrading status
-	CurrentState.UpgradingState = ""
-	CurrentState.UpgradingTarget = ""
-	CurrentState.UpgradingRetryNum = 0
-	CurrentState.UpgradingStep = ""
-	CurrentState.UpgradingProgressNum = 0
-	CurrentState.UpgradingProgress = ""
-	CurrentState.UpgradingError = ""
 
 	if tmsrunning, err := utils.IsTerminusRunning(ctx, kubeClient); err != nil {
 		currentTerminusState = SystemError

daemon/pkg/cluster/state/retry.go

@@ -0,0 +1,41 @@
+package state
+
+import (
+	"math"
+	"math/rand"
+	"time"
+)
+
+const (
+	retryBaseDelay     = 5 * time.Second
+	retryMaxDelay      = 10 * time.Minute
+	retryBackoffFactor = 2.0
+)
+
+func calculateNextRetryDelay(retryNum int) time.Duration {
+	backoffDelay := float64(retryBaseDelay) * math.Pow(retryBackoffFactor, float64(retryNum))
+
+	if backoffDelay > float64(retryMaxDelay) {
+		backoffDelay = float64(retryMaxDelay)
+	}
+
+	delay := time.Duration(backoffDelay)
+
+	jitter := float64(delay) * 0.25 * (rand.Float64()*2 - 1)
+	delay = time.Duration(float64(delay) + jitter)
+
+	if delay < 0 {
+		delay = retryBaseDelay
+	}
+
+	return delay
+}
+
+func calculateNextRetryTime(retryNum int) time.Time {
+	delay := calculateNextRetryDelay(retryNum)
+	return time.Now().Add(delay)
+}
+
+func CalculateNextRetryTime(retryNum int) time.Time {
+	return calculateNextRetryTime(retryNum)
+}

daemon/pkg/cluster/state/terminus.go

@@ -37,6 +37,7 @@ const (
 	Shutdown         TerminusState = "shutdown"
 	Restarting       TerminusState = "restarting"
 	Checking         TerminusState = "checking"
+	NetworkNotReady  TerminusState = "network-not-ready"
 )
 
 func (s TerminusState) String() string {

daemon/pkg/cluster/state/utils.go

@@ -88,6 +88,10 @@ func isProcessRunning(pidfile string) (bool, error) {
 		return false, err
 	}
 
+	if len(strings.TrimSpace(string(pidData))) == 0 {
+		return false, nil
+	}
+
 	pid, err := strconv.Atoi(string(pidData))
 	if err != nil {
 		return false, err
@@ -143,6 +147,28 @@ func GetOlaresUpgradeTarget() (*semver.Version, error) {
 	return version, nil
 }
 
+func IsUpgradeDownloadOnly() (bool, error) {
+	_, err := os.Stat(commands.UPGRADE_DOWNLOADONLY_FILE)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return false, nil
+		}
+		return false, err
+	}
+	return true, nil
+}
+
+func IsUpgradeDownloadCompleted() (bool, error) {
+	_, err := os.Stat(commands.UPGRADE_DOWNLOADED_FILE)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return false, nil
+		}
+		return false, err
+	}
+	return true, nil
+}
+
 func IsIpChangeRunning() (bool, error) {
 	running, err := isProcessRunning(commands.CHANGINGIP_PID_FILE)
 	if err != nil {

daemon/pkg/commands/collect_logs/cmd.go

@@ -63,6 +63,11 @@ func (i *collectLogs) Execute(ctx context.Context, p any) (res any, err error) {
 			return
 		}
 
+		if adminUser == nil {
+			errStr = "admin user not found"
+			return
+		}
+
 		hostPath, err := utils.GetUserspacePvcHostPath(ctx, adminUser.GetName(), kubeClient)
 		if err != nil {
 			errStr = fmt.Sprintf("get admin user host path error, %v", err)

daemon/pkg/commands/constants.go

@@ -16,20 +16,22 @@ var (
 	COMMAND_BASE_DIR  = "" // deprecated shell command base dir
 	CDN_URL           = "https://dc3p1870nn3cj.cloudfront.net"
 
-	OS_ROOT_DIR            = "/olares"
-	INSTALLING_PID_FILE    = "installing.pid"
-	UNINSTALLING_PID_FILE  = "uninstalling.pid"
-	CHANGINGIP_PID_FILE    = "changingip.pid"
-	UPGRADE_TARGET_FILE    = "upgrade.target"
-	PREV_IP_TO_CHANGE_FILE = ".prev_ip"
-	PREV_IP_CHANGE_FAILED  = ".ip_change_failed"
-	INSTALL_LOCK           = ".installed"
-	LOG_FILE               = "install.log"
-	TERMINUS_BASE_DIR      = ""
-	MOUNT_BASE_DIR         = path.Join(OS_ROOT_DIR, "share")
-	PREPARE_LOCK           = ".prepared"
-	REDIS_CONF             = OS_ROOT_DIR + "/data/redis/etc/redis.conf"
-	EXPORT_POD_LOGS_DIR    = "Home/pod_logs"
+	OS_ROOT_DIR               = "/olares"
+	INSTALLING_PID_FILE       = "installing.pid"
+	UNINSTALLING_PID_FILE     = "uninstalling.pid"
+	CHANGINGIP_PID_FILE       = "changingip.pid"
+	UPGRADE_TARGET_FILE       = "upgrade.target"
+	UPGRADE_DOWNLOADONLY_FILE = "upgrade.downloadonly"
+	UPGRADE_DOWNLOADED_FILE   = "upgrade.downloaded"
+	PREV_IP_TO_CHANGE_FILE    = ".prev_ip"
+	PREV_IP_CHANGE_FAILED     = ".ip_change_failed"
+	INSTALL_LOCK              = ".installed"
+	LOG_FILE                  = "install.log"
+	TERMINUS_BASE_DIR         = ""
+	MOUNT_BASE_DIR            = path.Join(OS_ROOT_DIR, "share")
+	PREPARE_LOCK              = ".prepared"
+	REDIS_CONF                = OS_ROOT_DIR + "/data/redis/etc/redis.conf"
+	EXPORT_POD_LOGS_DIR       = "Home/pod_logs"
 
 	ProgressNumFinished = 100
 )
@@ -45,6 +47,8 @@ func Init() {
 	UNINSTALLING_PID_FILE = filepath.Join(baseDir, UNINSTALLING_PID_FILE)
 	CHANGINGIP_PID_FILE = filepath.Join(baseDir, CHANGINGIP_PID_FILE)
 	UPGRADE_TARGET_FILE = filepath.Join(baseDir, UPGRADE_TARGET_FILE)
+	UPGRADE_DOWNLOADONLY_FILE = filepath.Join(baseDir, UPGRADE_DOWNLOADONLY_FILE)
+	UPGRADE_DOWNLOADED_FILE = filepath.Join(baseDir, UPGRADE_DOWNLOADED_FILE)
 	INSTALL_LOCK = filepath.Join(baseDir, INSTALL_LOCK)
 	PREPARE_LOCK = filepath.Join(baseDir, PREPARE_LOCK)
 	PREV_IP_TO_CHANGE_FILE = filepath.Join(baseDir, PREV_IP_TO_CHANGE_FILE)

daemon/pkg/commands/operations.go

@@ -19,14 +19,15 @@ const (
 	Uninstall                 Operations = "uninstall"
 	CreateUpgradeTarget       Operations = "createUpgradeTarget"
 	RemoveUpgradeTarget       Operations = "removeUpgradeTarget"
+	DownloadCLI               Operations = "downloadCLI"
 	DownloadWizard            Operations = "downloadWizard"
 	VersionCompatibilityCheck Operations = "versionCompatibilityCheck"
 	UpgradeHealthCheck        Operations = "upgradeHealthCheck"
 	DownloadComponent         Operations = "downloadComponent"
-	PrepareImages             Operations = "prepareImages"
-	PrepareOlaresd            Operations = "prepareOlaresd"
+	ImportImages              Operations = "importImages"
+	InstallOlaresd            Operations = "installOlaresd"
 	Upgrade                   Operations = "upgrade"
-	UpgradeCli                Operations = "upgradeCli"
+	InstallCLI                Operations = "installCLI"
 	Reboot                    Operations = "reboot"
 	Shutdown                  Operations = "shutdown"
 	ConnectWifi               Operations = "connectWifi"

daemon/pkg/commands/upgrade/check.go

@@ -15,6 +15,7 @@ import (
 	metav1 "k8s.io/apimachinery/pkg/apis/meta/v1"
 	"k8s.io/apimachinery/pkg/util/sets"
 	"k8s.io/apimachinery/pkg/util/yaml"
+	"k8s.io/klog/v2"
 )
 
 type versionCompatibilityCheck struct {
@@ -91,6 +92,19 @@ func NewHealthCheck() commands.Interface {
 }
 
 func (i *healthCheck) Execute(ctx context.Context, _ any) (res any, err error) {
+	klog.Info("Starting upgrade health check")
+
+	const minAvailableSpace = 100 * 1024 * 1024 * 1024 // 100GB in bytes
+	availableSpace, err := utils.GetDiskAvailableSpace("/")
+	if err != nil {
+		return nil, fmt.Errorf("error checking disk space: %s", err)
+	}
+	klog.Infof("Root partition available space: %.2fGB", float64(availableSpace)/(1024*1024*1024))
+	if availableSpace < minAvailableSpace {
+		return nil, fmt.Errorf("insufficient disk space: %.2fGB available, minimum 100GB required",
+			float64(availableSpace)/(1024*1024*1024))
+	}
+
 	client, err := utils.GetKubeClient()
 	if err != nil {
 		return nil, fmt.Errorf("error getting kubernetes client: %s", err)
@@ -132,5 +146,33 @@ func (i *healthCheck) Execute(ctx context.Context, _ any) (res any, err error) {
 		}
 	}
 
+	criticalNamespaces := []string{"os-platform", "os-framework"}
+	for _, namespace := range criticalNamespaces {
+		pods, err := client.CoreV1().Pods(namespace).List(ctx, metav1.ListOptions{})
+		if err != nil {
+			return nil, fmt.Errorf("error listing pods in namespace %s: %s", namespace, err)
+		}
+
+		for _, pod := range pods.Items {
+			if pod.Status.Phase == corev1.PodSucceeded {
+				continue
+			}
+
+			podStatus := utils.GetPodStatus(&pod)
+
+			if podStatus != "Running" && podStatus != "Completed" {
+				klog.Errorf("Pod %s/%s is not healthy: %s", namespace, pod.Name, podStatus)
+				return nil, fmt.Errorf("pod %s/%s is not healthy: %s", namespace, pod.Name, podStatus)
+			}
+
+			if !utils.IsPodReady(&pod) && pod.Status.Phase == corev1.PodRunning {
+				klog.Warningf("Pod %s/%s is running but not ready", namespace, pod.Name)
+				return nil, fmt.Errorf("pod %s/%s is running but not ready", namespace, pod.Name)
+			}
+		}
+	}
+
+	klog.Info("health checks passed for upgrade")
+
 	return newExecutionRes(true, nil), nil
 }

daemon/pkg/commands/upgrade/create_upgrade_target.go

@@ -0,0 +1,84 @@
+package upgrade
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+
+	"github.com/beclab/Olares/daemon/pkg/cluster/state"
+	"github.com/beclab/Olares/daemon/pkg/commands"
+)
+
+type UpgradeRequest struct {
+	Version      string `json:"version"`
+	DownloadOnly bool   `json:"downloadOnly"`
+}
+
+type createUpgradeTarget struct {
+	commands.Operation
+}
+
+var _ commands.Interface = &createUpgradeTarget{}
+
+func NewCreateUpgradeTarget() commands.Interface {
+	return &createUpgradeTarget{
+		Operation: commands.Operation{
+			Name: commands.CreateUpgradeTarget,
+		},
+	}
+}
+
+func (i *createUpgradeTarget) Execute(ctx context.Context, p any) (res any, err error) {
+	req, ok := p.(UpgradeRequest)
+	if !ok {
+		return nil, errors.New("invalid param")
+	}
+
+	if err := checkVersionConflicts(req.Version); err != nil {
+		return nil, err
+	}
+
+	if err := createUpgradeTargetFile(req.Version); err != nil {
+		return nil, fmt.Errorf("failed to create upgrade target: %v", err)
+	}
+
+	if req.DownloadOnly {
+		if err := createUpgradeDownloadOnlyFile(); err != nil {
+			return nil, fmt.Errorf("failed to create upgrade downloadonly file: %v", err)
+		}
+	} else {
+		if err := removeUpgradeDownloadOnlyFile(); err != nil && !os.IsNotExist(err) {
+			return nil, fmt.Errorf("failed to remove upgrade downloadonly file: %v", err)
+		}
+	}
+
+	state.StateTrigger <- struct{}{}
+
+	return NewExecutionRes(true, nil), nil
+}
+
+func checkVersionConflicts(version string) error {
+	if state.CurrentState.UpgradingState == state.InProgress {
+		return fmt.Errorf("system is currently upgrading")
+	}
+
+	upgradeTarget, err := state.GetOlaresUpgradeTarget()
+	if err == nil && upgradeTarget != nil && upgradeTarget.Original() != version {
+		return fmt.Errorf("different upgrade version %s already exists, please cancel it first", upgradeTarget.Original())
+	}
+
+	return nil
+}
+
+func createUpgradeTargetFile(version string) error {
+	return os.WriteFile(commands.UPGRADE_TARGET_FILE, []byte(version), 0755)
+}
+
+func createUpgradeDownloadOnlyFile() error {
+	return os.WriteFile(commands.UPGRADE_DOWNLOADONLY_FILE, []byte(""), 0755)
+}
+
+func removeUpgradeDownloadOnlyFile() error {
+	return os.Remove(commands.UPGRADE_DOWNLOADONLY_FILE)
+}

daemon/pkg/commands/upgrade/download_cli.go

@@ -0,0 +1,85 @@
+package upgrade
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"runtime"
+
+	"github.com/Masterminds/semver/v3"
+	"github.com/beclab/Olares/daemon/pkg/commands"
+	"k8s.io/klog/v2"
+)
+
+type downloadCLI struct {
+	commands.Operation
+}
+
+var _ commands.Interface = &downloadCLI{}
+
+func NewDownloadCLI() commands.Interface {
+	return &downloadCLI{
+		Operation: commands.Operation{
+			Name: commands.DownloadCLI,
+		},
+	}
+}
+
+func (i *downloadCLI) Execute(ctx context.Context, p any) (res any, err error) {
+	version, ok := p.(string)
+	if !ok {
+		return nil, errors.New("invalid param")
+	}
+
+	targetVersion, err := semver.NewVersion(version)
+	if err != nil {
+		return nil, fmt.Errorf("invalid target version %s: %v", version, err)
+	}
+
+	currentVersion, err := getCurrentCliVersion()
+	if err != nil {
+		// if we can't get the current version, assume we need to download
+		klog.Warningf("Failed to get current olares-cli version: %v, proceeding with download", err)
+	} else {
+		if !currentVersion.LessThan(targetVersion) {
+			return newExecutionRes(true, nil), nil
+		}
+	}
+
+	arch := "amd64"
+	if runtime.GOARCH == "arm" {
+		arch = "arm64"
+	}
+
+	destDir := filepath.Join(commands.TERMINUS_BASE_DIR, "pkg", "components")
+	if err := os.MkdirAll(destDir, 0755); err != nil {
+		return nil, fmt.Errorf("failed to create components directory: %v", err)
+	}
+
+	downloadURL := fmt.Sprintf("%s/olares-cli-v%s_linux_%s.tar.gz", commands.CDN_URL, version, arch)
+	tarFile := filepath.Join(destDir, fmt.Sprintf("olares-cli-v%s.tar.gz", version))
+
+	if err := downloadFile(downloadURL, tarFile); err != nil {
+		return nil, fmt.Errorf("failed to download olares-cli: %v", err)
+	}
+
+	if err := extractTarGz(tarFile, destDir); err != nil {
+		return nil, fmt.Errorf("failed to extract olares-cli: %v", err)
+	}
+
+	binaryPath := filepath.Join(destDir, "olares-cli")
+	versionedPath := filepath.Join(destDir, fmt.Sprintf("olares-cli-v%s", version))
+	if err := os.Rename(binaryPath, versionedPath); err != nil {
+		return nil, fmt.Errorf("failed to rename olares-cli binary: %v", err)
+	}
+
+	if err := os.Chmod(versionedPath, 0755); err != nil {
+		return nil, fmt.Errorf("failed to make olares-cli executable: %v", err)
+	}
+
+	os.Remove(tarFile)
+
+	return newExecutionRes(true, nil), nil
+}

daemon/pkg/commands/upgrade/import_images.go

@@ -26,10 +26,10 @@ type prepareImages struct {
 
 var _ commands.Interface = &prepareImages{}
 
-func NewPrepareImages() commands.Interface {
+func NewImportImages() commands.Interface {
 	return &prepareImages{
 		Operation: commands.Operation{
-			Name: commands.PrepareImages,
+			Name: commands.ImportImages,
 		},
 		progressKeywords: []progressKeyword{
 			{"Preload Container Images execute successfully", commands.ProgressNumFinished},
@@ -119,7 +119,7 @@ func (i *prepareImages) refreshProgress() error {
 			if strings.Contains(line.Text, p.KeyWord) {
 				lineProgress = p.ProgressNum
 			} else {
-				lineProgress = parseProgressFromItemProgress(line.Text)
+				lineProgress = parseImagePrepareProgressByItemProgress(line.Text)
 			}
 			if i.progress < lineProgress {
 				i.progress = lineProgress

daemon/pkg/commands/upgrade/install_cli.go

@@ -0,0 +1,67 @@
+package upgrade
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"github.com/Masterminds/semver/v3"
+	"github.com/beclab/Olares/daemon/pkg/commands"
+	"k8s.io/klog/v2"
+	"os"
+	"os/exec"
+	"path/filepath"
+)
+
+type installCLI struct {
+	commands.Operation
+}
+
+var _ commands.Interface = &installCLI{}
+
+func NewInstallCLI() commands.Interface {
+	return &installCLI{
+		Operation: commands.Operation{
+			Name: commands.InstallCLI,
+		},
+	}
+}
+
+func (i *installCLI) Execute(ctx context.Context, p any) (res any, err error) {
+	version, ok := p.(string)
+	if !ok {
+		return nil, errors.New("invalid param")
+	}
+
+	targetVersion, err := semver.NewVersion(version)
+	if err != nil {
+		return nil, fmt.Errorf("invalid target version %s: %v", version, err)
+	}
+
+	currentVersion, err := getCurrentCliVersion()
+	if err != nil {
+		klog.Warningf("Failed to get current olares-cli version: %v, proceeding with installation", err)
+	} else {
+		if !currentVersion.LessThan(targetVersion) {
+			return newExecutionRes(true, nil), nil
+		}
+	}
+
+	preDownloadedPath := filepath.Join(commands.TERMINUS_BASE_DIR, "pkg", "components", fmt.Sprintf("olares-cli-v%s", version))
+	if _, err := os.Stat(preDownloadedPath); err != nil {
+		klog.Warningf("Failed to find pre-downloaded binary path %s: %v", preDownloadedPath, err)
+		return newExecutionRes(false, nil), err
+	}
+
+	cmd := exec.Command("cp", "-f", preDownloadedPath, "/usr/local/bin/olares-cli")
+	err = cmd.Run()
+	if err != nil {
+		klog.Warningf("Failed to install olares-cli: %v", err)
+		return newExecutionRes(false, nil), err
+	}
+
+	if err := os.Chmod("/usr/local/bin/olares-cli", 0755); err != nil {
+		return nil, fmt.Errorf("failed to make olares-cli executable: %v", err)
+	}
+
+	return newExecutionRes(true, nil), nil
+}

daemon/pkg/commands/upgrade/install_olaresd.go

@@ -10,6 +10,7 @@ import (
 	"strings"
 	"time"
 
+	semver "github.com/Masterminds/semver/v3"
 	"github.com/beclab/Olares/daemon/pkg/cli"
 	"github.com/beclab/Olares/daemon/pkg/commands"
 	"github.com/nxadm/tail"
@@ -26,10 +27,10 @@ type prepareOlaresd struct {
 
 var _ commands.Interface = &prepareOlaresd{}
 
-func NewPrepareOlaresd() commands.Interface {
+func NewInstallOlaresd() commands.Interface {
 	return &prepareOlaresd{
 		Operation: commands.Operation{
-			Name: commands.PrepareOlaresd,
+			Name: commands.InstallOlaresd,
 		},
 		progressKeywords: []progressKeyword{
 			{"ReplaceOlaresdBinary success", 30},
@@ -52,6 +53,19 @@ func (i *prepareOlaresd) Execute(ctx context.Context, p any) (res any, err error
 	if !ok {
 		return nil, errors.New("invalid param")
 	}
+	targetVersion, err := semver.NewVersion(version)
+	if err != nil {
+		return nil, fmt.Errorf("invalid target version %s: %v", version, err)
+	}
+
+	currentVersion, err := getCurrentDaemonVersion()
+	if err != nil {
+		klog.Warningf("Failed to get current olaresd version: %v, proceeding with installation", err)
+	} else {
+		if !currentVersion.LessThan(targetVersion) {
+			return newExecutionRes(true, nil), nil
+		}
+	}
 
 	i.logFile = filepath.Join(commands.TERMINUS_BASE_DIR, "versions", "v"+version, "logs", "install.log")
 	if err := i.refreshProgress(); err != nil {

daemon/pkg/commands/upgrade/remove_upgrade_target.go

@@ -0,0 +1,57 @@
+package upgrade
+
+import (
+	"context"
+	"os"
+
+	"github.com/beclab/Olares/daemon/pkg/cluster/state"
+	"github.com/beclab/Olares/daemon/pkg/commands"
+)
+
+type removeUpgradeTarget struct {
+	commands.Operation
+}
+
+var _ commands.Interface = &removeUpgradeTarget{}
+
+func NewRemoveUpgradeTarget() commands.Interface {
+	return &removeUpgradeTarget{
+		Operation: commands.Operation{
+			Name: commands.RemoveUpgradeTarget,
+		},
+	}
+}
+
+func (i *removeUpgradeTarget) Execute(ctx context.Context, p any) (res any, err error) {
+	err = RemoveUpgradeFiles()
+	if err != nil {
+		return nil, err
+	}
+
+	state.CurrentState.UpgradingDownloadState = ""
+	state.CurrentState.UpgradingDownloadStep = ""
+	state.CurrentState.UpgradingDownloadProgress = ""
+	state.CurrentState.UpgradingDownloadProgressNum = 0
+	state.CurrentState.UpgradingDownloadError = ""
+
+	state.StateTrigger <- struct{}{}
+
+	return NewExecutionRes(true, nil), nil
+}
+
+func RemoveUpgradeFiles() error {
+	// attempt to remove all files whether they exist or not (idempotent)
+	files := []string{
+		commands.UPGRADE_TARGET_FILE,
+		commands.UPGRADE_DOWNLOADONLY_FILE,
+		commands.UPGRADE_DOWNLOADED_FILE,
+	}
+
+	for _, file := range files {
+		if err := os.Remove(file); err != nil && !os.IsNotExist(err) {
+			return err
+		}
+	}
+
+	return nil
+}

daemon/pkg/commands/upgrade/types.go

@@ -31,6 +31,10 @@ func newExecutionRes(finished bool, progressChan <-chan int) ExecutionRes {
 	}
 }
 
+func NewExecutionRes(finished bool, progressChan <-chan int) ExecutionRes {
+	return newExecutionRes(finished, progressChan)
+}
+
 type progressKeyword struct {
 	KeyWord     string
 	ProgressNum int
@@ -41,7 +45,7 @@ var itemProcessProgressRE = regexp.MustCompile(`\((\d+)/(\d+)\)`)
 
 func parseProgressFromItemProgress(line string) int {
 	matches := itemProcessProgressRE.FindAllStringSubmatch(line, 2)
-	if len(matches) != 3 {
+	if len(matches) != 1 || len(matches[0]) != 3 {
 		return 0
 	}
 	indexStr, totalStr := matches[0][1], matches[0][2]
@@ -53,5 +57,5 @@ func parseProgressFromItemProgress(line string) int {
 	if total == 0 || err != nil {
 		return 0
 	}
-	return int(math.Round(index / total * 90))
+	return int(math.Round((index / total) * 90.0))
 }

daemon/pkg/commands/upgrade/upgrade.go

@@ -11,7 +11,6 @@ import (
 	"time"
 
 	"github.com/beclab/Olares/daemon/pkg/cli"
-	"github.com/beclab/Olares/daemon/pkg/cluster/state"
 	"github.com/beclab/Olares/daemon/pkg/commands"
 	"github.com/nxadm/tail"
 	"k8s.io/klog/v2"
@@ -155,41 +154,6 @@ func (i *upgrade) refreshProgress() error {
 	return nil
 }
 
-type createTarget struct {
-	commands.Operation
-}
-
-var _ commands.Interface = &createTarget{}
-
-func NewCreateTarget() commands.Interface {
-	return &createTarget{
-		Operation: commands.Operation{
-			Name: commands.CreateUpgradeTarget,
-		},
-	}
-}
-
-func (i *createTarget) Execute(ctx context.Context, p any) (res any, err error) {
-	version, ok := p.(string)
-	if !ok {
-		err = errors.New("invalid param")
-		return
-	}
-
-	if err := createUpgradeTarget(version); err != nil {
-		return nil, fmt.Errorf("failed to create upgrade target: %v", err)
-	}
-
-	state.StateTrigger <- struct{}{}
-
-	return nil, nil
-
-}
-
-func createUpgradeTarget(version string) error {
-	return os.WriteFile(commands.UPGRADE_TARGET_FILE, []byte(version), 0755)
-}
-
 type removeTarget struct {
 	commands.Operation
 }
@@ -204,10 +168,7 @@ func NewRemoveTarget() commands.Interface {
 	}
 }
 
-func (i *removeTarget) Execute(_ context.Context, _ any) (res any, err error) {
-	if err := os.Remove(commands.UPGRADE_TARGET_FILE); err != nil && !os.IsNotExist(err) {
-		return nil, err
-	}
-
-	return newExecutionRes(true, nil), nil
+func (i *removeTarget) Execute(ctx context.Context, p any) (res any, err error) {
+	upgradeRemove := NewRemoveUpgradeTarget()
+	return upgradeRemove.Execute(ctx, p)
 }

daemon/pkg/commands/upgrade/upgrade_cli.go

@@ -1,135 +0,0 @@
-package upgrade
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"io"
-	"net/http"
-	"os"
-	"os/exec"
-	"path/filepath"
-	"runtime"
-	"strings"
-
-	"github.com/Masterminds/semver/v3"
-	"github.com/beclab/Olares/daemon/pkg/commands"
-	"k8s.io/klog/v2"
-)
-
-type upgradeCli struct {
-	commands.Operation
-}
-
-var _ commands.Interface = &upgradeCli{}
-
-func NewUpgradeCli() commands.Interface {
-	return &upgradeCli{
-		Operation: commands.Operation{
-			Name: commands.UpgradeCli,
-		},
-	}
-}
-
-func (i *upgradeCli) Execute(ctx context.Context, p any) (res any, err error) {
-	version, ok := p.(string)
-	if !ok {
-		return nil, errors.New("invalid param")
-	}
-
-	targetVersion, err := semver.NewVersion(version)
-	if err != nil {
-		return nil, fmt.Errorf("invalid target version %s: %v", version, err)
-	}
-
-	currentVersion, err := getCurrentCliVersion()
-	if err != nil {
-		// if we can't get the current version, assume we need to upgrade
-		klog.Warningf("Failed to get current olares-cli version: %v, proceeding with upgrade", err)
-	} else {
-		if !currentVersion.LessThan(targetVersion) {
-			return newExecutionRes(true, nil), nil
-		}
-	}
-
-	arch := "amd64"
-	if runtime.GOARCH == "arm" {
-		arch = "arm64"
-	}
-
-	tmpDir, err := os.MkdirTemp("", "olares-cli-upgrade-*")
-	if err != nil {
-		return nil, fmt.Errorf("failed to create temp directory: %v", err)
-	}
-	defer os.RemoveAll(tmpDir)
-
-	downloadURL := fmt.Sprintf("%s/olares-cli-v%s_linux_%s.tar.gz", commands.CDN_URL, version, arch)
-
-	tarFile := filepath.Join(tmpDir, "olares-cli.tar.gz")
-	if err := downloadFile(downloadURL, tarFile); err != nil {
-		return nil, fmt.Errorf("failed to download olares-cli: %v", err)
-	}
-
-	if err := extractTarGz(tarFile, tmpDir); err != nil {
-		return nil, fmt.Errorf("failed to extract olares-cli: %v", err)
-	}
-
-	binaryPath := filepath.Join(tmpDir, "olares-cli")
-	if err := os.Rename(binaryPath, "/usr/local/bin/olares-cli"); err != nil {
-		return nil, fmt.Errorf("failed to move olares-cli to /usr/local/bin: %v", err)
-	}
-
-	if err := os.Chmod("/usr/local/bin/olares-cli", 0755); err != nil {
-		return nil, fmt.Errorf("failed to make olares-cli executable: %v", err)
-	}
-
-	return newExecutionRes(true, nil), nil
-}
-
-func getCurrentCliVersion() (*semver.Version, error) {
-	cmd := exec.Command("olares-cli", "-v")
-	output, err := cmd.Output()
-	if err != nil {
-		return nil, fmt.Errorf("failed to execute olares-cli -v: %v", err)
-	}
-
-	// parse version from output
-	// expected format: "olares-cli version ${VERSION}"
-	parts := strings.Split(string(output), " ")
-	if len(parts) != 3 {
-		return nil, fmt.Errorf("unexpected version output format: %s", string(output))
-	}
-
-	version, err := semver.NewVersion(parts[2])
-	if err != nil {
-		return nil, fmt.Errorf("invalid version format: %v", err)
-	}
-
-	return version, nil
-}
-
-func downloadFile(url, filepath string) error {
-	resp, err := http.Get(url)
-	if err != nil {
-		return err
-	}
-	defer resp.Body.Close()
-
-	if resp.StatusCode != http.StatusOK {
-		return fmt.Errorf("bad status: %s", resp.Status)
-	}
-
-	out, err := os.Create(filepath)
-	if err != nil {
-		return err
-	}
-	defer out.Close()
-
-	_, err = io.Copy(out, resp.Body)
-	return err
-}
-
-func extractTarGz(tarFile, destDir string) error {
-	cmd := exec.Command("tar", "-xzf", tarFile, "-C", destDir)
-	return cmd.Run()
-}

daemon/pkg/commands/upgrade/utils.go

@@ -0,0 +1,99 @@
+package upgrade
+
+import (
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+	"os/exec"
+	"strings"
+
+	"github.com/Masterminds/semver/v3"
+)
+
+func getCurrentCliVersion() (*semver.Version, error) {
+	cmd := exec.Command("olares-cli", "-v")
+	output, err := cmd.Output()
+	if err != nil {
+		return nil, fmt.Errorf("failed to execute olares-cli -v: %v", err)
+	}
+
+	// parse version from output
+	// expected format: "olares-cli version ${VERSION}"
+	parts := strings.Split(string(output), " ")
+	if len(parts) != 3 {
+		return nil, fmt.Errorf("unexpected version output format: %s", string(output))
+	}
+
+	version, err := semver.NewVersion(strings.TrimSpace(parts[2]))
+	if err != nil {
+		return nil, fmt.Errorf("invalid version format: %v", err)
+	}
+
+	return version, nil
+}
+
+func getCurrentDaemonVersion() (*semver.Version, error) {
+	cmd := exec.Command("olaresd", "--version")
+	output, err := cmd.Output()
+	if err != nil {
+		return nil, fmt.Errorf("failed to execute olaresd --version: %v", err)
+	}
+
+	// parse version from output
+	// expected format: "olaresd version: v${VERSION}"
+	parts := strings.Split(string(output), " ")
+	if len(parts) != 3 {
+		return nil, fmt.Errorf("unexpected version output format: %s", string(output))
+	}
+
+	version, err := semver.NewVersion(strings.TrimPrefix(strings.TrimSpace(parts[2]), "v"))
+	if err != nil {
+		return nil, fmt.Errorf("invalid version format: %v", err)
+	}
+
+	return version, nil
+}
+
+func downloadFile(url, filepath string) error {
+	resp, err := http.Get(url)
+	if err != nil {
+		return err
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		return fmt.Errorf("bad status: %s", resp.Status)
+	}
+
+	out, err := os.Create(filepath)
+	if err != nil {
+		return err
+	}
+	defer out.Close()
+
+	_, err = io.Copy(out, resp.Body)
+	return err
+}
+
+func extractTarGz(tarFile, destDir string) error {
+	cmd := exec.Command("tar", "-xzf", tarFile, "-C", destDir)
+	return cmd.Run()
+}
+
+func copyFile(src, dst string) error {
+	sourceFile, err := os.Open(src)
+	if err != nil {
+		return err
+	}
+	defer sourceFile.Close()
+
+	destFile, err := os.Create(dst)
+	if err != nil {
+		return err
+	}
+	defer destFile.Close()
+
+	_, err = io.Copy(destFile, sourceFile)
+	return err
+}

daemon/pkg/utils/disk.go

@@ -16,3 +16,15 @@ func GetDiskSize() (uint64, error) {
 	size := fs.Blocks * uint64(fs.Bsize)
 	return size, nil
 }
+
+func GetDiskAvailableSpace(path string) (uint64, error) {
+	fs := syscall.Statfs_t{}
+	err := syscall.Statfs(path, &fs)
+	if err != nil {
+		klog.Error("get disk available space error, ", err)
+		return 0, err
+	}
+
+	available := fs.Bavail * uint64(fs.Bsize)
+	return available, nil
+}

daemon/pkg/utils/drivers_linux.go

@@ -89,7 +89,7 @@ func detectdStorageDevices(ctx context.Context, bus string) (usbDevs []storageDe
 
 		token := strings.Split(syspath, "/")
 		devPath := filepath.Join("/dev", token[len(token)-1])
-		klog.Info("device path:", device.Properties())
+		klog.V(8).Info("device path:", device.Properties())
 		vender := device.Properties()["ID_VENDOR"]
 		if vender == "" {
 			vender = device.Properties()["ID_USB_VENDOR"]
@@ -162,7 +162,7 @@ func getMountedPath(devs []storageDevice) ([]string, error) {
 	var paths []string
 	for _, m := range list {
 		if slices.ContainsFunc(devs, func(u storageDevice) bool { return u.DevPath == m.Device }) {
-			klog.Infof("mount: %v, %v, %v", m.Path, m.Device, devs)
+			klog.V(8).Infof("mount: %v, %v, %v", m.Path, m.Device, devs)
 			paths = append(paths, m.Path)
 		}
 	}

daemon/pkg/utils/k8s.go

@@ -278,25 +278,53 @@ func GetAdminUserTerminusName(ctx context.Context, client dynamic.Interface) (st
 
 }
 
+type Filter func(u *unstructured.Unstructured) bool
+
 func GetAdminUser(ctx context.Context, client dynamic.Interface) (*unstructured.Unstructured, error) {
+	u, err := ListUsers(ctx, client, func(u *unstructured.Unstructured) bool {
+		role, ok := u.GetAnnotations()[bflconst.UserAnnotationOwnerRole]
+		if !ok {
+			return false
+		}
+		return role == bflconst.RolePlatformAdmin
+	})
+	if err != nil {
+		klog.Error("list user error, ", err)
+		return nil, err
+	}
+
+	if len(u) == 0 {
+		klog.Info("admin user not found")
+		return nil, nil
+	}
+
+	return u[0], nil
+}
+
+func ListUsers(ctx context.Context, client dynamic.Interface, filters ...Filter) ([]*unstructured.Unstructured, error) {
 	users, err := client.Resource(UserGVR).List(ctx, metav1.ListOptions{})
 	if err != nil {
 		klog.Error("list user error, ", err)
 		return nil, err
 	}
 
+	var userList []*unstructured.Unstructured
 	for _, u := range users.Items {
-		role, ok := u.GetAnnotations()[bflconst.UserAnnotationOwnerRole]
-		if !ok {
+		var skip bool
+		for _, filter := range filters {
+			if !filter(&u) {
+				skip = true
+				break
+			}
+		}
+		if skip {
 			continue
 		}
 
-		if role == bflconst.RolePlatformAdmin {
-			return &u, nil
-		}
+		userList = append(userList, &u)
 	}
 
-	return nil, nil
+	return userList, nil
 }
 
 func isKeyPod(pod *corev1.Pod) bool {

daemon/pkg/utils/network_common.go

@@ -11,7 +11,7 @@ const CHECK_CONNECTIVITY_URL = "http://connectivity-check.ubuntu.com/"
 
 func CheckInterfaceIPv4Connectivity(ctx context.Context, interfaceName string) bool {
 	// try to connect to the CHECK_CONNECTIVITY_URL using the specified interface
-	cmd := exec.CommandContext(ctx, "curl", "--interface", interfaceName, "--connect-timeout", "5", "-s", "-o", "/dev/null", CHECK_CONNECTIVITY_URL)
+	cmd := exec.CommandContext(ctx, "curl", "-4", "--interface", interfaceName, "--connect-timeout", "5", "-s", "-o", "/dev/null", CHECK_CONNECTIVITY_URL)
 	if err := cmd.Run(); err == nil {
 		return true
 	}

daemon/pkg/utils/network_linux.go

@@ -81,7 +81,16 @@ func GetWifiDevice(ctx context.Context) (map[string]Device, error) {
 }
 
 func GetAllDevice(ctx context.Context) (map[string]Device, error) {
-	return deviceStatus(ctx, func(d *Device) bool { return true })
+	return deviceStatus(ctx, func(d *Device) bool {
+		managedByOthers := []string{"cali", "kube", "tun", "tailscale"}
+		for _, devPrefix := range managedByOthers {
+			if strings.HasPrefix(d.Name, devPrefix) {
+				return false
+			}
+		}
+
+		return true
+	})
 }
 
 func ManagedAllDevices(ctx context.Context) (map[string]Device, error) {
@@ -102,7 +111,6 @@ func ManagedAllDevices(ctx context.Context) (map[string]Device, error) {
 			cmd := exec.CommandContext(ctx, nmcli, "device", "set", d.Name, "managed", "yes")
 			cmd.Env = os.Environ()
 			output, err := cmd.CombinedOutput()
-			klog.Info(string(output))
 			if err != nil {
 				klog.Error("exec cmd error, ", err, ", nmcli device set ", d.Name, " managed yes")
 				return false
@@ -252,17 +260,17 @@ func showDeviceByNM(ctx context.Context, deviceName string, device *Device) erro
 		switch key {
 		case "IP4.ADDRESS[1]":
 			ipAndMask := strings.Split(value, "/")
-			if len(ipAndMask) > 2 {
+			if len(ipAndMask) > 1 {
 				device.Ipv4Address = ipAndMask[0]
 				cidr, err := strconv.Atoi(ipAndMask[1])
 				if err != nil {
 					klog.Error("convert cidr error, ", err)
-					return err
+					continue
 				}
 				mask, err := MaskFromCIDR(cidr)
 				if err != nil {
 					klog.Error("get mask from cidr error, ", err)
-					return err
+					continue
 				}
 				device.Ipv4Mask = mask
 			}
@@ -279,7 +287,7 @@ func showDeviceByNM(ctx context.Context, deviceName string, device *Device) erro
 		case "GENERAL.CONNECTION":
 			err := showConnectionByNM(ctx, value, device)
 			if err != nil {
-				klog.Error("get connection method error, ", err)
+				klog.V(8).Info("get connection method error, ", err, ", connection name: ", value)
 			}
 		default:
 			continue

daemon/pkg/utils/pod_status.go

@@ -0,0 +1,96 @@
+package utils
+
+import (
+	"fmt"
+	corev1 "k8s.io/api/core/v1"
+)
+
+// GetPodStatus returns a kubectl-like status string for a pod
+// because the pod.Status.Phase field is unreliable
+func GetPodStatus(pod *corev1.Pod) string {
+	if pod.DeletionTimestamp != nil {
+		if pod.Status.Reason == "NodeLost" {
+			return "Unknown"
+		}
+		return "Terminating"
+	}
+
+	for i, container := range pod.Status.InitContainerStatuses {
+		if container.State.Terminated != nil && container.State.Terminated.ExitCode == 0 {
+			continue
+		}
+
+		if container.State.Terminated != nil {
+			if container.State.Terminated.Reason != "" {
+				return fmt.Sprintf("Init:%s", container.State.Terminated.Reason)
+			}
+			if container.State.Terminated.Signal != 0 {
+				return fmt.Sprintf("Init:Signal:%d", container.State.Terminated.Signal)
+			}
+			return fmt.Sprintf("Init:ExitCode:%d", container.State.Terminated.ExitCode)
+		}
+
+		if container.State.Waiting != nil && container.State.Waiting.Reason != "" {
+			return fmt.Sprintf("Init:%s", container.State.Waiting.Reason)
+		}
+
+		return fmt.Sprintf("Init:%d/%d", i, len(pod.Spec.InitContainers))
+	}
+
+	hasRunning := false
+	for _, container := range pod.Status.ContainerStatuses {
+		if container.State.Waiting != nil && container.State.Waiting.Reason != "" {
+			return container.State.Waiting.Reason
+		}
+
+		if container.State.Terminated != nil && container.State.Terminated.Reason != "" {
+			return container.State.Terminated.Reason
+		}
+
+		if container.State.Terminated != nil && container.State.Terminated.Reason == "" {
+			if container.State.Terminated.Signal != 0 {
+				return fmt.Sprintf("Signal:%d", container.State.Terminated.Signal)
+			}
+			return fmt.Sprintf("ExitCode:%d", container.State.Terminated.ExitCode)
+		}
+
+		if container.State.Running != nil && container.Ready {
+			hasRunning = true
+		}
+	}
+
+	for _, condition := range pod.Status.Conditions {
+		if condition.Type == corev1.PodReady && condition.Status == corev1.ConditionFalse && condition.Reason != "" {
+			return condition.Reason
+		}
+	}
+
+	if pod.Status.Phase == corev1.PodRunning && hasRunning {
+		return "Running"
+	}
+
+	if pod.Status.Phase != "" {
+		return string(pod.Status.Phase)
+	}
+
+	if pod.Status.Reason != "" {
+		return pod.Status.Reason
+	}
+
+	return "Unknown"
+}
+
+// IsPodReady checks if a pod is fully ready (all containers ready)
+func IsPodReady(pod *corev1.Pod) bool {
+	if pod.Status.Phase != corev1.PodRunning {
+		return false
+	}
+
+	for _, condition := range pod.Status.Conditions {
+		if condition.Type == corev1.PodReady {
+			return condition.Status == corev1.ConditionTrue
+		}
+	}
+
+	return false
+}