[#6] 修改打包镜像

- [x] 完成log模块镜像构建、本地端到端写日志——收集——查询流程；
- [x] 完成bind模块构建；
- [x] 内置域名IP自动更新脚本，使用 /private/argus/etc目录下文件进行同步，容器启动时自动写IP，定时任务刷新更新DNS服务器IP和DNS规则；

Co-authored-by: root <root@curious.host.com>
Reviewed-on: #8
Reviewed-by: sundapeng <sundp@mail.zgclab.edu.cn>

build/build_images.sh

@@ -0,0 +1,138 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 帮助信息
+show_help() {
+    cat << EOF
+ARGUS Unified Build System - Image Build Tool
+
+Usage: $0 [OPTIONS]
+
+Options:
+  --intranet    Use intranet mirror for Ubuntu 22.04 packages
+  -h, --help    Show this help message
+
+Examples:
+  $0                # Build with default sources
+  $0 --intranet     # Build with intranet mirror
+
+EOF
+}
+
+# 解析命令行参数
+use_intranet=false
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --intranet)
+            use_intranet=true
+            shift
+            ;;
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1"
+            show_help
+            exit 1
+            ;;
+    esac
+done
+
+# 获取项目根目录
+root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+cd "$root"
+
+echo "======================================="
+echo "ARGUS Unified Build System"
+echo "======================================="
+
+if [[ "$use_intranet" == true ]]; then
+    echo "🌐 Mode: Intranet (Using internal mirror: 10.68.64.1)"
+    build_args="--build-arg USE_INTRANET=true"
+else
+    echo "🌐 Mode: Public (Using default package sources)"
+    build_args=""
+fi
+
+echo "📁 Build context: $root"
+echo ""
+
+# 构建镜像的函数
+build_image() {
+    local image_name=$1
+    local dockerfile_path=$2
+    local tag=$3
+
+    echo "🔄 Building $image_name image..."
+    echo "   Dockerfile: $dockerfile_path"
+    echo "   Tag: $tag"
+
+    if docker build $build_args -f "$dockerfile_path" -t "$tag" .; then
+        echo "✅ $image_name image built successfully"
+        return 0
+    else
+        echo "❌ Failed to build $image_name image"
+        return 1
+    fi
+}
+
+# 构建所有镜像
+images_built=()
+build_failed=false
+
+# 构建 Elasticsearch 镜像
+if build_image "Elasticsearch" "src/log/elasticsearch/build/Dockerfile" "argus-elasticsearch:latest"; then
+    images_built+=("argus-elasticsearch:latest")
+else
+    build_failed=true
+fi
+
+echo ""
+
+# 构建 Kibana 镜像
+if build_image "Kibana" "src/log/kibana/build/Dockerfile" "argus-kibana:latest"; then
+    images_built+=("argus-kibana:latest")
+else
+    build_failed=true
+fi
+
+echo ""
+
+# 构建 BIND9 镜像
+if build_image "BIND9" "src/bind/build/Dockerfile" "argus-bind9:latest"; then
+    images_built+=("argus-bind9:latest")
+else
+    build_failed=true
+fi
+
+echo ""
+echo "======================================="
+echo "📦 Build Summary"
+echo "======================================="
+
+if [[ ${#images_built[@]} -gt 0 ]]; then
+    echo "✅ Successfully built images:"
+    for image in "${images_built[@]}"; do
+        echo "   • $image"
+    done
+fi
+
+if [[ "$build_failed" == true ]]; then
+    echo ""
+    echo "❌ Some images failed to build. Please check the errors above."
+    exit 1
+fi
+
+if [[ "$use_intranet" == true ]]; then
+    echo ""
+    echo "🌐 Built with intranet mirror configuration"
+fi
+
+echo ""
+echo "🚀 Next steps:"
+echo "   cd src/log && ./scripts/save_images.sh     # Export log images"
+echo "   cd src/bind && ./scripts/save_images.sh    # Export bind images"
+echo "   cd src/log/tests && ./scripts/02_up.sh     # Start log services"
+echo ""

build/save_images.sh

@@ -0,0 +1,222 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 帮助信息
+show_help() {
+    cat << EOF
+ARGUS Unified Build System - Image Export Tool
+
+Usage: $0 [OPTIONS]
+
+Options:
+  --compress    Compress exported images with gzip
+  -h, --help    Show this help message
+
+Examples:
+  $0                # Export all images without compression
+  $0 --compress     # Export all images with gzip compression
+
+EOF
+}
+
+# 解析命令行参数
+use_compression=false
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --compress)
+            use_compression=true
+            shift
+            ;;
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        *)
+            echo "Unknown option: $1"
+            show_help
+            exit 1
+            ;;
+    esac
+done
+
+# 获取项目根目录
+root="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
+cd "$root"
+
+# 创建镜像输出目录
+images_dir="$root/images"
+mkdir -p "$images_dir"
+
+echo "======================================="
+echo "ARGUS Unified Build System - Image Export"
+echo "======================================="
+echo ""
+
+if [[ "$use_compression" == true ]]; then
+    echo "🗜️  Mode: With gzip compression"
+else
+    echo "📦 Mode: No compression"
+fi
+
+echo "📁 Output directory: $images_dir"
+echo ""
+
+# 定义镜像列表
+declare -A images=(
+    ["argus-elasticsearch:latest"]="argus-elasticsearch-latest.tar"
+    ["argus-kibana:latest"]="argus-kibana-latest.tar"
+    ["argus-bind9:latest"]="argus-bind9-latest.tar"
+)
+
+# 函数：检查镜像是否存在
+check_image() {
+    local image_name="$1"
+    if docker images --format "{{.Repository}}:{{.Tag}}" | grep -q "^$image_name$"; then
+        echo "✅ Image found: $image_name"
+        return 0
+    else
+        echo "❌ Image not found: $image_name"
+        return 1
+    fi
+}
+
+# 函数：显示镜像信息
+show_image_info() {
+    local image_name="$1"
+    echo "📋 Image info for $image_name:"
+    docker images "$image_name" --format "   Size: {{.Size}}, Created: {{.CreatedSince}}, ID: {{.ID}}"
+}
+
+# 函数：保存镜像
+save_image() {
+    local image_name="$1"
+    local output_file="$2"
+    local output_path="$images_dir/$output_file"
+
+    echo "🔄 Saving $image_name to $output_file..."
+
+    # 删除旧的镜像文件（如果存在）
+    if [[ -f "$output_path" ]]; then
+        echo "   Removing existing file: $output_file"
+        rm "$output_path"
+    fi
+
+    if [[ "$use_compression" == true && -f "$output_path.gz" ]]; then
+        echo "   Removing existing compressed file: $output_file.gz"
+        rm "$output_path.gz"
+    fi
+
+    # 保存镜像
+    docker save "$image_name" -o "$output_path"
+
+    if [[ "$use_compression" == true ]]; then
+        echo "   Compressing with gzip..."
+        gzip "$output_path"
+        output_path="$output_path.gz"
+        output_file="$output_file.gz"
+    fi
+
+    # 检查文件大小
+    local file_size=$(du -h "$output_path" | cut -f1)
+    echo "✅ Saved successfully: $output_file ($file_size)"
+}
+
+echo "🔍 Checking for ARGUS images..."
+echo ""
+
+# 检查所有镜像
+available_images=()
+missing_images=()
+
+for image_name in "${!images[@]}"; do
+    if check_image "$image_name"; then
+        show_image_info "$image_name"
+        available_images+=("$image_name")
+    else
+        missing_images+=("$image_name")
+    fi
+    echo ""
+done
+
+# 如果没有镜像存在，提示构建
+if [[ ${#available_images[@]} -eq 0 ]]; then
+    echo "❌ No ARGUS images found to export."
+    echo ""
+    echo "🔧 Please build the images first with:"
+    echo "   ./build/build_images.sh"
+    exit 1
+fi
+
+# 显示缺失的镜像
+if [[ ${#missing_images[@]} -gt 0 ]]; then
+    echo "⚠️  Missing images (will be skipped):"
+    for image_name in "${missing_images[@]}"; do
+        echo "   • $image_name"
+    done
+    echo ""
+fi
+
+echo "💾 Starting image export process..."
+echo ""
+
+# 保存所有可用的镜像
+exported_files=()
+for image_name in "${available_images[@]}"; do
+    output_file="${images[$image_name]}"
+    save_image "$image_name" "$output_file"
+
+    if [[ "$use_compression" == true ]]; then
+        exported_files+=("$output_file.gz")
+    else
+        exported_files+=("$output_file")
+    fi
+    echo ""
+done
+
+echo "======================================="
+echo "📦 Export Summary"
+echo "======================================="
+
+# 显示导出的文件
+echo "📁 Exported files in $images_dir:"
+total_size=0
+for file in "${exported_files[@]}"; do
+    full_path="$images_dir/$file"
+    if [[ -f "$full_path" ]]; then
+        size=$(du -h "$full_path" | cut -f1)
+        size_bytes=$(du -b "$full_path" | cut -f1)
+        total_size=$((total_size + size_bytes))
+        echo "   ✅ $file ($size)"
+    fi
+done
+
+# 显示总大小
+if [[ $total_size -gt 0 ]]; then
+    total_size_human=$(numfmt --to=iec --suffix=B $total_size)
+    echo ""
+    echo "📊 Total size: $total_size_human"
+fi
+
+echo ""
+echo "🚀 Usage instructions:"
+echo "   To load these images on another system:"
+
+if [[ "$use_compression" == true ]]; then
+    for file in "${exported_files[@]}"; do
+        if [[ -f "$images_dir/$file" ]]; then
+            base_name="${file%.gz}"
+            echo "     gunzip $file && docker load -i $base_name"
+        fi
+    done
+else
+    for file in "${exported_files[@]}"; do
+        if [[ -f "$images_dir/$file" ]]; then
+            echo "     docker load -i $file"
+        fi
+    done
+fi
+
+echo ""
+echo "✅ Image export completed successfully!"
+echo ""

src/alert/README.md

@@ -0,0 +1,13 @@
+# Alertmanager
+
+## 启动示例
+
+```bash
+docker run -d --name alertmanager \
+  -p 9093:9093 \
+  -v /opt/alertmanager/data:/alertmanager \
+  argus-alert:latest
+```
+
+## 动态配置
+修改alertmanager.yml后，调用`/-/reload`接口可以重新加载配置

src/alert/alertmanager/build/Dockerfile

@@ -0,0 +1,86 @@
+# 基于 Ubuntu 24.04
+FROM ubuntu:24.04
+
+# 切换到 root 用户
+USER root
+
+# 安装必要依赖
+RUN apt-get update && \
+    apt-get install -y wget supervisor net-tools inetutils-ping vim ca-certificates passwd && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# 设置 Alertmanager 版本
+ARG ALERTMANAGER_VERSION=0.28.1
+
+# 下载并解压 Alertmanager 二进制
+RUN wget https://github.com/prometheus/alertmanager/releases/download/v${ALERTMANAGER_VERSION}/alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
+    tar xvf alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz && \
+    mv alertmanager-${ALERTMANAGER_VERSION}.linux-amd64 /usr/local/alertmanager && \
+    rm alertmanager-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz
+
+ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
+ENV ARGUS_UID=2133
+ENV ARGUS_GID=2015
+
+RUN mkdir -p /usr/share/alertmanager && \
+    mkdir -p ${ALERTMANAGER_BASE_PATH} && \
+    mkdir -p /private/argus/etc && \
+    rm -rf /alertmanager && \
+    ln -s ${ALERTMANAGER_BASE_PATH} /alertmanager
+
+# 创建 alertmanager 用户（可自定义 UID/GID）
+# 创建 alertmanager 用户组
+RUN groupadd -g ${ARGUS_GID} alertmanager
+
+# 创建 alertmanager 用户并指定组
+RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} alertmanager
+
+RUN chown -R alertmanager:alertmanager /usr/share/alertmanager && \
+    chown -R alertmanager:alertmanager /alertmanager && \
+    chown -R alertmanager:alertmanager ${ALERTMANAGER_BASE_PATH} && \
+    chown -R alertmanager:alertmanager /private/argus/etc && \
+    chown -R alertmanager:alertmanager /usr/local/bin
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+
+# 配置部署时使用的 apt 源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+    echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# 创建 supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+# 复制 supervisor 配置文件
+COPY src/alert/alertmanager/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 复制启动脚本
+COPY src/alert/alertmanager/build/start-am-supervised.sh /usr/local/bin/start-am-supervised.sh
+RUN chmod +x /usr/local/bin/start-am-supervised.sh
+
+# 复制 Alertmanager 配置文件
+COPY src/alert/alertmanager/build/alertmanager.yml /etc/alertmanager/alertmanager.yml
+RUN chmod +x /etc/alertmanager/alertmanager.yml
+# COPY src/alert/alertmanager/build/alertmanager.yml ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
+
+# 复制 DNS 监控脚本
+COPY src/alert/alertmanager/build/dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+# 保持 root 用户，由 supervisor 控制 user 切换
+USER root
+
+# 暴露端口（Alertmanager 默认端口 9093）
+EXPOSE 9093
+
+# 使用 supervisor 作为入口点
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]
+

src/alert/alertmanager/build/alertmanager.yml

@@ -0,0 +1,19 @@
+global:
+  resolve_timeout: 5m
+
+route:
+  group_by: ['alertname', 'instance']   # 分组：相同 alertname + instance 的告警合并
+  group_wait: 30s        # 第一个告警后，等 30s 看是否有同组告警一起发
+  group_interval: 5m     # 同组告警变化后，至少 5 分钟再发一次
+  repeat_interval: 3h    # 相同告警，3 小时重复提醒一次
+  receiver: 'null'
+
+receivers:
+  - name: 'null'
+
+inhibit_rules:
+  - source_match:
+      severity: 'critical'     # critical 告警存在时
+    target_match:
+      severity: 'warning'      # 抑制相同 instance 的 warning 告警
+    equal: ['instance']

src/alert/alertmanager/build/dns-monitor.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# DNS监控脚本 - 每10秒检查dns.conf是否有变化
+# 如果有变化则执行update-dns.sh脚本
+
+DNS_CONF="/private/argus/etc/dns.conf"
+DNS_BACKUP="/tmp/dns.conf.backup"
+UPDATE_SCRIPT="/private/argus/etc/update-dns.sh"
+LOG_FILE="/var/log/supervisor/dns-monitor.log"
+
+# 确保日志文件存在
+touch "$LOG_FILE"
+
+log_message() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Monitor] $1" >> "$LOG_FILE"
+}
+
+log_message "DNS监控脚本启动"
+
+while true; do
+    if [ -f "$DNS_CONF" ]; then
+        if [ -f "$DNS_BACKUP" ]; then
+            # 比较文件内容
+            if ! cmp -s "$DNS_CONF" "$DNS_BACKUP"; then
+                log_message "检测到DNS配置变化"
+
+                # 更新备份文件
+                cp "$DNS_CONF" "$DNS_BACKUP"
+
+                # 执行更新脚本
+                if [ -x "$UPDATE_SCRIPT" ]; then
+                    log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                    "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                    if [ $? -eq 0 ]; then
+                        log_message "DNS更新脚本执行成功"
+                    else
+                        log_message "DNS更新脚本执行失败"
+                    fi
+                else
+                    log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+                fi
+            fi
+        else
+
+            # 第一次检测到配置文件，执行更新脚本
+            if [ -x "$UPDATE_SCRIPT" ]; then
+                log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                if [ $? -eq 0 ]; then
+                    log_message "DNS更新脚本执行成功"
+
+		    # 第一次运行，创建备份并执行更新
+		    cp "$DNS_CONF" "$DNS_BACKUP"
+		    log_message "创建DNS配置备份文件"
+
+                else
+                    log_message "DNS更新脚本执行失败"
+                fi
+            else
+                log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+            fi
+        fi
+    else
+        log_message "警告: DNS配置文件不存在: $DNS_CONF"
+    fi
+
+    sleep 10
+done

src/alert/alertmanager/build/start-am-supervised.sh

@@ -0,0 +1,26 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting Alertmanager under supervisor..."
+
+ALERTMANAGER_BASE_PATH=${ALERTMANAGER_BASE_PATH:-/private/argus/alert/alertmanager}
+
+echo "[INFO] Alertmanager base path: ${ALERTMANAGER_BASE_PATH}"
+
+# 生成配置文件
+echo "[INFO] Generating Alertmanager configuration file..."
+sed "s|\${ALERTMANAGER_BASE_PATH}|${ALERTMANAGER_BASE_PATH}|g" \
+    /etc/alertmanager/alertmanager.yml > ${ALERTMANAGER_BASE_PATH}/alertmanager.yml
+
+
+# 记录容器 IP 地址
+DOMAIN=alertmanager.alert.argus.com
+IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}')
+echo "current IP: ${IP}"
+echo "${IP}" > /private/argus/etc/${DOMAIN}
+
+
+echo "[INFO] Starting Alertmanager process..."
+
+# 启动 Alertmanager 主进程
+exec /usr/local/alertmanager/alertmanager --config.file=/etc/alertmanager/alertmanager.yml --storage.path=/alertmanager --cluster.listen-address=""

src/alert/alertmanager/build/supervisord.conf

@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:alertmanager]
+command=/usr/local/bin/start-am-supervised.sh
+user=alertmanager
+stdout_logfile=/var/log/supervisor/alertmanager.log
+stderr_logfile=/var/log/supervisor/alertmanager_error.log
+autorestart=true
+startretries=3
+startsecs=10
+stopwaitsecs=20
+killasgroup=true
+stopasgroup=true
+
+[program:dns-monitor]
+command=/usr/local/bin/dns-monitor.sh
+user=root
+stdout_logfile=/var/log/supervisor/dns-monitor.log
+stderr_logfile=/var/log/supervisor/dns-monitor_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

src/alert/alertmanager/config/rule_files/README.md

@@ -0,0 +1,60 @@
+# 告警配置
+
+> 参考：[自定义Prometheus告警规则](https://yunlzheng.gitbook.io/prometheus-book/parti-prometheus-ji-chu/alert/prometheus-alert-rule)
+
+在Prometheus中配置告警的有两个步骤：
+
+1. 写告警规则文件（rules文件）
+2. 在promethues.yml里加载规则，并配置Alertmanager
+
+## 1. 编写告警规则文件
+告警规则如下：
+```yml
+groups:
+  - name: example-rules
+    interval: 30s  # 每30秒评估一次
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "实例 {{ $labels.instance }} 已宕机"
+          description: "{{ $labels.instance }} 在 {{ $labels.job }} 中无响应超过 1 分钟。"
+
+      - alert: HighCpuUsage
+        expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "CPU 使用率过高"
+          description: "实例 {{ $labels.instance }} CPU 使用率超过 80% 持续 5 分钟。"
+```
+
+其中：
+
+- `alert`：告警规则的名称。
+- `expr`：基于PromQL表达式告警触发条件，用于计算是否有时间序列满足该条件。
+- `for`：评估等待时间，可选参数。用于表示只有当触发条件持续一段时间后才发送告警。在等待期间新产生告警的状态为pending。
+- `labels`：自定义标签，允许用户指定要附加到告警上的一组附加标签，可以在Alertmanager中做路由和分组。
+- `annotations`：用于指定一组附加信息，比如用于描述告警详细信息的文字等，annotations的内容在告警产生时会一同作为参数发送到Alertmanager。可以提供告警摘要和详细信息。
+
+## 2. promothues.yml里引用
+在prometheus.yml中加上`rule_files`和`alerting`:
+
+```yml
+global:
+  [ evaluation_interval: <duration> | default = 1m ]
+
+rule_files:
+  [ - <filepath_glob> ... ]
+
+alerting:
+  alertmanagers:
+    - static_configs:
+        - targets:
+            - "localhost:9093"   # Alertmanager 地址
+
+```

src/alert/alertmanager/config/rule_files/example_rules.yml

@@ -0,0 +1,37 @@
+groups:
+  - name: example-rules
+    interval: 30s  # 每30秒评估一次
+    rules:
+      - alert: InstanceDown
+        expr: up == 0
+        for: 1m
+        labels:
+          severity: critical
+        annotations:
+          summary: "实例 {{ $labels.instance }} 已宕机"
+          description: "{{ $labels.instance }} 在 {{ $labels.job }} 中无响应超过 1 分钟。"
+
+      - alert: HighCpuUsage
+        expr: 100 - (avg by (instance) (irate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "CPU 使用率过高"
+          description: "实例 {{ $labels.instance }} CPU 使用率超过 80% 持续 5 分钟。"
+      - alert: HighMemoryUsage
+        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 80
+        for: 5m
+        labels:
+          severity: warning
+        annotations:
+          summary: "内存使用率过高"
+          description: "实例 {{ $labels.instance }} 内存使用率超过 80% 持续 5 分钟。"
+      - alert: DiskSpaceLow
+        expr: (node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} - node_filesystem_free_bytes{fstype!~"tmpfs|overlay"}) / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"} * 100 > 90
+        for: 10m
+        labels:
+          severity: warning
+        annotations:
+          summary: "磁盘空间不足"
+          description: "实例 {{ $labels.instance }} 磁盘空间不足超过 90% 持续 10 分钟。"

src/bind/.gitignore

@@ -0,0 +1,2 @@
+
+images/

src/bind/build/Dockerfile

@@ -0,0 +1,66 @@
+FROM ubuntu:22.04
+
+# Set timezone and avoid interactive prompts
+ENV DEBIAN_FRONTEND=noninteractive
+ENV TZ=Asia/Shanghai
+
+# 设置构建参数
+ARG USE_INTRANET=false
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# Update package list and install required packages
+RUN apt-get update && \
+    apt-get install -y \
+    bind9 \
+    bind9utils \
+    bind9-doc \
+    supervisor \
+    net-tools \
+    inetutils-ping \
+    vim \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# 配置部署时使用的apt源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+	echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# Create supervisor configuration directory
+RUN mkdir -p /etc/supervisor/conf.d
+
+# Copy supervisor configuration
+COPY src/bind/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# Copy BIND9 configuration files
+COPY src/bind/build/named.conf.local /etc/bind/named.conf.local
+COPY src/bind/build/db.argus.com /etc/bind/db.argus.com
+
+# Copy startup and reload scripts
+COPY src/bind/build/startup.sh /usr/local/bin/startup.sh
+COPY src/bind/build/reload-bind9.sh /usr/local/bin/reload-bind9.sh
+COPY src/bind/build/argus_dns_sync.sh /usr/local/bin/argus_dns_sync.sh
+COPY src/bind/build/update-dns.sh /usr/local/bin/update-dns.sh
+
+# Make scripts executable
+RUN chmod +x /usr/local/bin/startup.sh /usr/local/bin/reload-bind9.sh  /usr/local/bin/argus_dns_sync.sh /usr/local/bin/update-dns.sh
+
+# Set proper ownership for BIND9 files
+RUN chown bind:bind /etc/bind/named.conf.local /etc/bind/db.argus.com
+
+# Expose DNS port
+EXPOSE 53/tcp 53/udp
+
+# Use root user as requested
+USER root
+
+# Start with startup script
+CMD ["/usr/local/bin/startup.sh"]

src/bind/build/argus_dns_sync.sh

@@ -0,0 +1,100 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+WATCH_DIR="/private/argus/etc"
+ZONE_DB="/private/argus/bind/db.argus.com"
+LOCKFILE="/var/lock/argus_dns_sync.lock"
+BACKUP_DIR="/private/argus/bind/.backup"
+SLEEP_SECONDS=10
+RELOAD_SCRIPT="/usr/local/bin/reload-bind9.sh"   # 这里放你已有脚本的路径
+
+mkdir -p "$(dirname "$LOCKFILE")" "$BACKUP_DIR"
+
+is_ipv4() {
+  local ip="$1"
+  [[ "$ip" =~ ^([0-9]{1,3}\.){3}[0-9]{1,3}$ ]] || return 1
+  IFS='.' read -r a b c d <<<"$ip"
+  for n in "$a" "$b" "$c" "$d"; do
+    (( n >= 0 && n <= 255 )) || return 1
+  done
+  return 0
+}
+
+get_current_ip() {
+  local name="$1"
+  sed -n -E "s/^${name}[[:space:]]+IN[[:space:]]+A[[:space:]]+([0-9.]+)[[:space:]]*$/\1/p" "$ZONE_DB" | head -n1
+}
+
+upsert_record() {
+  local name="$1"
+  local new_ip="$2"
+  local ts
+  ts="$(date +%Y%m%d-%H%M%S)"
+  local changed=0
+
+  cp -a "$ZONE_DB" "$BACKUP_DIR/db.argus.com.$ts.bak"
+
+  local cur_ip
+  cur_ip="$(get_current_ip "$name" || true)"
+
+  if [[ -z "$cur_ip" ]]; then
+    # Ensure the file ends with a newline before adding new record
+    if [[ -s "$ZONE_DB" ]] && [[ $(tail -c1 "$ZONE_DB" | wc -l) -eq 0 ]]; then
+      echo "" >> "$ZONE_DB"
+    fi
+    printf "%-20s IN A %s\n" "$name" "$new_ip" >> "$ZONE_DB"
+    echo "[ADD] ${name} -> ${new_ip}"
+    changed=1
+  elif [[ "$cur_ip" != "$new_ip" ]]; then
+    awk -v n="$name" -v ip="$new_ip" '
+      {
+        if ($1==n && $2=="IN" && $3=="A") {
+          printf "%-20s IN A %s\n", n, ip
+        } else {
+          print
+        }
+      }
+    ' "$ZONE_DB" > "${ZONE_DB}.tmp" && mv "${ZONE_DB}.tmp" "$ZONE_DB"
+    echo "[UPDATE] ${name}: ${cur_ip} -> ${new_ip}"
+    changed=1
+  else
+    echo "[SKIP] ${name} unchanged (${new_ip})"
+  fi
+
+  return $changed
+}
+
+while true; do
+  exec 9>"$LOCKFILE"
+  if flock -n 9; then
+    shopt -s nullglob
+    NEED_RELOAD=0
+
+    for f in "$WATCH_DIR"/*.argus.com; do
+      base="$(basename "$f")"
+      name="${base%.argus.com}"
+      ip="$(grep -Eo '([0-9]{1,3}\.){3}[0-9]{1,3}' "$f" | tail -n1 || true)"
+
+      if [[ -z "$ip" ]] || ! is_ipv4 "$ip"; then
+        echo "[WARN] $f 未找到有效 IPv4，跳过"
+        continue
+      fi
+
+      if upsert_record "$name" "$ip"; then
+        NEED_RELOAD=1
+      fi
+    done
+
+    if [[ $NEED_RELOAD -eq 1 ]]; then
+      echo "[INFO] 检测到 db.argus.com 变更，执行 reload-bind9.sh"
+      bash "$RELOAD_SCRIPT"
+    fi
+
+    flock -u 9
+  else
+    echo "[INFO] 已有同步任务在运行，跳过本轮"
+  fi
+
+  sleep "$SLEEP_SECONDS"
+done
+

src/bind/build/db.argus.com

@@ -0,0 +1,16 @@
+$TTL    604800
+@       IN      SOA     ns1.argus.com. admin.argus.com. (
+                              2         ; Serial
+                         604800         ; Refresh
+                          86400         ; Retry
+                        2419200         ; Expire
+                         604800 )       ; Negative Cache TTL
+
+; 定义 DNS 服务器
+@       IN      NS      ns1.argus.com.
+
+; 定义 ns1 主机
+ns1     IN      A       127.0.0.1
+
+; 定义 web 指向 12.4.5.6
+web     IN      A       12.4.5.6

src/bind/build/dns-monitor.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# DNS监控脚本 - 每10秒检查dns.conf是否有变化
+# 如果有变化则执行update-dns.sh脚本
+
+DNS_CONF="/private/argus/etc/dns.conf"
+DNS_BACKUP="/tmp/dns.conf.backup"
+UPDATE_SCRIPT="/private/argus/etc/update-dns.sh"
+LOG_FILE="/var/log/supervisor/dns-monitor.log"
+
+# 确保日志文件存在
+touch "$LOG_FILE"
+
+log_message() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Monitor] $1" >> "$LOG_FILE"
+}
+
+log_message "DNS监控脚本启动"
+
+while true; do
+    if [ -f "$DNS_CONF" ]; then
+        if [ -f "$DNS_BACKUP" ]; then
+            # 比较文件内容
+            if ! cmp -s "$DNS_CONF" "$DNS_BACKUP"; then
+                log_message "检测到DNS配置变化"
+
+                # 更新备份文件
+                cp "$DNS_CONF" "$DNS_BACKUP"
+
+                # 执行更新脚本
+                if [ -x "$UPDATE_SCRIPT" ]; then
+                    log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                    "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                    if [ $? -eq 0 ]; then
+                        log_message "DNS更新脚本执行成功"
+                    else
+                        log_message "DNS更新脚本执行失败"
+                    fi
+                else
+                    log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+                fi
+            fi
+        else
+
+            # 第一次检测到配置文件，执行更新脚本
+            if [ -x "$UPDATE_SCRIPT" ]; then
+                log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                if [ $? -eq 0 ]; then
+                    log_message "DNS更新脚本执行成功"
+
+		    # 第一次运行，创建备份并执行更新
+		    cp "$DNS_CONF" "$DNS_BACKUP"
+		    log_message "创建DNS配置备份文件"
+
+                else
+                    log_message "DNS更新脚本执行失败"
+                fi
+            else
+                log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+            fi
+        fi
+    else
+        log_message "警告: DNS配置文件不存在: $DNS_CONF"
+    fi
+
+    sleep 10
+done

src/bind/build/named.conf.local

@@ -0,0 +1,4 @@
+zone "argus.com" {
+    type master;
+    file "/etc/bind/db.argus.com";
+};

src/bind/build/reload-bind9.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+
+echo "Reloading BIND9 configuration..."
+
+# Check if configuration files are valid
+echo "Checking named.conf.local syntax..."
+if ! named-checkconf /etc/bind/named.conf.local; then
+    echo "ERROR: named.conf.local has syntax errors!"
+    exit 1
+fi
+
+echo "Checking zone file syntax..."
+if ! named-checkzone argus.com /etc/bind/db.argus.com; then
+    echo "ERROR: db.argus.com has syntax errors!"
+    exit 1
+fi
+
+# Reload BIND9 via supervisor
+echo "Reloading BIND9 service..."
+supervisorctl restart bind9
+
+if [ $? -eq 0 ]; then
+    echo "BIND9 reloaded successfully!"
+else
+    echo "ERROR: Failed to reload BIND9!"
+    exit 1
+fi

src/bind/build/startup.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+
+# Set /private permissions to 777 as requested
+chmod 777 /private 2>/dev/null || true
+
+# Create persistent directories for BIND9 configs and DNS sync
+mkdir -p /private/argus/bind
+mkdir -p /private/argus/etc
+
+# Copy configuration files to persistent storage if they don't exist
+if [ ! -f /private/argus/bind/named.conf.local ]; then
+    cp /etc/bind/named.conf.local /private/argus/bind/named.conf.local
+fi
+
+if [ ! -f /private/argus/bind/db.argus.com ]; then
+    cp /etc/bind/db.argus.com /private/argus/bind/db.argus.com
+fi
+
+# Copy update-dns.sh to /private/argus/etc/
+cp /usr/local/bin/update-dns.sh /private/argus/etc/update-dns.sh
+chown bind:bind /private/argus/etc/update-dns.sh
+chmod a+x /private/argus/etc/update-dns.sh
+
+# Create symlinks to use persistent configs
+ln -sf /private/argus/bind/named.conf.local /etc/bind/named.conf.local
+ln -sf /private/argus/bind/db.argus.com /etc/bind/db.argus.com
+
+# Set proper ownership
+chown bind:bind /private/argus/bind/named.conf.local /private/argus/bind/db.argus.com
+
+# 记录容器ip地址更新到dns.conf
+IP=`ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}'`
+echo current IP: ${IP}
+echo ${IP} > /private/argus/etc/dns.conf
+
+# Create supervisor log directory
+mkdir -p /var/log/supervisor
+
+# Start supervisor
+exec /usr/bin/supervisord -c /etc/supervisor/conf.d/supervisord.conf

src/bind/build/supervisord.conf

@@ -0,0 +1,37 @@
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisord]
+nodaemon=true
+user=root
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[program:bind9]
+command=/usr/sbin/named -g -c /etc/bind/named.conf -u bind
+user=bind
+autostart=true
+autorestart=true
+stderr_logfile=/var/log/supervisor/bind9.err.log
+stdout_logfile=/var/log/supervisor/bind9.out.log
+priority=10
+
+[program:argus-dns-sync]
+command=/usr/local/bin/argus_dns_sync.sh
+autostart=true
+autorestart=true
+startsecs=3
+stopsignal=TERM
+user=root
+stdout_logfile=/var/log/argus_dns_sync.out.log
+stderr_logfile=/var/log/argus_dns_sync.err.log
+; 根据环境调整环境变量（可选）
+; environment=RNDC_RELOAD="yes"
+

src/bind/build/update-dns.sh

@@ -0,0 +1,31 @@
+#!/bin/sh
+# update-dns.sh
+# 从 /private/argus/etc/dns.conf 读取 IP，写入 /etc/resolv.conf
+
+DNS_CONF="/private/argus/etc/dns.conf"
+RESOLV_CONF="/etc/resolv.conf"
+
+# 检查配置文件是否存在
+if [ ! -f "$DNS_CONF" ]; then
+  echo "配置文件不存在: $DNS_CONF" >&2
+  exit 1
+fi
+
+# 生成 resolv.conf 内容
+{
+  while IFS= read -r ip; do
+    # 跳过空行和注释
+    case "$ip" in
+      \#*) continue ;;
+      "") continue ;;
+    esac
+    echo "nameserver $ip"
+  done < "$DNS_CONF"
+} > "$RESOLV_CONF".tmp
+
+# 替换写入 /etc/resolv.conf
+cat "$RESOLV_CONF".tmp > "$RESOLV_CONF"
+rm -f "$RESOLV_CONF".tmp
+
+echo "已更新 $RESOLV_CONF"
+

src/bind/tests/docker-compose.yml

@@ -0,0 +1,16 @@
+services:
+  bind9:
+    image: argus-bind9:latest
+    container_name: argus-bind9-test
+    ports:
+      - "53:53/tcp"
+      - "53:53/udp"
+    volumes:
+      - ./private:/private
+    restart: unless-stopped
+    networks:
+      - bind-test-network
+
+networks:
+  bind-test-network:
+    driver: bridge

src/bind/tests/scripts/00_e2e_test.sh

@@ -0,0 +1,115 @@
+#!/bin/bash
+
+# End-to-end test for BIND9 DNS server
+# This script runs all tests in sequence to validate the complete functionality
+# Usage: ./00_e2e_test.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+echo "=========================================="
+echo "BIND9 DNS Server End-to-End Test Suite"
+echo "=========================================="
+
+# Track test results
+total_tests=0
+passed_tests=0
+failed_tests=0
+
+# Function to run a test step
+run_test_step() {
+    local step_name="$1"
+    local script_name="$2"
+    local description="$3"
+
+    echo ""
+    echo "[$step_name] $description"
+    echo "$(printf '=%.0s' {1..50})"
+
+    ((total_tests++))
+
+    if [ ! -f "$SCRIPT_DIR/$script_name" ]; then
+        echo "✗ Test script not found: $script_name"
+        ((failed_tests++))
+        return 1
+    fi
+
+    # Make sure script is executable
+    chmod +x "$SCRIPT_DIR/$script_name"
+
+    # Run the test
+    echo "Executing: $SCRIPT_DIR/$script_name"
+    if "$SCRIPT_DIR/$script_name"; then
+        echo "✓ $step_name completed successfully"
+        ((passed_tests++))
+        return 0
+    else
+        echo "✗ $step_name failed"
+        ((failed_tests++))
+        return 1
+    fi
+}
+
+# Cleanup any previous test environment (but preserve the Docker image)
+echo ""
+echo "[SETUP] Cleaning up any previous test environment..."
+if [ -f "$SCRIPT_DIR/05_cleanup.sh" ]; then
+    chmod +x "$SCRIPT_DIR/05_cleanup.sh"
+    "$SCRIPT_DIR/05_cleanup.sh" || true
+fi
+
+echo ""
+echo "Starting BIND9 DNS server end-to-end test sequence..."
+
+# Test sequence
+run_test_step "TEST-01" "01_start_container.sh" "Start BIND9 container" || true
+
+run_test_step "TEST-02" "02_dig_test.sh" "Initial DNS resolution test" || true
+
+run_test_step "TEST-03" "03_reload_test.sh" "Configuration reload with IP modification" || true
+
+run_test_step "TEST-03.5" "03.5_dns_sync_test.sh" "DNS auto-sync functionality test" || true
+
+run_test_step "TEST-04" "04_persistence_test.sh" "Configuration persistence after restart" || true
+
+# Final cleanup (but preserve logs for review)
+echo ""
+echo "[CLEANUP] Cleaning up test environment..."
+run_test_step "CLEANUP" "05_cleanup.sh" "Clean up containers and networks" || true
+
+# Test summary
+echo ""
+echo "=========================================="
+echo "TEST SUMMARY"
+echo "=========================================="
+echo "Total tests: $total_tests"
+echo "Passed: $passed_tests"
+echo "Failed: $failed_tests"
+
+if [ $failed_tests -eq 0 ]; then
+    echo ""
+    echo "✅ ALL TESTS PASSED!"
+    echo ""
+    echo "BIND9 DNS server functionality validated:"
+    echo "  ✓ Container startup and basic functionality"
+    echo "  ✓ DNS resolution for configured domains"
+    echo "  ✓ Configuration modification and reload"
+    echo "  ✓ DNS auto-sync from IP files"
+    echo "  ✓ Configuration persistence across restarts"
+    echo "  ✓ Cleanup and resource management"
+    echo ""
+    echo "The BIND9 DNS server is ready for production use."
+    exit 0
+else
+    echo ""
+    echo "❌ SOME TESTS FAILED!"
+    echo ""
+    echo "Please review the test output above to identify and fix issues."
+    echo "You may need to:"
+    echo "  - Check Docker installation and permissions"
+    echo "  - Verify network connectivity"
+    echo "  - Review BIND9 configuration files"
+    echo "  - Check system resources and port availability"
+    exit 1
+fi

src/bind/tests/scripts/01_start_container.sh

@@ -0,0 +1,38 @@
+#!/bin/bash
+
+# Start BIND9 test container
+# Usage: ./01_start_container.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_DIR="$(dirname "$SCRIPT_DIR")"
+
+cd "$TEST_DIR"
+
+echo "Starting BIND9 test container..."
+
+# Ensure private directory exists with proper permissions
+mkdir -p private
+chmod 777 private
+
+# Start the container
+docker compose up -d
+
+echo "Waiting for container to be ready..."
+sleep 5
+
+# Check if container is running
+if docker compose ps | grep -q "Up"; then
+    echo "✓ Container started successfully"
+    echo "Container status:"
+    docker compose ps
+else
+    echo "✗ Failed to start container"
+    docker compose logs
+    exit 1
+fi
+
+echo ""
+echo "BIND9 test environment is ready!"
+echo "DNS server listening on localhost:53"

src/bind/tests/scripts/02_dig_test.sh

@@ -0,0 +1,72 @@
+#!/bin/bash
+
+# Test DNS resolution using dig
+# Usage: ./02_dig_test.sh
+
+set -e
+
+echo "Testing DNS resolution with dig..."
+
+# Function to test DNS query
+test_dns_query() {
+    local hostname="$1"
+    local expected_ip="$2"
+    local description="$3"
+
+    echo ""
+    echo "Testing: $description"
+    echo "Query: $hostname.argus.com"
+    echo "Expected IP: $expected_ip"
+
+    # Perform dig query
+    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+
+    if [ "$result" = "QUERY_FAILED" ]; then
+        echo "✗ DNS query failed"
+        return 1
+    elif [ "$result" = "$expected_ip" ]; then
+        echo "✓ DNS query successful: $result"
+        return 0
+    else
+        echo "✗ DNS query returned unexpected result: $result"
+        return 1
+    fi
+}
+
+# Check if dig is available
+if ! command -v dig &> /dev/null; then
+    echo "Installing dig (dnsutils)..."
+    apt-get update && apt-get install -y dnsutils
+fi
+
+# Check if container is running
+if ! docker compose ps | grep -q "Up"; then
+    echo "Error: BIND9 container is not running"
+    echo "Please start the container first with: ./01_start_container.sh"
+    exit 1
+fi
+
+echo "=== DNS Resolution Tests ==="
+
+# Test cases based on current configuration
+failed_tests=0
+
+# Test ns1.argus.com -> 127.0.0.1
+if ! test_dns_query "ns1" "127.0.0.1" "Name server resolution"; then
+    ((failed_tests++))
+fi
+
+# Test web.argus.com -> 12.4.5.6
+if ! test_dns_query "web" "12.4.5.6" "Web server resolution"; then
+    ((failed_tests++))
+fi
+
+echo ""
+echo "=== Test Summary ==="
+if [ $failed_tests -eq 0 ]; then
+    echo "✓ All DNS tests passed!"
+    exit 0
+else
+    echo "✗ $failed_tests test(s) failed"
+    exit 1
+fi

src/bind/tests/scripts/03.5_dns_sync_test.sh

@@ -0,0 +1,256 @@
+#!/bin/bash
+
+# Test DNS auto-sync functionality using argus_dns_sync.sh
+# This test validates the automatic DNS record updates from IP files
+# Usage: ./03.5_dns_sync_test.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_DIR="$(dirname "$SCRIPT_DIR")"
+
+echo "=== DNS Auto-Sync Functionality Test ==="
+
+# Check if container is running
+if ! docker compose ps | grep -q "Up"; then
+    echo "Error: BIND9 container is not running"
+    echo "Please start the container first with: ./01_start_container.sh"
+    exit 1
+fi
+
+# Check if dig is available
+if ! command -v dig &> /dev/null; then
+    echo "Installing dig (dnsutils)..."
+    apt-get update && apt-get install -y dnsutils
+fi
+
+# Function to test DNS query
+test_dns_query() {
+    local hostname="$1"
+    local expected_ip="$2"
+    local description="$3"
+
+    echo "Testing: $description"
+    echo "Query: $hostname.argus.com -> Expected: $expected_ip"
+
+    # Wait a moment for DNS cache
+    sleep 2
+
+    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+
+    if [ "$result" = "$expected_ip" ]; then
+        echo "✓ $result"
+        return 0
+    else
+        echo "✗ Got: $result, Expected: $expected_ip"
+        return 1
+    fi
+}
+
+# Function to wait for sync to complete
+wait_for_sync() {
+    local timeout=15
+    local elapsed=0
+    echo "Waiting for DNS sync to complete (max ${timeout}s)..."
+
+    while [ $elapsed -lt $timeout ]; do
+        if docker compose exec bind9 test -f /var/lock/argus_dns_sync.lock; then
+            echo "Sync process is running..."
+        else
+            echo "Sync completed"
+            sleep 2  # Extra wait for DNS propagation
+            return 0
+        fi
+        sleep 2
+        elapsed=$((elapsed + 2))
+    done
+
+    echo "Warning: Sync may still be running after ${timeout}s"
+    return 0
+}
+
+echo ""
+echo "Step 1: Preparing test environment..."
+
+# Ensure required directories exist
+docker compose exec bind9 mkdir -p /private/argus/etc
+docker compose exec bind9 mkdir -p /private/argus/bind/.backup
+
+# Backup original configuration if it exists
+docker compose exec bind9 test -f /private/argus/bind/db.argus.com && \
+    docker compose exec bind9 cp /private/argus/bind/db.argus.com /private/argus/bind/db.argus.com.backup.test || true
+
+# Ensure initial configuration is available (may already be symlinked)
+docker compose exec bind9 test -f /private/argus/bind/db.argus.com || \
+    docker compose exec bind9 cp /etc/bind/db.argus.com /private/argus/bind/db.argus.com
+
+echo "✓ Test environment prepared"
+
+echo ""
+echo "Step 2: Testing initial DNS configuration..."
+
+# Get current IP for web.argus.com (may have been changed by previous tests)
+current_web_ip=$(dig @localhost web.argus.com A +short 2>/dev/null || echo "UNKNOWN")
+echo "Current web.argus.com IP: $current_web_ip"
+
+# Test that DNS is working (regardless of specific IP)
+if [ "$current_web_ip" = "UNKNOWN" ] || [ -z "$current_web_ip" ]; then
+    echo "DNS resolution not working for web.argus.com"
+    exit 1
+fi
+
+echo "✓ DNS resolution is working"
+
+echo ""
+echo "Step 3: Creating IP files for auto-sync..."
+
+# Create test IP files in the watch directory
+echo "Creating test1.argus.com with IP 10.0.0.100"
+docker compose exec bind9 bash -c 'echo "10.0.0.100" > /private/argus/etc/test1.argus.com'
+
+echo "Creating test2.argus.com with IP 10.0.0.200"
+docker compose exec bind9 bash -c 'echo "test2 service running on 10.0.0.200" > /private/argus/etc/test2.argus.com'
+
+echo "Creating api.argus.com with IP 192.168.1.50"
+docker compose exec bind9 bash -c 'echo "API server: 192.168.1.50 port 8080" > /private/argus/etc/api.argus.com'
+
+echo "✓ IP files created"
+
+echo ""
+echo "Step 4: Checking DNS sync process..."
+
+# Check if DNS sync process is already running (via supervisord)
+if docker compose exec bind9 pgrep -f argus_dns_sync.sh > /dev/null; then
+    echo "✓ DNS sync process already running (via supervisord)"
+else
+    echo "Starting DNS sync process manually..."
+    # Start the DNS sync process in background if not running
+    docker compose exec -d bind9 /usr/local/bin/argus_dns_sync.sh
+    echo "✓ DNS sync process started manually"
+fi
+
+# Wait for first sync cycle
+wait_for_sync
+
+echo ""
+echo "Step 5: Testing auto-synced DNS records..."
+
+failed_tests=0
+
+# Test new DNS records created by auto-sync
+if ! test_dns_query "test1" "10.0.0.100" "Auto-synced test1.argus.com"; then
+    ((failed_tests++))
+fi
+
+if ! test_dns_query "test2" "10.0.0.200" "Auto-synced test2.argus.com"; then
+    ((failed_tests++))
+fi
+
+if ! test_dns_query "api" "192.168.1.50" "Auto-synced api.argus.com"; then
+    ((failed_tests++))
+fi
+
+# Verify original records still work (use current IP from earlier)
+if ! test_dns_query "web" "$current_web_ip" "Original web.argus.com still working"; then
+    ((failed_tests++))
+fi
+
+if ! test_dns_query "ns1" "127.0.0.1" "Original ns1.argus.com still working"; then
+    ((failed_tests++))
+fi
+
+echo ""
+echo "Step 6: Testing IP update functionality..."
+
+# Update an existing IP file
+echo "Updating test1.argus.com IP from 10.0.0.100 to 10.0.0.150"
+docker compose exec bind9 bash -c 'echo "10.0.0.150" > /private/argus/etc/test1.argus.com'
+
+# Wait for sync
+wait_for_sync
+
+# Test updated record
+if ! test_dns_query "test1" "10.0.0.150" "Updated test1.argus.com IP"; then
+    ((failed_tests++))
+fi
+
+echo ""
+echo "Step 7: Testing invalid IP handling..."
+
+# Create file with invalid IP
+echo "Creating invalid.argus.com with invalid IP"
+docker compose exec bind9 bash -c 'echo "this is not an IP address" > /private/argus/etc/invalid.argus.com'
+
+# Wait for sync (should skip invalid IP)
+wait_for_sync
+
+# Verify invalid record was not added (should fail to resolve)
+result=$(dig @localhost invalid.argus.com A +short 2>/dev/null || echo "NO_RESULT")
+if [ "$result" = "NO_RESULT" ] || [ -z "$result" ]; then
+    echo "✓ Invalid IP correctly ignored"
+else
+    echo "✗ Invalid IP was processed: $result"
+    ((failed_tests++))
+fi
+
+echo ""
+echo "Step 8: Verifying backup functionality..."
+
+# Check if backups were created
+backup_count=$(docker compose exec bind9 ls -1 /private/argus/bind/.backup/ | wc -l || echo "0")
+if [ "$backup_count" -gt 0 ]; then
+    echo "✓ Configuration backups created ($backup_count files)"
+    # Show latest backup
+    docker compose exec bind9 ls -la /private/argus/bind/.backup/ | tail -1
+else
+    echo "✗ No backup files found"
+    ((failed_tests++))
+fi
+
+echo ""
+echo "Step 9: Cleanup..."
+
+# Note: We don't stop the DNS sync process since it's managed by supervisord
+echo "Note: DNS sync process will continue running (managed by supervisord)"
+
+# Clean up test files
+docker compose exec bind9 rm -f /private/argus/etc/test1.argus.com
+docker compose exec bind9 rm -f /private/argus/etc/test2.argus.com
+docker compose exec bind9 rm -f /private/argus/etc/api.argus.com
+docker compose exec bind9 rm -f /private/argus/etc/invalid.argus.com
+
+# Restore original configuration if backup exists
+docker compose exec bind9 test -f /private/argus/bind/db.argus.com.backup.test && \
+    docker compose exec bind9 cp /private/argus/bind/db.argus.com.backup.test /private/argus/bind/db.argus.com && \
+    docker compose exec bind9 rm /private/argus/bind/db.argus.com.backup.test || true
+
+# Reload original configuration
+docker compose exec bind9 /usr/local/bin/reload-bind9.sh
+
+echo "✓ Cleanup completed"
+
+echo ""
+echo "=== DNS Auto-Sync Test Summary ==="
+if [ $failed_tests -eq 0 ]; then
+    echo "✅ All DNS auto-sync tests passed!"
+    echo ""
+    echo "Validated functionality:"
+    echo "  ✓ Automatic DNS record creation from IP files"
+    echo "  ✓ IP address extraction from various file formats"
+    echo "  ✓ Dynamic DNS record updates"
+    echo "  ✓ Invalid IP address handling"
+    echo "  ✓ Configuration backup mechanism"
+    echo "  ✓ Preservation of existing DNS records"
+    echo ""
+    echo "The DNS auto-sync functionality is working correctly!"
+    exit 0
+else
+    echo "❌ $failed_tests DNS auto-sync test(s) failed!"
+    echo ""
+    echo "Please check:"
+    echo "  - argus_dns_sync.sh script configuration"
+    echo "  - File permissions in /private/argus/etc/"
+    echo "  - BIND9 reload functionality"
+    echo "  - Network connectivity and DNS resolution"
+    exit 1
+fi

src/bind/tests/scripts/03_reload_test.sh

@@ -0,0 +1,112 @@
+#!/bin/bash
+
+# Test DNS configuration reload with IP modification
+# Usage: ./03_reload_test.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_DIR="$(dirname "$SCRIPT_DIR")"
+
+echo "=== DNS Configuration Reload Test ==="
+
+# Check if container is running
+if ! docker compose ps | grep -q "Up"; then
+    echo "Error: BIND9 container is not running"
+    echo "Please start the container first with: ./01_start_container.sh"
+    exit 1
+fi
+
+# Check if dig is available
+if ! command -v dig &> /dev/null; then
+    echo "Installing dig (dnsutils)..."
+    apt-get update && apt-get install -y dnsutils
+fi
+
+# Function to test DNS query
+test_dns_query() {
+    local hostname="$1"
+    local expected_ip="$2"
+    local description="$3"
+
+    echo "Testing: $description"
+    echo "Query: $hostname.argus.com -> Expected: $expected_ip"
+
+    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+
+    if [ "$result" = "$expected_ip" ]; then
+        echo "✓ $result"
+        return 0
+    else
+        echo "✗ Got: $result, Expected: $expected_ip"
+        return 1
+    fi
+}
+
+echo ""
+echo "Step 1: Testing initial DNS configuration..."
+
+# Test initial configuration
+if ! test_dns_query "web" "12.4.5.6" "Initial web.argus.com resolution"; then
+    echo "Initial DNS test failed"
+    exit 1
+fi
+
+echo ""
+echo "Step 2: Modifying DNS configuration..."
+
+# Backup original configuration
+cp "$TEST_DIR/private/argus/bind/db.argus.com" "$TEST_DIR/private/argus/bind/db.argus.com.backup" 2>/dev/null || true
+
+# Create new configuration with modified IP
+DB_FILE="$TEST_DIR/private/argus/bind/db.argus.com"
+
+# Check if persistent config exists, if not use from container
+if [ ! -f "$DB_FILE" ]; then
+    echo "Persistent config not found, copying from container..."
+    docker compose exec bind9 cp /etc/bind/db.argus.com /private/argus/bind/db.argus.com
+    docker compose exec bind9 chown bind:bind /private/argus/bind/db.argus.com
+fi
+
+# Modify the IP address (12.4.5.6 -> 192.168.1.100)
+sed -i 's/12\.4\.5\.6/192.168.1.100/g' "$DB_FILE"
+
+# Increment serial number for DNS cache invalidation
+current_serial=$(grep -o "2[[:space:]]*;" "$DB_FILE" | grep -o "2")
+new_serial=$((current_serial + 1))
+sed -i "s/2[[:space:]]*;/${new_serial}         ;/" "$DB_FILE"
+
+echo "Modified configuration:"
+echo "- Changed web.argus.com IP: 12.4.5.6 -> 192.168.1.100"
+echo "- Updated serial number: $current_serial -> $new_serial"
+
+echo ""
+echo "Step 3: Reloading BIND9 configuration..."
+
+# Reload BIND9 configuration
+docker compose exec bind9 /usr/local/bin/reload-bind9.sh
+
+echo "Configuration reloaded"
+
+# Wait a moment for changes to take effect
+sleep 3
+
+echo ""
+echo "Step 4: Testing modified DNS configuration..."
+
+# Test modified configuration
+if ! test_dns_query "web" "192.168.1.100" "Modified web.argus.com resolution"; then
+    echo "Modified DNS test failed"
+    exit 1
+fi
+
+# Also verify ns1 still works
+if ! test_dns_query "ns1" "127.0.0.1" "ns1.argus.com still working"; then
+    echo "ns1 DNS test failed after reload"
+    exit 1
+fi
+
+echo ""
+echo "✓ DNS configuration reload test completed successfully!"
+echo "✓ IP address changed from 12.4.5.6 to 192.168.1.100"
+echo "✓ Configuration persisted and reloaded correctly"

src/bind/tests/scripts/04_persistence_test.sh

@@ -0,0 +1,115 @@
+#!/bin/bash
+
+# Test configuration persistence after container restart
+# Usage: ./04_persistence_test.sh
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_DIR="$(dirname "$SCRIPT_DIR")"
+
+echo "=== Configuration Persistence Test ==="
+
+# Check if dig is available
+if ! command -v dig &> /dev/null; then
+    echo "Installing dig (dnsutils)..."
+    apt-get update && apt-get install -y dnsutils
+fi
+
+# Function to test DNS query
+test_dns_query() {
+    local hostname="$1"
+    local expected_ip="$2"
+    local description="$3"
+
+    echo "Testing: $description"
+    echo "Query: $hostname.argus.com -> Expected: $expected_ip"
+
+    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+
+    if [ "$result" = "$expected_ip" ]; then
+        echo "✓ $result"
+        return 0
+    else
+        echo "✗ Got: $result, Expected: $expected_ip"
+        return 1
+    fi
+}
+
+echo ""
+echo "Step 1: Stopping current container..."
+
+# Stop the container
+docker compose down
+
+echo "Container stopped"
+
+echo ""
+echo "Step 2: Verifying persistent configuration exists..."
+
+# Check if modified configuration exists
+DB_FILE="$TEST_DIR/private/argus/bind/db.argus.com"
+
+if [ ! -f "$DB_FILE" ]; then
+    echo "✗ Persistent configuration file not found: $DB_FILE"
+    exit 1
+fi
+
+# Check if the modified IP is in the configuration
+if grep -q "192.168.1.100" "$DB_FILE"; then
+    echo "✓ Modified IP (192.168.1.100) found in persistent configuration"
+else
+    echo "✗ Modified IP not found in persistent configuration"
+    echo "Configuration content:"
+    cat "$DB_FILE"
+    exit 1
+fi
+
+echo ""
+echo "Step 3: Restarting container with persistent configuration..."
+
+# Start the container again
+docker compose up -d
+
+echo "Waiting for container to be ready..."
+sleep 5
+
+# Check if container is running
+if ! docker compose ps | grep -q "Up"; then
+    echo "✗ Failed to restart container"
+    docker compose logs
+    exit 1
+fi
+
+echo "✓ Container restarted successfully"
+
+echo ""
+echo "Step 4: Testing DNS resolution after restart..."
+
+# Wait a bit more for DNS to be fully ready
+sleep 5
+
+# Test that the modified configuration is still active
+if ! test_dns_query "web" "192.168.1.100" "Persistent web.argus.com resolution"; then
+    echo "✗ Persistent configuration test failed"
+    exit 1
+fi
+
+# Also verify ns1 still works
+if ! test_dns_query "ns1" "127.0.0.1" "ns1.argus.com still working"; then
+    echo "✗ ns1 DNS test failed after restart"
+    exit 1
+fi
+
+echo ""
+echo "Step 5: Verifying configuration files are linked correctly..."
+
+# Check that the persistent files are properly linked
+echo "Checking file links in container:"
+docker compose exec bind9 ls -la /etc/bind/named.conf.local /etc/bind/db.argus.com
+
+echo ""
+echo "✓ Configuration persistence test completed successfully!"
+echo "✓ Modified IP (192.168.1.100) persisted after container restart"
+echo "✓ Configuration files properly linked to persistent storage"
+echo "✓ DNS resolution working correctly with persisted configuration"

src/bind/tests/scripts/05_cleanup.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+# Clean up test environment and containers
+# Usage: ./05_cleanup.sh [--full]
+
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_DIR="$(dirname "$SCRIPT_DIR")"
+
+# Parse command line arguments
+FULL_CLEANUP=true
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --full)
+            FULL_CLEANUP=true
+            shift
+            ;;
+        *)
+            echo "Unknown option: $1"
+            echo "Usage: $0 [--full]"
+            echo "  --full: Also remove persistent data "
+            exit 1
+            ;;
+    esac
+done
+
+cd "$TEST_DIR"
+
+echo "=== Cleaning up BIND9 test environment ==="
+
+echo ""
+echo "Step 1: Stopping and removing containers..."
+
+# Stop and remove containers
+docker compose down -v
+
+echo "✓ Containers stopped and removed"
+
+echo ""
+echo "Step 2: Removing Docker networks..."
+
+# Clean up networks
+docker network prune -f > /dev/null 2>&1 || true
+
+echo "✓ Docker networks cleaned"
+
+if [ "$FULL_CLEANUP" = true ]; then
+    echo ""
+    echo "Step 3: Removing persistent data..."
+
+    # Remove persistent data directory
+    if [ -d "private" ]; then
+        rm -rf private
+        echo "✓ Persistent data directory removed"
+    else
+        echo "✓ No persistent data directory found"
+    fi
+
+else
+    echo ""
+    echo "Step 3: Preserving persistent data and Docker image..."
+    echo "✓ Persistent data preserved in: private/"
+    echo "✓ Docker image 'argus-bind9:latest' preserved"
+    echo ""
+    echo "To perform full cleanup including persistent data and image, run:"
+    echo "  $0 --full"
+fi
+
+echo ""
+echo "=== Cleanup Summary ==="
+echo "✓ Containers stopped and removed"
+echo "✓ Docker networks cleaned"
+
+if [ "$FULL_CLEANUP" = true ]; then
+    echo "✓ Persistent data removed"
+    echo ""
+    echo "Full cleanup completed! Test environment completely removed."
+else
+    echo "✓ Persistent data preserved"
+    echo "✓ Docker image preserved"
+    echo ""
+    echo "Basic cleanup completed! Run './01_start_container.sh' to restart testing."
+fi
+
+echo ""
+echo "Test environment cleanup finished."

src/log/.gitignore

@@ -0,0 +1,5 @@
+
+private/
+
+
+images/

src/log/README.md

@@ -0,0 +1,8 @@
+
+测试log模块开发
+
+elasticsearch: 部署镜像构建及启动脚本（解决账号问题、挂载目录、使用supervisor守护）
+kibana: 镜像构建
+fluent-bit: 安装包，脚本准备， 交付给大鹏统一组织客户端侧安装流程
+init: EK初始化脚本：数据视图创建脚本等
+

src/log/elasticsearch/build/Dockerfile

@@ -0,0 +1,56 @@
+FROM docker.elastic.co/elasticsearch/elasticsearch:8.13.4
+
+# 切换到 root 用户进行系统级安装
+USER root
+
+# 修改elasticsearch用户的UID和GID
+RUN usermod -u 2133 elasticsearch && \
+    groupmod -g 2015 elasticsearch && \
+    chown -R elasticsearch:elasticsearch /usr/share/elasticsearch
+
+# 设置构建参数
+ARG USE_INTRANET=false
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# 安装 supervisor, net-tools, vim
+RUN apt-get update && \
+    apt-get install -y supervisor net-tools inetutils-ping vim && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 配置部署时使用的apt源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+	echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# 创建 supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+
+# 复制 supervisor 配置文件
+COPY src/log/elasticsearch/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 复制启动脚本
+COPY src/log/elasticsearch/build/start-es-supervised.sh /usr/local/bin/start-es-supervised.sh
+RUN chmod +x /usr/local/bin/start-es-supervised.sh
+
+# 复制DNS监控脚本
+COPY src/log/elasticsearch/build/dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+# 保持 root 用户，由 supervisor 管理用户切换
+USER root
+
+# 暴露端口
+EXPOSE 9200 9300
+
+# 使用 supervisor 作为入口点
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

src/log/elasticsearch/build/dns-monitor.sh

@@ -0,0 +1 @@
+../../../bind/build/dns-monitor.sh

src/log/elasticsearch/build/start-es-supervised.sh

@@ -0,0 +1,32 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting Elasticsearch under supervisor..."
+
+# 创建数据目录并设置权限（如果不存在）
+mkdir -p /private/argus/log/elasticsearch
+
+# 创建软链接到Elasticsearch预期的数据目录
+if [ -L /usr/share/elasticsearch/data ]; then
+    rm /usr/share/elasticsearch/data
+elif [ -d /usr/share/elasticsearch/data ]; then
+    rm -rf /usr/share/elasticsearch/data
+fi
+
+ln -sf /private/argus/log/elasticsearch /usr/share/elasticsearch/data
+
+# 记录容器ip地址
+DOMAIN=es.log.argus.com
+IP=`ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}'`
+echo current IP: ${IP}
+echo ${IP} > /private/argus/etc/${DOMAIN}
+
+echo "[INFO] Data directory linked: /usr/share/elasticsearch/data -> /private/argus/log/elasticsearch"
+
+# 设置环境变量（ES配置通过docker-compose传递）
+export ES_JAVA_OPTS="${ES_JAVA_OPTS:-"-Xms512m -Xmx512m"}"
+
+echo "[INFO] Starting Elasticsearch process..."
+
+# 启动原始的Elasticsearch entrypoint
+exec /usr/local/bin/docker-entrypoint.sh elasticsearch

src/log/elasticsearch/build/supervisord.conf

@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:elasticsearch]
+command=/usr/local/bin/start-es-supervised.sh
+user=elasticsearch
+stdout_logfile=/var/log/supervisor/elasticsearch.log
+stderr_logfile=/var/log/supervisor/elasticsearch_error.log
+autorestart=true
+startretries=3
+startsecs=30
+stopwaitsecs=30
+killasgroup=true
+stopasgroup=true
+
+[program:dns-monitor]
+command=/usr/local/bin/dns-monitor.sh
+user=root
+stdout_logfile=/var/log/supervisor/dns-monitor.log
+stderr_logfile=/var/log/supervisor/dns-monitor_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

src/log/fluent-bit/build/etc/fluent-bit.conf

@@ -0,0 +1,37 @@
+[SERVICE]
+    Daemon       Off
+    Parsers_File parsers.conf
+    HTTP_Server  On
+    HTTP_Listen  0.0.0.0
+    HTTP_Port    2020
+    storage.path /buffers
+    storage.sync normal
+    storage.checksum on
+    storage.backlog.mem_limit 128M
+    # 备注：该镜像默认未开启 Hot Reload，修改配置后请重启容器。
+
+@INCLUDE inputs.d/*.conf
+
+[FILTER]
+    Name   parser
+    Match  app.*
+    Key_Name log
+    Parser timestamp_parser
+    Reserve_Data On
+    Preserve_Key On
+    Unescape_Key On
+
+[FILTER]
+    Name   record_modifier
+    Match  *
+    Record cluster  ${CLUSTER}
+    Record rack     ${RACK}
+    Record host     ${HOSTNAME}
+
+[FILTER]
+    Name   lua
+    Match  app.*
+    script inject_labels.lua
+    call   add_labels
+
+@INCLUDE outputs.d/*.conf

src/log/fluent-bit/build/etc/inject_labels.lua

@@ -0,0 +1,15 @@
+function add_labels(tag, ts, record)
+  record["job_id"] = os.getenv("FB_JOB_ID") or record["job_id"] or "unknown"
+  record["user"]   = os.getenv("FB_USER")   or record["user"]   or "unknown"
+  record["model"]  = os.getenv("FB_MODEL")  or record["model"]  or "unknown"
+  record["gpu_id"] = os.getenv("FB_GPU_ID") or record["gpu_id"] or "na"
+  local p = record["log_path"] or ""
+  if string.find(p, "/logs/infer/") then
+    record["role"] = "infer"
+  elseif string.find(p, "/logs/train/") then
+    record["role"] = "train"
+  else
+    record["role"] = record["role"] or "app"
+  end
+  return 1, ts, record
+end

src/log/fluent-bit/build/etc/inputs.d/10-train.conf

@@ -0,0 +1,10 @@
+[INPUT]
+    Name              tail
+    Path              /logs/train/*.log
+    Tag               app.train
+    Path_Key          log_path
+    Refresh_Interval  5
+    DB                /buffers/train.db
+    Skip_Long_Lines   On
+    storage.type      filesystem
+    multiline.parser  python,go,java

src/log/fluent-bit/build/etc/inputs.d/20-infer.conf

@@ -0,0 +1,10 @@
+[INPUT]
+    Name              tail
+    Path              /logs/infer/*.log
+    Tag               app.infer
+    Path_Key          log_path
+    Refresh_Interval  5
+    DB                /buffers/infer.db
+    Skip_Long_Lines   On
+    storage.type      filesystem
+    multiline.parser  python,go,java

src/log/fluent-bit/build/etc/outputs.d/10-es.conf

@@ -0,0 +1,24 @@
+# 重要：使用 Logstash_Format + Logstash_Prefix，生成 train-*/infer-* 索引
+[OUTPUT]
+    Name                es
+    Match               app.train
+    Host                ${ES_HOST}
+    Port                ${ES_PORT}
+    Logstash_Format     On
+    Logstash_Prefix     train
+    Replace_Dots        On
+    Generate_ID         On
+    Retry_Limit         False
+    Suppress_Type_Name  On
+
+[OUTPUT]
+    Name                es
+    Match               app.infer
+    Host                ${ES_HOST}
+    Port                ${ES_PORT}
+    Logstash_Format     On
+    Logstash_Prefix     infer
+    Replace_Dots        On
+    Generate_ID         On
+    Retry_Limit         False
+    Suppress_Type_Name  On

src/log/fluent-bit/build/etc/parsers.conf

@@ -0,0 +1,27 @@
+[MULTILINE_PARSER]
+    Name   python
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^\d{4}-\d{2}-\d{2}[\sT]/"  "cont"
+    Rule   "cont"         "/^\s+|^Traceback|^\tat\s+/" "cont"
+
+[MULTILINE_PARSER]
+    Name   go
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^[0-9]{4}\/[0-9]{2}\/[0-9]{2}/" "cont"
+    Rule   "cont"         "/^\s+|^\t/" "cont"
+
+[MULTILINE_PARSER]
+    Name   java
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}/" "cont"
+    Rule   "cont"         "/^\s+at\s+|^\t.../" "cont"
+
+[PARSER]
+    Name   timestamp_parser
+    Format regex
+    Regex  ^(?<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})\s+(?<level>\w+)\s+(?<message>.*)$
+    Time_Key    timestamp
+    Time_Format %Y-%m-%d %H:%M:%S

src/log/fluent-bit/build/start-fluent-bit.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting Fluent Bit setup in Ubuntu container..."
+
+# 安装必要的工具
+echo "[INFO] Installing required packages..."
+export DEBIAN_FRONTEND=noninteractive
+apt-get update -qq
+apt-get install -y -qq curl
+
+# 解压bundle到/tmp
+echo "[INFO] Extracting fluent-bit bundle..."
+cp -r /private/etc /tmp
+cp -r /private/packages /tmp
+cd /tmp
+
+# 安装 Fluent Bit 从 deb 包
+echo "[INFO] Installing Fluent Bit from deb package..."
+dpkg -i /tmp/packages/fluent-bit_3.1.9_amd64.deb || true
+apt-get install -f -y -qq  # 解决依赖问题
+
+# 验证 Fluent Bit 可以运行
+echo "[INFO] Fluent Bit version:"
+/opt/fluent-bit/bin/fluent-bit --version
+
+# 创建配置目录
+mkdir -p /etc/fluent-bit
+cp -r /tmp/etc/* /etc/fluent-bit/
+
+# 创建日志和缓冲区目录
+mkdir -p /logs/train /logs/infer /buffers
+chmod 755 /logs/train /logs/infer /buffers
+
+# 等待 Elasticsearch 就绪
+echo "[INFO] Waiting for Elasticsearch to be ready..."
+while ! curl -fs http://${ES_HOST}:${ES_PORT}/_cluster/health >/dev/null 2>&1; do
+    echo "  Waiting for ES at ${ES_HOST}:${ES_PORT}..."
+    sleep 5
+done
+echo "[INFO] Elasticsearch is ready"
+
+# 启动 Fluent Bit
+echo "[INFO] Starting Fluent Bit with configuration from /etc/fluent-bit/"
+echo "[INFO] Command: /opt/fluent-bit/bin/fluent-bit --config=/etc/fluent-bit/fluent-bit.conf"
+exec /opt/fluent-bit/bin/fluent-bit \
+    --config=/etc/fluent-bit/fluent-bit.conf

src/log/kibana/build/Dockerfile

@@ -0,0 +1,60 @@
+FROM docker.elastic.co/kibana/kibana:8.13.4
+
+# 切换到 root 用户进行系统级安装
+USER root
+
+# 修改kibana用户的UID和GID
+RUN usermod -u 2133 kibana && \
+    groupmod -g 2015 kibana && \
+    chown -R kibana:kibana /usr/share/kibana
+
+# 设置构建参数
+ARG USE_INTRANET=false
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes]  http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# 安装 supervisor, net-tools, vim
+RUN apt-get update && \
+    apt-get install -y supervisor net-tools inetutils-ping vim && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 配置部署时使用的apt源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# 创建 supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+
+# 复制 supervisor 配置文件
+COPY src/log/kibana/build/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 复制启动脚本
+COPY src/log/kibana/build/start-kibana-supervised.sh /usr/local/bin/start-kibana-supervised.sh
+COPY src/log/kibana/build/kibana-post-start.sh /usr/local/bin/kibana-post-start.sh
+RUN chmod +x /usr/local/bin/start-kibana-supervised.sh /usr/local/bin/kibana-post-start.sh
+
+# 复制DNS监控脚本
+COPY src/log/kibana/build/dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+# kibana需要用到 /root/.config/puppeteer 路径
+RUN chmod 777 /root
+
+# 保持 root 用户，由 supervisor 管理用户切换
+USER root
+
+# 暴露端口
+EXPOSE 5601
+
+# 使用 supervisor 作为入口点
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

src/log/kibana/build/dns-monitor.sh

@@ -0,0 +1 @@
+../../../bind/build/dns-monitor.sh

src/log/kibana/build/kibana-post-start.sh

@@ -0,0 +1,146 @@
+#!/bin/bash
+set -euo pipefail
+
+ES_HOST="${ELASTICSEARCH_HOSTS:-http://es:9200}"
+KB_HOST="http://localhost:5601"
+
+echo "[INFO] Starting Kibana post-start configuration..."
+
+# 等待 Elasticsearch 可用
+wait_for_elasticsearch() {
+    echo "[INFO] Waiting for Elasticsearch..."
+    local max_attempts=60
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs "$ES_HOST/_cluster/health" >/dev/null 2>&1; then
+            echo "[OK] Elasticsearch is available"
+            return 0
+        fi
+        echo "    Waiting for ES... ($attempt/$max_attempts)"
+        sleep 5
+        ((attempt++))
+    done
+
+    echo "[ERROR] Elasticsearch timeout"
+    return 1
+}
+
+# 等待 Kibana 可用
+wait_for_kibana() {
+    echo "[INFO] Waiting for Kibana..."
+    local max_attempts=120
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs "$KB_HOST/api/status" >/dev/null 2>&1; then
+            local status=$(curl -s "$KB_HOST/api/status" | grep -o '"level":"available"' || echo "")
+            if [ -n "$status" ]; then
+                echo "[OK] Kibana is available"
+                return 0
+            fi
+            echo "    Waiting for Kibana... ($attempt/$max_attempts, status: $status)"
+        else
+            echo "    Waiting for Kibana... ($attempt/$max_attempts, connection failed)"
+        fi
+        sleep 5
+        ((attempt++))
+    done
+
+    echo "[ERROR] Kibana timeout"
+    return 1
+}
+
+# 幂等设置索引副本数为0
+fix_replicas_idempotent() {
+    echo "[INFO] Checking and fixing index replicas..."
+
+    # 获取所有 train-* 和 infer-* 索引
+    local indices=$(curl -s "$ES_HOST/_cat/indices/train-*,infer-*?h=index" 2>/dev/null || echo "")
+
+    if [ -z "$indices" ]; then
+        echo "[INFO] No train-*/infer-* indices found, skipping replica adjustment"
+        return 0
+    fi
+
+    for idx in $indices; do
+        # 检查当前副本数
+        local current_replicas=$(curl -s "$ES_HOST/$idx/_settings" | grep -o '"number_of_replicas":"[^"]*"' | cut -d'"' -f4 || echo "")
+
+        if [ "$current_replicas" != "0" ]; then
+            echo "[INFO] Setting replicas to 0 for index: $idx (current: $current_replicas)"
+            curl -fsS -X PUT "$ES_HOST/$idx/_settings" \
+                -H 'Content-Type: application/json' \
+                -d '{"index":{"number_of_replicas":0}}' >/dev/null || {
+                echo "[WARN] Failed to set replicas for $idx"
+                continue
+            }
+            echo "[OK] Updated replicas for $idx"
+        else
+            echo "[INFO] Index $idx already has 0 replicas, skipping"
+        fi
+    done
+}
+
+# 幂等创建数据视图
+create_data_views_idempotent() {
+    echo "[INFO] Checking and creating data views..."
+
+    # 检查是否存在匹配的索引
+    local train_indices=$(curl -s "$ES_HOST/_cat/indices/train-*?h=index" 2>/dev/null | wc -l || echo "0")
+    local infer_indices=$(curl -s "$ES_HOST/_cat/indices/infer-*?h=index" 2>/dev/null | wc -l || echo "0")
+
+    # 创建 train 数据视图
+    if [ "$train_indices" -gt 0 ]; then
+        # 检查数据视图是否已存在
+        local train_exists=$(curl -s "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null | grep '"title":"train-\*"' | wc -l )
+
+        if [ "$train_exists" -eq 0 ]; then
+            echo "[INFO] Creating data view for train-* indices"
+            curl -fsS -X POST "$KB_HOST/api/data_views/data_view" \
+                -H 'kbn-xsrf: true' \
+                -H 'Content-Type: application/json' \
+                -d '{"data_view":{"name":"train","title":"train-*","timeFieldName":"@timestamp"}}' \
+                >/dev/null && echo "[OK] Created train data view" || echo "[WARN] Failed to create train data view"
+        else
+            echo "[INFO] Train data view already exists, skipping"
+        fi
+    else
+        echo "[INFO] No train-* indices found, skipping train data view creation"
+    fi
+
+    # 创建 infer 数据视图
+    if [ "$infer_indices" -gt 0 ]; then
+        # 检查数据视图是否已存在
+        local infer_exists=$(curl -s "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null | grep '"title":"infer-\*"' | wc -l )
+
+        if [ "$infer_exists" -eq 0 ]; then
+            echo "[INFO] Creating data view for infer-* indices"
+            curl -fsS -X POST "$KB_HOST/api/data_views/data_view" \
+                -H 'kbn-xsrf: true' \
+                -H 'Content-Type: application/json' \
+                -d '{"data_view":{"name":"infer","title":"infer-*","timeFieldName":"@timestamp"}}' \
+                >/dev/null && echo "[OK] Created infer data view" || echo "[WARN] Failed to create infer data view"
+        else
+            echo "[INFO] Infer data view already exists, skipping"
+        fi
+    else
+        echo "[INFO] No infer-* indices found, skipping infer data view creation"
+    fi
+}
+
+# 主逻辑
+main() {
+    # 等待服务可用
+    wait_for_elasticsearch || exit 1
+    wait_for_kibana || exit 1
+
+    # 执行幂等配置
+    fix_replicas_idempotent
+    create_data_views_idempotent
+
+    echo "[INFO] Kibana post-start configuration completed"
+}
+
+# 运行主逻辑
+main

src/log/kibana/build/start-kibana-supervised.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting Kibana under supervisor..."
+
+mkdir -p /private/argus/log/kibana
+
+# 创建软链接到Kibana预期的数据目录
+if [ -L /usr/share/kibana/data ]; then
+    rm /usr/share/kibana/data
+elif [ -d /usr/share/kibana/data ]; then
+    rm -rf /usr/share/kibana/data
+fi
+
+ln -sf /private/argus/log/kibana /usr/share/kibana/data
+
+echo "[INFO] Data directory linked: /usr/share/kibana/data -> /private/argus/log/kibana"
+
+# 记录容器ip地址
+DOMAIN=kibana.log.argus.com
+IP=`ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}'`
+echo current IP: ${IP}
+echo ${IP} > /private/argus/etc/${DOMAIN}
+
+# 设置环境变量
+export ELASTICSEARCH_HOSTS="${ELASTICSEARCH_HOSTS:-"http://es:9200"}"
+
+echo "[INFO] Connecting to Elasticsearch at: $ELASTICSEARCH_HOSTS"
+
+# 启动后台配置任务
+echo "[INFO] Starting background post-start configuration..."
+/usr/local/bin/kibana-post-start.sh &
+
+echo "[INFO] Starting Kibana process..."
+
+# 启动原始的Kibana entrypoint
+exec /usr/local/bin/kibana-docker

src/log/kibana/build/supervisord.conf

@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:kibana]
+command=/usr/local/bin/start-kibana-supervised.sh
+user=kibana
+stdout_logfile=/var/log/supervisor/kibana.log
+stderr_logfile=/var/log/supervisor/kibana_error.log
+autorestart=true
+startretries=3
+startsecs=30
+stopwaitsecs=30
+killasgroup=true
+stopasgroup=true
+
+[program:dns-monitor]
+command=/usr/local/bin/dns-monitor.sh
+user=root
+stdout_logfile=/var/log/supervisor/dns-monitor.log
+stderr_logfile=/var/log/supervisor/dns-monitor_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

src/log/tests/docker-compose.yml

@@ -0,0 +1,85 @@
+version: "3.8"
+services:
+  es:
+    build:
+      context: ../elasticsearch/build
+      dockerfile: Dockerfile
+    image: argus-elasticsearch:latest
+    environment:
+      - discovery.type=single-node
+      - xpack.security.enabled=false
+      - ES_JAVA_OPTS=-Xms512m -Xmx512m
+    volumes:
+      - ./private/argus/:/private/argus/
+    ports: ["9200:9200"]
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fs http://localhost:9200 >/dev/null || exit 1"]
+      interval: 10s
+      timeout: 5s
+      retries: 30
+
+  kibana:
+    build:
+      context: ../kibana/build
+      dockerfile: Dockerfile
+    image: argus-kibana:latest
+    environment:
+      - ELASTICSEARCH_HOSTS=http://es.log.argus.com:9200
+    volumes:
+      - ./private/argus/:/private/argus/
+    ports: ["5601:5601"]
+    depends_on:
+      es:
+        condition: service_healthy
+
+  fluent-bit-host01:
+    image: ubuntu:22.04
+    environment:
+      - CLUSTER=local
+      - RACK=dev
+      - HOSTNAME=host01
+      - ES_HOST=es
+      - ES_PORT=9200
+    volumes:
+      - ../fluent-bit/build:/private/
+    ports: ["2020:2020"]
+    depends_on:
+      es:
+        condition: service_healthy
+    command: /private/start-fluent-bit.sh
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fs http://localhost:2020/api/v2/metrics >/dev/null || exit 1"]
+      interval: 15s
+      timeout: 10s
+      retries: 30
+
+  fluent-bit-host02:
+    image: ubuntu:22.04
+    environment:
+      - CLUSTER=local
+      - RACK=dev
+      - HOSTNAME=host02
+      - ES_HOST=es
+      - ES_PORT=9200
+    volumes:
+      - ../fluent-bit/build:/private/
+    ports: ["2021:2020"]
+    depends_on:
+      es:
+        condition: service_healthy
+    command: /private/start-fluent-bit.sh
+    healthcheck:
+      test: ["CMD-SHELL", "curl -fs http://localhost:2020/api/v2/metrics >/dev/null || exit 1"]
+      interval: 15s
+      timeout: 10s
+      retries: 30
+
+  bind9:
+      image: argus-bind9:latest
+      ports:
+        - "53:53/tcp"
+        - "53:53/udp"
+      volumes:
+        - ./private/argus:/private/argus/
+      restart: unless-stopped
+

src/log/tests/scripts/01_bootstrap.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+set -euo pipefail
+root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
+
+# 创建新的private目录结构 (基于argus目录结构)
+echo "[INFO] Creating private directory structure for supervisor-based containers..."
+mkdir -p "$root/private/argus/log/elasticsearch"
+mkdir -p "$root/private/argus/log/kibana"
+mkdir -p "$root/private/argus/etc/"
+
+
+# 设置数据目录权限（ES 和 Kibana 容器都使用 UID 1000）
+echo "[INFO] Setting permissions for data directories..."
+sudo chown -R 2133:2015 "$root/private/argus/log/elasticsearch" 2>/dev/null || true
+sudo chown -R 2133:2015 "$root/private/argus/log/kibana" 2>/dev/null || true
+sudo chown -R 2133:2015 "$root/private/argus/etc" 2>/dev/null || true
+
+echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"
+
+# 检查fluent-bit相关文件是否存在
+if [[ ! -f "$root/../fluent-bit/fluent-bit-bundle.tar.gz" ]]; then
+    echo "[WARN] fluent-bit/fluent-bit-bundle.tar.gz 不存在，请确保已创建该文件"
+fi
+
+if [[ ! -f "$root/../fluent-bit/start-fluent-bit.sh" ]]; then
+    echo "[WARN] fluent-bit/start-fluent-bit.sh 不存在，请确保已创建该启动脚本"
+fi
+
+echo "[OK] 初始化完成: private/argus/log/{elasticsearch,kibana}"
+echo "[INFO] Fluent-bit files should be in fluent-bit/ directory"

src/log/tests/scripts/02_up.sh

@@ -0,0 +1,10 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+compose_cmd="docker compose"
+if ! $compose_cmd version >/dev/null 2>&1; then
+  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
+    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
+fi
+$compose_cmd -p logging-mvp up -d --remove-orphans
+echo "[OK] 服务已启动：ES http://localhost:9200  Kibana http://localhost:5601  Fluent-Bit host01 http://localhost:2020  Fluent-Bit host02 http://localhost:2021"

src/log/tests/scripts/03_send_test_host01.sh

@@ -0,0 +1,31 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 获取fluent-bit-host01容器名称
+container_name="logging-mvp-fluent-bit-host01-1"
+
+# 检查容器是否存在并运行
+if ! docker ps | grep -q "$container_name"; then
+    echo "[ERROR] Fluent Bit容器 $container_name 未运行"
+    exit 1
+fi
+
+# 创建日志目录
+docker exec "$container_name" mkdir -p /logs/train /logs/infer
+
+# 写入训练日志 (host01)
+docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=1 loss=1.23 model=bert\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host01] training step=2 loss=1.15 model=bert\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+
+# 写入推理日志 (host01)
+docker exec "$container_name" sh -c "printf '%s ERROR [host01] inference failed on batch=1\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
+docker exec "$container_name" sh -c "cat <<'STACK' >> /logs/infer/infer-demo.log
+Traceback (most recent call last):
+  File \"inference.py\", line 15, in <module>
+    raise RuntimeError(\"CUDA out of memory on host01\")
+RuntimeError: CUDA out of memory on host01
+STACK"
+
+echo "[OK] 已通过docker exec写入测试日志到 host01 容器内："
+echo " - /logs/train/train-demo.log"
+echo " - /logs/infer/infer-demo.log"

src/log/tests/scripts/03_send_test_host02.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# 获取fluent-bit-host02容器名称
+container_name="logging-mvp-fluent-bit-host02-1"
+
+# 检查容器是否存在并运行
+if ! docker ps | grep -q "$container_name"; then
+    echo "[ERROR] Fluent Bit容器 $container_name 未运行"
+    exit 1
+fi
+
+# 创建日志目录
+docker exec "$container_name" mkdir -p /logs/train /logs/infer
+
+# 写入训练日志 (host02)
+docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=1 loss=1.45 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=2 loss=1.38 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] training step=3 loss=1.32 model=gpt\n' \"\$(date '+%F %T')\" >> /logs/train/train-demo.log"
+
+# 写入推理日志 (host02)  
+docker exec "$container_name" sh -c "printf '%s WARN [host02] inference slow on batch=5 latency=2.3s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
+docker exec "$container_name" sh -c "printf '%s INFO [host02] inference completed batch=6 latency=0.8s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
+
+echo "[OK] 已通过docker exec写入测试日志到 host02 容器内："
+echo " - /logs/train/train-demo.log"
+echo " - /logs/infer/infer-demo.log"

src/log/tests/scripts/04_query_es.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -euo pipefail
+ES="${ES:-http://localhost:9200}"
+echo "[i] 查询 ES 端点：$ES"
+curl -fsS "$ES/_cat/indices?v" | egrep 'train-|infer-|logstash' || true
+printf "train-* 计数："; curl -fsS "$ES/train-*/_count" | sed -E 's/.*"count":([0-9]+).*/\1/'; echo
+printf "infer-* 计数："; curl -fsS "$ES/infer-*/_count" | sed -E 's/.*"count":([0-9]+).*/\1/'; echo

src/log/tests/scripts/05_down.sh

@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+set -euo pipefail
+cd "$(dirname "$0")/.."
+compose_cmd="docker compose"
+if ! $compose_cmd version >/dev/null 2>&1; then
+  if command -v docker-compose >/dev/null 2>&1; then compose_cmd="docker-compose"; else
+    echo "需要 Docker Compose，请安装后重试" >&2; exit 1; fi
+fi
+$compose_cmd -p logging-mvp down
+echo "[OK] 已停止所有容器"
+
+# 清理private目录内容
+echo "[INFO] 清理private目录内容..."
+cd "$(dirname "$0")/.."
+if [ -d "private" ]; then
+    # 删除private目录及其所有内容
+    rm -rf private
+    echo "[OK] 已清理private目录"
+else
+    echo "[INFO] private目录不存在，无需清理"
+fi

src/log/tests/scripts/06_dns_test.sh

@@ -0,0 +1,208 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS DNS监控功能测试"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(date +%s)
+
+# 函数：显示测试步骤
+show_step() {
+    echo ""
+    echo "🔄 Step $1: $2"
+    echo "----------------------------------------"
+}
+
+# 函数：验证步骤结果
+verify_step() {
+    if [ $? -eq 0 ]; then
+        echo "✅ $1 - SUCCESS"
+    else
+        echo "❌ $1 - FAILED"
+        exit 1
+    fi
+}
+
+# 函数：等待服务就绪
+wait_for_services() {
+    echo "[INFO] Waiting for services to be ready..."
+    local max_attempts=60
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs http://localhost:9200/_cluster/health >/dev/null 2>&1 && \
+           curl -fs http://localhost:5601/api/status >/dev/null 2>&1; then
+            echo "[OK] Services are ready!"
+            return 0
+        fi
+        echo "    Waiting for services... ($attempt/$max_attempts)"
+        sleep 5
+        ((attempt++))
+    done
+
+    echo "[ERROR] Services not ready after $max_attempts attempts"
+    return 1
+}
+
+# 函数：检查容器中的/etc/resolv.conf
+check_resolv_conf() {
+    local service_name=$1
+    local expected_dns=$2
+
+    echo "[INFO] 检查 $service_name 容器的 /etc/resolv.conf..."
+
+    local resolv_content=$(docker exec "${service_name}" cat /etc/resolv.conf 2>/dev/null || echo "")
+    if echo "$resolv_content" | grep -q "nameserver $expected_dns"; then
+        echo "✅ $service_name resolv.conf contains nameserver $expected_dns"
+        return 0
+    else
+        echo "❌ $service_name resolv.conf does not contain nameserver $expected_dns"
+        echo "实际内容:"
+        echo "$resolv_content"
+        return 1
+    fi
+}
+
+# 函数：检查DNS监控日志
+check_dns_monitor_logs() {
+    local service_name=$1
+
+    echo "[INFO] 检查 $service_name 的DNS监控日志..."
+
+    local dns_logs=$(docker exec "$service_name" tail -n 20 /var/log/supervisor/dns-monitor.log 2>/dev/null || echo "")
+    if [ -n "$dns_logs" ]; then
+        echo "✅ $service_name DNS监控日志存在"
+        echo "最近的日志:"
+        echo "$dns_logs"
+        return 0
+    else
+        echo "❌ $service_name DNS监控日志为空或不存在"
+        return 1
+    fi
+}
+
+# 函数：确保目录结构存在
+ensure_directories() {
+    echo "[INFO] 确保目录结构存在..."
+    # 确保目录存在
+    mkdir -p ./private/argus/etc/
+    echo "✅ 目录结构准备完成（注：使用真实的update-dns.sh脚本）"
+}
+
+# 开始DNS监控测试
+show_step "1" "Bootstrap - Initialize environment"
+./scripts/01_bootstrap.sh
+verify_step "Bootstrap"
+
+# 确保目录结构
+ensure_directories
+
+show_step "2" "Startup - Start all services"
+./scripts/02_up.sh
+verify_step "Service startup"
+
+# 等待服务完全就绪
+wait_for_services || exit 1
+
+show_step "3" "Create initial DNS configuration"
+# 创建初始的DNS配置文件 - 只有一个IP
+echo "[INFO] 创建初始的dns.conf文件 (8.8.8.8)..."
+cat > ./private/argus/etc/dns.conf << 'EOF'
+8.8.8.8
+EOF
+
+echo "✅ 初始dns.conf文件创建成功 (8.8.8.8)"
+verify_step "Initial DNS configuration creation"
+
+# 等待DNS监控检测到配置文件
+echo "[INFO] 等待DNS监控检测并处理初始配置..."
+sleep 15
+
+show_step "4" "Verify initial DNS configuration processing"
+# 检查两个容器的DNS监控日志
+check_dns_monitor_logs "logging-mvp-es-1"
+verify_step "Elasticsearch DNS monitor logs"
+
+check_dns_monitor_logs "logging-mvp-kibana-1"
+verify_step "Kibana DNS monitor logs"
+
+# 检查resolv.conf是否包含新的DNS服务器
+check_resolv_conf "logging-mvp-es-1" "8.8.8.8"
+verify_step "Elasticsearch resolv.conf initial check"
+
+check_resolv_conf "logging-mvp-kibana-1" "8.8.8.8"
+verify_step "Kibana resolv.conf initial check"
+
+show_step "5" "Modify DNS configuration and test auto-update"
+# 修改DNS配置文件 - 改为另一个IP
+echo "[INFO] 修改dns.conf文件，改为1.1.1.1..."
+cat > ./private/argus/etc/dns.conf << 'EOF'
+1.1.1.1
+EOF
+
+echo "✅ dns.conf文件更新成功，改为1.1.1.1"
+
+# 等待DNS监控检测到配置变化
+echo "[INFO] 等待DNS监控检测配置变化并执行更新..."
+sleep 15
+
+show_step "6" "Verify DNS configuration auto-update"
+# 再次检查DNS监控日志，应该看到配置变化检测
+echo "[INFO] 检查DNS监控是否检测到配置变化..."
+
+# 检查elasticsearch容器
+echo "[INFO] 检查elasticsearch容器的DNS监控日志（最近30行）..."
+docker exec logging-mvp-es-1 tail -n 30 /var/log/supervisor/dns-monitor.log || true
+
+# 检查kibana容器
+echo "[INFO] 检查kibana容器的DNS监控日志（最近30行）..."
+docker exec logging-mvp-kibana-1 tail -n 30 /var/log/supervisor/dns-monitor.log || true
+
+# 验证新的DNS服务器是否被添加到resolv.conf
+check_resolv_conf "logging-mvp-es-1" "1.1.1.1"
+verify_step "Elasticsearch resolv.conf after update"
+
+check_resolv_conf "logging-mvp-kibana-1" "1.1.1.1"
+verify_step "Kibana resolv.conf after update"
+
+show_step "7" "Final verification - Check DNS configuration"
+# 最终验证DNS配置
+echo "[INFO] 最终验证elasticsearch容器的resolv.conf..."
+docker exec logging-mvp-es-1 cat /etc/resolv.conf
+
+echo "[INFO] 最终验证kibana容器的resolv.conf..."
+docker exec logging-mvp-kibana-1 cat /etc/resolv.conf
+
+echo "[INFO] 最终dns.conf内容:"
+cat ./private/argus/etc/dns.conf
+
+verify_step "Final DNS configuration verification"
+
+show_step "8" "Cleanup - Stop all services"
+./scripts/05_down.sh
+verify_step "Service cleanup"
+
+# 清理测试文件
+rm -f ./private/argus/etc/dns.conf
+# 注：不删除update-dns.sh，因为这是真实的脚本
+
+# 计算总测试时间
+test_end_time=$(date +%s)
+total_time=$((test_end_time - test_start_time))
+
+echo ""
+echo "======================================="
+echo "🎉 DNS监控功能测试完成!"
+echo "======================================="
+echo "📊 测试总结:"
+echo "   • 总耗时: ${total_time}秒"
+echo "   • 初始DNS配置: 8.8.8.8"
+echo "   • 更新DNS配置: 1.1.1.1"
+echo "   • DNS监控脚本正常工作"
+echo "   • 容器resolv.conf自动覆盖更新成功"
+echo ""
+echo "✅ DNS自动更新功能测试通过!"
+echo ""

src/log/tests/scripts/e2e_test.sh

@@ -0,0 +1,169 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS Log System End-to-End Test"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(date +%s)
+
+# 函数：获取ES中的日志计数
+get_log_count() {
+    local train_count=$(curl -s "http://localhost:9200/train-*/_count" 2>/dev/null | grep -o '"count":[0-9]*' | cut -d':' -f2 || echo "0")
+    local infer_count=$(curl -s "http://localhost:9200/infer-*/_count" 2>/dev/null | grep -o '"count":[0-9]*' | cut -d':' -f2 || echo "0")
+    echo "$((train_count + infer_count))"
+}
+
+# 函数：等待服务就绪
+wait_for_services() {
+    echo "[INFO] Waiting for all services to be ready..."
+    local max_attempts=60
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs http://localhost:9200/_cluster/health >/dev/null 2>&1 && \
+           curl -fs http://localhost:5601/api/status >/dev/null 2>&1 && \
+           curl -fs http://localhost:2020/api/v2/metrics >/dev/null 2>&1 && \
+           curl -fs http://localhost:2021/api/v2/metrics >/dev/null 2>&1; then
+            echo "[OK] All services are ready!"
+            return 0
+        fi
+        echo "    Waiting for services... ($attempt/$max_attempts)"
+        sleep 5
+        ((attempt++))
+    done
+
+    echo "[ERROR] Services not ready after $max_attempts attempts"
+    return 1
+}
+
+# 函数：显示测试步骤
+show_step() {
+    echo ""
+    echo "🔄 Step $1: $2"
+    echo "----------------------------------------"
+}
+
+# 函数：验证步骤结果
+verify_step() {
+    if [ $? -eq 0 ]; then
+        echo "✅ $1 - SUCCESS"
+    else
+        echo "❌ $1 - FAILED"
+        exit 1
+    fi
+}
+
+# 开始端到端测试
+show_step "1" "Bootstrap - Initialize environment"
+./scripts/01_bootstrap.sh
+verify_step "Bootstrap"
+
+show_step "2" "Startup - Start all services"
+./scripts/02_up.sh
+verify_step "Service startup"
+
+# 等待服务完全就绪
+wait_for_services || exit 1
+
+# 记录发送测试数据前的日志计数
+initial_count=$(get_log_count)
+echo "[INFO] Initial log count: $initial_count"
+
+show_step "3a" "Send test data - Host01"
+./scripts/03_send_test_host01.sh
+verify_step "Test data sending (host01)"
+
+show_step "3b" "Send test data - Host02"
+./scripts/03_send_test_host02.sh
+verify_step "Test data sending (host02)"
+
+# 等待数据被处理
+echo "[INFO] Waiting for data to be processed..."
+sleep 10
+
+show_step "4" "Verify data - Query Elasticsearch"
+./scripts/04_query_es.sh
+verify_step "Data verification"
+
+# 记录发送测试数据后的日志计数
+final_count=$(get_log_count)
+echo "[INFO] Final log count: $final_count"
+
+# 验证日志数量是否增加
+if [ "$final_count" -gt "$initial_count" ]; then
+    added_logs=$((final_count - initial_count))
+    echo "✅ Log count verification - SUCCESS: Added $added_logs logs (from $initial_count to $final_count)"
+else
+    echo "❌ Log count verification - FAILED: Expected count to increase, but got $initial_count -> $final_count"
+    exit 1
+fi
+
+# 验证预期的最小日志数量（每个主机应该发送一些日志）
+expected_min_logs=4  # 至少应该有几条日志
+if [ "$final_count" -ge "$expected_min_logs" ]; then
+    echo "✅ Minimum log threshold - SUCCESS: $final_count logs (>= $expected_min_logs expected)"
+else
+    echo "❌ Minimum log threshold - FAILED: Only $final_count logs (>= $expected_min_logs expected)"
+    exit 1
+fi
+
+# 检查服务健康状态
+show_step "Health" "Check service health"
+echo "[INFO] Checking service health..."
+
+# 检查 Elasticsearch 健康状态
+es_health=$(curl -s "http://localhost:9200/_cluster/health" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
+if [ "$es_health" = "green" ] || [ "$es_health" = "yellow" ]; then
+    echo "✅ Elasticsearch health: $es_health"
+else
+    echo "❌ Elasticsearch health: $es_health"
+fi
+
+# 检查 Kibana 状态
+if curl -fs "http://localhost:5601/api/status" >/dev/null 2>&1; then
+    kb_status="available"
+    echo "✅ Kibana status: $kb_status"
+else
+    kb_status="unavailable"
+    echo "⚠️  Kibana status: $kb_status"
+fi
+
+# 检查 Fluent-Bit 指标
+fb_host01_uptime=$(curl -s "http://localhost:2020/api/v2/metrics" | grep "fluentbit_uptime" | head -1 | grep -o "[0-9]\+$" || echo "0")
+fb_host02_uptime=$(curl -s "http://localhost:2021/api/v2/metrics" | grep "fluentbit_uptime" | head -1 | grep -o "[0-9]\+$" || echo "0")
+
+if [ "$fb_host01_uptime" -gt 0 ] && [ "$fb_host02_uptime" -gt 0 ]; then
+    echo "✅ Fluent-Bit services: host01 uptime=${fb_host01_uptime}s, host02 uptime=${fb_host02_uptime}s"
+else
+    echo "⚠️  Fluent-Bit services: host01 uptime=${fb_host01_uptime}s, host02 uptime=${fb_host02_uptime}s"
+fi
+
+verify_step "Service health check"
+
+show_step "5" "Cleanup - Stop all services"
+./scripts/05_down.sh
+verify_step "Service cleanup"
+
+# 计算总测试时间
+test_end_time=$(date +%s)
+total_time=$((test_end_time - test_start_time))
+
+echo ""
+echo "======================================="
+echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
+echo "======================================="
+echo "📊 Test Summary:"
+echo "   • Initial logs: $initial_count"
+echo "   • Final logs: $final_count"
+echo "   • Added logs: $added_logs"
+echo "   • Total time: ${total_time}s"
+echo "   • ES health: $es_health"
+echo "   • Kibana status: $kb_status"
+echo "   • DNS resolv: ✅ Passed (ES domain verified)"
+echo "   • All services started and stopped successfully"
+echo ""
+echo "✅ The ARGUS log system is working correctly!"
+echo ""

src/web/.gitignore

@@ -0,0 +1,45 @@
+# Node modules
+node_modules/
+
+# Build output
+/dist
+/build
+
+# Dependency directories
+jspm_packages/
+
+# Logs
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Editor directories and files
+.idea/
+.vscode/
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?
+
+# OS generated files
+.DS_Store
+Thumbs.db
+
+# Environment variables
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# Testing
+/coverage/
+
+# Optional: service worker cache
+/.pwa-cache/
+
+# Misc
+*.log
+
+.vite/

src/web/README.md

@@ -0,0 +1,12 @@
+# Argus-web
+
+架构：React + Vite + Mantine
+
+
+## 打包部署
+根目录下运行
+```bash
+bash src/web/buld_tools/frontend/build.sh
+```
+
+

src/web/build_tools/frontend/Dockerfile

@@ -0,0 +1,91 @@
+# ========== 构建阶段 ==========
+FROM node:20 AS builder
+
+# 设置工作目录
+WORKDIR /app/src/web
+
+# 复制依赖文件并安装
+COPY src/web/package*.json ./
+
+RUN npm install
+
+# 复制源码并打包
+COPY src/web ./
+RUN npm run build
+
+# ========== 运行阶段 ==========
+FROM ubuntu:24.04
+
+USER root
+
+# 安装 nginx 和 supervisor
+RUN apt-get update && \
+    apt-get install -y nginx supervisor curl vim net-tools inetutils-ping ca-certificates passwd && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+ENV FRONTEND_BASE_PATH=/private/argus/web/frontend
+ENV ARGUS_UID=2133
+ENV ARGUS_GID=2015
+
+RUN mkdir -p ${FRONTEND_BASE_PATH} && \
+    mkdir -p /private/argus/etc
+
+# 创建 web 用户（可自定义 UID/GID）
+# 创建 web 用户组
+RUN groupadd -g ${ARGUS_GID} web
+
+# 创建 web 用户并指定组
+RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} web
+
+RUN chown -R web:web ${FRONTEND_BASE_PATH} && \
+    chown -R web:web /private/argus/etc && \
+    chown -R web:web /usr/local/bin
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+
+# 配置部署时使用的 apt 源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+    echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# 前端编译产物放到 nginx 目录
+COPY --from=builder /app/src/web/dist /usr/share/nginx/html
+
+# 复制 nginx 配置（保证 React 前端路由兼容）
+COPY src/web/build_tools/frontend/nginx.conf /etc/nginx/nginx.conf
+# COPY src/web/build_tools/frontend/conf.d/ /etc/nginx/conf.d/
+
+# 复制 supervisor 配置
+COPY src/web/build_tools/frontend/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 创建 supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+# 复制启动脚本
+COPY src/web/build_tools/frontend/start-web-supervised.sh /usr/local/bin/start-web-supervised.sh
+RUN chmod +x /usr/local/bin/start-web-supervised.sh
+
+# 复制 DNS 监控脚本
+COPY src/web/build_tools/frontend/dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+# 复制健康检查脚本
+COPY src/web/build_tools/frontend/health-check.sh /usr/local/bin/health-check.sh
+RUN chmod +x /usr/local/bin/health-check.sh
+
+# 暴露端口
+EXPOSE 80
+
+# 保持 root 用户，由 supervisor 控制 user 切换
+USER root
+
+# 以 supervisor 为入口
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

src/web/build_tools/frontend/build.sh

@@ -0,0 +1,4 @@
+docker pull node:20
+docker pull ubuntu:24.04
+docker build -f src/web/build_tools/frontend/Dockerfile -t argus-web:0.1.1 .
+rm -f argus-web-0.1.1.tar && sudo docker image save argus-web:0.1.1 > argus-web-0.1.1.tar

src/web/build_tools/frontend/dns-monitor.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# DNS监控脚本 - 每10秒检查dns.conf是否有变化
+# 如果有变化则执行update-dns.sh脚本
+
+DNS_CONF="/private/argus/etc/dns.conf"
+DNS_BACKUP="/tmp/dns.conf.backup"
+UPDATE_SCRIPT="/private/argus/etc/update-dns.sh"
+LOG_FILE="/var/log/supervisor/dns-monitor.log"
+
+# 确保日志文件存在
+touch "$LOG_FILE"
+
+log_message() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Monitor] $1" >> "$LOG_FILE"
+}
+
+log_message "DNS监控脚本启动"
+
+while true; do
+    if [ -f "$DNS_CONF" ]; then
+        if [ -f "$DNS_BACKUP" ]; then
+            # 比较文件内容
+            if ! cmp -s "$DNS_CONF" "$DNS_BACKUP"; then
+                log_message "检测到DNS配置变化"
+
+                # 更新备份文件
+                cp "$DNS_CONF" "$DNS_BACKUP"
+
+                # 执行更新脚本
+                if [ -x "$UPDATE_SCRIPT" ]; then
+                    log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                    "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                    if [ $? -eq 0 ]; then
+                        log_message "DNS更新脚本执行成功"
+                    else
+                        log_message "DNS更新脚本执行失败"
+                    fi
+                else
+                    log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+                fi
+            fi
+        else
+
+            # 第一次检测到配置文件，执行更新脚本
+            if [ -x "$UPDATE_SCRIPT" ]; then
+                log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                if [ $? -eq 0 ]; then
+                    log_message "DNS更新脚本执行成功"
+
+		    # 第一次运行，创建备份并执行更新
+		    cp "$DNS_CONF" "$DNS_BACKUP"
+		    log_message "创建DNS配置备份文件"
+
+                else
+                    log_message "DNS更新脚本执行失败"
+                fi
+            else
+                log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+            fi
+        fi
+    else
+        log_message "警告: DNS配置文件不存在: $DNS_CONF"
+    fi
+
+    sleep 10
+done

src/web/build_tools/frontend/health-check.sh

@@ -0,0 +1,16 @@
+#!/bin/bash
+set -euo pipefail
+
+URL="http://127.0.0.1:80"
+
+echo "[INFO] Starting frontend health check loop for $URL..."
+
+while true; do
+    if curl -s --max-time 5 "$URL" > /dev/null; then
+        echo "[OK] $(date '+%Y-%m-%d %H:%M:%S') Frontend is healthy"
+    else
+        echo "[ERROR] $(date '+%Y-%m-%d %H:%M:%S') Frontend health check failed"
+        exit 1
+    fi
+    sleep 10
+done

src/web/build_tools/frontend/nginx.conf

@@ -0,0 +1,56 @@
+user  web;
+worker_processes  auto;
+
+events {
+    worker_connections  1024;
+}
+
+http {
+    include       mime.types;
+    default_type  application/octet-stream;
+    sendfile      on;
+
+    # React 前端服务
+    server {
+        listen 80;
+        server_name web.argus.com;
+
+        root /usr/share/nginx/html;
+        index index.html;
+
+        # React 前端路由兼容
+        location / {
+            try_files $uri /index.html;
+        }
+    }
+
+
+    # Master 服务，需要增加 CORS 支持
+    server {
+    listen 80;
+    server_name master.argus.com;
+
+    location / {
+        proxy_pass http://master.argus.com;
+        proxy_set_header Host $host;
+        proxy_set_header X-Real-IP $remote_addr;
+        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        proxy_set_header X-Forwarded-Proto $scheme;
+
+        # CORS 支持
+        add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
+        add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
+        add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
+
+        if ($request_method = OPTIONS) {
+            add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
+            add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
+            add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
+            add_header 'Content-Length' 0;
+            add_header 'Content-Type' 'text/plain';
+            return 204;
+        }
+    }
+}
+
+}

src/web/build_tools/frontend/start-web-supervised.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting React frontend under supervisor..."
+
+DNS_DIR="/private/argus/etc"
+DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
+DOMAIN=web.argus.com
+WEB_DOMAIN_FILE="${DNS_DIR}/${DOMAIN}"
+RUNTIME_USER="${ARGUS_RUNTIME_USER:-argus}"
+RUNTIME_UID="${ARGUS_BUILD_UID:-2133}"
+RUNTIME_GID="${ARGUS_BUILD_GID:-2015}"
+
+mkdir -p "$DNS_DIR"
+chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true
+
+if [[ -x "$DNS_SCRIPT" ]]; then
+  echo "[INFO] Running update-dns.sh before master starts"
+  # 若脚本存在则执行，保证容器使用 bind 作为 DNS
+  "$DNS_SCRIPT" || echo "[WARN] update-dns.sh execution failed"
+else
+  echo "[WARN] DNS update script not found or not executable: $DNS_SCRIPT"
+fi
+
+
+# 记录容器 IP
+IP=$(ifconfig | grep -A 1 eth0 | grep inet | awk '{print $2}' || true)
+if [[ -n "${IP}" ]]; then
+  echo "current IP: ${IP}"
+  echo "${IP}" > "$WEB_DOMAIN_FILE"
+  chown "$RUNTIME_UID:$RUNTIME_GID" "$WEB_DOMAIN_FILE" 2>/dev/null || true
+else
+  echo "[WARN] Failed to detect web IP via ifconfig"
+fi
+
+echo "[INFO] Launching nginx..."
+
+# 启动 nginx 前台模式
+exec /usr/sbin/nginx -g "daemon off;"

src/web/build_tools/frontend/supervisord.conf

@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:web]
+command=/usr/local/bin/start-web-supervised.sh
+user=root
+stdout_logfile=/var/log/supervisor/web.log
+stderr_logfile=/var/log/supervisor/web_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[program:web-health]
+command=/usr/local/bin/health-check.sh
+user=web
+stdout_logfile=/var/log/supervisor/web-health.log
+stderr_logfile=/var/log/supervisor/web-health_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

src/web/build_tools/proxy/Dockerfile

@@ -0,0 +1,69 @@
+FROM ubuntu:24.04
+
+USER root
+
+# 安装 nginx 和 supervisor
+RUN apt-get update && \
+    apt-get install -y nginx supervisor curl vim net-tools inetutils-ping ca-certificates passwd && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+ENV FRONTEND_BASE_PATH=/private/argus/web/proxy
+ENV ARGUS_UID=2133
+ENV ARGUS_GID=2015
+
+RUN mkdir -p ${FRONTEND_BASE_PATH} && \
+    mkdir -p /private/argus/etc
+
+# 创建 proxy 用户（可自定义 UID/GID）
+# 创建 proxy 用户组
+RUN groupadd -g ${ARGUS_GID} web_proxy
+
+# 创建 proxy 用户并指定组
+RUN useradd -M -s /usr/sbin/nologin -u ${ARGUS_UID} -g ${ARGUS_GID} web_proxy
+
+RUN chown -R web_proxy:web_proxy ${FRONTEND_BASE_PATH} && \
+    chown -R web_proxy:web_proxy /private/argus/etc && \
+    chown -R web_proxy:web_proxy /usr/local/bin
+
+# 配置内网 apt 源 (如果指定了内网选项)
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+
+# 配置部署时使用的 apt 源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+    echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+
+# 复制 nginx 配置（保证 React 前端路由兼容）
+COPY src/web/build_tools/proxy/nginx.conf.template /etc/nginx/nginx.conf.template
+COPY src/web/build_tools/proxy/conf.d/ /etc/nginx/conf.d/
+
+# 复制 supervisor 配置
+COPY src/web/build_tools/proxy/supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 创建 supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+# 复制启动脚本
+COPY src/web/build_tools/proxy/start-proxy-supervised.sh /usr/local/bin/start-proxy-supervised.sh
+RUN chmod +x /usr/local/bin/start-proxy-supervised.sh
+
+# 复制 DNS 监控脚本
+COPY src/web/build_tools/proxy/dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+# 暴露端口
+EXPOSE 80
+
+# 保持 root 用户，由 supervisor 控制 user 切换
+USER root
+
+# 以 supervisor 为入口
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf"]

src/web/build_tools/proxy/conf.d/alert.conf

@@ -0,0 +1,8 @@
+server {
+    listen 80;
+    server_name alertmanager.alert.argus.com;
+
+    location / {
+        proxy_pass http://alertmanager.alert.argus.com:9093;
+    }
+}

src/web/build_tools/proxy/conf.d/log.conf

@@ -0,0 +1,19 @@
+# Elasticsearch
+server {
+    listen 80;
+    server_name es.log.argus.com;
+
+    location / {
+        proxy_pass http://es.log.argus.com;
+    }
+}
+
+# Kibana
+server {
+    listen 80;
+    server_name kibana.log.argus.com;
+
+    location / {
+        proxy_pass http://kibana.log.argus.com;
+    }
+}

src/web/build_tools/proxy/conf.d/master.conf

@@ -0,0 +1,27 @@
+server {
+    listen 80;
+    server_name master.argus.com;
+
+    location / {
+        # proxy_pass http://master.argus.com;
+        proxy_pass http://master.argus.com;
+        # proxy_set_header Host $host;
+        # proxy_set_header X-Real-IP $remote_addr;
+        # proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+        # proxy_set_header X-Forwarded-Proto $scheme;
+
+        # # CORS 支持
+        # add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
+        # add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
+        # add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
+
+        # if ($request_method = OPTIONS) {
+        #     add_header 'Access-Control-Allow-Origin' 'http://web.argus.com' always;
+        #     add_header 'Access-Control-Allow-Methods' 'GET, POST, PUT, DELETE, OPTIONS' always;
+        #     add_header 'Access-Control-Allow-Headers' 'Origin, Content-Type, Accept, Authorization' always;
+        #     add_header 'Content-Length' 0;
+        #     add_header 'Content-Type' 'text/plain';
+        #     return 204;
+        # }
+    }
+}

src/web/build_tools/proxy/conf.d/metric.conf

@@ -0,0 +1,19 @@
+# Prometheus
+server {
+    listen 80;
+    server_name prometheus.metric.argus.com;
+
+    location / {
+        proxy_pass http://prom.metric.argus.com;
+    }
+}
+
+# # Grafana
+# server {
+#     listen 80;
+#     server_name grafana.metric.argus.com;
+
+#     location / {
+#         proxy_pass http://grafana.metric.argus.com;
+#     }
+# }

src/web/build_tools/proxy/conf.d/web.conf

@@ -0,0 +1,8 @@
+server {
+    listen 80;
+    server_name web.argus.com;
+
+    location / {
+        proxy_pass http://web.argus.com:80;
+    }
+}

src/web/build_tools/proxy/dns-monitor.sh

@@ -0,0 +1,68 @@
+#!/bin/bash
+
+# DNS监控脚本 - 每10秒检查dns.conf是否有变化
+# 如果有变化则执行update-dns.sh脚本
+
+DNS_CONF="/private/argus/etc/dns.conf"
+DNS_BACKUP="/tmp/dns.conf.backup"
+UPDATE_SCRIPT="/private/argus/etc/update-dns.sh"
+LOG_FILE="/var/log/supervisor/dns-monitor.log"
+
+# 确保日志文件存在
+touch "$LOG_FILE"
+
+log_message() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') [DNS-Monitor] $1" >> "$LOG_FILE"
+}
+
+log_message "DNS监控脚本启动"
+
+while true; do
+    if [ -f "$DNS_CONF" ]; then
+        if [ -f "$DNS_BACKUP" ]; then
+            # 比较文件内容
+            if ! cmp -s "$DNS_CONF" "$DNS_BACKUP"; then
+                log_message "检测到DNS配置变化"
+
+                # 更新备份文件
+                cp "$DNS_CONF" "$DNS_BACKUP"
+
+                # 执行更新脚本
+                if [ -x "$UPDATE_SCRIPT" ]; then
+                    log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                    "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                    if [ $? -eq 0 ]; then
+                        log_message "DNS更新脚本执行成功"
+                    else
+                        log_message "DNS更新脚本执行失败"
+                    fi
+                else
+                    log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+                fi
+            fi
+        else
+
+            # 第一次检测到配置文件，执行更新脚本
+            if [ -x "$UPDATE_SCRIPT" ]; then
+                log_message "执行DNS更新脚本: $UPDATE_SCRIPT"
+                "$UPDATE_SCRIPT" >> "$LOG_FILE" 2>&1
+                if [ $? -eq 0 ]; then
+                    log_message "DNS更新脚本执行成功"
+
+		    # 第一次运行，创建备份并执行更新
+		    cp "$DNS_CONF" "$DNS_BACKUP"
+		    log_message "创建DNS配置备份文件"
+
+                else
+                    log_message "DNS更新脚本执行失败"
+                fi
+            else
+                log_message "警告: 更新脚本不存在或不可执行: $UPDATE_SCRIPT"
+            fi
+        fi
+    else
+        log_message "警告: DNS配置文件不存在: $DNS_CONF"
+    fi
+
+    sleep 10
+done

src/web/build_tools/proxy/nginx.conf.template

@@ -0,0 +1,36 @@
+user  web_proxy;
+worker_processes  auto;
+
+events {
+    worker_connections  1024;
+}
+
+server {
+    listen 80 default_server;
+    server_name _;
+
+    location / {
+        proxy_pass http://web.argus.com:80;
+    }
+}
+
+http {
+    include       mime.types;
+    default_type  application/octet-stream;
+    sendfile      on;
+
+    # 使用系统 resolv.conf（由 update-dns.sh 动态更新）
+    resolver __RESOLVERS__ valid=30s ipv6=off;
+
+    # 启用访问日志
+    access_log  /var/log/nginx/access.log;
+    error_log   /var/log/nginx/error.log;
+
+    # 反向代理默认头部
+    proxy_set_header Host $host;
+    proxy_set_header X-Real-IP $remote_addr;
+    proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
+    proxy_set_header X-Forwarded-Proto $scheme;
+
+    include /etc/nginx/conf.d/*.conf;
+}

src/web/build_tools/proxy/start-proxy-supervised.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting proxy under supervisor..."
+
+TEMPLATE="/etc/nginx/nginx.conf.template"
+TARGET="/etc/nginx/nginx.conf"
+DNS_CONF_PRIVATE="/private/argus/etc/dns.conf"
+DNS_CONF_SYSTEM="/etc/resolv.conf"
+DNS_DIR="/private/argus/etc"
+DNS_SCRIPT="${DNS_DIR}/update-dns.sh"
+RUNTIME_UID="${ARGUS_BUILD_UID:-2133}"
+RUNTIME_GID="${ARGUS_BUILD_GID:-2015}"
+
+mkdir -p "$DNS_DIR"
+chown -R "$RUNTIME_UID:$RUNTIME_GID" "$DNS_DIR" 2>/dev/null || true
+
+if [[ -x "$DNS_SCRIPT" ]]; then
+  echo "[INFO] Running update-dns.sh before master starts"
+  # 若脚本存在则执行，保证容器使用 bind 作为 DNS
+  "$DNS_SCRIPT" || echo "[WARN] update-dns.sh execution failed"
+else
+  echo "[WARN] DNS update script not found or not executable: $DNS_SCRIPT"
+fi
+
+# ========== 读取 DNS ==========
+if [ -f "$DNS_CONF_PRIVATE" ]; then
+  echo "从 $DNS_CONF_PRIVATE 读取 DNS 服务器..."
+  RESOLVERS=$(awk '/^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$/ {print $1}' "$DNS_CONF_PRIVATE" | tr '\n' ' ')
+fi
+
+# 如果 /private 文件不存在则 fallback
+if [ -z "${RESOLVERS:-}" ]; then
+  echo "未在 $DNS_CONF_PRIVATE 中找到有效 DNS，使用系统 /etc/resolv.conf"
+  RESOLVERS=$(awk '/^nameserver/ {print $2}' "$DNS_CONF_SYSTEM" | tr '\n' ' ')
+fi
+
+# 最后兜底：若仍为空，使用公共 DNS
+if [ -z "$RESOLVERS" ]; then
+  echo "警告: 未找到任何 DNS，使用默认 8.8.8.8"
+  RESOLVERS="8.8.8.8"
+fi
+
+echo "检测到 DNS 服务器列表: $RESOLVERS"
+
+# ========== 生成 nginx.conf ==========
+if [ -f "$TEMPLATE" ]; then
+  echo "从模板生成 nginx.conf ..."
+  sed "s|__RESOLVERS__|$RESOLVERS|" "$TEMPLATE" > "$TARGET"
+else
+  echo "错误: 找不到 nginx.conf.template ($TEMPLATE)"
+  exit 1
+fi
+
+# 打印生成结果供排查
+grep resolver "$TARGET" || true
+
+echo "[INFO] Launching nginx..."
+
+# 启动 nginx 前台模式
+exec /usr/sbin/nginx -g "daemon off;"

src/web/build_tools/proxy/supervisord.conf

@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:proxy]
+command=/usr/local/bin/start-proxy-supervised.sh
+user=root
+stdout_logfile=/var/log/supervisor/web-proxy.log
+stderr_logfile=/var/log/supervisor/web-proxy_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[program:dns-monitor]
+command=/usr/local/bin/dns-monitor.sh
+user=root
+stdout_logfile=/var/log/supervisor/dns-monitor.log
+stderr_logfile=/var/log/supervisor/dns-monitor_error.log
+autorestart=true
+startretries=3
+startsecs=5
+stopwaitsecs=10
+killasgroup=true
+stopasgroup=true
+
+[unix_http_server]
+file=/var/run/supervisor.sock
+chmod=0700
+
+[supervisorctl]
+serverurl=unix:///var/run/supervisor.sock
+
+[rpcinterface:supervisor]
+supervisor.rpcinterface_factory = supervisor.rpcinterface:make_main_rpcinterface

src/web/eslint.config.js

@@ -0,0 +1,29 @@
+import js from '@eslint/js'
+import globals from 'globals'
+import reactHooks from 'eslint-plugin-react-hooks'
+import reactRefresh from 'eslint-plugin-react-refresh'
+import { defineConfig, globalIgnores } from 'eslint/config'
+
+export default defineConfig([
+  globalIgnores(['dist']),
+  {
+    files: ['**/*.{js,jsx}'],
+    extends: [
+      js.configs.recommended,
+      reactHooks.configs['recommended-latest'],
+      reactRefresh.configs.vite,
+    ],
+    languageOptions: {
+      ecmaVersion: 2020,
+      globals: globals.browser,
+      parserOptions: {
+        ecmaVersion: 'latest',
+        ecmaFeatures: { jsx: true },
+        sourceType: 'module',
+      },
+    },
+    rules: {
+      'no-unused-vars': ['error', { varsIgnorePattern: '^[A-Z_]' }],
+    },
+  },
+])

src/web/index.html

@@ -0,0 +1,13 @@
+<!DOCTYPE html>
+<html lang="zh-CN">
+  <head>
+    <meta charset="UTF-8" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>GPU集群运维系统</title>
+    <link rel="icon" type="image/png" href="/src/assets/argus.png" />
+  </head>
+  <body>
+    <div id="root"></div>
+    <script type="module" src="/src/main.jsx"></script>
+  </body>
+</html>

src/web/package.json

@@ -0,0 +1,34 @@
+{
+  "name": "argus-web",
+  "private": true,
+  "version": "0.0.0",
+  "type": "module",
+  "scripts": {
+    "dev": "vite",
+    "build": "vite build",
+    "lint": "eslint .",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "@emotion/react": "^11.14.0",
+    "@mantine/core": "^8.3.1",
+    "@mantine/hooks": "^8.3.1",
+    "@mantine/notifications": "^8.3.1",
+    "@tabler/icons-react": "^3.34.1",
+    "react": "^19.1.1",
+    "react-dom": "^19.1.1",
+    "react-router-dom": "^7.8.2",
+    "tabler-icons-react": "^1.56.0"
+  },
+  "devDependencies": {
+    "@eslint/js": "^9.33.0",
+    "@types/react": "^19.1.10",
+    "@types/react-dom": "^19.1.7",
+    "@vitejs/plugin-react": "^5.0.0",
+    "eslint": "^9.33.0",
+    "eslint-plugin-react-hooks": "^5.2.0",
+    "eslint-plugin-react-refresh": "^0.4.20",
+    "globals": "^16.3.0",
+    "vite": "^7.1.2"
+  }
+}

src/web/public/vite.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="31.88" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 257"><defs><linearGradient id="IconifyId1813088fe1fbc01fb466" x1="-.828%" x2="57.636%" y1="7.652%" y2="78.411%"><stop offset="0%" stop-color="#41D1FF"></stop><stop offset="100%" stop-color="#BD34FE"></stop></linearGradient><linearGradient id="IconifyId1813088fe1fbc01fb467" x1="43.376%" x2="50.316%" y1="2.242%" y2="89.03%"><stop offset="0%" stop-color="#FFEA83"></stop><stop offset="8.333%" stop-color="#FFDD35"></stop><stop offset="100%" stop-color="#FFA800"></stop></linearGradient></defs><path fill="url(#IconifyId1813088fe1fbc01fb466)" d="M255.153 37.938L134.897 252.976c-2.483 4.44-8.862 4.466-11.382.048L.875 37.958c-2.746-4.814 1.371-10.646 6.827-9.67l120.385 21.517a6.537 6.537 0 0 0 2.322-.004l117.867-21.483c5.438-.991 9.574 4.796 6.877 9.62Z"></path><path fill="url(#IconifyId1813088fe1fbc01fb467)" d="M185.432.063L96.44 17.501a3.268 3.268 0 0 0-2.634 3.014l-5.474 92.456a3.268 3.268 0 0 0 3.997 3.378l24.777-5.718c2.318-.535 4.413 1.507 3.936 3.838l-7.361 36.047c-.495 2.426 1.782 4.5 4.151 3.78l15.304-4.649c2.372-.72 4.652 1.36 4.15 3.788l-11.698 56.621c-.732 3.542 3.979 5.473 5.943 2.437l1.313-2.028l72.516-144.72c1.215-2.423-.88-5.186-3.54-4.672l-25.505 4.922c-2.396.462-4.435-1.77-3.759-4.114l16.646-57.705c.677-2.35-1.37-4.583-3.769-4.113Z"></path></svg>

src/web/src/App.css

@@ -0,0 +1,42 @@
+#root {
+  max-width: 1280px;
+  margin: 0 auto;
+  padding: 2rem;
+  text-align: center;
+}
+
+.logo {
+  height: 6em;
+  padding: 1.5em;
+  will-change: filter;
+  transition: filter 300ms;
+}
+.logo:hover {
+  filter: drop-shadow(0 0 2em #646cffaa);
+}
+.logo.react:hover {
+  filter: drop-shadow(0 0 2em #61dafbaa);
+}
+
+@keyframes logo-spin {
+  from {
+    transform: rotate(0deg);
+  }
+  to {
+    transform: rotate(360deg);
+  }
+}
+
+@media (prefers-reduced-motion: no-preference) {
+  a:nth-of-type(2) .logo {
+    animation: logo-spin infinite 20s linear;
+  }
+}
+
+.card {
+  padding: 2em;
+}
+
+.read-the-docs {
+  color: #888;
+}

src/web/src/App.jsx

@@ -0,0 +1,40 @@
+import { AppShell } from "@mantine/core";
+import { Routes, Route, Navigate } from "react-router-dom";
+import Sidebar from "./components/Sidebar";
+import HeaderBar from "./components/HeaderBar";
+import Dashboard from "./pages/Dashboard";
+import NodePage from "./pages/NodePage";
+import Metrics from "./pages/Metrics";
+import Logs from "./pages/Logs";
+import Alerts from "./pages/Alerts";
+
+export default function App() {
+  return (
+    <AppShell
+      padding="md"
+      header={{ height: 60 }}
+      navbar={{ width: 240, breakpoint: "sm" }}
+    >
+      <AppShell.Header>
+        <HeaderBar />
+      </AppShell.Header>
+
+      <AppShell.Navbar>
+        <Sidebar />
+      </AppShell.Navbar>
+
+      <AppShell.Main>
+        <Routes>
+          <Route path="/" element={<Navigate to="/dashboard" replace />} />
+
+          <Route path="/dashboard" element={<Dashboard />} />
+          <Route path="/nodeInfo" element={<NodePage />} />
+          <Route path="/metrics" element={<Metrics />} />
+          <Route path="/logs" element={<Logs />} />
+          <Route path="/alerts" element={<Alerts />} />
+          <Route path="*" element={<div>404 Not Found</div>} />
+        </Routes>
+      </AppShell.Main>
+    </AppShell>
+  );
+}

src/web/src/assets/react.svg

@@ -0,0 +1 @@
+<svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" class="iconify iconify--logos" width="35.93" height="32" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 228"><path fill="#00D8FF" d="M210.483 73.824a171.49 171.49 0 0 0-8.24-2.597c.465-1.9.893-3.777 1.273-5.621c6.238-30.281 2.16-54.676-11.769-62.708c-13.355-7.7-35.196.329-57.254 19.526a171.23 171.23 0 0 0-6.375 5.848a155.866 155.866 0 0 0-4.241-3.917C100.759 3.829 77.587-4.822 63.673 3.233C50.33 10.957 46.379 33.89 51.995 62.588a170.974 170.974 0 0 0 1.892 8.48c-3.28.932-6.445 1.924-9.474 2.98C17.309 83.498 0 98.307 0 113.668c0 15.865 18.582 31.778 46.812 41.427a145.52 145.52 0 0 0 6.921 2.165a167.467 167.467 0 0 0-2.01 9.138c-5.354 28.2-1.173 50.591 12.134 58.266c13.744 7.926 36.812-.22 59.273-19.855a145.567 145.567 0 0 0 5.342-4.923a168.064 168.064 0 0 0 6.92 6.314c21.758 18.722 43.246 26.282 56.54 18.586c13.731-7.949 18.194-32.003 12.4-61.268a145.016 145.016 0 0 0-1.535-6.842c1.62-.48 3.21-.974 4.76-1.488c29.348-9.723 48.443-25.443 48.443-41.52c0-15.417-17.868-30.326-45.517-39.844Zm-6.365 70.984c-1.4.463-2.836.91-4.3 1.345c-3.24-10.257-7.612-21.163-12.963-32.432c5.106-11 9.31-21.767 12.459-31.957c2.619.758 5.16 1.557 7.61 2.4c23.69 8.156 38.14 20.213 38.14 29.504c0 9.896-15.606 22.743-40.946 31.14Zm-10.514 20.834c2.562 12.94 2.927 24.64 1.23 33.787c-1.524 8.219-4.59 13.698-8.382 15.893c-8.067 4.67-25.32-1.4-43.927-17.412a156.726 156.726 0 0 1-6.437-5.87c7.214-7.889 14.423-17.06 21.459-27.246c12.376-1.098 24.068-2.894 34.671-5.345a134.17 134.17 0 0 1 1.386 6.193ZM87.276 214.515c-7.882 2.783-14.16 2.863-17.955.675c-8.075-4.657-11.432-22.636-6.853-46.752a156.923 156.923 0 0 1 1.869-8.499c10.486 2.32 22.093 3.988 34.498 4.994c7.084 9.967 14.501 19.128 21.976 27.15a134.668 134.668 0 0 1-4.877 4.492c-9.933 8.682-19.886 14.842-28.658 17.94ZM50.35 144.747c-12.483-4.267-22.792-9.812-29.858-15.863c-6.35-5.437-9.555-10.836-9.555-15.216c0-9.322 13.897-21.212 37.076-29.293c2.813-.98 5.757-1.905 8.812-2.773c3.204 10.42 7.406 21.315 12.477 32.332c-5.137 11.18-9.399 22.249-12.634 32.792a134.718 134.718 0 0 1-6.318-1.979Zm12.378-84.26c-4.811-24.587-1.616-43.134 6.425-47.789c8.564-4.958 27.502 2.111 47.463 19.835a144.318 144.318 0 0 1 3.841 3.545c-7.438 7.987-14.787 17.08-21.808 26.988c-12.04 1.116-23.565 2.908-34.161 5.309a160.342 160.342 0 0 1-1.76-7.887Zm110.427 27.268a347.8 347.8 0 0 0-7.785-12.803c8.168 1.033 15.994 2.404 23.343 4.08c-2.206 7.072-4.956 14.465-8.193 22.045a381.151 381.151 0 0 0-7.365-13.322Zm-45.032-43.861c5.044 5.465 10.096 11.566 15.065 18.186a322.04 322.04 0 0 0-30.257-.006c4.974-6.559 10.069-12.652 15.192-18.18ZM82.802 87.83a323.167 323.167 0 0 0-7.227 13.238c-3.184-7.553-5.909-14.98-8.134-22.152c7.304-1.634 15.093-2.97 23.209-3.984a321.524 321.524 0 0 0-7.848 12.897Zm8.081 65.352c-8.385-.936-16.291-2.203-23.593-3.793c2.26-7.3 5.045-14.885 8.298-22.6a321.187 321.187 0 0 0 7.257 13.246c2.594 4.48 5.28 8.868 8.038 13.147Zm37.542 31.03c-5.184-5.592-10.354-11.779-15.403-18.433c4.902.192 9.899.29 14.978.29c5.218 0 10.376-.117 15.453-.343c-4.985 6.774-10.018 12.97-15.028 18.486Zm52.198-57.817c3.422 7.8 6.306 15.345 8.596 22.52c-7.422 1.694-15.436 3.058-23.88 4.071a382.417 382.417 0 0 0 7.859-13.026a347.403 347.403 0 0 0 7.425-13.565Zm-16.898 8.101a358.557 358.557 0 0 1-12.281 19.815a329.4 329.4 0 0 1-23.444.823c-7.967 0-15.716-.248-23.178-.732a310.202 310.202 0 0 1-12.513-19.846h.001a307.41 307.41 0 0 1-10.923-20.627a310.278 310.278 0 0 1 10.89-20.637l-.001.001a307.318 307.318 0 0 1 12.413-19.761c7.613-.576 15.42-.876 23.31-.876H128c7.926 0 15.743.303 23.354.883a329.357 329.357 0 0 1 12.335 19.695a358.489 358.489 0 0 1 11.036 20.54a329.472 329.472 0 0 1-11 20.722Zm22.56-122.124c8.572 4.944 11.906 24.881 6.52 51.026c-.344 1.668-.73 3.367-1.15 5.09c-10.622-2.452-22.155-4.275-34.23-5.408c-7.034-10.017-14.323-19.124-21.64-27.008a160.789 160.789 0 0 1 5.888-5.4c18.9-16.447 36.564-22.941 44.612-18.3ZM128 90.808c12.625 0 22.86 10.235 22.86 22.86s-10.235 22.86-22.86 22.86s-22.86-10.235-22.86-22.86s10.235-22.86 22.86-22.86Z"></path></svg>

src/web/src/components/AlertFilters.jsx

@@ -0,0 +1,38 @@
+import { Group, Select } from "@mantine/core";
+
+export function AlertFilters({ filters, setFilters, nodeOptions }) {
+  return (
+    <Group spacing="md">
+      <Select
+        label="严重性"
+        value={filters.severity}
+        onChange={(value) => setFilters((f) => ({ ...f, severity: value }))}
+        data={[
+          { value: "all", label: "全部" },
+          { value: "critical", label: "严重" },
+          { value: "warning", label: "警告" },
+          { value: "info", label: "信息" },
+        ]}
+        w={150}
+      />
+      <Select
+        label="状态"
+        value={filters.state}
+        onChange={(value) => setFilters((f) => ({ ...f, state: value }))}
+        data={[
+          { value: "all", label: "全部" },
+          { value: "active", label: "Active" },
+          { value: "resolved", label: "Resolved" },
+        ]}
+        w={150}
+      />
+      <Select
+        label="节点"
+        value={filters.instance}
+        onChange={(value) => setFilters((f) => ({ ...f, instance: value }))}
+        data={nodeOptions}
+        w={150}
+      />
+    </Group>
+  );
+}

src/web/src/components/AlertStats.jsx

@@ -0,0 +1,47 @@
+import { Card, Group, Text, Badge, Stack, Anchor } from "@mantine/core";
+import { Link } from "react-router-dom";
+
+export function AlertStats({ stats, layout = "row", title, link }) {
+  const Wrapper = layout === "row" ? Group : Stack;
+
+  return (
+    <Card withBorder radius="md" shadow="sm" p="md" mb="md">
+      {(title || link) && (
+        <Group position="apart" mb="sm">
+          {title && <Text fw={700} size="lg">{title}</Text>}
+          {link && (
+            <Anchor component={Link} to={link} size="sm" underline>
+              查看更多
+            </Anchor>
+          )}
+        </Group>
+      )}
+
+      <Wrapper spacing="xl" grow>
+        <Group spacing="xs">
+          <Badge color="gray" radius="sm" variant="filled">●</Badge>
+          <Text size="sm" fw={500}>总数</Text>
+          <Text fw={700} color="gray">{stats.total || 0}</Text>
+        </Group>
+
+        <Group spacing="xs">
+          <Badge color="red" radius="sm" variant="filled">●</Badge>
+          <Text size="sm" fw={500}>严重</Text>
+          <Text fw={700} color="red">{stats.critical || 0}</Text>
+        </Group>
+
+        <Group spacing="xs">
+          <Badge color="orange" radius="sm" variant="filled">●</Badge>
+          <Text size="sm" fw={500}>警告</Text>
+          <Text fw={700} color="orange">{stats.warning || 0}</Text>
+        </Group>
+
+        <Group spacing="xs">
+          <Badge color="blue" radius="sm" variant="filled">●</Badge>
+          <Text size="sm" fw={500}>信息</Text>
+          <Text fw={700} color="blue">{stats.info || 0}</Text>
+        </Group>
+      </Wrapper>
+    </Card>
+  );
+}

src/web/src/components/AlertTable.jsx

@@ -0,0 +1,96 @@
+import { Table, Group, ActionIcon, Button } from "@mantine/core";
+import { IconChevronUp, IconChevronDown } from "@tabler/icons-react";
+
+export function AlertTable({
+  alerts,
+  paginatedAlerts,
+  page,
+  setPage,
+  pageSize,
+  sortedAlerts,
+  sortConfig,
+  handleSort,
+  getRowColor,
+  getSeverityColor,
+  getStateBadge,
+  formatRelativeTime,
+}) {
+  const totalPages = Math.ceil(sortedAlerts.length / pageSize);
+
+  return (
+    <>
+      <Table striped highlightOnHover>
+        <Table.Thead>
+          <Table.Tr>
+            {[
+              { key: "alertname", label: "名称" },
+              { key: "instance", label: "节点" },
+              { key: "severity", label: "严重性" },
+              { key: "state", label: "状态" },
+              { key: "startsAt", label: "开始时间" },
+              { key: "endsAt", label: "结束时间" },
+              { key: "updatedAt", label: "更新时间" },
+              { key: "summary", label: "描述" },
+            ].map((col) => (
+              <Table.Th key={col.key}>
+                <Group spacing={4}>
+                  {col.label}
+                  {["severity", "startsAt", "instance"].includes(col.key) && (
+                    <ActionIcon size="xs" onClick={() => handleSort(col.key)}>
+                      {sortConfig.key === col.key && sortConfig.direction === "asc" ? (
+                        <IconChevronUp size={14} />
+                      ) : (
+                        <IconChevronDown size={14} />
+                      )}
+                    </ActionIcon>
+                  )}
+                </Group>
+              </Table.Th>
+            ))}
+          </Table.Tr>
+        </Table.Thead>
+        <Table.Tbody>
+          {paginatedAlerts.map((alert, i) => (
+            <Table.Tr key={i} style={{ backgroundColor: getRowColor(alert) }}>
+              <Table.Td>{alert.labels?.alertname || "-"}</Table.Td>
+              <Table.Td>{alert.labels?.instance || "-"}</Table.Td>
+              <Table.Td style={{ color: getSeverityColor(alert.labels?.severity) }}>
+                {alert.labels?.severity || "info"}
+              </Table.Td>
+              <Table.Td>{getStateBadge(alert.status?.state)}</Table.Td>
+              <Table.Td title={alert.startsAt || "-"}>{formatRelativeTime(alert.startsAt)}</Table.Td>
+              <Table.Td title={alert.endsAt || "-"}>
+                {alert.endsAt ? new Date(alert.endsAt).toLocaleString() : "-"}
+              </Table.Td>
+              <Table.Td title={alert.updatedAt || "-"}>{formatRelativeTime(alert.updatedAt)}</Table.Td>
+              <Table.Td>{alert.annotations?.summary || "-"}</Table.Td>
+            </Table.Tr>
+          ))}
+        </Table.Tbody>
+      </Table>
+
+      {/* 分页控件 */}
+      <Group position="apart" mt="sm">
+        <Button
+          disabled={page === 1}
+          onClick={() => setPage((p) => Math.max(1, p - 1))}
+          variant="outline"
+          size="xs"
+        >
+          上一页
+        </Button>
+        <span>
+          {page} / {totalPages}
+        </span>
+        <Button
+          disabled={page >= totalPages}
+          onClick={() => setPage((p) => p + 1)}
+          variant="outline"
+          size="xs"
+        >
+          下一页
+        </Button>
+      </Group>
+    </>
+  );
+}

src/web/src/components/EntryCard.jsx

@@ -0,0 +1,66 @@
+import { Card, Flex, Image, Text, UnstyledButton } from "@mantine/core";
+import { IconArrowRight } from "@tabler/icons-react";
+
+export default function EntryCard({ label, href, icon }) {
+  return (
+    <Card
+      shadow="sm"
+      p="lg"
+      withBorder
+      radius="md"
+      style={{
+        position: "relative",
+        aspectRatio: "1 / 1",
+        transition: "transform 0.2s, box-shadow 0.2s",
+      }}
+      sx={(theme) => ({
+        '&:hover': {
+          transform: 'translateY(-4px)',
+          boxShadow: theme.shadows.md,
+        },
+      })}
+    >
+      {/* 图标 + 标题 居中 */}
+      <Flex
+        direction="column"
+        align="center"
+        justify="center"
+        style={{ flex: 1, textAlign: "center", gap: "12px", height: "100%" }}
+      >
+        <Image src={icon} alt={label} width={48} height={48} fit="contain" />
+        <Text fw={600}>{label}</Text>
+      </Flex>
+
+      {/* 悬浮圆形箭头按钮 + 动画效果 */}
+      <UnstyledButton
+        component="a"
+        href={href}
+        target="_blank"
+        rel="noopener noreferrer"
+        style={{
+          position: "absolute",
+          bottom: 16,
+          right: 16,
+          width: 40,
+          height: 40,
+          borderRadius: "50%",
+          display: "flex",
+          alignItems: "center",
+          justifyContent: "center",
+          backgroundColor: "rgba(0, 0, 0, 0.05)",
+          transition: "background-color 0.2s, transform 0.2s",
+        }}
+        onMouseEnter={(e) => {
+          e.currentTarget.style.backgroundColor = "rgba(0, 0, 0, 0.15)";
+          e.currentTarget.style.transform = "translateX(4px)";
+        }}
+        onMouseLeave={(e) => {
+          e.currentTarget.style.backgroundColor = "rgba(0, 0, 0, 0.05)";
+          e.currentTarget.style.transform = "translateX(0)";
+        }}
+      >
+        <IconArrowRight size={18} />
+      </UnstyledButton>
+    </Card>
+  );
+}

src/web/src/components/HeaderBar.jsx

@@ -0,0 +1,13 @@
+import { Group, Text } from "@mantine/core";
+import { SystemIcon } from "../components/SystemIcon";
+
+export default function HeaderBar() {
+  return (
+    <Group justify="space-between" h="100%" px="md">
+      <Group spacing="sm" align="center">
+        <SystemIcon size={32} />
+        <Text fw={700}>GPU 集群运维系统</Text>
+      </Group>
+    </Group>
+  );
+}

src/web/src/components/HealthCard.jsx

@@ -0,0 +1,62 @@
+import { Card, Group, Text, RingProgress } from "@mantine/core";
+
+// 给一些常见状态定义颜色，没定义的就用 gray
+const statusColors = {
+  healthy: "green",
+  warning: "yellow",
+  error: "red",
+  online: "green",
+  offline: "gray",
+};
+
+export function HealthCard({ health }) {
+  const totalNodes = health?.total || 0;
+  const stats = health?.status_statistics || [];
+
+  // 计算环形图 sections
+  const sections = stats.map((s) => ({
+    value: (s.count / totalNodes) * 100,
+    color: statusColors[s.status] || "gray",
+  }));
+
+  // 计算一个主展示百分比（这里沿用原来的逻辑，用 online 或 healthy 优先）
+  const mainStatus = stats.find(
+    (s) => s.status === "online" || s.status === "healthy"
+  );
+  const mainPercent = mainStatus
+    ? ((mainStatus.count / totalNodes) * 100).toFixed(1)
+    : "0.0";
+
+  return (
+    <Card shadow="sm" radius="md" p="lg">
+      <Text fw={700} size="lg" mb="md">节点健康状态</Text>
+
+      <Group spacing="xl" align="center">
+        <RingProgress
+          size={140}
+          thickness={14}
+          sections={sections}
+          label={
+            <Text fw={700} ta="center" size="lg">
+              {mainPercent}%
+            </Text>
+          }
+        />
+
+        <div style={{ display: "flex", flexDirection: "column", justifyContent: "center", gap: 8 }}>
+          {stats.map((s, idx) => (
+            <div
+              key={idx}
+              style={{ display: "flex", justifyContent: "space-between", width: 140 }}
+            >
+              <Text size="sm" color={statusColors[s.status] || "gray"}>
+                {s.status}
+              </Text>
+              <Text fw={600}>{s.count}</Text>
+            </div>
+          ))}
+        </div>
+      </Group>
+    </Card>
+  );
+}

src/web/src/components/NodeConfigCard.jsx

@@ -0,0 +1,150 @@
+import { useState, useEffect } from "react";
+import { Card, Text, Group, TextInput, Stack, ActionIcon } from "@mantine/core";
+import { IconEdit, IconX, IconCheck, IconPlus, IconTrash } from "@tabler/icons-react";
+import { apiRequest } from "../config/request";
+import { MASTER_API } from "../config/api";
+
+export default function NodeConfigCard({ nodeId, config = {}, onSaved }) {
+  const [editing, setEditing] = useState(false);
+  const [configList, setConfigList] = useState([]);
+  const [newKey, setNewKey] = useState("");
+  const [newValue, setNewValue] = useState("");
+  const [saving, setSaving] = useState(false);
+
+  useEffect(() => {
+    const arr = Object.entries(config || {});
+    setConfigList(arr);
+  }, [config]);
+
+  const removeConfig = (index) => {
+    setConfigList((prev) => prev.filter((_, i) => i !== index));
+  };
+
+  const updateConfig = (index, key, value) => {
+    setConfigList((prev) =>
+      prev.map((item, i) => (i === index ? [key, value] : item))
+    );
+  };
+
+  const addConfig = () => {
+    if (newKey && !configList.find(([k]) => k === newKey)) {
+      setConfigList((prev) => [...prev, [newKey, newValue]]);
+      setNewKey("");
+      setNewValue("");
+    }
+  };
+
+  const handleSave = async () => {
+    setSaving(true);
+    try {
+      let finalList = [...configList];
+      // 如果有未点击“+”的新配置，补充进去
+      if (newKey && !finalList.find(([k]) => k === newKey)) {
+        finalList = [...finalList, [newKey, newValue]];
+        setNewKey("");
+        setNewValue("");
+      }
+
+      const configObj = Object.fromEntries(finalList);
+
+      await apiRequest(MASTER_API.CONFIG(nodeId), {
+        method: "PUT",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ config: configObj }),
+      });
+
+      setConfigList(finalList); // 更新 state，保持 UI 同步
+      setEditing(false);
+      onSaved && onSaved();
+    } finally {
+      setSaving(false);
+    }
+  };
+
+
+  return (
+    <Card shadow="sm" radius="md" withBorder>
+      <Group position="apart" mb="sm">
+        <Text fw={600}>配置信息</Text>
+        <Group spacing="xs">
+          {editing ? (
+            <>
+              <ActionIcon
+                color="green"
+                size="sm"
+                loading={saving}
+                onClick={handleSave}
+              >
+                <IconCheck size={16} />
+              </ActionIcon>
+              <ActionIcon color="red" size="sm" onClick={() => setEditing(false)}>
+                <IconX size={16} />
+              </ActionIcon>
+            </>
+          ) : (
+            <ActionIcon color="blue" size="sm" onClick={() => setEditing(true)}>
+              <IconEdit size={16} />
+            </ActionIcon>
+          )}
+        </Group>
+      </Group>
+
+      {editing ? (
+        <Stack spacing="xs">
+          {configList.map(([key, value], idx) => (
+            <Group key={idx} spacing="xs">
+              <TextInput
+                placeholder="Key"
+                value={key}
+                onChange={(e) => updateConfig(idx, e.target.value, value)}
+              />
+              <TextInput
+                placeholder="Value"
+                value={value}
+                onChange={(e) => updateConfig(idx, key, e.target.value)}
+              />
+              <ActionIcon color="red" onClick={() => removeConfig(idx)}>
+                <IconTrash size={16} />
+              </ActionIcon>
+            </Group>
+          ))}
+          <Group spacing="xs">
+            <TextInput
+              placeholder="新增 Key"
+              value={newKey}
+              onChange={(e) => setNewKey(e.target.value)}
+            />
+            <TextInput
+              placeholder="新增 Value"
+              value={newValue}
+              onChange={(e) => setNewValue(e.target.value)}
+              onKeyDown={(e) => {
+                if (e.key === "Enter") {
+                  e.preventDefault();
+                  addConfig();
+                }
+              }}
+            />
+
+            <ActionIcon color="blue" onClick={addConfig}>
+              <IconPlus size={16} />
+            </ActionIcon>
+          </Group>
+        </Stack>
+      ) : (
+        <Stack spacing="xs">
+          {configList.length > 0 ? (
+            configList.map(([key, value], idx) => (
+              <Group key={idx} spacing="xs">
+                <Text fw={500}>{key}:</Text>
+                <Text>{String(value)}</Text>
+              </Group>
+            ))
+          ) : (
+            <Text c="dimmed">暂无配置</Text>
+          )}
+        </Stack>
+      )}
+    </Card>
+  );
+}

src/web/src/components/NodeDetailDrawer.jsx

@@ -0,0 +1,131 @@
+import { useState, useEffect } from "react"; 
+import {
+  Drawer,
+  Text,
+  Loader,
+  Center,
+  ScrollArea,
+  Group,
+  Divider,
+  ThemeIcon,
+  Stack,
+  ActionIcon,
+} from "@mantine/core";
+import { IconRefresh } from "@tabler/icons-react";
+import { healthStatus } from "../config/status";
+import { apiRequest } from "../config/request";
+import { MASTER_API } from "../config/api";
+
+import NodeConfigCard from "./NodeConfigCard";
+import NodeLabelCard from "./NodeLabelCard";
+import NodeMetaCard from "./NodeMetaCard";
+import NodeHealthCard from "./NodeHealthCard";
+
+export default function NodeDetailDrawer({ opened, nodeId, onClose }) {
+  const [node, setNode] = useState(null);
+  const [loading, setLoading] = useState(false);
+
+  const fetchNodeDetail = async (id) => {
+    if (!id) return;
+    setLoading(true);
+    try {
+      const res = await apiRequest(MASTER_API.DETAIL(id));
+      setNode(res);
+    } finally {
+      setLoading(false);
+    }
+  };
+
+  useEffect(() => {
+    if (opened && nodeId) fetchNodeDetail(nodeId);
+  }, [opened, nodeId]);
+
+  return (
+    <Drawer
+      opened={opened}
+      onClose={onClose}
+      position="right"
+      size="lg"
+      title="节点详情"
+      padding="lg"
+      overlayProps={{ backgroundOpacity: 0.4, blur: 4 }}
+    >
+      {loading && !node ? (
+        <Center h={200}>
+          <Loader size="sm" />
+        </Center>
+      ) : node ? (
+        <div style={{ height: "90vh", display: "flex", flexDirection: "column" }}>
+          {/* 固定头部基础信息 */}
+          <div
+            style={{
+              position: "sticky",
+              top: 0,
+              background: "white",
+              zIndex: 10,
+              paddingBottom: 8,
+            }}
+          >
+            <Group spacing="sm" align="center" position="apart">
+              <Group spacing="sm" align="center">
+                <ThemeIcon
+                  size="lg"
+                  radius="xl"
+                  color={healthStatus(node.status).color}
+                  variant="light"
+                >
+                  {healthStatus(node.status).icon}
+                </ThemeIcon>
+
+                <Text fw={700} size="xl">{node.name}</Text>
+                <Text c="dimmed">{node.type}</Text>
+                <Text c={healthStatus(node.status).color}>{node.status}</Text>
+                <Text c="dimmed" size="sm">
+                  最近上报时间: {new Date(node.last_report).toLocaleString()}
+                </Text>
+              </Group>
+
+              {/* 刷新按钮固定在右侧 */}
+              <ActionIcon
+                color="blue"
+                variant="light"
+                onClick={() => fetchNodeDetail(node.id)}
+                disabled={loading}
+              >
+                <IconRefresh size={18} />
+              </ActionIcon>
+            </Group>
+
+            <Divider my="sm" />
+          </div>
+
+          {/* 滚动内容 */}
+          <ScrollArea style={{ flex: 1 }}>
+            <Stack spacing="md">
+              {/* 配置信息 */}
+              <NodeConfigCard nodeId={node.id} config={node.config || {}} onSaved={() => fetchNodeDetail(node.id)} />
+
+              {/* 标签信息 */}
+              <NodeLabelCard nodeId={node.id} labels={Array.isArray(node.label) ? node.label : []} onSaved={() => fetchNodeDetail(node.id)} />
+
+              {/* 元数据 */}
+              <NodeMetaCard node={node} />
+
+              {/* 健康信息 */}
+              <NodeHealthCard node={node} />
+
+              {/* 其他基础信息展示 */}
+              <Stack spacing="xs">
+                <Text fw={500}>注册时间: <Text span c="dimmed">{new Date(node.register_time).toLocaleString()}</Text></Text>
+                <Text fw={500}>最近上报时间: <Text span c="dimmed">{new Date(node.last_report).toLocaleString()}</Text></Text>
+                <Text fw={500}>最后更新时间: <Text span c="dimmed">{new Date(node.last_updated).toLocaleString()}</Text></Text>
+              </Stack>
+            </Stack>
+          </ScrollArea>
+        </div>
+      ) : (
+        <Text c="dimmed">暂无数据</Text>
+      )}
+    </Drawer>
+  );
+}