dev_1.0.0_yuyr 完成 log和bind模块开发部署测试 (#8)

- [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>
2025-09-22 16:39:38 +08:00
parent 26e1c964ed
commit 8a38d3d0b2
48 changed files with 2744 additions and 0 deletions
--- a/src/log/.gitignore
+++ b/src/log/.gitignore
@@ -0,0 +1,5 @@
+
+private/
+
+
+images/
--- a/src/log/README.md
+++ b/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
+
--- a/src/log/elasticsearch/build/Dockerfile
+++ b/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"]
--- a/src/log/elasticsearch/build/dns-monitor.sh
+++ b/src/log/elasticsearch/build/dns-monitor.sh
@@ -0,0 +1 @@
+../../../bind/build/dns-monitor.sh
--- a/src/log/elasticsearch/build/start-es-supervised.sh
+++ b/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
--- a/src/log/elasticsearch/build/supervisord.conf
+++ b/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
--- a/src/log/fluent-bit/build/etc/fluent-bit.conf
+++ b/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
--- a/src/log/fluent-bit/build/etc/inject_labels.lua
+++ b/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
--- a/src/log/fluent-bit/build/etc/inputs.d/10-train.conf
+++ b/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
--- a/src/log/fluent-bit/build/etc/inputs.d/20-infer.conf
+++ b/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
--- a/src/log/fluent-bit/build/etc/outputs.d/10-es.conf
+++ b/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                ${ES_PORT}
+    Logstash_Format     On
+    Logstash_Prefix     infer
+    Replace_Dots        On
+    Generate_ID         On
+    Retry_Limit         False
+    Suppress_Type_Name  On
--- a/src/log/fluent-bit/build/etc/parsers.conf
+++ b/src/log/fluent-bit/build/etc/parsers.conf
@@ -0,0 +1,27 @@
+[MULTILINE_PARSER]
+    Name   python
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^\d{4}-\d{2}-\d{2}[\sT]/"  "cont"
+    Rule   "cont"         "/^\s+|^Traceback|^\tat\s+/" "cont"
+
+[MULTILINE_PARSER]
+    Name   go
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^[0-9]{4}\/[0-9]{2}\/[0-9]{2}/" "cont"
+    Rule   "cont"         "/^\s+|^\t/" "cont"
+
+[MULTILINE_PARSER]
+    Name   java
+    Type   regex
+    Flush  2
+    Rule   "start_state"  "/^\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2}/" "cont"
+    Rule   "cont"         "/^\s+at\s+|^\t.../" "cont"
+
+[PARSER]
+    Name   timestamp_parser
+    Format regex
+    Regex  ^(?<timestamp>\d{4}-\d{2}-\d{2} \d{2}:\d{2}:\d{2})\s+(?<level>\w+)\s+(?<message>.*)$
+    Time_Key    timestamp
+    Time_Format %Y-%m-%d %H:%M:%S
--- a/src/log/fluent-bit/build/packages/fluent-bit_3.1.9_amd64.deb
+++ b/src/log/fluent-bit/build/packages/fluent-bit_3.1.9_amd64.deb
--- a/src/log/fluent-bit/build/start-fluent-bit.sh
+++ b/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
--- a/src/log/kibana/build/Dockerfile
+++ b/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"]
--- a/src/log/kibana/build/dns-monitor.sh
+++ b/src/log/kibana/build/dns-monitor.sh
@@ -0,0 +1 @@
+../../../bind/build/dns-monitor.sh
--- a/src/log/kibana/build/kibana-post-start.sh
+++ b/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
--- a/src/log/kibana/build/start-kibana-supervised.sh
+++ b/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
--- a/src/log/kibana/build/supervisord.conf
+++ b/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
--- a/src/log/tests/docker-compose.yml
+++ b/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
+
--- a/src/log/tests/scripts/01_bootstrap.sh
+++ b/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"
--- a/src/log/tests/scripts/02_up.sh
+++ b/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"
--- a/src/log/tests/scripts/03_send_test_host01.sh
+++ b/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"
--- a/src/log/tests/scripts/03_send_test_host02.sh
+++ b/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 "$container_name" sh -c "printf '%s INFO [host02] inference completed batch=6 latency=0.8s\n' \"\$(date '+%F %T')\" >> /logs/infer/infer-demo.log"
+
+echo "[OK] 已通过docker exec写入测试日志到 host02 容器内："
+echo " - /logs/train/train-demo.log"
+echo " - /logs/infer/infer-demo.log"
--- a/src/log/tests/scripts/04_query_es.sh
+++ b/src/log/tests/scripts/04_query_es.sh
@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -euo pipefail
+ES="${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
--- a/src/log/tests/scripts/05_down.sh
+++ b/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 "$0")/.."
+if [ -d "private" ]; then
+    # 删除private目录及其所有内容
+    rm -rf private
+    echo "[OK] 已清理private目录"
+else
+    echo "[INFO] private目录不存在，无需清理"
+fi
--- a/src/log/tests/scripts/06_dns_test.sh
+++ b/src/log/tests/scripts/06_dns_test.sh
@@ -0,0 +1,208 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS DNS监控功能测试"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(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: ${total_time}秒"
+echo "   • 初始DNS配置: 8.8.8.8"
+echo "   • 更新DNS配置: 1.1.1.1"
+echo "   • DNS监控脚本正常工作"
+echo "   • 容器resolv.conf自动覆盖更新成功"
+echo ""
+echo "✅ DNS自动更新功能测试通过!"
+echo ""
--- a/src/log/tests/scripts/e2e_test.sh
+++ b/src/log/tests/scripts/e2e_test.sh
@@ -0,0 +1,169 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS Log System End-to-End Test"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(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 ""