Merge branch 'dev_1.0.0_xuxt' into dev_1.0.0_xuxt_2

Co-authored-by: sundapeng.sdp <sundapeng@hashdata.cn>
Reviewed-on: #27
Reviewed-by: yuyr <yuyr@zgclab.edu.cn>
Reviewed-by: xuxt <xuxt@zgclab.edu.cn>

.gitignore

@@ -0,0 +1 @@
+.idea/

README.md

@@ -5,3 +5,10 @@
 项目文档：【腾讯文档】GPU集群运维系统
 https://docs.qq.com/doc/DQUxDdmhIZ1dpeERk
 
+## 构建账号配置
+
+镜像构建和运行账号的 UID/GID 可通过 `configs/build_user.conf` 配置，详细说明见 `doc/build-user-config.md`。
+
+## 本地端口占用提示
+
+如需运行 BIND 模块端到端测试且宿主机 53 端口已占用，可通过环境变量 `HOST_DNS_PORT`（默认 1053）指定对外映射端口，例如 `HOST_DNS_PORT=12053 ./scripts/00_e2e_test.sh`。

build/build_images.sh

@@ -10,6 +10,7 @@ Usage: $0 [OPTIONS]
 Options:
   --intranet        Use intranet mirror for log/bind builds
   --master-offline  Build master offline image (requires src/master/offline_wheels.tar.gz)
+  --no-cache        Build all images without using Docker layer cache
   -h, --help        Show this help message
 
 Examples:
@@ -21,7 +22,9 @@ EOF
 }
 
 use_intranet=false
+build_master=true
 build_master_offline=false
+no_cache=false
 
 while [[ $# -gt 0 ]]; do
   case $1 in
@@ -29,10 +32,19 @@ while [[ $# -gt 0 ]]; do
       use_intranet=true
       shift
       ;;
+    --master)
+      build_master=true
+      shift
+      ;;
     --master-offline)
+      build_master=true
       build_master_offline=true
       shift
       ;;
+    --no-cache)
+      no_cache=true
+      shift
+      ;;
     -h|--help)
       show_help
       exit 0
@@ -59,6 +71,10 @@ cd "$root"
 load_build_user
 build_args+=("--build-arg" "ARGUS_BUILD_UID=${ARGUS_BUILD_UID}" "--build-arg" "ARGUS_BUILD_GID=${ARGUS_BUILD_GID}")
 
+if [[ "$no_cache" == true ]]; then
+  build_args+=("--no-cache")
+fi
+
 master_root="$root/src/master"
 master_offline_tar="$master_root/offline_wheels.tar.gz"
 master_offline_dir="$master_root/offline_wheels"
@@ -142,11 +158,26 @@ fi
 
 echo ""
 
-if [[ "$build_master_offline" == true ]]; then
+if [[ "$build_master" == true ]]; then
-  echo "🏗️  Building master offline image"
+  echo ""
+  echo "🔄 Building Master image..."
   pushd "$master_root" >/dev/null
-  if ./scripts/build_images.sh --offline --tag argus-master:offline; then
+  master_args=("--tag" "argus-master:latest")
-    images_built+=("argus-master:offline")
+  if [[ "$use_intranet" == true ]]; then
+    master_args+=("--intranet")
+  fi
+  if [[ "$build_master_offline" == true ]]; then
+    master_args+=("--offline")
+  fi
+  if [[ "$no_cache" == true ]]; then
+    master_args+=("--no-cache")
+  fi
+  if ./scripts/build_images.sh "${master_args[@]}"; then
+    if [[ "$build_master_offline" == true ]]; then
+      images_built+=("argus-master:offline")
+    else
+      images_built+=("argus-master:latest")
+    fi
   else
     build_failed=true
   fi

src/agent/.gitignore

@@ -1,3 +1,5 @@
 build/
 *.egg-info/
 __pycache__/
+
+.env

src/agent/README.md

@@ -34,6 +34,18 @@ Agent 不再依赖配置文件；所有参数均由环境变量与主机名推
 | `MASTER_ENDPOINT` | 是 | N/A | Master 基础地址，可写 `http://host:3000` 或 `host:3000`（自动补全 `http://`）。 |
 | `REPORT_INTERVAL_SECONDS` | 否 | `60` | 状态上报间隔（秒）。必须为正整数。 |
 | `AGENT_HOSTNAME` | 否 | `$(hostname)` | 覆盖容器内主机名，便于测试或特殊命名需求。 |
+| `AGENT_ENV` | 否 | 来源于主机名 | 运行环境标识（如 `dev`、`prod`）。与 `AGENT_USER`、`AGENT_INSTANCE` 必须同时设置。 |
+| `AGENT_USER` | 否 | 来源于主机名 | 归属用户或团队标识。与 `AGENT_ENV`、`AGENT_INSTANCE` 必须同时设置。 |
+| `AGENT_INSTANCE` | 否 | 来源于主机名 | 实例编号或别名。与 `AGENT_ENV`、`AGENT_USER` 必须同时设置。 |
+
+主机名与元数据的解析优先级：
+
+1. 若设置 `AGENT_ENV` / `AGENT_USER` / `AGENT_INSTANCE` 且全部存在，则直接使用这些值。
+2. 否则检查历史 `node.json`（注册成功后由 Master 返回的信息），若包含 `env` / `user` / `instance` 则沿用。
+3. 若以上均不可用，则按历史约定从主机名解析 `env-user-instance` 前缀。
+4. 如果仍无法得到完整结果，Agent 启动会失败并提示需要提供上述环境变量。
+
+> 提示：在首次部署时需确保环境变量或主机名能够提供完整信息。完成注册后，Agent 会把 Master 返回的元数据写入 `node.json`，后续重启无需再次提供环境变量就能保持一致性。
 
 派生路径：
 

src/agent/app/collector.py

@@ -18,13 +18,12 @@ _HOSTNAME_PATTERN = re.compile(r"^([^-]+)-([^-]+)-([^-]+)-.*$")
 def collect_metadata(config: AgentConfig) -> Dict[str, Any]:
     """汇总节点注册需要的静态信息。"""
     hostname = config.hostname
-    env, user, instance = _parse_hostname(hostname)
     meta = {
         "hostname": hostname,
         "ip": _detect_ip_address(),
-        "env": env,
+        "env": config.environment,
-        "user": user,
+        "user": config.user,
-        "instance": instance,
+        "instance": config.instance,
         "cpu_number": _detect_cpu_count(),
         "memory_in_bytes": _detect_memory_bytes(),
         "gpu_number": _detect_gpu_count(),

src/agent/app/config.py

@@ -6,14 +6,21 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Final
 
+from .state import load_node_state
 from .version import VERSION
+from .log import get_logger
 
 DEFAULT_REPORT_INTERVAL_SECONDS: Final[int] = 60
 
+LOGGER = get_logger("argus.agent.config")
+
 
 @dataclass(frozen=True)
 class AgentConfig:
     hostname: str
+    environment: str
+    user: str
+    instance: str
     node_file: str
     version: str
     master_endpoint: str
@@ -47,11 +54,68 @@ def _resolve_hostname() -> str:
     return os.environ.get("AGENT_HOSTNAME") or socket.gethostname()
 
 
+def _load_metadata_from_state(node_file: str) -> tuple[str, str, str] | None:
+    state = load_node_state(node_file)
+    if not state:
+        return None
+
+    meta = state.get("meta_data") or {}
+    env = meta.get("env") or state.get("env")
+    user = meta.get("user") or state.get("user")
+    instance = meta.get("instance") or state.get("instance")
+
+    if env and user and instance:
+        LOGGER.debug("Metadata resolved from node state", extra={"node_file": node_file})
+        return env, user, instance
+
+    LOGGER.warning(
+        "node.json missing metadata fields; ignoring",
+        extra={"node_file": node_file, "meta_data": meta},
+    )
+    return None
+
+
+def _resolve_metadata_fields(hostname: str, node_file: str) -> tuple[str, str, str]:
+    env = os.environ.get("AGENT_ENV")
+    user = os.environ.get("AGENT_USER")
+    instance = os.environ.get("AGENT_INSTANCE")
+
+    if env and user and instance:
+        return env, user, instance
+
+    if any([env, user, instance]):
+        LOGGER.warning(
+            "Incomplete metadata environment variables; falling back to persisted metadata",
+            extra={
+                "has_env": bool(env),
+                "has_user": bool(user),
+                "has_instance": bool(instance),
+            },
+        )
+
+    state_metadata = _load_metadata_from_state(node_file)
+    if state_metadata is not None:
+        return state_metadata
+
+    from .collector import _parse_hostname  # Local import to avoid circular dependency
+
+    env, user, instance = _parse_hostname(hostname)
+
+    if not all([env, user, instance]):
+        raise ValueError(
+            "Failed to determine metadata fields; set AGENT_ENV/USER/INSTANCE or use supported hostname pattern"
+        )
+
+    return env, user, instance
+
+
 def load_config() -> AgentConfig:
     """从环境变量推导配置，移除了外部配置文件依赖。"""
 
     hostname = _resolve_hostname()
     node_file = f"/private/argus/agent/{hostname}/node.json"
+    environment, user, instance = _resolve_metadata_fields(hostname, node_file)
+
     health_dir = f"/private/argus/agent/{hostname}/health/"
 
     master_endpoint_env = os.environ.get("MASTER_ENDPOINT")
@@ -66,6 +130,9 @@ def load_config() -> AgentConfig:
 
     return AgentConfig(
         hostname=hostname,
+        environment=environment,
+        user=user,
+        instance=instance,
         node_file=node_file,
         version=VERSION,
         master_endpoint=master_endpoint,

src/agent/tests/docker-compose.yml

@@ -1,19 +1,19 @@
 services:
   bind:
-    image: ${BIND_IMAGE_TAG:-argus-bind9:e2e}
+    image: ${BIND_IMAGE_TAG:-argus-bind9:latest}
     container_name: argus-bind-agent-e2e
     volumes:
       - ./private:/private
-    restart: unless-stopped
     networks:
       default:
         ipv4_address: 172.28.0.2
     environment:
       - "ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}"
       - "ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}"
+    restart: always
 
   master:
-    image: argus-master:dev
+    image: argus-master:latest
     container_name: argus-master-agent-e2e
     depends_on:
       - bind
@@ -32,9 +32,10 @@ services:
     networks:
       default:
         ipv4_address: 172.28.0.10
+    restart: always
 
   agent:
-    image: ubuntu:24.04
+    image: ubuntu:22.04
     container_name: argus-agent-e2e
     hostname: dev-e2euser-e2einst-pod-0
     depends_on:
@@ -57,6 +58,37 @@ services:
     networks:
       default:
         ipv4_address: 172.28.0.20
+    restart: always
+
+  agent_env:
+    image: ubuntu:22.04
+    container_name: argus-agent-env-e2e
+    hostname: host_abc
+    depends_on:
+      - master
+      - bind
+    environment:
+      - MASTER_ENDPOINT=http://master.argus.com:3000
+      - REPORT_INTERVAL_SECONDS=2
+      - AGENT_ENV=prod
+      - AGENT_USER=ml
+      - AGENT_INSTANCE=node-3
+      - AGENT_HOSTNAME=host_abc
+      - "ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}"
+      - "ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}"
+    volumes:
+      - ./private/argus/agent/host_abc:/private/argus/agent/host_abc
+      - ./private/argus/agent/host_abc/health:/private/argus/agent/host_abc/health
+      - ./private/argus/etc:/private/argus/etc
+      - ../dist/argus-agent:/usr/local/bin/argus-agent:ro
+      - ./scripts/agent_entrypoint.sh:/usr/local/bin/agent-entrypoint.sh:ro
+      - ../scripts/agent_deployment_verify.sh:/usr/local/bin/agent_deployment_verify.sh:ro
+    entrypoint:
+      - /usr/local/bin/agent-entrypoint.sh
+    networks:
+      default:
+        ipv4_address: 172.28.0.21
+    restart: always
 
 networks:
   default:

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

@@ -7,10 +7,10 @@ SCRIPTS=(
   "02_up.sh"
   "03_wait_and_assert_registration.sh"
   "04_write_health_files.sh"
-  "08_verify_agent.sh"
+  "05_verify_agent.sh"
-  "05_assert_status_on_master.sh"
+  "06_assert_status_on_master.sh"
-  "06_restart_agent_and_reregister.sh"
+  "07_restart_agent_and_reregister.sh"
-  "07_down.sh"
+  "08_down.sh"
 )
 
 for script in "${SCRIPTS[@]}"; do

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

@@ -15,9 +15,17 @@ AGENT_HEALTH_DIR="$PRIVATE_ROOT/argus/agent/$AGENT_HOSTNAME/health"
 MASTER_PRIVATE_DIR="$PRIVATE_ROOT/argus/master"
 METRIC_PRIVATE_DIR="$PRIVATE_ROOT/argus/metric/prometheus"
 DNS_DIR="$PRIVATE_ROOT/argus/etc"
-BIND_IMAGE_TAG="${BIND_IMAGE_TAG:-argus-bind9:e2e}"
+BIND_IMAGE_TAG="${BIND_IMAGE_TAG:-argus-bind9:latest}"
 BIND_ROOT="$(cd "$MASTER_ROOT/../bind" && pwd)"
 
+ensure_image() {
+  local image="$1"
+  if ! docker image inspect "$image" >/dev/null 2>&1; then
+    echo "[ERROR] Docker image '$image' 未找到，请先运行统一构建脚本 (例如 ./build/build_images.sh) 生成所需镜像" >&2
+    exit 1
+  fi
+}
+
 mkdir -p "$AGENT_CONFIG_DIR"
 mkdir -p "$AGENT_HEALTH_DIR"
 mkdir -p "$MASTER_PRIVATE_DIR"
@@ -35,9 +43,8 @@ else
   echo "[WARN] bind update script missing at $BIND_ROOT/build/update-dns.sh"
 fi
 
-pushd "$MASTER_ROOT" >/dev/null
+ensure_image "argus-master:latest"
-./scripts/build_images.sh --tag argus-master:dev
+ensure_image "$BIND_IMAGE_TAG"
-popd >/dev/null
 
 AGENT_BINARY="$AGENT_ROOT/dist/argus-agent"
 
@@ -50,11 +57,6 @@ if [[ ! -x "$AGENT_BINARY" ]]; then
   exit 1
 fi
 
-# 中文提示：构建测试专用 bind9 镜像，确保解析服务可用
-pushd "$REPO_ROOT" >/dev/null
-docker build -f src/bind/build/Dockerfile -t "$BIND_IMAGE_TAG" .
-popd >/dev/null
-
 echo "$AGENT_BINARY" > "$TMP_ROOT/agent_binary_path"
 echo "$BIND_IMAGE_TAG" > "$TMP_ROOT/bind_image_tag"
 

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

@@ -28,7 +28,7 @@ if [[ ! -x "$AGENT_BINARY" ]]; then
   exit 1
 fi
 
-BIND_IMAGE_TAG_VALUE="argus-bind9:e2e"
+BIND_IMAGE_TAG_VALUE="argus-bind9:latest"
 if [[ -f "$TMP_ROOT/bind_image_tag" ]]; then
   BIND_IMAGE_TAG_VALUE="$(cat "$TMP_ROOT/bind_image_tag")"
 fi
@@ -41,7 +41,7 @@ compose() {
   fi
 }
 
-docker container rm -f argus-agent-e2e argus-master-agent-e2e argus-bind-agent-e2e >/dev/null 2>&1 || true
+docker container rm -f argus-agent-e2e argus-agent-env-e2e argus-master-agent-e2e argus-bind-agent-e2e >/dev/null 2>&1 || true
 
 docker network rm tests_default >/dev/null 2>&1 || true
 

src/agent/tests/scripts/03_wait_and_assert_registration.sh

@@ -6,11 +6,14 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 TMP_ROOT="$TEST_ROOT/tmp"
 API_BASE="http://localhost:32300/api/v1/master"
 AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
+ENV_AGENT_HOSTNAME="host_abc"
 NODE_FILE="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/node.json"
+ENV_NODE_FILE="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME/node.json"
 
 mkdir -p "$TMP_ROOT"
 
-node_id=""
+primary_node_id=""
+env_node_id=""
 for _ in {1..30}; do
   sleep 2
   response=$(curl -sS "$API_BASE/nodes" || true)
@@ -19,24 +22,49 @@ for _ in {1..30}; do
   fi
   list_file="$TMP_ROOT/nodes_list.json"
   echo "$response" > "$list_file"
-  node_id=$(python3 - "$list_file" <<'PY'
+  readarray -t node_ids < <(python3 - "$list_file" "$AGENT_HOSTNAME" "$ENV_AGENT_HOSTNAME" <<'PY'
 import json, sys
+
 with open(sys.argv[1]) as handle:
     nodes = json.load(handle)
-print(nodes[0]["id"] if nodes else "")
+
+target_primary = sys.argv[2]
+target_env = sys.argv[3]
+
+primary_id = ""
+env_id = ""
+
+for node in nodes:
+    if node.get("name") == target_primary:
+        primary_id = node.get("id", "")
+    if node.get("name") == target_env:
+        env_id = node.get("id", "")
+
+print(primary_id)
+print(env_id)
 PY
-)
+  )
-  if [[ -n "$node_id" ]]; then
+
+  primary_node_id="${node_ids[0]}"
+  env_node_id="${node_ids[1]}"
+
+  if [[ -n "$primary_node_id" && -n "$env_node_id" ]]; then
     break
   fi
  done
 
-if [[ -z "$node_id" ]]; then
+if [[ -z "$primary_node_id" ]]; then
-  echo "[ERROR] Agent did not register within timeout" >&2
+  echo "[ERROR] Primary agent did not register within timeout" >&2
   exit 1
 fi
 
-echo "$node_id" > "$TMP_ROOT/node_id"
+if [[ -z "$env_node_id" ]]; then
+  echo "[ERROR] Env-variable agent did not register within timeout" >&2
+  exit 1
+fi
+
+echo "$primary_node_id" > "$TMP_ROOT/node_id"
+echo "$env_node_id" > "$TMP_ROOT/node_id_host_abc"
 
 if [[ ! -f "$NODE_FILE" ]]; then
   echo "[ERROR] node.json not created at $NODE_FILE" >&2
@@ -50,8 +78,20 @@ with open(sys.argv[1]) as handle:
 assert "id" in node and node["id"], "node.json missing id"
 PY
 
+if [[ ! -f "$ENV_NODE_FILE" ]]; then
+  echo "[ERROR] node.json not created at $ENV_NODE_FILE" >&2
+  exit 1
+fi
+
+python3 - "$ENV_NODE_FILE" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+assert "id" in node and node["id"], "env agent node.json missing id"
+PY
+
 detail_file="$TMP_ROOT/initial_detail.json"
-curl -sS "$API_BASE/nodes/$node_id" -o "$detail_file"
+curl -sS "$API_BASE/nodes/$primary_node_id" -o "$detail_file"
 python3 - "$detail_file" "$TMP_ROOT/initial_ip" <<'PY'
 import json, sys, pathlib
 with open(sys.argv[1]) as handle:
@@ -62,4 +102,5 @@ if not ip:
 pathlib.Path(sys.argv[2]).write_text(ip)
 PY
 
-echo "[INFO] Agent registered with node id $node_id"
+echo "[INFO] Agent registered with node id $primary_node_id"
+echo "[INFO] Env-variable agent registered with node id $env_node_id"

src/agent/tests/scripts/05_verify_agent.sh

@@ -0,0 +1,60 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$TEST_ROOT/.." && pwd)"
+VERIFY_SCRIPT="$REPO_ROOT/scripts/agent_deployment_verify.sh"
+ENV_NODE_ID_FILE="$TEST_ROOT/tmp/node_id_host_abc"
+PRIMARY_CONTAINER="argus-agent-e2e"
+ENV_CONTAINER="argus-agent-env-e2e"
+PRIMARY_HOSTNAME="dev-e2euser-e2einst-pod-0"
+ENV_HOSTNAME="host_abc"
+
+if ! docker ps --format '{{.Names}}' | grep -q "^${PRIMARY_CONTAINER}$"; then
+  echo "[WARN] agent container not running; skip verification"
+  exit 0
+fi
+
+if docker exec -i "$PRIMARY_CONTAINER" bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
+  echo "[INFO] curl/jq already installed in agent container"
+else
+  echo "[INFO] Installing curl/jq in agent container"
+  docker exec -i "$PRIMARY_CONTAINER" bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
+fi
+
+if [[ ! -f "$VERIFY_SCRIPT" ]]; then
+  echo "[ERROR] Verification script missing at $VERIFY_SCRIPT" >&2
+  exit 1
+fi
+
+run_verifier() {
+  local container="$1" hostname="$2"
+
+  if ! docker ps --format '{{.Names}}' | grep -q "^${container}$"; then
+    echo "[WARN] container $container not running; skip"
+    return
+  fi
+
+  if ! docker exec -i "$container" bash -lc 'command -v /usr/local/bin/agent_deployment_verify.sh >/dev/null'; then
+    echo "[ERROR] /usr/local/bin/agent_deployment_verify.sh missing in $container" >&2
+    exit 1
+  fi
+
+  echo "[INFO] Running verification for $hostname in $container"
+  docker exec -i "$container" env VERIFY_HOSTNAME="$hostname" /usr/local/bin/agent_deployment_verify.sh
+}
+
+run_verifier "$PRIMARY_CONTAINER" "$PRIMARY_HOSTNAME"
+
+if docker ps --format '{{.Names}}' | grep -q "^${ENV_CONTAINER}$"; then
+  if docker exec -i "$ENV_CONTAINER" bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
+    echo "[INFO] curl/jq already installed in env agent container"
+  else
+    echo "[INFO] Installing curl/jq in env agent container"
+    docker exec -i "$ENV_CONTAINER" bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
+  fi
+  run_verifier "$ENV_CONTAINER" "$ENV_HOSTNAME"
+else
+  echo "[WARN] env-driven agent container not running; skip secondary verification"
+fi

src/agent/tests/scripts/06_assert_status_on_master.sh

@@ -6,6 +6,8 @@ TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 TMP_ROOT="$TEST_ROOT/tmp"
 API_BASE="http://localhost:32300/api/v1/master"
 NODE_ID="$(cat "$TMP_ROOT/node_id")"
+ENV_NODE_ID="$(cat "$TMP_ROOT/node_id_host_abc")"
+ENV_HOSTNAME="host_abc"
 NODES_JSON="$TEST_ROOT/private/argus/metric/prometheus/nodes.json"
 
 success=false
@@ -41,13 +43,36 @@ if [[ ! -f "$NODES_JSON" ]]; then
   exit 1
 fi
 
-python3 - "$NODES_JSON" <<'PY'
+python3 - "$NODES_JSON" "$NODE_ID" "$ENV_NODE_ID" <<'PY'
 import json, sys
 with open(sys.argv[1]) as handle:
     nodes = json.load(handle)
-assert len(nodes) == 1, nodes
+
-entry = nodes[0]
+expected_primary = sys.argv[2]
-assert entry["node_id"], entry
+expected_env = sys.argv[3]
+
+ids = {entry.get("node_id") for entry in nodes}
+assert expected_primary in ids, nodes
+assert expected_env in ids, nodes
+assert len(nodes) >= 2, nodes
 PY
 
 echo "[INFO] Master reflects agent health and nodes.json entries"
+
+env_detail_file="$TMP_ROOT/env_agent_detail.json"
+curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_detail_file"
+python3 - "$env_detail_file" "$ENV_HOSTNAME" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+
+expected_name = sys.argv[2]
+
+assert node.get("name") == expected_name, node
+meta = node.get("meta_data", {})
+assert meta.get("env") == "prod", meta
+assert meta.get("user") == "ml", meta
+assert meta.get("instance") == "node-3", meta
+PY
+
+echo "[INFO] Env-variable agent reports expected metadata"

src/agent/tests/scripts/06_restart_agent_and_reregister.sh

@@ -1,125 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-TMP_ROOT="$TEST_ROOT/tmp"
-API_BASE="http://localhost:32300/api/v1/master"
-NODE_ID="$(cat "$TMP_ROOT/node_id")"
-AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
-NETWORK_NAME="tests_default"
-NEW_AGENT_IP="172.28.0.200"
-ENTRYPOINT_SCRIPT="$SCRIPT_DIR/agent_entrypoint.sh"
-
-# 中文提示：重启场景也需要同样的入口脚本，确保 DNS 注册逻辑一致
-if [[ ! -f "$ENTRYPOINT_SCRIPT" ]]; then
-  echo "[ERROR] agent entrypoint script missing at $ENTRYPOINT_SCRIPT" >&2
-  exit 1
-fi
-
-if [[ ! -f "$TMP_ROOT/agent_binary_path" ]]; then
-  echo "[ERROR] Agent binary path missing; rerun bootstrap" >&2
-  exit 1
-fi
-
-AGENT_BINARY="$(cat "$TMP_ROOT/agent_binary_path")"
-if [[ ! -x "$AGENT_BINARY" ]]; then
-  echo "[ERROR] Agent binary not executable: $AGENT_BINARY" >&2
-  exit 1
-fi
-
-compose() {
-  if docker compose version >/dev/null 2>&1; then
-    docker compose "$@"
-  else
-    docker-compose "$@"
-  fi
-}
-
-before_file="$TMP_ROOT/before_restart.json"
-curl -sS "$API_BASE/nodes/$NODE_ID" -o "$before_file"
-prev_last_updated=$(python3 - "$before_file" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-print(node.get("last_updated", ""))
-PY
-)
-prev_ip=$(python3 - "$before_file" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-print(node["meta_data"].get("ip", ""))
-PY
-)
-initial_ip=$(cat "$TMP_ROOT/initial_ip")
-if [[ "$prev_ip" != "$initial_ip" ]]; then
-  echo "[ERROR] Expected initial IP $initial_ip, got $prev_ip" >&2
-  exit 1
-fi
-
-pushd "$TEST_ROOT" >/dev/null
-compose rm -sf agent
-popd >/dev/null
-
-docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
-
-AGENT_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME"
-HEALTH_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/health"
-
-# 先以 sleep 方式启动容器，确保我们掌握注册时的网络状态
-if ! docker run -d \
-  --name argus-agent-e2e \
-  --hostname "$AGENT_HOSTNAME" \
-  --network "$NETWORK_NAME" \
-  --ip "$NEW_AGENT_IP" \
-  -v "$AGENT_DIR:/private/argus/agent/$AGENT_HOSTNAME" \
-  -v "$HEALTH_DIR:/private/argus/agent/$AGENT_HOSTNAME/health" \
-  -v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
-  -v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
-  -v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
-  -e MASTER_ENDPOINT=http://master.argus.com:3000 \
-  -e REPORT_INTERVAL_SECONDS=2 \
-  --entrypoint /usr/local/bin/agent-entrypoint.sh \
-  ubuntu:24.04 >/dev/null; then
-  echo "[ERROR] Failed to start agent container with custom IP" >&2
-  exit 1
-fi
-
-success=false
-detail_file="$TMP_ROOT/post_restart.json"
-for _ in {1..20}; do
-  sleep 3
-  if ! curl -sS "$API_BASE/nodes/$NODE_ID" -o "$detail_file"; then
-    continue
-  fi
-  if python3 - "$detail_file" "$prev_last_updated" "$NODE_ID" "$prev_ip" "$NEW_AGENT_IP" <<'PY'
-import json, sys
-with open(sys.argv[1]) as handle:
-    node = json.load(handle)
-prev_last_updated = sys.argv[2]
-expected_id = sys.argv[3]
-old_ip = sys.argv[4]
-expected_ip = sys.argv[5]
-last_updated = node.get("last_updated")
-current_ip = node["meta_data"].get("ip")
-assert node["id"] == expected_id
-if current_ip != expected_ip:
-    raise SystemExit(1)
-if current_ip == old_ip:
-    raise SystemExit(1)
-if not last_updated or last_updated == prev_last_updated:
-    raise SystemExit(1)
-PY
-  then
-    success=true
-    break
-  fi
-done
-
-if [[ "$success" != true ]]; then
-  echo "[ERROR] Agent did not report expected new IP $NEW_AGENT_IP after restart" >&2
-  exit 1
-fi
-
-echo "[INFO] Agent restart produced successful re-registration with IP change"

src/agent/tests/scripts/07_restart_agent_and_reregister.sh

@@ -0,0 +1,254 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+TMP_ROOT="$TEST_ROOT/tmp"
+API_BASE="http://localhost:32300/api/v1/master"
+NODE_ID="$(cat "$TMP_ROOT/node_id")"
+ENV_NODE_ID_FILE="$TMP_ROOT/node_id_host_abc"
+if [[ ! -f "$ENV_NODE_ID_FILE" ]]; then
+  echo "[ERROR] Env agent node id file missing at $ENV_NODE_ID_FILE" >&2
+  exit 1
+fi
+
+ENV_NODE_ID="$(cat "$ENV_NODE_ID_FILE")"
+AGENT_HOSTNAME="dev-e2euser-e2einst-pod-0"
+ENV_AGENT_HOSTNAME="host_abc"
+NETWORK_NAME="tests_default"
+NEW_AGENT_IP="172.28.0.200"
+NEW_ENV_AGENT_IP="172.28.0.210"
+ENTRYPOINT_SCRIPT="$SCRIPT_DIR/agent_entrypoint.sh"
+VERIFY_SCRIPT="$TEST_ROOT/../scripts/agent_deployment_verify.sh"
+ENV_FILE="$TEST_ROOT/.env"
+
+# 中文提示：重启场景也需要同样的入口脚本，确保 DNS 注册逻辑一致
+if [[ ! -f "$ENTRYPOINT_SCRIPT" ]]; then
+  echo "[ERROR] agent entrypoint script missing at $ENTRYPOINT_SCRIPT" >&2
+  exit 1
+fi
+
+if [[ ! -f "$VERIFY_SCRIPT" ]]; then
+  echo "[ERROR] agent verification script missing at $VERIFY_SCRIPT" >&2
+  exit 1
+fi
+
+if [[ ! -f "$TMP_ROOT/agent_binary_path" ]]; then
+  echo "[ERROR] Agent binary path missing; rerun bootstrap" >&2
+  exit 1
+fi
+
+AGENT_BINARY="$(cat "$TMP_ROOT/agent_binary_path")"
+if [[ ! -x "$AGENT_BINARY" ]]; then
+  echo "[ERROR] Agent binary not executable: $AGENT_BINARY" >&2
+  exit 1
+fi
+
+if [[ -f "$ENV_FILE" ]]; then
+  set -a
+  # shellcheck disable=SC1090
+  source "$ENV_FILE"
+  set +a
+else
+  REPO_ROOT="$(cd "$TEST_ROOT/../../.." && pwd)"
+  # shellcheck disable=SC1090
+  source "$REPO_ROOT/scripts/common/build_user.sh"
+  load_build_user
+fi
+
+AGENT_UID="${ARGUS_BUILD_UID:-2133}"
+AGENT_GID="${ARGUS_BUILD_GID:-2015}"
+
+compose() {
+  if docker compose version >/dev/null 2>&1; then
+    docker compose "$@"
+  else
+    docker-compose "$@"
+  fi
+}
+
+before_file="$TMP_ROOT/before_restart.json"
+curl -sS "$API_BASE/nodes/$NODE_ID" -o "$before_file"
+prev_last_updated=$(python3 - "$before_file" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+print(node.get("last_updated", ""))
+PY
+)
+prev_ip=$(python3 - "$before_file" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+print(node["meta_data"].get("ip", ""))
+PY
+)
+initial_ip=$(cat "$TMP_ROOT/initial_ip")
+if [[ "$prev_ip" != "$initial_ip" ]]; then
+  echo "[ERROR] Expected initial IP $initial_ip, got $prev_ip" >&2
+  exit 1
+fi
+
+env_before_file="$TMP_ROOT/env_before_restart.json"
+curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_before_file"
+env_prev_last_updated=$(python3 - "$env_before_file" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+print(node.get("last_updated", ""))
+PY
+)
+env_prev_ip=$(python3 - "$env_before_file" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+print(node["meta_data"].get("ip", ""))
+PY
+)
+
+pushd "$TEST_ROOT" >/dev/null
+compose rm -sf agent
+compose rm -sf agent_env
+popd >/dev/null
+
+docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
+docker container rm -f argus-agent-env-e2e >/dev/null 2>&1 || true
+
+AGENT_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME"
+HEALTH_DIR="$TEST_ROOT/private/argus/agent/$AGENT_HOSTNAME/health"
+
+ENV_AGENT_DIR="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME"
+ENV_HEALTH_DIR="$TEST_ROOT/private/argus/agent/$ENV_AGENT_HOSTNAME/health"
+
+# 先以 sleep 方式启动容器，确保我们掌握注册时的网络状态
+if ! docker run -d \
+  --name argus-agent-e2e \
+  --hostname "$AGENT_HOSTNAME" \
+  --network "$NETWORK_NAME" \
+  --ip "$NEW_AGENT_IP" \
+  -v "$AGENT_DIR:/private/argus/agent/$AGENT_HOSTNAME" \
+  -v "$HEALTH_DIR:/private/argus/agent/$AGENT_HOSTNAME/health" \
+  -v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
+  -v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
+  -v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
+  -v "$VERIFY_SCRIPT:/usr/local/bin/agent_deployment_verify.sh:ro" \
+  -e MASTER_ENDPOINT=http://master.argus.com:3000 \
+  -e REPORT_INTERVAL_SECONDS=2 \
+  -e ARGUS_BUILD_UID="$AGENT_UID" \
+  -e ARGUS_BUILD_GID="$AGENT_GID" \
+  --entrypoint /usr/local/bin/agent-entrypoint.sh \
+  ubuntu:22.04 >/dev/null; then
+  echo "[ERROR] Failed to start agent container with custom IP" >&2
+  exit 1
+fi
+
+success=false
+detail_file="$TMP_ROOT/post_restart.json"
+for _ in {1..20}; do
+  sleep 3
+  if ! curl -sS "$API_BASE/nodes/$NODE_ID" -o "$detail_file"; then
+    continue
+  fi
+  if python3 - "$detail_file" "$prev_last_updated" "$NODE_ID" "$prev_ip" "$NEW_AGENT_IP" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+prev_last_updated = sys.argv[2]
+expected_id = sys.argv[3]
+old_ip = sys.argv[4]
+expected_ip = sys.argv[5]
+last_updated = node.get("last_updated")
+current_ip = node["meta_data"].get("ip")
+assert node["id"] == expected_id
+if current_ip != expected_ip:
+    raise SystemExit(1)
+if current_ip == old_ip:
+    raise SystemExit(1)
+if not last_updated or last_updated == prev_last_updated:
+    raise SystemExit(1)
+PY
+  then
+    success=true
+    break
+  fi
+done
+
+if [[ "$success" != true ]]; then
+  echo "[ERROR] Agent did not report expected new IP $NEW_AGENT_IP after restart" >&2
+  exit 1
+fi
+
+echo "[INFO] Agent restart produced successful re-registration with IP change"
+
+# ---- Restart env-driven agent without metadata environment variables ----
+
+if [[ ! -d "$ENV_AGENT_DIR" ]]; then
+  echo "[ERROR] Env agent data dir missing at $ENV_AGENT_DIR" >&2
+  exit 1
+fi
+
+if [[ ! -d "$ENV_HEALTH_DIR" ]]; then
+  mkdir -p "$ENV_HEALTH_DIR"
+fi
+
+if ! docker run -d \
+  --name argus-agent-env-e2e \
+  --hostname "$ENV_AGENT_HOSTNAME" \
+  --network "$NETWORK_NAME" \
+  --ip "$NEW_ENV_AGENT_IP" \
+  -v "$ENV_AGENT_DIR:/private/argus/agent/$ENV_AGENT_HOSTNAME" \
+  -v "$ENV_HEALTH_DIR:/private/argus/agent/$ENV_AGENT_HOSTNAME/health" \
+  -v "$TEST_ROOT/private/argus/etc:/private/argus/etc" \
+  -v "$AGENT_BINARY:/usr/local/bin/argus-agent:ro" \
+  -v "$ENTRYPOINT_SCRIPT:/usr/local/bin/agent-entrypoint.sh:ro" \
+  -v "$VERIFY_SCRIPT:/usr/local/bin/agent_deployment_verify.sh:ro" \
+  -e MASTER_ENDPOINT=http://master.argus.com:3000 \
+  -e REPORT_INTERVAL_SECONDS=2 \
+  -e ARGUS_BUILD_UID="$AGENT_UID" \
+  -e ARGUS_BUILD_GID="$AGENT_GID" \
+  --entrypoint /usr/local/bin/agent-entrypoint.sh \
+  ubuntu:22.04 >/dev/null; then
+  echo "[ERROR] Failed to start env-driven agent container without metadata env" >&2
+  exit 1
+fi
+
+env_success=false
+env_detail_file="$TMP_ROOT/env_post_restart.json"
+for _ in {1..20}; do
+  sleep 3
+  if ! curl -sS "$API_BASE/nodes/$ENV_NODE_ID" -o "$env_detail_file"; then
+    continue
+  fi
+  if python3 - "$env_detail_file" "$env_prev_last_updated" "$ENV_NODE_ID" "$env_prev_ip" "$NEW_ENV_AGENT_IP" <<'PY'
+import json, sys
+with open(sys.argv[1]) as handle:
+    node = json.load(handle)
+prev_last_updated = sys.argv[2]
+expected_id = sys.argv[3]
+old_ip = sys.argv[4]
+expected_ip = sys.argv[5]
+last_updated = node.get("last_updated")
+current_ip = node["meta_data"].get("ip")
+meta = node.get("meta_data", {})
+assert node["id"] == expected_id
+if current_ip != expected_ip:
+    raise SystemExit(1)
+if current_ip == old_ip:
+    raise SystemExit(1)
+if not last_updated or last_updated == prev_last_updated:
+    raise SystemExit(1)
+if meta.get("env") != "prod" or meta.get("user") != "ml" or meta.get("instance") != "node-3":
+    raise SystemExit(1)
+PY
+  then
+    env_success=true
+    break
+  fi
+done
+
+if [[ "$env_success" != true ]]; then
+  echo "[ERROR] Env-driven agent did not reuse persisted metadata after restart" >&2
+  exit 1
+fi
+
+echo "[INFO] Env-driven agent restart succeeded with persisted metadata"

src/agent/tests/scripts/08_down.sh

@@ -13,7 +13,7 @@ compose() {
   fi
 }
 
-docker container rm -f argus-agent-e2e >/dev/null 2>&1 || true
+docker container rm -f argus-agent-e2e argus-agent-env-e2e >/dev/null 2>&1 || true
 
 pushd "$TEST_ROOT" >/dev/null
 compose down --remove-orphans

src/agent/tests/scripts/08_verify_agent.sh

@@ -1,26 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-TEST_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
-VERIFY_SCRIPT="$(cd "$TEST_ROOT/.." && pwd)/scripts/agent_deployment_verify.sh"
-
-if ! docker ps --format '{{.Names}}' | grep -q '^argus-agent-e2e$'; then
-  echo "[WARN] agent container not running; skip verification"
-  exit 0
-fi
-
-if docker exec -i argus-agent-e2e bash -lc 'command -v curl >/dev/null && command -v jq >/dev/null'; then
-  echo "[INFO] curl/jq already installed in agent container"
-else
-  echo "[INFO] Installing curl/jq in agent container"
-  docker exec -i argus-agent-e2e bash -lc 'apt-get update >/dev/null 2>&1 && apt-get install -y curl jq >/dev/null 2>&1' || true
-fi
-
-if docker exec -i argus-agent-e2e bash -lc 'command -v /usr/local/bin/agent_deployment_verify.sh >/dev/null'; then
-  docker exec -i argus-agent-e2e /usr/local/bin/agent_deployment_verify.sh
-elif [[ -x "$VERIFY_SCRIPT" ]]; then
-  docker exec -i argus-agent-e2e "$VERIFY_SCRIPT"
-else
-  echo "[WARN] agent_deployment_verify.sh not found"
-fi

src/agent/tests/test_config_metadata.py

@@ -0,0 +1,151 @@
+from __future__ import annotations
+
+import os
+import unittest
+from contextlib import contextmanager
+from unittest.mock import patch
+
+from app.config import AgentConfig, load_config
+
+
+@contextmanager
+def temp_env(**overrides: str | None):
+    originals: dict[str, str | None] = {}
+    try:
+        for key, value in overrides.items():
+            originals[key] = os.environ.get(key)
+            if value is None:
+                os.environ.pop(key, None)
+            else:
+                os.environ[key] = value
+        yield
+    finally:
+        for key, original in originals.items():
+            if original is None:
+                os.environ.pop(key, None)
+            else:
+                os.environ[key] = original
+
+
+class LoadConfigMetadataTests(unittest.TestCase):
+    @patch("app.config.Path.mkdir")
+    def test_metadata_from_environment_variables(self, mock_mkdir):
+        with temp_env(
+            MASTER_ENDPOINT="http://master.local",
+            AGENT_HOSTNAME="dev-user-one-pod",
+            AGENT_ENV="prod",
+            AGENT_USER="ops",
+            AGENT_INSTANCE="node-1",
+        ):
+            config = load_config()
+
+        self.assertEqual(config.environment, "prod")
+        self.assertEqual(config.user, "ops")
+        self.assertEqual(config.instance, "node-1")
+        mock_mkdir.assert_called()
+
+    @patch("app.config.Path.mkdir")
+    def test_metadata_falls_back_to_hostname(self, mock_mkdir):
+        with temp_env(
+            MASTER_ENDPOINT="http://master.local",
+            AGENT_HOSTNAME="qa-team-abc-pod-2",
+            AGENT_ENV=None,
+            AGENT_USER=None,
+            AGENT_INSTANCE=None,
+        ):
+            config = load_config()
+
+        self.assertEqual(config.environment, "qa")
+        self.assertEqual(config.user, "team")
+        self.assertEqual(config.instance, "abc")
+        mock_mkdir.assert_called()
+
+    @patch("app.config._load_metadata_from_state", return_value=("prod", "ops", "node-1"))
+    @patch("app.config.Path.mkdir")
+    def test_metadata_from_node_state(self, mock_mkdir, mock_state):
+        with temp_env(
+            MASTER_ENDPOINT="http://master.local",
+            AGENT_HOSTNAME="host_abc",
+            AGENT_ENV=None,
+            AGENT_USER=None,
+            AGENT_INSTANCE=None,
+        ):
+            config = load_config()
+
+        self.assertEqual(config.environment, "prod")
+        self.assertEqual(config.user, "ops")
+        self.assertEqual(config.instance, "node-1")
+        mock_state.assert_called_once()
+        mock_mkdir.assert_called()
+
+    @patch("app.config.Path.mkdir")
+    def test_partial_environment_variables_fallback(self, mock_mkdir):
+        with temp_env(
+            MASTER_ENDPOINT="http://master.local",
+            AGENT_HOSTNAME="stage-ml-001-node",
+            AGENT_ENV="prod",
+            AGENT_USER=None,
+            AGENT_INSTANCE=None,
+        ):
+            config = load_config()
+
+        self.assertEqual(config.environment, "stage")
+        self.assertEqual(config.user, "ml")
+        self.assertEqual(config.instance, "001")
+        mock_mkdir.assert_called()
+
+    @patch("app.config.Path.mkdir")
+    def test_invalid_hostname_raises_error(self, mock_mkdir):
+        with temp_env(
+            MASTER_ENDPOINT="http://master.local",
+            AGENT_HOSTNAME="invalidhostname",
+            AGENT_ENV=None,
+            AGENT_USER=None,
+            AGENT_INSTANCE=None,
+        ):
+            with self.assertRaises(ValueError):
+                load_config()
+
+        mock_mkdir.assert_not_called()
+
+
+class CollectMetadataTests(unittest.TestCase):
+    @patch("app.collector._detect_ip_address", return_value="127.0.0.1")
+    @patch("app.collector._detect_gpu_count", return_value=0)
+    @patch("app.collector._detect_memory_bytes", return_value=1024)
+    @patch("app.collector._detect_cpu_count", return_value=8)
+    def test_collect_metadata_uses_config_fields(
+        self,
+        mock_cpu,
+        mock_memory,
+        mock_gpu,
+        mock_ip,
+    ):
+        config = AgentConfig(
+            hostname="dev-user-001-pod",
+            environment="prod",
+            user="ops",
+            instance="node-1",
+            node_file="/tmp/node.json",
+            version="1.0.0",
+            master_endpoint="http://master.local",
+            report_interval_seconds=60,
+            health_dir="/tmp/health",
+        )
+
+        from app.collector import collect_metadata
+
+        metadata = collect_metadata(config)
+
+        self.assertEqual(metadata["env"], "prod")
+        self.assertEqual(metadata["user"], "ops")
+        self.assertEqual(metadata["instance"], "node-1")
+        self.assertEqual(metadata["hostname"], "dev-user-001-pod")
+        self.assertEqual(metadata["ip"], "127.0.0.1")
+        self.assertEqual(metadata["cpu_number"], 8)
+        self.assertEqual(metadata["memory_in_bytes"], 1024)
+        self.assertEqual(metadata["gpu_number"], 0)
+
+
+if __name__ == "__main__":
+    unittest.main()

src/alert/README.md

@@ -0,0 +1,31 @@
+# Alertmanager
+
+## 构建
+1. 首先设置构建和部署的环境变量, 在项目根目录下执行：
+```bash
+cp src/alert/tests/.env.example src/alert/tests/.env
+```
+
+然后找到复制出来的.env文件，修改环境变量。
+
+2. 使用脚本构建，在项目根目录下执行：
+
+```bash
+bash src/alert/alertmanager/build/build.sh
+```
+
+构建成功后，会在项目根目录下生成argus-alertmanager-latest.tar
+
+## 部署
+
+提供docker-compose部署。在src/alert/tests目录下
+```bash
+docker-compose up -d
+```
+
+## 动态配置
+配置文件放在`/private/argus/alert/alertmanager/alertmanager.yml`下，修改alertmanager.yml后，调用`http://alertmanager.alert.argus.com:9093/-/reload`接口(POST)可以重新加载配置.
+
+```bash
+curl -X POST http://localhost:9093/-/reload
+```

src/alert/alertmanager/build/Dockerfile

@@ -0,0 +1,89 @@
+# 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-${ALERTMANAGER_VERSION}.linux-amd64.tar.gz
+
+ENV ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
+
+ARG ARGUS_UID=2133
+ARG ARGUS_GID=2015
+ENV ARGUS_UID=${ARGUS_UID}
+ENV ARGUS_GID=${ARGUS_GID}
+
+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/build.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+set -euo pipefail
+docker pull ubuntu:24.04
+
+source src/alert/tests/.env
+
+docker build \
+  --build-arg ARGUS_UID=${ARGUS_UID} \
+  --build-arg ARGUS_GID=${ARGUS_GID} \
+  -f src/alert/alertmanager/build/Dockerfile \
+  -t argus-alertmanager:latest .
+
+docker save -o argus-alertmanager-latest.tar argus-alertmanager:latest

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 +1,27 @@
+#!/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/${DOMAIN}
+chmod 755 /private/argus/etc/${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:
+            - "alertmanager.alert.argus.com: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/alert/tests/.env

@@ -0,0 +1,5 @@
+DATA_ROOT=/home/argus/tmp/private/argus
+ARGUS_UID=1048
+ARGUS_GID=1048
+
+USE_INTRANET=false

src/alert/tests/.env.example

@@ -0,0 +1,5 @@
+DATA_ROOT=/home/argus/tmp/private/argus
+ARGUS_UID=1048
+ARGUS_GID=1048
+
+USE_INTRANET=false

src/alert/tests/data/alertmanager/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/tests/data/etc/alertmanager.alert.argus.com

@@ -0,0 +1 @@
+172.18.0.2

src/alert/tests/docker-compose.yml

@@ -0,0 +1,37 @@
+services:
+  alertmanager:
+    build:
+      context: ../../../
+      dockerfile: src/alert/alertmanager/build/Dockerfile
+      args:
+        ARGUS_UID: ${ARGUS_UID:-2133}
+        ARGUS_GID: ${ARGUS_GID:-2015}
+        USE_INTRANET: ${USE_INTRANET:-false}
+    image: argus-alertmanager:latest
+    container_name: argus-alertmanager
+    environment:
+      - ALERTMANAGER_BASE_PATH=/private/argus/alert/alertmanager
+      - ARGUS_UID=${ARGUS_UID:-2133}
+      - ARGUS_GID=${ARGUS_GID:-2015}
+    ports:
+      - "${ARGUS_PORT:-9093}:9093"
+    volumes:
+      - ${DATA_ROOT:-./data}/alert/alertmanager:/private/argus/alert/alertmanager
+      - ${DATA_ROOT:-./data}/etc:/private/argus/etc
+    networks:
+      - argus-debug-net
+    restart: unless-stopped
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+networks:
+  argus-debug-net:
+    driver: bridge
+    name: argus-debug-net
+
+volumes:
+  alertmanager_data:
+    driver: local

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

@@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+set -euo pipefail
+root="$(cd "$(dirname "${BASH_SOURCE[0]}")/../" && pwd)"
+project_root="$(cd "$root/../../.." && pwd)"
+
+source "$project_root/scripts/common/build_user.sh"
+load_build_user
+
+# 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 "$root/private/argus/alert/alertmanager"
+mkdir -p "$root/private/argus/etc/"
+
+# 设置数据目录权限
+echo "[INFO] Setting permissions for data directories..."
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/alert/alertmanager" 2>/dev/null || true
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
+
+echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"

src/alert/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 alert-mvp up -d --remove-orphans
+echo "[OK] 服务已启动：Alertmanager http://localhost:9093"

src/alert/tests/scripts/03_alertmanager_add_alert.sh

@@ -0,0 +1,106 @@
+#!/bin/bash
+set -euo pipefail
+
+# ==========================================================
+# Alertmanager 测试脚本
+# ==========================================================
+
+ALERTMANAGER_URL="http://localhost:9093"
+TEST_ALERT_NAME_CRITICAL="NodeDown"
+TEST_ALERT_NAME_WARNING="HighCPU"
+TMP_LOG="/tmp/test-alertmanager.log"
+
+# 等待参数
+am_wait_attempts=30
+am_wait_interval=2
+
+GREEN="\033[1;32m"
+RED="\033[1;31m"
+YELLOW="\033[1;33m"
+RESET="\033[0m"
+
+# ==========================================================
+# 函数定义
+# ==========================================================
+
+wait_for_alertmanager() {
+  local attempt=1
+  echo "[INFO] 等待 Alertmanager 启动中..."
+  while (( attempt <= am_wait_attempts )); do
+    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
+      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
+      return 0
+    fi
+    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
+    sleep "${am_wait_interval}"
+    (( attempt++ ))
+  done
+  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
+  return 1
+}
+
+log_step() {
+  echo -e "${YELLOW}==== $1 ====${RESET}"
+}
+
+# ==========================================================
+# 主流程
+# ==========================================================
+
+log_step "测试 Alertmanager 开始"
+echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
+
+# Step 1: 等待 Alertmanager 启动
+wait_for_alertmanager
+
+# Step 2: 触发一个critical测试告警
+echo "[INFO] 发送critical测试告警..."
+curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
+  -H "Content-Type: application/json" \
+  -d '[
+    {
+      "labels": {
+        "alertname": "'"${TEST_ALERT_NAME_CRITICAL}"'",
+        "instance": "node-1",
+        "severity": "critical"
+      },
+      "annotations": {
+        "summary": "节点 node-1 宕机"
+      }
+    }
+  ]' \
+  -o "$TMP_LOG"
+
+if [ $? -eq 0 ]; then
+  echo -e "${GREEN}[OK] 已成功发送critical测试告警${RESET}"
+else
+  echo -e "${RED}[ERROR] critical告警发送失败！${RESET}"
+  cat "$TMP_LOG"
+  exit 1
+fi
+
+# Step 3: 触发一个warning测试告警
+echo "[INFO] 发送warning测试告警..."
+curl -fsS -X POST "${ALERTMANAGER_URL}/api/v2/alerts" \
+  -H "Content-Type: application/json" \
+  -d '[
+    {
+      "labels": {
+        "alertname": "'"${TEST_ALERT_NAME_WARNING}"'",
+        "instance": "node-1",
+        "severity": "warning"
+      },
+      "annotations": {
+        "summary": "节点 node-1 CPU 使用率过高"
+      }
+    }
+  ]' \
+  -o "$TMP_LOG"
+
+if [ $? -eq 0 ]; then
+  echo -e "${GREEN}[OK] 已成功发送warning测试告警${RESET}"
+else
+  echo -e "${RED}[ERROR] warning告警发送失败！${RESET}"
+  cat "$TMP_LOG"
+  exit 1
+fi

src/alert/tests/scripts/04_query_alerts.sh

@@ -0,0 +1,71 @@
+#!/bin/bash
+set -euo pipefail
+
+# ==========================================================
+# Alertmanager 测试脚本（含启动等待）
+# ==========================================================
+
+ALERTMANAGER_URL="http://localhost:9093"
+TEST_ALERT_NAME_CRITICAL="NodeDown"
+TEST_ALERT_NAME_WARNING="HighCPU"
+TMP_LOG="/tmp/test-alertmanager.log"
+
+# 等待参数
+am_wait_attempts=30
+am_wait_interval=2
+
+GREEN="\033[1;32m"
+RED="\033[1;31m"
+YELLOW="\033[1;33m"
+RESET="\033[0m"
+
+# ==========================================================
+# 函数定义
+# ==========================================================
+
+wait_for_alertmanager() {
+  local attempt=1
+  echo "[INFO] 等待 Alertmanager 启动中..."
+  while (( attempt <= am_wait_attempts )); do
+    if curl -fsS "${ALERTMANAGER_URL}/api/v2/status" >/dev/null 2>&1; then
+      echo -e "${GREEN}[OK] Alertmanager 已就绪 (attempt=${attempt}/${am_wait_attempts})${RESET}"
+      return 0
+    fi
+    echo "[..] Alertmanager 尚未就绪 (${attempt}/${am_wait_attempts})"
+    sleep "${am_wait_interval}"
+    (( attempt++ ))
+  done
+  echo -e "${RED}[ERROR] Alertmanager 在 ${am_wait_attempts} 次尝试后仍未就绪${RESET}"
+  return 1
+}
+
+log_step() {
+  echo -e "${YELLOW}==== $1 ====${RESET}"
+}
+
+# ==========================================================
+# 主流程
+# ==========================================================
+
+log_step "查询 Alertmanager 当前告警列表开始"
+echo "[INFO] Alertmanager 地址: $ALERTMANAGER_URL"
+
+# Step 1: 等待 Alertmanager 启动
+wait_for_alertmanager
+
+# Step 2: 查询当前告警列表
+echo "[INFO] 查询当前告警..."
+sleep 1
+curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | jq '.' || {
+  echo -e "${RED}[WARN] 无法解析返回 JSON，请检查 jq 是否安装${RESET}"
+  curl -s "${ALERTMANAGER_URL}/api/v2/alerts"
+}
+
+# Step 3: 检查告警是否包含 NodeDown
+if curl -fsS "${ALERTMANAGER_URL}/api/v2/alerts" | grep -q "${TEST_ALERT_NAME_CRITICAL}"; then
+  echo -e "${GREEN}✅ 测试通过：Alertmanager 已成功接收告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
+else
+  echo -e "${RED}❌ 测试失败：未检测到告警 ${TEST_ALERT_NAME_CRITICAL}${RESET}"
+fi
+
+log_step "测试结束"

src/alert/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 alert-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/alert/tests/scripts/e2e_test.sh

@@ -0,0 +1,105 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+echo "======================================="
+echo "ARGUS Alert System End-to-End Test"
+echo "======================================="
+echo ""
+
+# 记录测试开始时间
+test_start_time=$(date +%s)
+
+# 函数：等待服务就绪
+wait_for_services() {
+    echo "[INFO] Waiting for all services to be ready..."
+    local max_attempts=${SERVICE_WAIT_ATTEMPTS:-120}
+    local attempt=1
+
+    while [ $attempt -le $max_attempts ]; do
+        if curl -fs http://localhost:9093/api/v2/status >/dev/null 2>&1; then
+            echo "[OK] All services are ready!"
+            return 0
+        fi
+        echo "    Waiting for services... ($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
+
+# 发送告警数据
+show_step "3" "Add alerts - Send test alerts to Alertmanager"
+./scripts/03_alertmanager_add_alert.sh
+verify_step "Send test alerts"
+
+# 查询告警数据
+show_step "4" "Verify data - Query Alertmanager"
+./scripts/04_query_alerts.sh
+verify_step "Data verification"
+
+
+# 检查服务健康状态
+show_step "Health" "Check service health"
+echo "[INFO] Checking service health..."
+
+# 检查 Alertmanager 状态
+if curl -fs "http://localhost:9093/api/v2/status" >/dev/null 2>&1; then
+    am_status="available"
+    echo "✅ Alertmanager status: $am_status"
+else
+    am_status="unavailable"
+    echo "⚠️  Alertmanager status: $am_status"
+fi
+verify_step "Service health check"
+
+# 清理环境
+show_step "5" "Cleanup - Stop all services"
+./scripts/05_down.sh
+verify_step "Service cleanup"
+
+# 计算总测试时间
+test_end_time=$(date +%s)
+total_time=$((test_end_time - test_start_time))
+
+echo ""
+echo "======================================="
+echo "🎉 END-TO-END TEST COMPLETED SUCCESSFULLY!"
+echo "======================================="
+echo "📊 Test Summary:"
+echo "   • Total time: ${total_time}s"
+echo "   • Alertmanager status: $am_status"
+echo "   • All services started and stopped successfully"
+echo ""
+echo "✅ The ARGUS Alert system is working correctly!"
+echo ""

src/bind/build/dns-monitor.sh

@@ -17,6 +17,9 @@ log_message() {
 
 log_message "DNS监控脚本启动"
 
+log_message "删除DNS备份文件（如果存在）"
+rm -f $DNS_BACKUP
+
 while true; do
     if [ -f "$DNS_CONF" ]; then
         if [ -f "$DNS_BACKUP" ]; then

src/bind/tests/docker-compose.yml

@@ -3,8 +3,8 @@ services:
     image: argus-bind9:latest
     container_name: argus-bind9-test
     ports:
-      - "53:53/tcp"
+      - "${HOST_DNS_PORT:-1053}:53/tcp"
-      - "53:53/udp"
+      - "${HOST_DNS_PORT:-1053}:53/udp"
     volumes:
       - ./private:/private
     restart: unless-stopped
@@ -13,4 +13,4 @@ services:
 
 networks:
   bind-test-network:
-    driver: bridge
+    driver: bridge

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

@@ -7,6 +7,9 @@
 set -e
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
+export HOST_DNS_PORT
 
 echo "=========================================="
 echo "BIND9 DNS Server End-to-End Test Suite"
@@ -112,4 +115,4 @@ else
     echo "  - Review BIND9 configuration files"
     echo "  - Check system resources and port availability"
     exit 1
-fi
+fi

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

@@ -7,13 +7,17 @@ set -e
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(dirname "$SCRIPT_DIR")"
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
+export HOST_DNS_PORT
 
 cd "$TEST_DIR"
 
 echo "Starting BIND9 test container..."
 
 # Ensure private directory exists with proper permissions
-mkdir -p private
+mkdir -p private/argus/bind
+mkdir -p private/argus/etc
 chmod 777 private
 
 # Start the container
@@ -35,4 +39,4 @@ fi
 
 echo ""
 echo "BIND9 test environment is ready!"
-echo "DNS server listening on localhost:53"
+echo "DNS server listening on localhost:${HOST_DNS_PORT}"

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

@@ -5,7 +5,10 @@
 
 set -e
 
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
 echo "Testing DNS resolution with dig..."
+echo "Using DNS server localhost:${HOST_DNS_PORT}"
 
 # Function to test DNS query
 test_dns_query() {
@@ -19,7 +22,7 @@ test_dns_query() {
     echo "Expected IP: $expected_ip"
 
     # Perform dig query
-    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+    result=$(dig @localhost -p "$HOST_DNS_PORT" "$hostname".argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
 
     if [ "$result" = "QUERY_FAILED" ]; then
         echo "✗ DNS query failed"
@@ -69,4 +72,4 @@ if [ $failed_tests -eq 0 ]; then
 else
     echo "✗ $failed_tests test(s) failed"
     exit 1
-fi
+fi

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

@@ -6,10 +6,13 @@
 
 set -e
 
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(dirname "$SCRIPT_DIR")"
 
 echo "=== DNS Auto-Sync Functionality Test ==="
+echo "Using DNS server localhost:${HOST_DNS_PORT}"
 
 # Check if container is running
 if ! docker compose ps | grep -q "Up"; then
@@ -36,7 +39,7 @@ test_dns_query() {
     # Wait a moment for DNS cache
     sleep 2
 
-    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+    result=$(dig @localhost -p "$HOST_DNS_PORT" "$hostname".argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
 
     if [ "$result" = "$expected_ip" ]; then
         echo "✓ $result"
@@ -90,7 +93,7 @@ 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=$(dig @localhost web.argus.com A +short 2>/dev/null || echo "UNKNOWN")
+current_web_ip=$(dig @localhost -p "$HOST_DNS_PORT" 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)
@@ -185,7 +188,7 @@ docker compose exec bind9 bash -c 'echo "this is not an IP address" > /private/a
 wait_for_sync
 
 # Verify invalid record was not added (should fail to resolve)
-result=$(dig @localhost invalid.argus.com A +short 2>/dev/null || echo "NO_RESULT")
+result=$(dig @localhost -p "$HOST_DNS_PORT" invalid.argus.com A +short 2>/dev/null || echo "NO_RESULT")
 if [ "$result" = "NO_RESULT" ] || [ -z "$result" ]; then
     echo "✓ Invalid IP correctly ignored"
 else

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

@@ -5,10 +5,13 @@
 
 set -e
 
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(dirname "$SCRIPT_DIR")"
 
 echo "=== DNS Configuration Reload Test ==="
+echo "Using DNS server localhost:${HOST_DNS_PORT}"
 
 # Check if container is running
 if ! docker compose ps | grep -q "Up"; then
@@ -32,7 +35,7 @@ test_dns_query() {
     echo "Testing: $description"
     echo "Query: $hostname.argus.com -> Expected: $expected_ip"
 
-    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+    result=$(dig @localhost -p "$HOST_DNS_PORT" "$hostname".argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
 
     if [ "$result" = "$expected_ip" ]; then
         echo "✓ $result"
@@ -109,4 +112,4 @@ 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"
+echo "✓ Configuration persisted and reloaded correctly"

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

@@ -5,10 +5,13 @@
 
 set -e
 
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(dirname "$SCRIPT_DIR")"
 
 echo "=== Configuration Persistence Test ==="
+echo "Using DNS server localhost:${HOST_DNS_PORT}"
 
 # Check if dig is available
 if ! command -v dig &> /dev/null; then
@@ -25,7 +28,7 @@ test_dns_query() {
     echo "Testing: $description"
     echo "Query: $hostname.argus.com -> Expected: $expected_ip"
 
-    result=$(dig @localhost $hostname.argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
+    result=$(dig @localhost -p "$HOST_DNS_PORT" "$hostname".argus.com A +short 2>/dev/null || echo "QUERY_FAILED")
 
     if [ "$result" = "$expected_ip" ]; then
         echo "✓ $result"
@@ -112,4 +115,4 @@ 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"
+echo "✓ DNS resolution working correctly with persisted configuration"

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

@@ -7,6 +7,9 @@ set -e
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 TEST_DIR="$(dirname "$SCRIPT_DIR")"
+HOST_DNS_PORT="${HOST_DNS_PORT:-1053}"
+
+export HOST_DNS_PORT
 
 # Parse command line arguments
 FULL_CLEANUP=true

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

@@ -2,7 +2,7 @@
 set -euo pipefail
 
 ES_HOST="${ELASTICSEARCH_HOSTS:-http://es:9200}"
-KB_HOST="http://localhost:5601"
+KB_HOST="${KB_HOST:-http://127.0.0.1:5601}"
 
 echo "[INFO] Starting Kibana post-start configuration..."
 
@@ -83,50 +83,37 @@ fix_replicas_idempotent() {
 }
 
 # 幂等创建数据视图
+create_or_ensure_data_view() {
+    local name="$1"
+    local title="$2"
+
+    local list_response
+    list_response=$(curl -fsS "$KB_HOST/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null || echo "")
+
+    if [ -z "$list_response" ]; then
+        echo "[WARN] Failed to list data views, skipping creation check for $title"
+        return
+    fi
+
+    if echo "$list_response" | grep -Fq "\"title\":\"$title\""; then
+        echo "[INFO] Data view $title already exists, skipping"
+        return
+    fi
+
+    echo "[INFO] Creating data view for $title indices (allowNoIndex)"
+
+    curl -fsS -X POST "$KB_HOST/api/data_views/data_view?allowNoIndex=true" \
+        -H 'kbn-xsrf: true' \
+        -H 'Content-Type: application/json' \
+        -d "{\"data_view\":{\"name\":\"$name\",\"title\":\"$title\",\"timeFieldName\":\"@timestamp\",\"allowNoIndex\":true}}" \
+        >/dev/null && echo "[OK] Created $name data view" || echo "[WARN] Failed to create $name data view"
+}
+
 create_data_views_idempotent() {
     echo "[INFO] Checking and creating data views..."
 
-    # 检查是否存在匹配的索引
+    create_or_ensure_data_view "train" "train-*"
-    local train_indices=$(curl -s "$ES_HOST/_cat/indices/train-*?h=index" 2>/dev/null | wc -l || echo "0")
+    create_or_ensure_data_view "infer" "infer-*"
-    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

src/log/tests/docker-compose.yml

@@ -17,6 +17,7 @@ services:
       interval: 10s
       timeout: 5s
       retries: 30
+    restart: always
 
   kibana:
     build:
@@ -73,13 +74,11 @@ services:
       interval: 15s
       timeout: 10s
       retries: 30
+    restart: always
 
   bind9:
       image: argus-bind9:latest
-      ports:
-        - "53:53/tcp"
-        - "53:53/udp"
       volumes:
         - ./private/argus:/private/argus/
-      restart: unless-stopped
+      restart: always
 

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

@@ -15,9 +15,9 @@ 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 "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/log/elasticsearch" 2>/dev/null || true
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/log/elasticsearch" 2>/dev/null || true
-sudo chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/log/kibana" 2>/dev/null || true
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/log/kibana" 2>/dev/null || true
-sudo chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" "$root/private/argus/etc" 2>/dev/null || true
 
 echo "[INFO] Supervisor-based containers will manage their own scripts and configurations"
 

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

@@ -1,7 +1,42 @@
 #!/usr/bin/env bash
 set -euo pipefail
+
+# ES endpoint and wait strategy
 ES="${ES:-http://localhost:9200}"
+es_wait_attempts="${ES_WAIT_ATTEMPTS:-60}"      # total attempts to wait for ES
+es_wait_interval="${ES_WAIT_INTERVAL:-2}"        # seconds between attempts
+
 echo "[i] 查询 ES 端点：$ES"
+
+wait_for_es() {
+  local attempt=1
+  while (( attempt <= es_wait_attempts )); do
+    # 等待集群达到至少 yellow 状态；请求失败则重试
+    if curl -fsS "$ES/_cluster/health?wait_for_status=yellow&timeout=1s" >/dev/null 2>&1; then
+      echo "[ok] Elasticsearch 已就绪 (attempt=${attempt}/${es_wait_attempts})"
+      return 0
+    fi
+    echo "[..] 等待 Elasticsearch 可用中 (${attempt}/${es_wait_attempts})"
+    sleep "${es_wait_interval}"
+    (( attempt++ ))
+  done
+  echo "[err] Elasticsearch 在 ${es_wait_attempts} 次尝试后仍不可用"
+  return 1
+}
+
+safe_count() {
+  # 对缺失索引返回 0，避免 404 触发失败
+  local pattern="$1"
+  local json
+  json=$(curl -fsS "$ES/${pattern}/_count?ignore_unavailable=true&allow_no_indices=true" 2>/dev/null || echo '{}')
+  echo "$json" | sed -E 's/.*"count":([0-9]+).*/\1/' | awk 'NF{print $0;exit} END{if(NR==0)print 0}'
+}
+
+wait_for_es
+
+# 列出相关索引（可能为空，允许）
 curl -fsS "$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
+# 打印计数，缺失索引按 0 处理
+printf "train-* 计数："; safe_count "train-*"; echo
+printf "infer-* 计数："; safe_count "infer-*"; echo

src/log/tests/scripts/e2e_test.sh

@@ -115,20 +115,32 @@ show_step "Health" "Check service health"
 echo "[INFO] Checking service health..."
 
 # 检查 Elasticsearch 健康状态
+health_check_ok=1
 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"
+    health_check_ok=0
 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: $kb_status"
+
+    data_views_json=$(curl -fs "http://localhost:5601/api/data_views" -H 'kbn-xsrf: true' 2>/dev/null || true)
+    if echo "$data_views_json" | grep -F '"title":"train-*"' >/dev/null 2>&1 && \
+       echo "$data_views_json" | grep -F '"title":"infer-*"' >/dev/null 2>&1; then
+        echo "✅ Kibana data views: train-* and infer-* present"
+    else
+        echo "❌ Kibana data views missing: train-* or infer-*"
+        health_check_ok=0
+    fi
 else
     kb_status="unavailable"
     echo "⚠️  Kibana status: $kb_status"
+    health_check_ok=0
 fi
 
 # 检查 Fluent-Bit 指标
@@ -139,6 +151,13 @@ 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"
+    health_check_ok=0
+fi
+
+if [ "$health_check_ok" -eq 1 ]; then
+    true
+else
+    false
 fi
 
 verify_step "Service health check"

src/master/README.md

@@ -11,7 +11,7 @@ Argus Master 是基于 Flask + SQLite 的节点管理服务，负责：
 
 ```bash
 cd src/master
-./scripts/build_images.sh            # 生成 argus-master:dev 镜像
+./scripts/build_images.sh            # 生成 argus-master:latest 镜像
 ```
 
 如需离线构建，先在有网环境运行准备脚本：
@@ -25,7 +25,7 @@ cd src/master
 
 ```bash
 cd src/master
-./scripts/build_images.sh --offline --tag argus-master:dev
+./scripts/build_images.sh --offline --tag argus-master:latest
 ```
 
 若内网缺少 `python:3.11-slim`，请提前在外网 `docker save` 后通过离线介质 `docker load`。

src/master/scripts/build_images.sh

@@ -3,22 +3,24 @@ set -euo pipefail
 
 usage() {
   cat >&2 <<'USAGE'
-Usage: $0 [--intranet] [--offline] [--tag <image_tag>]
+Usage: $0 [--intranet] [--offline] [--tag <image_tag>] [--no-cache]
 
 Options:
   --intranet           使用指定的 PyPI 镜像源（默认清华镜像）。
   --offline            完全离线构建，依赖 offline_wheels/ 目录中的离线依赖包。
-  --tag <image_tag>    自定义镜像标签，默认 argus-master:dev。
+  --tag <image_tag>    自定义镜像标签，默认 argus-master:latest。
+  --no-cache           不使用 Docker 构建缓存。
 USAGE
 }
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 PROJECT_ROOT="$(cd "$SCRIPT_DIR/../../.." && pwd)"
 MODULE_ROOT="$PROJECT_ROOT/src/master"
-IMAGE_TAG="${IMAGE_TAG:-argus-master:dev}"
+IMAGE_TAG="${IMAGE_TAG:-argus-master:latest}"
 DOCKERFILE="src/master/Dockerfile"
 BUILD_ARGS=()
 OFFLINE_MODE=0
+NO_CACHE=0
 
 source "$PROJECT_ROOT/scripts/common/build_user.sh"
 load_build_user
@@ -45,6 +47,11 @@ while [[ "$#" -gt 0 ]]; do
       IMAGE_TAG="$2"
       shift 2
       ;;
+    --no-cache)
+      NO_CACHE=1
+      BUILD_ARGS+=("--no-cache")
+      shift
+      ;;
     -h|--help)
       usage
       exit 0

src/master/scripts/save_images.sh

@@ -8,7 +8,7 @@ usage() {
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 PROJECT_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
 DEFAULT_OUTPUT="$PROJECT_ROOT/images/argus-master-dev.tar"
-IMAGE_TAG="${IMAGE_TAG:-argus-master:dev}"
+IMAGE_TAG="${IMAGE_TAG:-argus-master:latest}"
 OUTPUT_PATH="$DEFAULT_OUTPUT"
 
 while [[ "$#" -gt 0 ]]; do

src/master/tests/docker-compose.yml

@@ -1,6 +1,6 @@
 services:
   master:
-    image: ${MASTER_IMAGE_TAG:-argus-master:dev}
+    image: ${MASTER_IMAGE_TAG:-argus-master:latest}
     container_name: argus-master-e2e
     environment:
       - OFFLINE_THRESHOLD_SECONDS=6

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

@@ -17,7 +17,7 @@ SCRIPTS=(
 
 for script in "${SCRIPTS[@]}"; do
   echo "[TEST] Running $script"
-  MASTER_IMAGE_TAG="${MASTER_IMAGE_TAG:-argus-master:dev}" "$SCRIPT_DIR/$script"
+  MASTER_IMAGE_TAG="${MASTER_IMAGE_TAG:-argus-master:latest}" "$SCRIPT_DIR/$script"
   echo "[TEST] $script completed"
   echo
 done

src/master/tests/scripts/01_up_master.sh

@@ -44,7 +44,7 @@ fi
 
 pushd "$TEST_ROOT" >/dev/null
 compose down --remove-orphans || true
-MASTER_IMAGE_TAG="${MASTER_IMAGE_TAG:-argus-master:dev}" compose up -d
+MASTER_IMAGE_TAG="${MASTER_IMAGE_TAG:-argus-master:latest}" compose up -d
 popd >/dev/null
 
 echo "[INFO] Master container is up on http://localhost:31300"

src/metric/.gitignore

@@ -0,0 +1,7 @@
+/prometheus/data/
+/client-plugins/dcgm-exporter-installer/
+/client-plugins/demo-all-in-one/artifact/
+/client-plugins/demo-all-in-one/publish/
+/client-plugins/demo-all-in-one/checklist
+/client-plugins/demo-all-in-one/VERSION
+/client-plugins/all-in-one-full/

src/metric/client-plugins/all-in-one-demo/README.md

@@ -0,0 +1,65 @@
+# 客户侧组件安装包构建、发布流程
+
+## 第一步：配置版本和组件
+
+首先搞定配置文件：
+
+1. 把 `.checklist.example` 重命名成 `checklist`
+2. 把 `.VERSION.example` 重命名成 `VERSION`
+
+### checklist 文件格式
+```
+# 组件名称 目录路径 版本号 [依赖组件] [安装顺序]
+dcgm-exporter-installer /path/to/dcgm-exporter-installer 1.1.0
+node-exporter-installer /path/to/node-exporter-installer 1.1.0
+```
+
+### VERSION 文件
+设置需要发布的版本号，比如 `1.29.0`
+
+> 建议用 `version-manager.sh` 来管理版本
+
+## 第二步：构建安装包
+
+直接跑脚本：
+```bash
+./package_artifact.sh
+```
+
+构建完的东西会放在 `artifact/` 目录下，按版本分文件夹。
+
+如果版本已经存在了，想要覆盖重新构建：
+```bash
+./package_artifact.sh --force
+```
+
+构建完可以手工测试安装包。
+
+## 第三步：发布安装包
+
+用这个脚本发布：
+```bash
+./publish_artifact.sh
+```
+
+发布后的内容在 `publish/` 目录里，包含：
+- 压缩版本的安装包
+- 一键安装的bash脚本
+
+## 第四步：部署到FTP服务器
+
+把发布的内容上传到FTP服务器，客户端就可以通过一键命令安装：
+
+```bash
+curl -fsSL 'ftp://{$USER}:{$PASSWD}@{$your-ftp-server}/setup.sh' -o setup.sh
+
+# root用户直接执行，非root用户需要使用sudo
+chmod +x setup.sh
+bash setup.sh --server {$your-ftp-server} --user {$USER} --password {$PASSWD}
+
+示例：
+curl -fsS 'ftp://ftpuser:ZGClab1234!@177.177.70.200/setup.sh' -o setup.sh
+chmod +x setup.sh
+bash setup.sh --server {$域名} --user ftpuser --password 'ZGClab1234!'
+
+```

src/metric/client-plugins/all-in-one-demo/config/.VERSION.example

@@ -0,0 +1 @@
+1.29.0

src/metric/client-plugins/all-in-one-demo/config/.checklist.example

@@ -0,0 +1,3 @@
+# 组件名称 目录路径 版本号 [依赖组件] [安装顺序]
+dcgm-exporter-installer /Users/sundapeng/Project/nlp/aiops/client-plugins/dcgm-exporter-installer 1.1.0
+node-exporter-installer /Users/sundapeng/Project/nlp/aiops/client-plugins/node-exporter-installer 1.1.0

src/metric/client-plugins/all-in-one-demo/config/.config.env.example

@@ -0,0 +1,8 @@
+# Argus Metric 配置文件示例
+# 复制此文件为 config.env 并根据需要修改配置
+
+# 连接master服务
+MASTER_ENDPOINT=master.argus.com:3000
+
+# 上报状态间隔描述（秒）
+REPORT_INTERVAL_SECONDS=60

src/metric/client-plugins/all-in-one-demo/config/config.env

@@ -0,0 +1,3 @@
+# Elasticsearch
+ES_HOST=es.log.argus.com
+ES_PORT=9200

src/metric/client-plugins/all-in-one-demo/config/dns.conf.example

@@ -0,0 +1 @@
+177.177.17.106

src/metric/client-plugins/all-in-one-demo/plugins/node-exporter/check_health.sh

@@ -0,0 +1,55 @@
+#!/bin/bash
+
+# Node Exporter 健康检查脚本
+# 输出 JSON 格式结果
+
+set -e
+
+# 检查 Node Exporter 健康状态
+check_health() {
+    local url="http://localhost:9100"
+    local metrics_url="$url/metrics"
+    local name="node-exporter"
+    local status="unhealth"
+    local reason=""
+    
+    # 检查 curl 是否可用
+    if ! command -v curl &> /dev/null; then
+        reason="curl 命令不可用，无法进行健康检查"
+        echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+        exit 1
+    fi
+    
+    # 测试根路径连接
+    local http_code=$(curl -s -o /dev/null -w "%{http_code}" "$url" 2>/dev/null || echo "000")
+    
+    if [[ "$http_code" == "200" ]]; then
+        # 测试 metrics 端点
+        local metrics_code=$(curl -s -o /dev/null -w "%{http_code}" "$metrics_url" 2>/dev/null || echo "000")
+        
+        if [[ "$metrics_code" == "200" ]]; then
+            status="health"
+            reason="success"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 0
+        else
+            reason="Metrics 端点异常 (HTTP $metrics_code)"
+            echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+            exit 1
+        fi
+    else
+        reason="HTTP 服务异常 (HTTP $http_code)，请检查 Node Exporter 是否正在运行在端口 9100"
+        echo "{\"name\": \"$name\", \"status\": \"$status\", \"reason\": \"$reason\"}"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    check_health
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/plugins/node-exporter/install.sh

@@ -0,0 +1,343 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 更新安装记录
+update_install_record() {
+    local pid="$1"
+    # 使用传入的安装目录参数，如果没有则使用默认值
+    local install_base_dir="${2:-/opt/argus-metric/current}"
+    local install_record="$install_base_dir/.install_record"
+    
+    # 如果安装记录文件不存在，说明是首次安装，由主安装脚本统一创建
+    if [[ ! -f "$install_record" ]]; then
+        log_info "安装记录文件不存在，将由主安装脚本创建"
+        return 0
+    fi
+    
+    # 如果文件存在，说明是重启场景，只更新 PID 字段
+    if command -v jq &> /dev/null; then
+        # 读取当前 PID
+        local current_pid=$(jq -r '.components."node-exporter".pid // ""' "$install_record" 2>/dev/null)
+        
+        if [[ -z "$current_pid" ]]; then
+            log_warning "无法读取当前 PID，跳过更新"
+            return 1
+        fi
+        
+        # 使用 jq 只更新 pid 字段，保持字符串类型，保留其他字段
+        jq --arg new_pid "$pid" '.components."node-exporter".pid = $new_pid' "$install_record" > "$install_record.tmp" && mv "$install_record.tmp" "$install_record"
+        log_info "PID 已更新: $current_pid -> $pid"
+    else
+        log_warning "jq 命令不可用，无法更新安装记录文件"
+    fi
+}
+
+# 显示帮助信息
+show_help() {
+    echo "Node Exporter 安装脚本"
+    echo
+    echo "用法: $0 [选项]"
+    echo
+    echo "选项:"
+    echo "  --help     显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0          # 安装 Node Exporter"
+    echo
+}
+
+# 解析命令行参数
+INSTALL_DIR=""
+for arg in "$@"; do
+    case $arg in
+        --help|-h)
+            show_help
+            exit 0
+            ;;
+        *)
+            # 如果参数不是以--开头，则认为是安装目录
+            if [[ ! "$arg" =~ ^-- ]]; then
+                INSTALL_DIR="$arg"
+            else
+                log_error "未知参数: $arg"
+                show_help
+                exit 1
+            fi
+            ;;
+    esac
+done
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    source /etc/os-release
+    log_info "检测到操作系统: $NAME $VERSION"
+    
+    # 检查是否为 Linux 系统
+    if [[ "$ID" != "ubuntu" && "$ID" != "debian" && "$ID" != "centos" && "$ID" != "rhel" && "$ID" != "fedora" ]]; then
+        log_warning "此脚本主要针对常见 Linux 发行版，其他系统可能需要调整"
+    fi
+    
+    # 检查系统架构
+    local arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    if [[ "$arch" != "x86_64" && "$arch" != "amd64" ]]; then
+        log_warning "当前架构为 $arch，node_exporter 主要支持 x86_64/amd64"
+    fi
+}
+
+stop_existing_service() {
+    log_info "检查并停止可能运行的 Node Exporter 服务..."
+
+    # 当前脚本 PID，防止误杀
+    SELF_PID=$$
+
+    # 1. 停止 systemd 服务（如果存在）
+    if systemctl list-units --full -all | grep -q "node_exporter.service"; then
+        log_info "检测到 systemd 服务 node_exporter，正在停止..."
+        systemctl stop node_exporter || true
+        systemctl disable node_exporter || true
+    fi
+
+    # 2. 清理可能存在的 PID 文件
+    for pid_file in /var/run/node-exporter.pid /var/run/node_exporter.pid /tmp/node_exporter.pid; do
+        if [[ -f "$pid_file" ]]; then
+            local pid=$(cat "$pid_file")
+            if kill -0 "$pid" 2>/dev/null; then
+                log_info "发现 Node Exporter (PID: $pid)，正在停止..."
+                kill "$pid"
+                sleep 2
+                kill -0 "$pid" 2>/dev/null && kill -9 "$pid"
+            fi
+            rm -f "$pid_file"
+        fi
+    done
+
+    # 3. 用 pgrep 查找进程，排除当前脚本
+    local pids=$(pgrep -f "node_exporter|node-exporter|/usr/local/bin/node-exporter" | grep -vw "$SELF_PID" || true)
+    if [[ -n "$pids" ]]; then
+        log_info "发现 Node Exporter 进程 (PID: $pids)，正在停止..."
+        for pid in $pids; do
+            if kill -0 "$pid" 2>/dev/null; then
+                kill "$pid" 2>/dev/null || true
+                sleep 1
+                kill -0 "$pid" 2>/dev/null && kill -9 "$pid" 2>/dev/null || true
+            fi
+        done
+    fi
+
+    # 4. 兜底：检查是否有进程占用 9100 端口
+    local listen_pids=$(lsof -ti:9100 2>/dev/null || true)
+    if [[ -n "$listen_pids" ]]; then
+        log_warning "发现占用 9100 端口的进程 (PID: $listen_pids)，强制终止..."
+        for pid in $listen_pids; do
+            kill -9 "$pid" 2>/dev/null || true
+        done
+        sleep 1
+    fi
+
+    # 5. 最终验证
+    if netstat -tuln 2>/dev/null | grep -q ":9100 "; then
+        log_error "端口 9100 仍被占用，请手动检查"
+        return 1
+    else
+        log_success "旧的 Node Exporter 已完全停止"
+    fi
+}
+
+
+# 安装 Node Exporter 二进制文件
+install_node_exporter() {
+    log_info "安装 Node Exporter..."
+    
+    local binary_file="bin/node_exporter"
+    local install_dir="/usr/local/bin"
+    
+    if [[ ! -f "$binary_file" ]]; then
+        log_error "找不到 Node Exporter 二进制文件: $binary_file"
+        exit 1
+    fi
+    
+    # 停止可能运行的服务
+    stop_existing_service
+    
+    # 复制二进制文件并重命名为统一格式
+    cp "$binary_file" "$install_dir/node-exporter"
+    chmod +x "$install_dir/node-exporter"
+    
+    log_success "Node Exporter 二进制文件安装完成"
+}
+
+# 创建用户和组
+create_user() {
+    log_info "创建 node_exporter 用户..."
+    
+    # 检查用户是否已存在
+    if id "node_exporter" &>/dev/null; then
+        log_info "用户 node_exporter 已存在"
+    else
+        useradd --no-create-home --shell /bin/false node_exporter
+        log_success "用户 node_exporter 创建完成"
+    fi
+}
+
+# 安装配置文件
+install_config() {
+    log_info "安装配置文件..."
+    
+    local config_dir="/etc/node_exporter"
+    
+    # 创建配置目录
+    mkdir -p "$config_dir"
+    
+    # 创建文本文件收集器目录
+    mkdir -p "/var/lib/node_exporter/textfile_collector"
+    chown node_exporter:node_exporter "/var/lib/node_exporter/textfile_collector"
+}
+
+# 启动 Node Exporter 服务
+start_node_exporter() {
+    log_info "启动 Node Exporter 服务..."
+    
+    local binary_path="/usr/local/bin/node-exporter"
+    local log_file="/var/log/node-exporter.log"
+    local pid_file="/var/run/node-exporter.pid"
+    
+    # 检查服务是否已经在运行
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "Node Exporter 服务已在运行 (PID: $pid)"
+            return 0
+        else
+            log_warning "发现过期的 PID 文件，正在清理..."
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 检查端口是否被占用
+    if netstat -tuln 2>/dev/null | grep -q ":9100 "; then
+        log_warning "端口 9100 已被占用，请检查是否有其他服务在运行"
+        return 1
+    fi
+    
+    # 启动服务
+    log_info "正在启动 Node Exporter..."
+    nohup "$binary_path" --web.listen-address=:9100 > "$log_file" 2>&1 &
+    local pid=$!
+    
+    # 保存 PID
+    echo "$pid" > "$pid_file"
+    
+    # 等待服务启动
+    sleep 2
+    
+    # 检查服务是否成功启动
+    if kill -0 "$pid" 2>/dev/null; then
+        log_success "Node Exporter 服务启动成功 (PID: $pid)"
+        log_info "日志文件: $log_file"
+        log_info "PID 文件: $pid_file"
+        
+        # 更新安装记录
+        update_install_record "$pid" "$INSTALL_DIR"
+    else
+        log_error "Node Exporter 服务启动失败"
+        rm -f "$pid_file"
+        return 1
+    fi
+}
+
+
+
+# 显示安装信息
+show_install_info() {
+    log_success "Node Exporter 安装完成！"
+    echo
+    echo "安装信息:"
+    echo "  二进制文件: /usr/local/bin/node-exporter"
+    echo "  运行用户: node_exporter"
+    echo "  配置目录: /etc/node_exporter/"
+    echo "  默认端口: 9100"
+    echo
+    echo "使用方法:"
+    echo "  手动启动: /usr/local/bin/node-exporter --web.listen-address=:9100"
+    echo "  后台启动: nohup /usr/local/bin/node-exporter --web.listen-address=:9100 &"
+    echo
+    echo "测试连接:"
+    echo "  curl http://localhost:9100/metrics"
+    echo "  curl http://localhost:9100"
+    echo
+    echo "Prometheus 配置示例:"
+    echo "  - job_name: 'node_exporter'"
+    echo "    static_configs:"
+    echo "      - targets: ['localhost:9100']"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Node Exporter 安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    check_system
+    
+    log_info "开始安装 Node Exporter..."
+    
+    install_node_exporter
+    create_user
+    install_config
+    start_node_exporter
+    
+    show_install_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi
+

src/metric/client-plugins/all-in-one-demo/plugins/node-exporter/package.sh

@@ -0,0 +1,87 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+# 获取当前目录
+CURRENT_DIR=$(pwd)
+PACKAGE_NAME="node-exporter-$(date +%Y%m%d-%H%M%S)"
+PACKAGE_FILE="${PACKAGE_NAME}.tar.gz"
+
+log_info "开始打包 Node Exporter 安装包..."
+
+# 检查必要文件
+log_info "检查必要文件..."
+
+required_files=(
+    "install.sh"
+    "uninstall.sh"
+    "bin/node_exporter"
+    "check_health.sh"
+)
+
+missing_files=()
+for file in "${required_files[@]}"; do
+    if [[ ! -f "$file" ]]; then
+        missing_files+=("$file")
+    fi
+done
+
+if [[ ${#missing_files[@]} -gt 0 ]]; then
+    echo "缺少以下文件:"
+    for file in "${missing_files[@]}"; do
+        echo "  - $file"
+    done
+    exit 1
+fi
+
+log_success "所有必要文件检查完成"
+
+# 创建临时目录
+TEMP_DIR=$(mktemp -d)
+log_info "创建临时目录: $TEMP_DIR"
+
+# 复制文件到临时目录
+cp -r . "$TEMP_DIR/$PACKAGE_NAME"
+
+# 进入临时目录
+cd "$TEMP_DIR"
+
+# 创建压缩包
+log_info "创建压缩包: $PACKAGE_FILE"
+tar -czf "$PACKAGE_FILE" "$PACKAGE_NAME"
+
+# 移动压缩包到原目录
+mv "$PACKAGE_FILE" "$CURRENT_DIR/"
+
+# 清理临时目录
+rm -rf "$TEMP_DIR"
+
+# 返回原目录
+cd "$CURRENT_DIR"
+
+# 显示结果
+log_success "打包完成！"
+echo
+echo "安装包文件: $PACKAGE_FILE"
+echo "文件大小: $(du -h "$PACKAGE_FILE" | cut -f1)"
+echo
+echo "使用方法:"
+echo "1. 将 $PACKAGE_FILE 传输到目标服务器"
+echo "2. 解压: tar -xzf $PACKAGE_FILE"
+echo "3. 进入目录: cd $PACKAGE_NAME"
+echo "4. 运行安装: sudo ./install.sh"
+echo
+echo "注意: 请确保所有必要文件都存在"

src/metric/client-plugins/all-in-one-demo/plugins/node-exporter/uninstall.sh

@@ -0,0 +1,239 @@
+#!/bin/bash
+
+# Node Exporter 卸载脚本
+# 版本: 1.0
+# 作者: AIOps Team
+# 日期: $(date +%Y-%m-%d)
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 停止运行中的进程
+stop_processes() {
+    log_info "停止 Node Exporter 进程..."
+    
+    local pid_file="/var/run/node-exporter.pid"
+    local stopped=false
+    
+    # 首先尝试通过 PID 文件停止服务
+    if [[ -f "$pid_file" ]]; then
+        local pid=$(cat "$pid_file")
+        if kill -0 "$pid" 2>/dev/null; then
+            log_info "通过 PID 文件停止服务 (PID: $pid)..."
+            kill "$pid"
+            sleep 3
+            
+            # 检查进程是否已停止
+            if kill -0 "$pid" 2>/dev/null; then
+                log_warning "进程未响应，强制终止..."
+                kill -9 "$pid" 2>/dev/null || true
+            fi
+            log_success "Node Exporter 进程已停止"
+            stopped=true
+        else
+            log_warning "PID 文件存在但进程已不存在，清理 PID 文件"
+            rm -f "$pid_file"
+        fi
+    fi
+    
+    # 查找并杀死所有 node_exporter 和 node-exporter 进程
+    local pids=$(pgrep -f "node_exporter\|node-exporter" 2>/dev/null || true)
+    if [[ -n "$pids" ]]; then
+        log_info "发现 node_exporter 或 node-exporter 进程，正在停止..."
+        for pid in $pids; do
+            log_info "停止进程 PID: $pid"
+            kill "$pid" 2>/dev/null || true
+        done
+        sleep 2
+        
+        # 检查是否还有进程在运行，如果有则强制终止
+        local remaining_pids=$(pgrep -f "node_exporter\|node-exporter" 2>/dev/null || true)
+        if [[ -n "$remaining_pids" ]]; then
+            log_warning "进程未响应，强制终止..."
+            for pid in $remaining_pids; do
+                log_info "强制终止进程 PID: $pid"
+                kill -9 "$pid" 2>/dev/null || true
+            done
+            sleep 1
+        fi
+        
+        # 最终检查
+        if pgrep -f "node_exporter\|node-exporter" > /dev/null; then
+            log_error "无法停止所有 node_exporter 进程"
+        else
+            log_success "所有 Node Exporter 进程已停止"
+            stopped=true
+        fi
+    else
+        log_info "Node Exporter 进程未运行"
+    fi
+    
+    # 清理 PID 文件
+    rm -f "$pid_file"
+    
+    if [[ "$stopped" == "false" ]]; then
+        log_warning "未发现需要停止的 Node Exporter 进程"
+    fi
+}
+
+# 删除二进制文件
+remove_binary() {
+    log_info "删除 Node Exporter 二进制文件..."
+    
+    local binary_files=(
+        "/usr/local/bin/node-exporter"
+        "/usr/local/bin/node_exporter"
+    )
+    
+    local deleted=false
+    for binary_file in "${binary_files[@]}"; do
+        if [[ -f "$binary_file" ]]; then
+            rm -f "$binary_file"
+            log_success "二进制文件已删除: $binary_file"
+            deleted=true
+        fi
+    done
+    
+    if [[ "$deleted" == "false" ]]; then
+        log_info "二进制文件不存在"
+    fi
+}
+
+# 删除配置文件
+remove_config() {
+    log_info "删除配置文件..."
+    
+    local config_dir="/etc/node_exporter"
+    
+    if [[ -d "$config_dir" ]]; then
+        rm -rf "$config_dir"
+        log_success "配置目录已删除"
+    else
+        log_info "配置目录不存在"
+    fi
+}
+
+# 删除数据目录
+remove_data_dir() {
+    log_info "删除数据目录..."
+    
+    local data_dir="/var/lib/node_exporter"
+    
+    if [[ -d "$data_dir" ]]; then
+        rm -rf "$data_dir"
+        log_success "数据目录已删除"
+    else
+        log_info "数据目录不存在"
+    fi
+}
+
+# 检查用户状态（可选）
+check_user_status() {
+    log_info "检查 node_exporter 用户状态..."
+    
+    if id "node_exporter" &>/dev/null; then
+        log_info "检测到 node_exporter 用户存在"
+        log_warning "node_exporter 是系统用户，可能被其他服务使用"
+        log_info "为了系统稳定性，将保留 node_exporter 用户"
+        log_info "如需手动删除，请运行: sudo userdel node_exporter"
+    else
+        log_info "node_exporter 用户不存在"
+    fi
+}
+
+# 清理日志文件
+cleanup_logs() {
+    log_info "清理日志文件..."
+    
+    # 清理 journal 日志
+    journalctl --vacuum-time=1s --quiet || true
+    
+    # 删除安装脚本创建的日志文件
+    rm -f /var/log/node-exporter.log
+    
+    log_success "日志文件已清理"
+}
+
+# 显示卸载信息
+show_uninstall_info() {
+    log_success "Node Exporter 卸载完成！"
+    echo
+    echo "已删除的内容:"
+    echo "  - 二进制文件: /usr/local/bin/node-exporter"
+    echo "  - 配置目录: /etc/node_exporter"
+    echo "  - 数据目录: /var/lib/node_exporter"
+    echo "  - 相关日志文件"
+    echo
+    echo "注意:"
+    echo "  - node_exporter 用户已保留（系统用户，可能被其他服务使用）"
+    echo "  - 如需完全清理，请手动检查并删除相关文件"
+    echo
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Node Exporter 卸载脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    check_root
+    
+    log_warning "此操作将完全卸载 Node Exporter"
+    read -p "确认继续？(y/N): " confirm
+    
+    if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+        log_info "取消卸载操作"
+        exit 0
+    fi
+    
+    log_info "开始卸载 Node Exporter..."
+    
+    stop_processes
+    remove_binary
+    remove_config
+    remove_data_dir
+    cleanup_logs
+    
+    # 检查用户状态
+    check_user_status
+    
+    show_uninstall_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/check_health.sh

@@ -0,0 +1,286 @@
+#!/bin/bash
+
+# 整体健康检查脚本，调用各个组件的健康检查并将结果写入 .health_log 文件
+
+set -e
+
+# PID 文件检测，防止重复执行
+PIDFILE="/var/run/check_health.pid"
+if [ -f "$PIDFILE" ] && kill -0 $(cat "$PIDFILE") 2>/dev/null; then
+    echo "健康检查脚本已在运行中，跳过本次执行" >&2
+    exit 0
+fi
+echo $$ > "$PIDFILE"
+trap "rm -f $PIDFILE" EXIT
+
+# 获取脚本所在目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+HEALTH_LOG_FILE="$SCRIPT_DIR/.health_log"
+INSTALL_RECORD_FILE="$SCRIPT_DIR/.install_record"
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数 - 输出到 stderr 避免影响 JSON 结果
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1" >&2
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1" >&2
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1" >&2
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1" >&2
+}
+
+# 检查单个组件健康状态
+check_component() {
+    local component_name="$1"
+    local check_script_path="$2"
+
+    log_info "检查 $component_name 健康状态..."
+
+    if [[ ! -f "$check_script_path" ]]; then
+        log_error "健康检查脚本不存在: $check_script_path"
+        echo "{\"name\": \"$component_name\", \"status\": \"unhealth\", \"reason\": \"健康检查脚本不存在: $check_script_path\"}"
+        return 1
+    fi
+
+    if [[ ! -x "$check_script_path" ]]; then
+        log_error "健康检查脚本无执行权限: $check_script_path"
+        echo "{\"name\": \"$component_name\", \"status\": \"unhealth\", \"reason\": \"健康检查脚本无执行权限: $check_script_path\"}"
+        return 1
+    fi
+
+    # 执行健康检查脚本，只捕获 stdout，stderr 输出到终端
+    local result
+    if result=$("$check_script_path" 2>/dev/null); then
+        log_success "$component_name 健康检查通过"
+        echo "$result"
+        return 0
+    else
+        log_warning "$component_name 健康检查失败"
+        echo "$result"
+        return 1
+    fi
+}
+
+# 生成时间戳
+get_timestamp() {
+    date '+%Y-%m-%d %H:%M:%S'
+}
+
+# 生成UTC时间戳
+get_utc_timestamp() {
+    date -u '+%Y-%m-%dT%H:%M:%SZ'
+}
+
+# 获取主机名
+get_hostname() {
+    echo "${HOSTNAME:-$(hostname)}"
+}
+
+# 创建健康状态目录
+create_health_dir() {
+    local hostname=$(get_hostname)
+    local health_dir="/private/argus/agent/$hostname/health"
+    
+    if [[ ! -d "$health_dir" ]]; then
+        log_info "创建健康状态目录: $health_dir"
+        mkdir -p "$health_dir"
+    fi
+    
+    echo "$health_dir"
+}
+
+# 写入单个模块的健康状态JSON文件
+write_component_health_json() {
+    local component_name="$1"
+    local status="$2"
+    local error_msg="$3"
+    local health_dir="$4"
+    
+    # 生成模块名前缀-xxx.json格式的文件名
+    local module_prefix="metric"
+    local filename="${module_prefix}-${component_name}.json"
+    local filepath="$health_dir/$filename"
+    
+    # 生成UTC时间戳
+    local timestamp=$(get_utc_timestamp)
+    
+    # 构建JSON内容
+    local json_content=$(cat << EOF
+{
+    "status": "$status",
+    "error": "$error_msg",
+    "timestamp": "$timestamp"
+}
+EOF
+)
+    
+    # 写入文件
+    echo "$json_content" > "$filepath"
+    log_info "已写入模块健康状态文件: $filepath"
+}
+
+# 从安装记录文件中读取组件安装目录
+read_install_record() {
+    local install_record_file="$1"
+
+    if [[ ! -f "$install_record_file" ]]; then
+        log_error "安装记录文件不存在: $install_record_file"
+        return 1
+    fi
+
+    # 检查是否有 jq 命令来解析 JSON
+    if command -v jq &> /dev/null; then
+        # 使用 jq 解析 JSON
+        local components_json
+        if components_json=$(jq -r '.components | to_entries[] | "\(.key):\(.value.install_dir)"' "$install_record_file" 2>/dev/null); then
+            echo "$components_json"
+            return 0
+        else
+            log_error "无法解析安装记录文件 JSON 格式: $install_record_file"
+            return 1
+        fi
+    else
+        # 如果没有 jq，尝试简单的文本解析
+        log_warning "jq 命令不可用，尝试简单文本解析"
+
+        # 查找所有 install_dir 行
+        local components=()
+        while IFS= read -r line; do
+            if [[ "$line" =~ \"install_dir\":[[:space:]]*\"([^\"]+)\" ]]; then
+                local install_dir="${BASH_REMATCH[1]}"
+                # 从路径中提取组件名称
+                local component_name=$(basename "$install_dir")
+                components+=("$component_name:$install_dir")
+            fi
+        done < "$install_record_file"
+
+        if [[ ${#components[@]} -gt 0 ]]; then
+            printf '%s\n' "${components[@]}"
+            return 0
+        else
+            log_error "无法从安装记录文件中提取组件信息"
+            return 1
+        fi
+    fi
+}
+
+# 主函数
+main() {
+    echo "==========================================" >&2
+    echo "    整体健康检查脚本" >&2
+    echo "==========================================" >&2
+    echo >&2
+
+    # 记录健康检查开始时间
+    local start_time=$(get_timestamp)
+    log_info "健康检查开始时间: $start_time"
+
+    # 创建健康状态目录
+    local health_dir
+    health_dir=$(create_health_dir)
+
+    # 从安装记录文件中读取组件信息
+    log_info "从安装记录文件读取组件信息: $INSTALL_RECORD_FILE"
+    local components_info
+    if ! components_info=$(read_install_record "$INSTALL_RECORD_FILE"); then
+        log_error "无法读取安装记录文件，健康检查终止"
+        exit 1
+    fi
+
+    # 存储所有检查结果
+    local all_results=()
+    local overall_status="health"
+
+    # 逐个检查组件
+    while IFS= read -r component_info; do
+        if [[ -n "$component_info" ]]; then
+            IFS=':' read -r component_name install_dir <<< "$component_info"
+            local check_script_path="$install_dir/check_health.sh"
+
+            local result
+            local component_status="healthy"
+            local error_msg=""
+            
+            if result=$(check_component "$component_name" "$check_script_path"); then
+                all_results+=("$result")
+            else
+                all_results+=("$result")
+                overall_status="unhealth"
+                component_status="unhealthy"
+                # 从结果中提取错误信息
+                if command -v jq &> /dev/null; then
+                    error_msg=$(echo "$result" | jq -r '.reason // ""' 2>/dev/null || echo "")
+                else
+                    # 简单的文本解析提取错误信息
+                    if [[ "$result" =~ \"reason\":[[:space:]]*\"([^\"]+)\" ]]; then
+                        error_msg="${BASH_REMATCH[1]}"
+                    fi
+                fi
+            fi
+            
+            # 写入单个模块的健康状态JSON文件
+            write_component_health_json "$component_name" "$component_status" "$error_msg" "$health_dir"
+        fi
+    done <<< "$components_info"
+
+    # 记录健康检查结束时间
+    local end_time=$(get_timestamp)
+    log_info "健康检查结束时间: $end_time"
+
+    # 构建完整的健康检查结果 JSON
+    local health_check_result=$(cat << EOF
+{
+  "start_time": "$start_time",
+  "end_time": "$end_time",
+  "overall_status": "$overall_status",
+  "components": [
+$(printf '%s,\n' "${all_results[@]}" | sed '$s/,$//')
+  ]
+}
+EOF
+)
+
+    # 写入健康日志文件
+    log_info "将健康检查结果写入日志文件: $HEALTH_LOG_FILE"
+    echo "$health_check_result" >> "$HEALTH_LOG_FILE"
+
+    # 输出 JSON 结果到 stdout
+    echo "$health_check_result"
+
+    # 显示总结到 stderr
+    echo >&2
+    echo "==========================================" >&2
+    echo "    健康检查总结" >&2
+    echo "==========================================" >&2
+    echo "开始时间: $start_time" >&2
+    echo "结束时间: $end_time" >&2
+    echo "整体状态: $overall_status" >&2
+    echo "日志文件: $HEALTH_LOG_FILE" >&2
+    echo >&2
+
+    if [[ "$overall_status" == "health" ]]; then
+        log_success "所有组件健康检查通过！"
+        exit 0
+    else
+        log_error "部分组件健康检查失败，请查看上述详细信息"
+        exit 1
+    fi
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/check_version.sh

@@ -0,0 +1,240 @@
+#!/bin/bash
+
+# 版本校验脚本
+# 比较本地 LATEST_VERSION 与 FTP 的 VERSION 版本，如果不一致则更新对应版本
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数 - 输出到 stderr 避免影响函数返回值
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1" >&2
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1" >&2
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1" >&2
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1" >&2
+}
+
+# 获取脚本所在目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+# 动态获取当前版本目录
+get_current_version_dir() {
+    # 查找 /opt/argus-metric/versions/ 下的最新版本目录
+    local versions_dir="/opt/argus-metric/versions"
+    if [[ -d "$versions_dir" ]]; then
+        # 按版本号排序，获取最新的版本目录
+        local latest_version_dir=$(ls -1 "$versions_dir" 2>/dev/null | sort -V | tail -1)
+        if [[ -n "$latest_version_dir" ]]; then
+            echo "$versions_dir/$latest_version_dir"
+        else
+            echo "/opt/argus-metric"
+        fi
+    else
+        echo "/opt/argus-metric"
+    fi
+}
+
+# 获取当前版本目录
+CURRENT_VERSION_DIR=$(get_current_version_dir)
+# LATEST_VERSION 文件在根目录
+LOCAL_VERSION_FILE="/opt/argus-metric/LATEST_VERSION"
+REMOTE_VERSION_URL=""
+LOG_FILE="$CURRENT_VERSION_DIR/.version_check.log"
+
+# 从环境变量或配置文件获取 FTP 服务器信息
+get_ftp_config() {
+    # 优先从环境变量获取配置
+    log_info "获取 FTP 配置信息..."
+    
+    # 如果环境变量中没有设置，则尝试从配置文件读取
+    if [[ -z "$FTP_SERVER" || -z "$FTP_USER" || -z "$FTP_PASSWORD" ]]; then
+        local config_file="$SCRIPT_DIR/../config/config.env"
+        if [[ -f "$config_file" ]]; then
+            log_info "从配置文件读取 FTP 配置: $config_file"
+            source "$config_file"
+        fi
+    else
+        log_info "使用环境变量中的 FTP 配置"
+    fi
+    
+    # 设置默认值（如果环境变量和配置文件都没有设置）
+    FTP_SERVER="${FTP_SERVER:-localhost}"
+    FTP_USER="${FTP_USER:-ftpuser}"
+    FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+    
+    # 构建远程版本文件 URL
+    REMOTE_VERSION_URL="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/LATEST_VERSION"
+    
+    log_info "FTP 配置来源: ${FTP_CONFIG_SOURCE:-环境变量/配置文件}"
+}
+
+# 获取远程版本号
+get_remote_version() {
+    log_info "从 FTP 服务器获取远程版本号..."
+    log_info "远程地址: $REMOTE_VERSION_URL"
+    
+    # 先测试 FTP 连接
+    log_info "测试 FTP 连接..."
+    if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null 2>&1; then
+        log_success "FTP 服务器连接成功"
+    else
+        log_error "无法连接到 FTP 服务器: $FTP_SERVER"
+        return 1
+    fi
+    
+    # 测试 LATEST_VERSION 文件是否存在
+    log_info "检查远程 LATEST_VERSION 文件是否存在..."
+    if curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/LATEST_VERSION" >/dev/null 2>&1; then
+        log_success "远程 LATEST_VERSION 文件存在"
+    else
+        log_error "远程 LATEST_VERSION 文件不存在或无法访问"
+        return 1
+    fi
+    
+    # 获取远程版本号
+    local remote_version
+    if remote_version=$(curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfL "ftp://${FTP_SERVER}/LATEST_VERSION" 2>/dev/null | tr -d '[:space:]'); then
+        if [[ -n "$remote_version" ]]; then
+            log_success "获取到远程版本号: $remote_version"
+            echo "$remote_version"
+        else
+            log_error "远程版本号为空"
+            return 1
+        fi
+    else
+        log_error "获取远程版本号失败"
+        return 1
+    fi
+}
+
+# 获取本地版本号
+get_local_version() {
+    if [[ -f "$LOCAL_VERSION_FILE" ]]; then
+        local local_version=$(cat "$LOCAL_VERSION_FILE" 2>/dev/null | tr -d '[:space:]')
+        if [[ -n "$local_version" ]]; then
+            log_info "本地版本号: $local_version"
+            echo "$local_version"
+        else
+            log_warning "本地版本文件为空"
+            echo ""
+        fi
+    else
+        log_warning "本地版本文件不存在: $LOCAL_VERSION_FILE"
+        echo ""
+    fi
+}
+
+# 更新到新版本
+update_to_version() {
+    local new_version="$1"
+    local temp_dir="/tmp/argus-update-$$"
+    local setup_script="$temp_dir/setup.sh"
+    
+    log_info "开始更新到版本: $new_version"
+    
+    # 创建临时目录
+    mkdir -p "$temp_dir"
+    
+    # 下载最新的 setup.sh
+    log_info "从 FTP 服务器下载最新的安装脚本..."
+    local setup_url="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/setup.sh"
+    
+    if curl -fsS "$setup_url" -o "$setup_script"; then
+        log_success "安装脚本下载完成"
+    else
+        log_error "下载安装脚本失败: $setup_url"
+        rm -rf "$temp_dir"
+        return 1
+    fi
+    
+    # 添加执行权限
+    chmod +x "$setup_script"
+    
+    # 执行安装脚本
+    log_info "执行安装脚本进行版本更新..."
+    if "$setup_script" --server "$FTP_SERVER" --user "$FTP_USER" --password "$FTP_PASSWORD" --version "$new_version"; then
+        log_success "版本更新完成: $new_version"
+        rm -rf "$temp_dir"
+        return 0
+    else
+        log_error "版本更新失败: $new_version"
+        rm -rf "$temp_dir"
+        return 1
+    fi
+}
+
+# 记录检查日志
+log_check() {
+    local message="$1"
+    local timestamp=$(date '+%Y-%m-%d %H:%M:%S')
+    echo "[$timestamp] $message" >> "$LOG_FILE"
+}
+
+# 主函数
+main() {
+    log_info "开始版本校验检查..."
+    log_check "版本校验检查开始"
+    
+    # 确保系统目录存在
+    mkdir -p "/opt/argus-metric"
+    mkdir -p "$CURRENT_VERSION_DIR"
+    
+    log_info "当前版本目录: $CURRENT_VERSION_DIR"
+    
+    # 获取 FTP 配置
+    get_ftp_config
+    
+    # 获取本地版本号
+    local local_version
+    local_version=$(get_local_version)
+    
+    # 获取远程版本号
+    local remote_version
+    if ! remote_version=$(get_remote_version); then
+        log_error "无法获取远程版本号，跳过本次检查"
+        log_check "版本校验失败：无法获取远程版本号"
+        exit 1
+    fi
+    
+    # 比较版本号
+    if [[ "$local_version" == "$remote_version" ]]; then
+        log_info "版本一致，无需更新 (本地: $local_version, 远程: $remote_version)"
+        log_check "版本校验完成：版本一致 ($local_version)"
+    else
+        log_info "检测到版本不一致 (本地: $local_version, 远程: $remote_version)"
+        log_check "检测到版本不一致：本地($local_version) -> 远程($remote_version)"
+        
+        # 更新到新版本
+        if update_to_version "$remote_version"; then
+            log_success "版本更新成功: $local_version -> $remote_version"
+            log_check "版本更新成功：$local_version -> $remote_version"
+        else
+            log_error "版本更新失败"
+            log_check "版本更新失败：$local_version -> $remote_version"
+            exit 1
+        fi
+    fi
+    
+    log_success "版本校验检查完成"
+    log_check "版本校验检查完成"
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/install_artifact.sh

@@ -0,0 +1,995 @@
+#!/bin/bash
+
+set -e
+
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 配置变量
+INSTALL_DIR="${1:-$(pwd)}"  # 使用第一个参数作为安装目录，如果没有参数则使用当前目录
+TEMP_DIR="/tmp/metrics-install-$$"
+VERSION_FILE="version.json"
+
+
+# 加载配置文件
+load_config() {
+    local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+    local config_file="$script_dir/config.env"
+    
+    if [[ -f "$config_file" ]]; then
+        log_info "加载配置文件: $config_file"
+        # 导出配置文件中的环境变量
+        set -a  # 自动导出所有变量
+        source "$config_file"
+        set +a  # 关闭自动导出
+        log_success "配置文件加载完成"
+    else
+        log_warning "配置文件不存在: $config_file，使用默认配置"
+    fi
+}
+
+# 复制配置文件到安装目录
+copy_config_files() {
+    log_info "复制配置文件到安装目录..."
+    
+    local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+    local source_config="$script_dir/../config/config.env"
+    local target_config="$INSTALL_DIR/config.env"
+    
+    if [[ -f "$source_config" ]]; then
+        # 检查源文件和目标文件是否是同一个文件
+        if [[ "$source_config" == "$target_config" ]]; then
+            log_info "配置文件已在目标位置，跳过复制"
+            log_success "配置文件已存在: $target_config"
+        else
+            if cp "$source_config" "$target_config"; then
+                log_success "配置文件复制完成: $target_config"
+            else
+                log_error "配置文件复制失败"
+                return 1
+            fi
+        fi
+    else
+        log_warning "源配置文件不存在: $source_config"
+    fi
+    
+    # 复制版本校验脚本
+    log_info "复制版本校验脚本到安装目录..."
+    local target_check_version="$INSTALL_DIR/check_version.sh"
+    
+    # 检查目标文件是否已存在（从 artifact 包中解压出来的）
+    if [[ -f "$target_check_version" ]]; then
+        log_info "版本校验脚本已存在，设置执行权限..."
+        chmod +x "$target_check_version"
+        log_success "版本校验脚本权限设置完成: $target_check_version"
+    else
+        log_warning "版本校验脚本不存在: $target_check_version"
+        log_info "请确保 check_version.sh 已包含在 artifact 包中"
+    fi
+}
+
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0 [安装目录]"
+        log_info "如果不指定安装目录，将使用当前目录: $(pwd)"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    source /etc/os-release
+    log_info "检测到操作系统: $NAME $VERSION"
+    
+    # 检查系统架构
+    arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    # 检查磁盘空间
+    available_space=$(df / | awk 'NR==2 {print $4}')
+    if [[ $available_space -lt 10485760 ]]; then  # 10GB in KB
+        log_warning "可用磁盘空间不足 10GB，当前可用: $(($available_space / 1024 / 1024))GB"
+    fi
+    
+    # 检查内存
+    total_mem=$(free -m | awk 'NR==2{print $2}')
+    if [[ $total_mem -lt 4096 ]]; then  # 4GB
+        log_warning "系统内存不足 4GB，当前: ${total_mem}MB"
+    fi
+}
+
+# 查找版本文件
+find_version_file() {
+    log_info "查找版本信息文件..."
+    
+    # 在当前目录查找
+    if [[ -f "$VERSION_FILE" ]]; then
+        VERSION_FILE_PATH="$(pwd)/$VERSION_FILE"
+        log_success "找到版本文件: $VERSION_FILE"
+        return 0
+    fi
+    
+    # 在 artifact 目录查找
+    for version_dir in artifact/*/; do
+        if [[ -f "${version_dir}${VERSION_FILE}" ]]; then
+            VERSION_FILE_PATH="$(cd "$(dirname "${version_dir}${VERSION_FILE}")" && pwd)/$(basename "${version_dir}${VERSION_FILE}")"
+            log_success "找到版本文件: $VERSION_FILE_PATH"
+            return 0
+        fi
+    done
+    
+    log_error "未找到版本信息文件 $VERSION_FILE"
+    exit 1
+}
+
+# 解析版本信息
+parse_version_info() {
+    log_info "解析版本信息..."
+    
+    if [[ ! -f "$VERSION_FILE_PATH" ]]; then
+        log_error "版本文件不存在: $VERSION_FILE_PATH"
+        exit 1
+    fi
+    
+    # 使用 jq 解析 JSON（如果可用）
+    if command -v jq &> /dev/null; then
+        # 验证JSON文件格式
+        if ! jq empty "$VERSION_FILE_PATH" 2>/dev/null; then
+            log_error "JSON文件格式错误，请检查 $VERSION_FILE_PATH"
+            exit 1
+        fi
+        
+        VERSION=$(jq -r '.version' "$VERSION_FILE_PATH")
+        BUILD_TIME=$(jq -r '.build_time' "$VERSION_FILE_PATH")
+        
+        # 解析 artifact_list
+        if jq -e '.artifact_list' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.artifact_list | to_entries[] | "\(.key):\(.value)"' "$VERSION_FILE_PATH" > "$TEMP_DIR/components.txt"
+        else
+            log_error "version.json 中缺少 artifact_list 字段"
+            exit 1
+        fi
+        
+        # 解析 checksums
+        if jq -e '.checksums' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.checksums | to_entries[] | "\(.key):\(.value)"' "$VERSION_FILE_PATH" > "$TEMP_DIR/checksums.txt"
+        else
+            log_error "version.json 中缺少 checksums 字段"
+            exit 1
+        fi
+        
+        # 解析 install_order（现在包含完整的文件名）
+        if jq -e '.install_order' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.install_order[]' "$VERSION_FILE_PATH" > "$TEMP_DIR/install_order.txt"
+        else
+            log_error "version.json 中缺少 install_order 字段"
+            exit 1
+        fi
+        
+    else
+        log_warning "jq 未安装，使用简单的 JSON 解析"
+        # 简单的 JSON 解析
+        VERSION=$(grep '"version"' "$VERSION_FILE_PATH" | sed 's/.*"version": *"\([^"]*\)".*/\1/')
+        BUILD_TIME=$(grep '"build_time"' "$VERSION_FILE_PATH" | sed 's/.*"build_time": *"\([^"]*\)".*/\1/')
+        
+        # 解析 artifact_list（跳过字段名本身）
+        grep -A 100 '"artifact_list"' "$VERSION_FILE_PATH" | grep -v '"artifact_list"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)":\s*"[^"]*".*/\1/')
+            version=$(echo "$line" | sed 's/.*"[^"]*":\s*"\([^"]*\)".*/\1/')
+            echo "$component:$version" >> "$TEMP_DIR/components.txt"
+        done
+        
+        # 解析 checksums（跳过字段名本身）
+        grep -A 100 '"checksums"' "$VERSION_FILE_PATH" | grep -v '"checksums"' | grep -E '^\s*"[^"]+":\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)":\s*"[^"]*".*/\1/')
+            checksum=$(echo "$line" | sed 's/.*"[^"]*":\s*"\([^"]*\)".*/\1/')
+            echo "$component:$checksum" >> "$TEMP_DIR/checksums.txt"
+        done
+        
+        # 解析 install_order（跳过字段名本身，只取数组元素）
+        grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -v '"install_order"' | grep -E '^\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)".*/\1/')
+            echo "$component" >> "$TEMP_DIR/install_order.txt"
+        done
+        
+        # 验证解析结果
+        if [[ ! -f "$TEMP_DIR/components.txt" || ! -s "$TEMP_DIR/components.txt" ]]; then
+            log_error "无法解析 artifact_list，请检查 version.json 格式"
+            exit 1
+        fi
+        
+        if [[ ! -f "$TEMP_DIR/checksums.txt" || ! -s "$TEMP_DIR/checksums.txt" ]]; then
+            log_error "无法解析 checksums，请检查 version.json 格式"
+            exit 1
+        fi
+        
+        if [[ ! -f "$TEMP_DIR/install_order.txt" || ! -s "$TEMP_DIR/install_order.txt" ]]; then
+            log_error "无法解析 install_order，请检查 version.json 格式"
+            exit 1
+        fi
+    fi
+    
+    log_success "版本信息解析完成"
+    log_info "  版本: $VERSION"
+    log_info "  构建时间: $BUILD_TIME"
+    
+    component_count=0
+    if [[ -f "$TEMP_DIR/components.txt" ]]; then
+        component_count=$(wc -l < "$TEMP_DIR/components.txt")
+        log_info "  组件数量: $component_count"
+        log_info "  组件列表:"
+        while IFS= read -r line; do
+            component=$(echo "$line" | cut -d':' -f1)
+            version=$(echo "$line" | cut -d':' -f2)
+            log_info "    - $component v$version"
+        done < "$TEMP_DIR/components.txt"
+    else
+        log_error "components.txt 文件不存在"
+        exit 1
+    fi
+}
+
+# 验证文件完整性
+verify_checksums() {
+    log_info "验证文件完整性..."
+    
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    log_info "Artifact 目录: $artifact_dir"
+    failed_verification=0
+    
+    if [[ -f "$TEMP_DIR/checksums.txt" ]]; then
+        while IFS= read -r line; do
+            component=$(echo "$line" | cut -d':' -f1)
+            expected_checksum=$(echo "$line" | cut -d':' -f2-)
+            
+            # 查找匹配的 tar 文件
+            actual_file=""
+            for file in "$artifact_dir/${component}-"*.tar.gz; do
+                if [[ -f "$file" ]]; then
+                    actual_file="$file"
+                    break
+                fi
+            done
+            
+            if [[ -z "$actual_file" ]]; then
+                log_error "找不到组件文件: $component"
+                failed_verification=1
+                continue
+            fi
+            
+            # 计算实际校验和
+            actual_checksum="sha256:$(sha256sum "$actual_file" | cut -d' ' -f1)"
+            
+            if [[ "$actual_checksum" == "$expected_checksum" ]]; then
+                log_success "  $component: 校验通过"
+            else
+                log_error "  $component: 校验失败"
+                log_error "    期望: $expected_checksum"
+                log_error "    实际: $actual_checksum"
+                failed_verification=1
+            fi
+        done < "$TEMP_DIR/checksums.txt"
+    fi
+    
+    if [[ $failed_verification -eq 1 ]]; then
+        log_error "文件完整性验证失败"
+        exit 1
+    fi
+    
+    log_success "所有文件校验通过"
+}
+
+# 创建安装目录
+create_install_dirs() {
+    log_info "创建安装目录..."
+    
+    mkdir -p "$INSTALL_DIR"
+    mkdir -p "$TEMP_DIR"
+    
+    log_success "安装目录创建完成: $INSTALL_DIR"
+}
+
+# 获取系统版本
+get_system_version() {
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        return 1
+    fi
+    
+    source /etc/os-release
+    
+    # 提取主版本号
+    case "$VERSION_ID" in
+        "20.04")
+            echo "ubuntu20"
+            ;;
+        "22.04")
+            echo "ubuntu22"
+            ;;
+        *)
+            log_warning "未识别的Ubuntu版本: $VERSION_ID，尝试使用ubuntu22"
+            echo "ubuntu22"
+            ;;
+    esac
+}
+
+# 安装系统依赖包
+install_system_deps() {
+    log_info "检查系统依赖包..."
+
+    local script_dir="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+    local deps_dir="$script_dir/deps"
+
+    # 检查deps目录是否存在
+    if [[ ! -d "$deps_dir" ]]; then
+        log_info "deps 目录不存在，跳过系统依赖包安装"
+        return 0
+    fi
+
+    # 获取系统版本对应的依赖目录
+    local system_version=$(get_system_version)
+    local version_deps_dir="$deps_dir/$system_version"
+    
+    log_info "检测到系统版本: $system_version"
+    
+    # 检查版本特定的依赖目录是否存在
+    if [[ ! -d "$version_deps_dir" ]]; then
+        log_warning "未找到 $system_version 版本的依赖目录: $version_deps_dir"
+        # 回退到旧的逻辑，检查根deps目录
+        local deps_count=$(find "$deps_dir" -name "*.tar.gz" | wc -l)
+        if [[ $deps_count -eq 0 ]]; then
+            log_info "deps 目录中没有 tar.gz 文件，跳过系统依赖包安装"
+            return 0
+        fi
+        version_deps_dir="$deps_dir"
+    else
+        # 检查版本目录中是否有tar.gz文件
+        local deps_count=$(find "$version_deps_dir" -name "*.tar.gz" | wc -l)
+        if [[ $deps_count -eq 0 ]]; then
+            log_info "$system_version 版本目录中没有 tar.gz 文件，跳过系统依赖包安装"
+            return 0
+        fi
+    fi
+
+    log_info "找到 $system_version 版本的依赖包，开始安装..."
+
+    # 创建临时目录用于解压依赖包
+    local deps_temp_dir="${TEMP_DIR:-/tmp}/deps"
+    mkdir -p "$deps_temp_dir"
+
+    # 定义要检查的核心依赖
+    local CORE_DEPS=(jq cron curl)
+    local FAILED_DEPS=()
+
+    # 处理每个tar.gz文件
+    find "$version_deps_dir" -name "*.tar.gz" | while read tar_file; do
+        local tar_basename=$(basename "$tar_file")
+        local extract_name="${tar_basename%.tar.gz}"
+
+        log_info "处理依赖包: $tar_basename"
+
+        # 解压到临时目录
+        local extract_dir="$deps_temp_dir/$extract_name"
+        mkdir -p "$extract_dir"
+
+        if tar -xzf "$tar_file" -C "$extract_dir" 2>/dev/null; then
+            log_success "  $tar_basename 解压完成"
+        else
+            log_error "  $tar_basename 解压失败"
+            continue
+        fi
+
+        # 进入解压目录，查找deb包
+        cd "$extract_dir" || continue
+        local deb_files=(*.deb)
+        if [[ ${#deb_files[@]} -gt 0 ]]; then
+            log_info "  找到 ${#deb_files[@]} 个 deb 包，开始安装..."
+
+            for deb in "${deb_files[@]}"; do
+                local pkg_name
+                pkg_name=$(dpkg-deb -f "$deb" Package 2>/dev/null)
+
+                # 如果已安装，则跳过
+                if dpkg -s "$pkg_name" &>/dev/null; then
+                    log_success "  $pkg_name 已安装，跳过"
+                    continue
+                fi
+
+                # 尝试安装
+                log_info "  安装 $pkg_name..."
+                if DEBIAN_FRONTEND=noninteractive dpkg -i "$deb" &>/dev/null; then
+                    log_success "  $pkg_name 安装成功"
+                else
+                    log_warning "  $pkg_name 安装失败，尝试修复依赖..."
+                    if DEBIAN_FRONTEND=noninteractive apt-get install -f -y &>/dev/null; then
+                        if dpkg -s "$pkg_name" &>/dev/null; then
+                            log_success "  $pkg_name 修复安装成功"
+                        else
+                            log_error "  $pkg_name 仍未安装成功"
+                            FAILED_DEPS+=("$pkg_name")
+                        fi
+                    else
+                        log_error "  $pkg_name 自动修复失败"
+                        FAILED_DEPS+=("$pkg_name")
+                    fi
+                fi
+            done
+        else
+            log_info "  $tar_basename 中没有找到deb包，跳过"
+        fi
+
+        # 返回到依赖临时目录
+        cd "$deps_temp_dir" || continue
+    done
+
+    # 检查并启动 cron 服务
+    start_cron_service
+
+    # 总结安装结果
+    if [[ ${#FAILED_DEPS[@]} -gt 0 ]]; then
+        log_error "以下系统依赖未能成功安装，安装终止，请手动安装后重试："
+        for f in "${FAILED_DEPS[@]}"; do
+            echo "  - $f"
+        done
+        exit 1
+    else
+        log_success "系统依赖包安装完成，全部就绪"
+    fi
+}
+
+# 启动 cron 服务
+start_cron_service() {
+    log_info "检查并启动 cron 服务..."
+    
+    # 检查 cron 是否已经在运行
+    if pgrep -x "cron" > /dev/null; then
+        log_success "cron 服务已在运行"
+        return 0
+    fi
+    
+    # 检查 /usr/sbin/cron 是否存在
+    if [[ ! -f "/usr/sbin/cron" ]]; then
+        log_warning "cron 可执行文件不存在，跳过启动"
+        return 1
+    fi
+    
+    # 启动 cron 服务
+    log_info "启动 cron 服务..."
+    if /usr/sbin/cron start 2>/dev/null || /usr/sbin/cron 2>/dev/null; then
+        log_success "cron 服务启动成功"
+        
+        sleep 2
+        
+        if pgrep -x "cron" > /dev/null; then
+            log_success "cron 服务运行正常"
+        else
+            log_warning "cron 服务可能未正常启动"
+        fi
+    else
+        log_error "cron 服务启动失败"
+        return 1
+    fi
+}
+
+# 安装组件
+install_components() {
+    log_info "开始安装组件..."
+    
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    log_info "Artifact 目录: $artifact_dir"
+    install_count=0
+    total_count=0
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        total_count=$(wc -l < "$TEMP_DIR/install_order.txt")
+    fi
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        while IFS= read -r filename; do
+            install_count=$((install_count + 1))
+            
+            # 从文件名中提取组件名（去掉时间戳后缀）
+            component=$(echo "$filename" | sed 's/-[0-9]\{8\}-[0-9]\{6\}\.tar\.gz$//')
+            
+            log_info "[$install_count/$total_count] 安装 $component..."
+            log_info "  文件名: $filename"
+            
+            # 直接使用完整的文件名
+            tar_file="$artifact_dir/$filename"
+            
+            if [[ ! -f "$tar_file" ]]; then
+                log_error "找不到组件文件: $filename"
+                log_info "  期望路径: $tar_file"
+                log_info "  当前目录: $(pwd)"
+                log_info "  目录内容:"
+                ls -la "$artifact_dir" | while read line; do
+                    log_info "    $line"
+                done
+                exit 1
+            fi
+            
+            log_info "  找到文件: $tar_file"
+            
+            # 解压到临时目录
+            component_temp_dir="$TEMP_DIR/$component"
+            mkdir -p "$component_temp_dir"
+            
+            if tar -xzf "$tar_file" -C "$component_temp_dir" 2>/dev/null; then
+                log_success "  $component 解压完成"
+            else
+                log_error "  $component 解压失败"
+                exit 1
+            fi
+            
+            # 查找解压后的目录
+            extracted_dir=""
+            for dir in "$component_temp_dir"/*; do
+                if [[ -d "$dir" ]]; then
+                    extracted_dir="$dir"
+                    break
+                fi
+            done
+            
+            if [[ -z "$extracted_dir" ]]; then
+                log_error "  $component 解压后未找到目录"
+                exit 1
+            fi
+            
+            # 执行安装脚本
+            if [[ -f "$extracted_dir/install.sh" ]]; then
+                log_info "  执行 $component 安装脚本..."
+                if (cd "$extracted_dir" && ./install.sh "$INSTALL_DIR"); then
+                    log_success "  $component 安装完成"
+                else
+                    log_error "  $component 安装失败"
+                    exit 1
+                fi
+            else
+                log_error "  $component 缺少 install.sh 文件"
+                exit 1
+            fi
+            
+            # 将解压后的目录移动到安装目录，保留组件目录
+            component_install_dir="$INSTALL_DIR/$component"
+            # 简化安装逻辑：直接删除旧目录，不进行备份
+            if [[ -d "$component_install_dir" ]]; then
+                log_info "  组件目录已存在，删除旧版本: $component_install_dir"
+                rm -rf "$component_install_dir"
+                # log_info "  组件目录已存在，备份后更新: $component_install_dir"
+                # mv "$component_install_dir" "${component_install_dir}.backup.$(date +%Y%m%d_%H%M%S)"
+            fi
+            mv "$extracted_dir" "$component_install_dir"
+            log_success "  组件目录已保存: $component_install_dir"
+            
+            # 清理临时文件
+            rm -rf "$component_temp_dir"
+        done < "$TEMP_DIR/install_order.txt"
+    fi
+    
+    log_success "所有组件安装完成"
+}
+
+# 创建安装记录
+create_install_record() {
+    log_info "创建安装记录..."
+    
+    # 等待一段时间确保所有进程都已启动
+    log_info "等待进程启动..."
+    sleep 3
+    
+    local install_time=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+    local install_record_file="$INSTALL_DIR/.install_record"
+    
+    # 创建 JSON 格式的安装记录
+    cat > "$install_record_file" << EOF
+{
+  "version": "$VERSION",
+  "build_time": "$BUILD_TIME",
+  "install_time": "$install_time",
+  "install_dir": "$INSTALL_DIR",
+  "install_pid": $$,
+  "components": {
+EOF
+
+    # 添加组件信息
+    local first_component=true
+    if [[ -f "$TEMP_DIR/components.txt" ]]; then
+        while IFS= read -r line; do
+            component=$(echo "$line" | cut -d':' -f1)
+            version=$(echo "$line" | cut -d':' -f2)
+            
+            # 获取组件的进程信息
+            local component_pid=""
+            
+            # 根据组件名查找进程，使用多种方法确保能找到PID
+            case "$component" in
+                "node-exporter")
+                    # 尝试多种方式查找node_exporter进程
+                    component_pid=$(pgrep -f "node_exporter" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(pgrep -f "node-exporter" | head -1)
+                    fi
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "node_exporter" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+                "dcgm-exporter")
+                    # 查找dcgm-exporter进程
+                    component_pid=$(pgrep -f "dcgm-exporter" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(pgrep -f "dcgm_exporter" | head -1)
+                    fi
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "dcgm-exporter" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+                "fluent-bit")
+                    # 查找fluent-bit进程
+                    component_pid=$(pgrep -f "fluent-bit" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(pgrep -f "fluent_bit" | head -1)
+                    fi
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "fluent-bit" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+                "argus-agent")
+                    # 查找argus-agent进程
+                    component_pid=$(pgrep -f "argus-agent" | head -1)
+                    if [[ -z "$component_pid" ]]; then
+                        component_pid=$(ps aux | grep -v grep | grep "argus-agent" | awk '{print $2}' | head -1)
+                    fi
+                    ;;
+            esac
+            
+            # 记录找到的PID信息
+            if [[ -n "$component_pid" ]]; then
+                log_info "  找到 $component 进程 PID: $component_pid"
+            else
+                log_warning "  未找到 $component 进程"
+            fi
+            
+            # 添加逗号分隔符
+            if [[ "$first_component" == "true" ]]; then
+                first_component=false
+            else
+                echo "," >> "$install_record_file"
+            fi
+            
+            # 添加组件信息
+            cat >> "$install_record_file" << EOF
+    "$component": {
+      "version": "$version",
+      "pid": "$component_pid",
+      "install_dir": "$INSTALL_DIR/$component"
+    }
+EOF
+        done < "$TEMP_DIR/components.txt"
+    fi
+    
+    # 结束 JSON
+    cat >> "$install_record_file" << EOF
+  }
+}
+EOF
+
+    log_success "安装记录已创建: $install_record_file"
+}
+
+# 检查cron任务是否已存在
+check_cron_task_exists() {
+    local task_pattern="$1"
+    local temp_cron="$2"
+    
+    if grep -q "$task_pattern" "$temp_cron"; then
+        return 0  # 任务已存在
+    else
+        return 1  # 任务不存在
+    fi
+}
+
+# 设置健康检查定时任务
+setup_health_check_cron() {
+    log_info "设置健康检查定时任务..."
+    
+    # 直接使用当前安装目录，不依赖current软链接
+    # INSTALL_DIR 是 /opt/argus-metric/versions/1.34.0
+    local check_health_script="$INSTALL_DIR/check_health.sh"
+    
+    # 检查健康检查脚本是否存在
+    if [[ ! -f "$check_health_script" ]]; then
+        log_error "健康检查脚本不存在: $check_health_script"
+        return 1
+    fi
+    
+    # 确保脚本有执行权限
+    chmod +x "$check_health_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    
+    # 获取当前用户的crontab（如果存在）
+    crontab -l 2>/dev/null > "$temp_cron" || touch "$temp_cron"
+    
+    # 检查并删除旧的健康检查任务
+    if check_cron_task_exists "check_health.sh" "$temp_cron"; then
+        log_info "发现旧的健康检查定时任务，正在更新..."
+        # 删除所有包含check_health.sh的行
+        grep -v "check_health.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的健康检查定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每5分钟执行一次）
+    echo "# Argus-Metrics 健康检查定时任务" >> "$temp_cron"
+    echo "*/5 * * * * $check_health_script >> $INSTALL_DIR/.health_cron.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "健康检查定时任务设置成功"
+        log_info "  执行频率: 每5分钟"
+        log_info "  日志文件: $INSTALL_DIR/.health_cron.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "健康检查定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "健康检查通过crontab自动执行"
+}
+
+# 设置 DNS 同步定时任务
+setup_dns_sync_cron() {
+    log_info "设置 DNS 同步定时任务..."
+    
+    # 使用当前版本目录中的 DNS 同步脚本
+    local sync_dns_script="$INSTALL_DIR/sync_dns.sh"
+    
+    # 检查 DNS 同步脚本是否存在
+    if [[ ! -f "$sync_dns_script" ]]; then
+        log_warning "DNS 同步脚本不存在: $sync_dns_script"
+        log_warning "跳过 DNS 同步定时任务设置"
+        return 0
+    fi
+    
+    # 确保脚本有执行权限
+    chmod +x "$sync_dns_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    
+    # 获取当前用户的crontab（如果存在）
+    crontab -l 2>/dev/null > "$temp_cron" || touch "$temp_cron"
+    
+    # 检查并删除旧的 DNS 同步任务
+    if check_cron_task_exists "sync_dns.sh" "$temp_cron"; then
+        log_info "发现旧的 DNS 同步定时任务，正在更新..."
+        # 删除所有包含sync_dns.sh的行
+        grep -v "sync_dns.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的 DNS 同步定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每1分钟执行一次）
+    # 直接使用版本目录中的 DNS 同步脚本
+    echo "# Argus-Metrics DNS 同步定时任务" >> "$temp_cron"
+    echo "* * * * * $sync_dns_script >> $INSTALL_DIR/.dns_sync.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "DNS 同步定时任务设置成功"
+        log_info "  执行频率: 每1分钟"
+        log_info "  日志文件: $INSTALL_DIR/.dns_sync.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "DNS 同步定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "DNS 同步通过crontab自动执行"
+}
+
+# 设置版本校验定时任务
+setup_version_check_cron() {
+    log_info "设置版本校验定时任务..."
+    
+    # 使用当前版本目录中的版本校验脚本
+    local check_version_script="$INSTALL_DIR/check_version.sh"
+    
+    # 检查脚本是否存在
+    if [[ ! -f "$check_version_script" ]]; then
+        log_warning "版本校验脚本不存在: $check_version_script"
+        log_info "跳过版本校验定时任务设置"
+        return 0
+    fi
+    
+    # 确保脚本可执行
+    chmod +x "$check_version_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    crontab -l > "$temp_cron" 2>/dev/null || touch "$temp_cron"
+    
+    # 检查是否已存在版本校验定时任务
+    if check_cron_task_exists "check_version.sh" "$temp_cron"; then
+        log_info "发现旧的版本校验定时任务，正在更新..."
+        # 删除所有包含check_version.sh的行
+        grep -v "check_version.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的版本校验定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每30分钟执行一次）
+    echo "# Argus-Metrics 版本校验定时任务" >> "$temp_cron"
+    echo "*/1 * * * * $check_version_script >> $INSTALL_DIR/.version_check.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "版本校验定时任务设置成功"
+        log_info "  执行频率: 每1分钟"
+        log_info "  日志文件: $INSTALL_DIR/.version_check.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "版本校验定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "版本校验通过crontab自动执行"
+}
+
+# 设置自动重启定时任务
+setup_restart_cron() {
+    log_info "设置自动重启定时任务..."
+    
+    # 使用当前版本目录中的重启脚本
+    local restart_script="$INSTALL_DIR/restart_unhealthy.sh"
+    
+    # 检查脚本是否存在
+    if [[ ! -f "$restart_script" ]]; then
+        log_warning "重启脚本不存在: $restart_script"
+        log_info "跳过自动重启定时任务设置"
+        return 0
+    fi
+    
+    # 确保脚本可执行
+    chmod +x "$restart_script"
+    
+    # 创建临时crontab文件
+    local temp_cron="/tmp/crontab_$$"
+    crontab -l > "$temp_cron" 2>/dev/null || touch "$temp_cron"
+    
+    # 检查是否已存在自动重启定时任务
+    if check_cron_task_exists "restart_unhealthy.sh" "$temp_cron"; then
+        log_info "发现旧的自动重启定时任务，正在更新..."
+        # 删除所有包含restart_unhealthy.sh的行
+        grep -v "restart_unhealthy.sh" "$temp_cron" > "$temp_cron.new"
+        mv "$temp_cron.new" "$temp_cron"
+        log_info "旧的自动重启定时任务已删除"
+    fi
+    
+    # 添加新的定时任务（每2分钟执行一次）
+    echo "# Argus-Metrics 自动重启定时任务" >> "$temp_cron"
+    echo "*/2 * * * * $restart_script >> $INSTALL_DIR/.restart.log 2>&1" >> "$temp_cron"
+    
+    # 安装新的crontab
+    if crontab "$temp_cron"; then
+        log_success "自动重启定时任务设置成功"
+        log_info "  执行频率: 每2分钟"
+        log_info "  日志文件: $INSTALL_DIR/.restart.log"
+        log_info "  查看定时任务: crontab -l"
+        log_info "  删除定时任务: crontab -e"
+    else
+        log_error "自动重启定时任务设置失败"
+        rm -f "$temp_cron"
+        return 1
+    fi
+    
+    # 清理临时文件
+    rm -f "$temp_cron"
+    
+    log_info "自动重启检查通过crontab自动执行"
+}
+
+# 显示安装信息
+show_install_info() {
+    log_success "Argus-Metrics All-in-One 安装完成！"
+}
+
+cleanup() {
+    if [[ -d "$TEMP_DIR" ]]; then
+        rm -rf "$TEMP_DIR"
+    fi
+}
+
+trap cleanup EXIT
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus-Metrics All-in-One 安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    # 加载配置文件
+    load_config
+    
+    log_info "安装目录: $INSTALL_DIR"
+    echo
+    
+    check_root
+    check_system
+    find_version_file
+    create_install_dirs
+    install_system_deps     
+    parse_version_info    
+    verify_checksums
+    install_components
+    copy_config_files
+    create_install_record
+    setup_health_check_cron
+    setup_dns_sync_cron
+    setup_version_check_cron
+    setup_restart_cron
+    
+    # 注释掉立即执行健康检查，避免与cron任务重复执行
+    # log_info "立即执行一次健康检查..."
+    # local check_health_script="$INSTALL_DIR/check_health.sh"
+    # if [[ -f "$check_health_script" ]]; then
+    #     if "$check_health_script" >> "$INSTALL_DIR/.health_check.log" 2>&1; then
+    #         log_success "健康检查执行完成"
+    #     else
+    #         log_warning "健康检查执行失败，请检查日志: $INSTALL_DIR/.health_check.log"
+    #     fi
+    # else
+    #     log_warning "健康检查脚本不存在: $check_health_script"
+    # fi
+    
+    show_install_info
+}
+
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/package_artifact.sh

@@ -0,0 +1,474 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "AIOps All-in-One 打包脚本"
+    echo
+    echo "用法: $0 [选项]"
+    echo
+    echo "选项:"
+    echo "  --force     强制重新打包，即使版本已存在"
+    echo "  --help     显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0              # 正常打包，跳过已存在的版本"
+    echo "  $0 --force      # 强制重新打包"
+    echo
+}
+
+# 解析命令行参数
+FORCE_PACKAGE=false
+if [[ "$1" == "--force" ]]; then
+    FORCE_PACKAGE=true
+    log_info "强制重新打包模式"
+elif [[ "$1" == "--help" || "$1" == "-h" ]]; then
+    show_help
+    exit 0
+fi
+
+# 获取当前目录和版本
+CURRENT_DIR=$(pwd)
+VERSION=$(cat config/VERSION 2>/dev/null || echo "1.0.0")
+ARTIFACT_DIR="artifact/$VERSION"
+
+log_info "开始打包 AIOps All-in-One 安装包 v$VERSION"
+
+# 检查必要文件
+log_info "检查必要文件..."
+if [[ ! -f "config/VERSION" ]]; then
+    log_error "VERSION 文件不存在"
+    exit 1
+fi
+
+if [[ ! -f "config/checklist" ]]; then
+    log_error "checklist 文件不存在"
+    exit 1
+fi
+
+# 检查是否已存在该版本
+if [[ -d "$ARTIFACT_DIR" && "$FORCE_PACKAGE" == "false" ]]; then
+    log_info "检查版本 $VERSION 是否已存在..."
+    
+    # 检查 version.json 是否存在
+    if [[ -f "$ARTIFACT_DIR/version.json" ]]; then
+        log_info "找到已存在的版本信息文件"
+        
+        # 检查是否所有组件文件都存在
+        missing_files=0
+        existing_components=0
+        
+        # 解析已存在的 version.json 来检查文件
+        if command -v jq &> /dev/null; then
+            # 使用 jq 解析
+            while IFS= read -r component; do
+                existing_components=$((existing_components + 1))
+                # 查找对应的 tar 文件
+                found_file=false
+                for file in "$ARTIFACT_DIR/${component}-"*.tar.gz; do
+                    if [[ -f "$file" ]]; then
+                        found_file=true
+                        break
+                    fi
+                done
+                if [[ "$found_file" == "false" ]]; then
+                    missing_files=$((missing_files + 1))
+                    log_warning "  缺少文件: $component"
+                fi
+            done < <(jq -r '.artifact_list | keys[]' "$ARTIFACT_DIR/version.json" 2>/dev/null)
+        else
+            # 简单的文件检查
+            for file in "$ARTIFACT_DIR"/*.tar.gz; do
+                if [[ -f "$file" ]]; then
+                    existing_components=$((existing_components + 1))
+                fi
+            done
+        fi
+        
+        # 如果所有文件都存在，则跳过打包
+        if [[ $missing_files -eq 0 && $existing_components -gt 0 ]]; then
+            log_success "版本 $VERSION 已完整打包，跳过重复打包"
+            echo
+            echo "现有文件:"
+            ls -la "$ARTIFACT_DIR"
+            echo
+            echo "如需强制重新打包，请删除目录: rm -rf $ARTIFACT_DIR"
+            echo "或使用: ./package.sh --force"
+            exit 0
+        else
+            log_warning "版本 $VERSION 存在但不完整，将重新打包"
+            log_info "  现有组件: $existing_components"
+            log_info "  缺少文件: $missing_files"
+        fi
+    else
+        log_warning "版本目录存在但缺少 version.json，将重新打包"
+    fi
+fi
+
+# 创建 artifact 目录
+mkdir -p "$ARTIFACT_DIR"
+log_info "创建输出目录: $ARTIFACT_DIR"
+
+# 创建临时文件存储数据
+TEMP_DIR=$(mktemp -d)
+COMPONENTS_FILE="$TEMP_DIR/components.txt"
+VERSIONS_FILE="$TEMP_DIR/versions.txt"
+DEPENDENCIES_FILE="$TEMP_DIR/dependencies.txt"
+INSTALL_ORDER_FILE="$TEMP_DIR/install_order.txt"
+CHECKSUMS_FILE="$TEMP_DIR/checksums.txt"
+ARTIFACT_LIST_FILE="$TEMP_DIR/artifact_list.txt"
+
+# 解析 checklist 文件
+log_info "解析组件清单..."
+line_num=0
+component_count=0
+
+while IFS= read -r line; do
+    [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+    
+    line_num=$((line_num + 1))
+    
+    # 解析行: 组件名 目录路径 版本 [依赖组件] [安装顺序]
+    read -r component component_path version dep_component order <<< "$line"
+    
+    if [[ -z "$component" || -z "$component_path" || -z "$version" ]]; then
+        log_warning "跳过无效行 $line_num: $line"
+        continue
+    fi
+    
+    # 存储组件信息
+    echo "$component" >> "$COMPONENTS_FILE"
+    echo "$component:$version" >> "$VERSIONS_FILE"
+    echo "$component:$component_path" >> "$TEMP_DIR/component_paths.txt"
+    
+    if [[ -n "$dep_component" && "$dep_component" != "$component" ]]; then
+        echo "$component:$dep_component" >> "$DEPENDENCIES_FILE"
+    fi
+    
+    if [[ -n "$order" && "$order" =~ ^[0-9]+$ ]]; then
+        echo "$order:$component" >> "$INSTALL_ORDER_FILE"
+    else
+        # 如果没有指定顺序，按解析顺序分配
+        echo "$line_num:$component" >> "$INSTALL_ORDER_FILE"
+    fi
+    
+    component_count=$((component_count + 1))
+    log_info "  - $component v$version"
+done < config/checklist
+
+if [[ $component_count -eq 0 ]]; then
+    log_error "没有找到有效的组件"
+    rm -rf "$TEMP_DIR"
+    exit 1
+fi
+
+log_success "找到 $component_count 个组件"
+
+# 检查组件目录是否存在
+log_info "检查组件目录..."
+missing_components=()
+
+while IFS= read -r component; do
+    # 获取组件路径
+    component_path=$(grep "^$component:" "$TEMP_DIR/component_paths.txt" | cut -d':' -f2-)
+    if [[ -z "$component_path" ]]; then
+        log_error "未找到组件 $component 的路径配置"
+        log_info "请检查 component_paths.txt 文件或添加路径配置"
+        exit 1
+    fi
+    
+    if [[ ! -d "$component_path" ]]; then
+        missing_components+=("$component:$component_path")
+    fi
+done < "$COMPONENTS_FILE"
+
+if [[ ${#missing_components[@]} -gt 0 ]]; then
+    log_error "以下组件目录不存在:"
+    for component_path in "${missing_components[@]}"; do
+        echo "  - $component_path"
+    done
+    rm -rf "$TEMP_DIR"
+    exit 1
+fi
+
+# 打包各个组件
+log_info "开始打包组件..."
+
+while IFS= read -r component; do
+    # 获取组件版本和路径
+    version=$(grep "^$component:" "$VERSIONS_FILE" | cut -d':' -f2)
+    component_path=$(grep "^$component:" "$TEMP_DIR/component_paths.txt" | cut -d':' -f2-)
+    if [[ -z "$component_path" ]]; then
+        log_error "未找到组件 $component 的路径配置"
+        log_info "请检查 component_paths.txt 文件或添加路径配置"
+        exit 1
+    fi
+    
+    log_info "打包 $component v$version..."
+    log_info "  组件路径: $component_path"
+    
+    # 进入组件目录
+    cd "$component_path"
+    
+    # 检查组件是否有 package.sh
+    if [[ ! -f "package.sh" ]]; then
+        log_error "$component 缺少 package.sh 文件"
+        cd "$CURRENT_DIR"
+        rm -rf "$TEMP_DIR"
+        exit 1
+    fi
+    
+    # 执行组件的打包脚本
+    if ./package.sh; then
+        # 查找生成的 tar 包
+        tar_file=$(find . -name "*.tar.gz" -type f | head -1)
+        if [[ -n "$tar_file" ]]; then
+            # 移动到 artifact 目录
+            mv "$tar_file" "$CURRENT_DIR/$ARTIFACT_DIR/"
+            tar_filename=$(basename "$tar_file")
+            
+            # 计算校验和
+            checksum=$(sha256sum "$CURRENT_DIR/$ARTIFACT_DIR/$tar_filename" | cut -d' ' -f1)
+            echo "$component:sha256:$checksum" >> "$CHECKSUMS_FILE"
+            echo "$component:$version" >> "$ARTIFACT_LIST_FILE"
+            
+            # 将完整的文件名存储到安装顺序文件中
+            echo "$tar_filename" >> "$TEMP_DIR/install_order_files.txt"
+            
+            log_success "  $component 打包完成: $tar_filename"
+        else
+            log_error "$component 打包失败，未找到生成的 tar 包"
+            cd "$CURRENT_DIR"
+            rm -rf "$TEMP_DIR"
+            exit 1
+        fi
+    else
+        log_error "$component 打包失败"
+        cd "$CURRENT_DIR"
+        rm -rf "$TEMP_DIR"
+        exit 1
+    fi
+    
+    # 返回主目录
+    cd "$CURRENT_DIR"
+done < "$COMPONENTS_FILE"
+
+# 生成 version.json
+log_info "生成版本信息文件..."
+version_json="$ARTIFACT_DIR/version.json"
+
+# 构建依赖关系 JSON
+deps_json=""
+if [[ -f "$DEPENDENCIES_FILE" ]]; then
+    first=true
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        dep=$(echo "$line" | cut -d':' -f2)
+        if [[ "$first" == "true" ]]; then
+            deps_json="\"$component\":[\"$dep\"]"
+            first=false
+        else
+            deps_json="$deps_json,\"$component\":[\"$dep\"]"
+        fi
+    done < "$DEPENDENCIES_FILE"
+fi
+
+# 构建安装顺序数组
+order_array=""
+if [[ -f "$TEMP_DIR/install_order_files.txt" ]]; then
+    first=true
+    while IFS= read -r filename; do
+        if [[ "$first" == "true" ]]; then
+            order_array="\"$filename\""
+            first=false
+        else
+            order_array="$order_array,\"$filename\""
+        fi
+    done < "$TEMP_DIR/install_order_files.txt"
+fi
+
+# 构建 artifact_list JSON
+artifact_json=""
+if [[ -f "$ARTIFACT_LIST_FILE" ]]; then
+    first=true
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        version=$(echo "$line" | cut -d':' -f2)
+        if [[ "$first" == "true" ]]; then
+            artifact_json="\"$component\":\"$version\""
+            first=false
+        else
+            artifact_json="$artifact_json,\"$component\":\"$version\""
+        fi
+    done < "$ARTIFACT_LIST_FILE"
+fi
+
+# 构建 checksums JSON
+checksums_json=""
+if [[ -f "$CHECKSUMS_FILE" ]]; then
+    first=true
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        checksum=$(echo "$line" | cut -d':' -f2-)
+        if [[ "$first" == "true" ]]; then
+            checksums_json="\"$component\":\"$checksum\""
+            first=false
+        else
+            checksums_json="$checksums_json,\"$component\":\"$checksum\""
+        fi
+    done < "$CHECKSUMS_FILE"
+fi
+
+# 生成完整的 version.json
+cat > "$version_json" << EOF
+{
+  "version": "$VERSION",
+  "build_time": "$(date -u +%Y-%m-%dT%H:%M:%SZ)",
+  "artifact_list": {
+    $artifact_json
+  },
+  "checksums": {
+    $checksums_json
+  },
+  "dependencies": {
+    $deps_json
+  },
+  "install_order": [
+    $order_array
+  ]
+}
+EOF
+
+log_success "版本信息文件生成完成: $version_json"
+
+# 复制`安装`脚本到 artifact 目录
+log_info "复制安装脚本..."
+if [[ -f "scripts/install_artifact.sh" ]]; then
+    cp "scripts/install_artifact.sh" "$ARTIFACT_DIR/install.sh"
+    chmod +x "$ARTIFACT_DIR/install.sh"
+    log_success "安装脚本复制完成: $ARTIFACT_DIR/install.sh"
+else
+    log_warning "scripts/install_artifact.sh 文件不存在"
+fi
+
+# 复制`卸载`脚本到 artifact 目录
+log_info "复制卸载脚本..."
+if [[ -f "scripts/uninstall_artifact.sh" ]]; then
+    cp "scripts/uninstall_artifact.sh" "$ARTIFACT_DIR/uninstall.sh"
+    chmod +x "$ARTIFACT_DIR/uninstall.sh"
+    log_success "卸载脚本复制完成: $ARTIFACT_DIR/uninstall.sh"
+else
+    log_warning "scripts/uninstall_artifact.sh 文件不存在"
+fi
+
+# 复制`健康检查`脚本到 artifact 目录
+log_info "复制健康检查脚本..."
+if [[ -f "scripts/check_health.sh" ]]; then
+    cp "scripts/check_health.sh" "$ARTIFACT_DIR/check_health.sh"
+    chmod +x "$ARTIFACT_DIR/check_health.sh"
+    log_success "健康检查脚本复制完成: $ARTIFACT_DIR/check_health.sh"
+else
+    log_warning "scripts/check_health.sh 文件不存在"
+fi
+
+# 复制`DNS 同步`脚本到 artifact 目录
+log_info "复制 DNS 同步脚本..."
+if [[ -f "scripts/sync_dns.sh" ]]; then
+    cp "scripts/sync_dns.sh" "$ARTIFACT_DIR/sync_dns.sh"
+    chmod +x "$ARTIFACT_DIR/sync_dns.sh"
+    log_success "DNS 同步脚本复制完成: $ARTIFACT_DIR/sync_dns.sh"
+else
+    log_warning "scripts/sync_dns.sh 文件不存在"
+fi
+
+# 复制`版本校验`脚本到 artifact 目录
+log_info "复制版本校验脚本..."
+if [[ -f "scripts/check_version.sh" ]]; then
+    cp "scripts/check_version.sh" "$ARTIFACT_DIR/check_version.sh"
+    chmod +x "$ARTIFACT_DIR/check_version.sh"
+    log_success "版本校验脚本复制完成: $ARTIFACT_DIR/check_version.sh"
+else
+    log_warning "scripts/check_version.sh 文件不存在"
+fi
+
+# 复制`自动重启`脚本到 artifact 目录
+log_info "复制自动重启脚本..."
+if [[ -f "scripts/restart_unhealthy.sh" ]]; then
+    cp "scripts/restart_unhealthy.sh" "$ARTIFACT_DIR/restart_unhealthy.sh"
+    chmod +x "$ARTIFACT_DIR/restart_unhealthy.sh"
+    log_success "自动重启脚本复制完成: $ARTIFACT_DIR/restart_unhealthy.sh"
+else
+    log_warning "scripts/restart_unhealthy.sh 文件不存在"
+fi
+
+# 复制配置文件到 artifact 目录
+log_info "复制配置文件..."
+if [[ -f "config/config.env" ]]; then
+    cp "config/config.env" "$ARTIFACT_DIR/"
+    log_success "配置文件复制完成: $ARTIFACT_DIR/config.env"
+else
+    log_warning "config 目录不存在，跳过配置文件复制"
+fi
+
+# DNS 配置文件不需要复制到版本目录，直接从 FTP 服务器根目录获取
+
+# 复制 deps 目录到 artifact 目录
+log_info "复制系统依赖包..."
+if [[ -d "deps" ]]; then
+    cp -r "deps" "$ARTIFACT_DIR/"
+    log_success "系统依赖包复制完成: $ARTIFACT_DIR/deps"
+    
+    # 显示deps目录内容
+    log_info "  依赖包列表:"
+    find "$ARTIFACT_DIR/deps" -name "*.tar.gz" -exec basename {} \; | while read dep_file; do
+        log_info "    - $dep_file"
+    done
+else
+    log_warning "deps 目录不存在，跳过依赖包复制"
+fi
+
+# 显示打包结果
+log_success "打包完成！"
+echo
+echo "版本: $VERSION"
+echo "输出目录: $ARTIFACT_DIR"
+echo "包含组件:"
+if [[ -f "$ARTIFACT_LIST_FILE" ]]; then
+    while IFS= read -r line; do
+        component=$(echo "$line" | cut -d':' -f1)
+        version=$(echo "$line" | cut -d':' -f2)
+        echo "  - $component v$version"
+    done < "$ARTIFACT_LIST_FILE"
+fi
+echo
+echo "文件列表:"
+ls -la "$ARTIFACT_DIR"
+echo
+
+# 清理临时文件
+rm -rf "$TEMP_DIR"

src/metric/client-plugins/all-in-one-demo/scripts/publish_artifact.sh

@@ -0,0 +1,265 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+GREEN='\033[0;32m'
+BLUE='\033[0;34m'
+RED='\033[0;31m'
+YELLOW='\033[1;33m'
+NC='\033[0m' # No Color
+
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "Argus-Metric Artifact 发布脚本"
+    echo
+    echo "用法: $0 <版本号> [选项]"
+    echo
+    echo "参数:"
+    echo "  <版本号>              要发布的版本号，对应 artifact 目录中的版本"
+    echo
+    echo "选项:"
+    echo "  --output-dir <路径>   指定输出目录 (默认: /private/argus/ftp/share/)"
+    echo "  --owner <uid:gid>     指定文件所有者 (默认: 2133:2015)"
+    echo "  -h, --help           显示此帮助信息"
+    echo
+    echo "示例:"
+    echo "  $0 1.20.0                                    # 使用默认配置发布"
+    echo "  $0 1.20.0 --output-dir /tmp/publish          # 指定输出目录"
+    echo "  $0 1.20.0 --owner 1000:1000                  # 指定文件所有者"
+    echo "  $0 1.20.0 --output-dir /srv/ftp --owner root:root  # 同时指定两者"
+    echo
+}
+
+# 默认配置
+DEFAULT_PUBLISH_DIR="/private/argus/ftp/share/"
+DEFAULT_OWNER="2133:2015"
+
+# 解析参数
+VERSION=""
+PUBLISH_DIR="$DEFAULT_PUBLISH_DIR"
+OWNER="$DEFAULT_OWNER"
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        -h|--help)
+            show_help
+            exit 0
+            ;;
+        --output-dir)
+            PUBLISH_DIR="$2"
+            shift 2
+            ;;
+        --owner)
+            OWNER="$2"
+            shift 2
+            ;;
+        *)
+            if [[ -z "$VERSION" ]]; then
+                VERSION="$1"
+                shift
+            else
+                log_error "未知参数: $1"
+                show_help
+                exit 1
+            fi
+            ;;
+    esac
+done
+
+# 检查版本号是否提供
+if [[ -z "$VERSION" ]]; then
+    log_error "请提供版本号参数"
+    show_help
+    exit 1
+fi
+
+ARTIFACT_DIR="artifact/$VERSION"
+
+# 检查版本目录是否存在
+if [[ ! -d "$ARTIFACT_DIR" ]]; then
+    log_error "版本目录不存在: $ARTIFACT_DIR"
+    exit 1
+fi
+
+log_info "开始发布版本: $VERSION"
+log_info "输出目录: $PUBLISH_DIR"
+log_info "文件所有者: $OWNER"
+
+# 确保发布目录存在
+log_info "确保发布目录存在: $PUBLISH_DIR"
+sudo mkdir -p "$PUBLISH_DIR"
+
+# 创建临时目录用于打包
+TEMP_PACKAGE_DIR="/tmp/argus-metric-package-$$"
+mkdir -p "$TEMP_PACKAGE_DIR"
+
+# 复制所有 tar.gz 文件到临时目录
+log_info "准备 artifact 文件..."
+tar_files=$(find "$ARTIFACT_DIR" -name "*.tar.gz" -type f)
+
+if [[ -z "$tar_files" ]]; then
+    log_error "在 $ARTIFACT_DIR 中未找到 tar.gz 文件"
+    exit 1
+fi
+
+for file in $tar_files; do
+    filename=$(basename "$file")
+    log_info "  准备: $filename"
+    cp "$file" "$TEMP_PACKAGE_DIR/"
+done
+
+# 复制版本信息文件
+if [[ -f "$ARTIFACT_DIR/version.json" ]]; then
+    log_info "复制版本信息文件..."
+    cp "$ARTIFACT_DIR/version.json" "$TEMP_PACKAGE_DIR/"
+fi
+
+# 复制健康检查脚本
+if [[ -f "$ARTIFACT_DIR/check_health.sh" ]]; then
+    log_info "复制健康检查脚本..."
+    cp "$ARTIFACT_DIR/check_health.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/check_health.sh" ]]; then
+    log_info "复制健康检查脚本 (从当前目录)..."
+    cp "scripts/check_health.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 check_health.sh 文件"
+fi
+
+# 复制 DNS 同步脚本
+if [[ -f "$ARTIFACT_DIR/sync_dns.sh" ]]; then
+    log_info "复制 DNS 同步脚本..."
+    cp "$ARTIFACT_DIR/sync_dns.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/sync_dns.sh" ]]; then
+    log_info "复制 DNS 同步脚本 (从当前目录)..."
+    cp "scripts/sync_dns.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 sync_dns.sh 文件"
+fi
+
+# 复制版本校验脚本
+if [[ -f "$ARTIFACT_DIR/check_version.sh" ]]; then
+    log_info "复制版本校验脚本..."
+    cp "$ARTIFACT_DIR/check_version.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/check_version.sh" ]]; then
+    log_info "复制版本校验脚本 (从当前目录)..."
+    cp "scripts/check_version.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 check_version.sh 文件"
+fi
+
+# 复制重启失败脚本
+if [[ -f "$ARTIFACT_DIR/restart_unhealthy.sh" ]]; then
+    log_info "复制重启失败脚本..."
+    cp "$ARTIFACT_DIR/restart_unhealthy.sh" "$TEMP_PACKAGE_DIR/"
+elif [[ -f "scripts/restart_unhealthy.sh" ]]; then
+    log_info "复制重启失败脚本 (从当前目录)..."
+    cp "scripts/restart_unhealthy.sh" "$TEMP_PACKAGE_DIR/"
+else
+    log_warning "未找到 restart_unhealthy.sh 文件"
+fi
+
+# 复制安装脚本并重命名为 install.sh
+if [[ -f "scripts/install_artifact.sh" ]]; then
+    log_info "复制安装脚本..."
+    cp "scripts/install_artifact.sh" "$TEMP_PACKAGE_DIR/install.sh"
+fi
+
+if [[ -f "scripts/uninstall_artifact.sh" ]]; then
+    log_info "复制卸载脚本..."
+    cp "scripts/uninstall_artifact.sh" "$TEMP_PACKAGE_DIR/uninstall.sh"
+fi
+
+# 复制配置文件
+if [[ -f "$ARTIFACT_DIR/config.env" ]]; then
+    log_info "复制配置文件..."
+    cp "$ARTIFACT_DIR/config.env" "$TEMP_PACKAGE_DIR/"
+    log_success "配置文件复制完成"
+else
+    log_warning "未找到 config.env 文件"
+fi
+
+# DNS 配置文件将在后面直接复制到发布目录根目录，不包含在 tar.gz 中
+
+# 复制 deps 目录
+if [[ -d "$ARTIFACT_DIR/deps" ]]; then
+    log_info "复制系统依赖包..."
+    cp -r "$ARTIFACT_DIR/deps" "$TEMP_PACKAGE_DIR/"
+    log_success "系统依赖包复制完成"
+fi
+
+# 创建tar包，使用新的命名规范
+TAR_NAME="argus-metric_$(echo $VERSION | tr '.' '_').tar.gz"
+log_info "创建发布包: $TAR_NAME"
+cd "$TEMP_PACKAGE_DIR"
+sudo tar -czf "$PUBLISH_DIR/$TAR_NAME" *
+cd - > /dev/null
+
+# 设置文件所有者
+log_info "设置文件所有者为: $OWNER"
+sudo chown "$OWNER" "$PUBLISH_DIR/$TAR_NAME"
+
+# 清理临时目录
+rm -rf "$TEMP_PACKAGE_DIR"
+
+# 更新 LATEST_VERSION 文件
+log_info "更新 LATEST_VERSION 文件..."
+echo "$VERSION" | sudo tee "$PUBLISH_DIR/LATEST_VERSION" > /dev/null
+sudo chown "$OWNER" "$PUBLISH_DIR/LATEST_VERSION"
+
+# 复制 DNS 配置文件到发布目录根目录（直接从 config 目录复制）
+if [[ -f "config/dns.conf" ]]; then
+    log_info "复制 DNS 配置文件到发布目录根目录..."
+    sudo cp "config/dns.conf" "$PUBLISH_DIR/"
+    sudo chown "$OWNER" "$PUBLISH_DIR/dns.conf"
+    log_success "DNS 配置文件复制完成: $PUBLISH_DIR/dns.conf"
+else
+    log_warning "未找到 config/dns.conf 文件，跳过 DNS 配置文件复制"
+fi
+
+# 复制 setup.sh 到发布目录
+if [[ -f "scripts/setup.sh" ]]; then
+    log_info "复制 setup.sh 到发布目录..."
+    sudo cp "scripts/setup.sh" "$PUBLISH_DIR/"
+    sudo chown "$OWNER" "$PUBLISH_DIR/setup.sh"
+fi
+
+# 显示发布结果
+log_success "版本 $VERSION 发布完成！"
+echo
+echo "发布目录: $PUBLISH_DIR"
+echo "发布包: $PUBLISH_DIR/$TAR_NAME"
+echo "包大小: $(du -h "$PUBLISH_DIR/$TAR_NAME" | cut -f1)"
+echo "最新版本: $(cat "$PUBLISH_DIR/LATEST_VERSION")"
+echo
+echo "发布目录中的文件:"
+ls -la "$PUBLISH_DIR" | while read line; do
+    echo "  $line"
+done
+echo
+echo "使用方法:"
+echo "  1. 确保 /srv/ftp/share 目录可通过 FTP 访问"
+echo "  2. 用户首先下载安装脚本:"
+echo "     curl -u ftpuser:admin1234 ftp://10.211.55.4/setup.sh -o setup.sh"
+echo "  3. 然后执行安装 (自动获取最新版本):"
+echo "     sudo sh setup.sh"
+echo "  4. 或者指定版本安装:"
+echo "     sudo sh setup.sh --version $VERSION"
+echo "  5. 或者指定不同的FTP服务器:"
+echo "     sudo sh setup.sh --server 192.168.1.100 --user myuser --password mypass"

src/metric/client-plugins/all-in-one-demo/scripts/restart_unhealthy.sh

@@ -0,0 +1,337 @@
+#!/bin/bash
+
+# 此脚本会检查各组件的健康状态，并重启不健康的组件
+
+# PID 文件检测，防止重复执行
+PIDFILE="/var/run/restart_unhealthy.pid"
+if [ -f "$PIDFILE" ] && kill -0 $(cat "$PIDFILE") 2>/dev/null; then
+    echo "自动重启脚本已在运行中，跳过本次执行" >&2
+    exit 0
+fi
+echo $$ > "$PIDFILE"
+trap "rm -f $PIDFILE" EXIT
+
+# 获取脚本所在目录
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+INSTALL_RECORD_FILE="$SCRIPT_DIR/.install_record"
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m'
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $(date '+%Y-%m-%d %H:%M:%S') - $1"
+}
+
+# 加载配置文件
+load_config() {
+    local config_file="$SCRIPT_DIR/config.env"
+    
+    if [[ -f "$config_file" ]]; then
+        log_info "加载配置文件: $config_file"
+        set -a
+        source "$config_file"
+        set +a
+        log_success "配置文件加载完成"
+    else
+        log_warning "配置文件不存在: $config_file，使用默认配置"
+    fi
+}
+
+# 检查单个组件健康状态
+check_component_health() {
+    local component_name="$1"
+    local check_script_path="$2"
+
+    if [[ ! -f "$check_script_path" ]]; then
+        log_error "$component_name: 健康检查脚本不存在: $check_script_path"
+        return 1
+    fi
+
+    if [[ ! -x "$check_script_path" ]]; then
+        chmod +x "$check_script_path" 2>/dev/null || true
+    fi
+
+    # 执行健康检查，捕获退出码
+    if "$check_script_path" > /dev/null 2>&1; then
+        return 0
+    else
+        return 1
+    fi
+}
+
+# 重启单个组件
+restart_component() {
+    local component_name="$1"
+    local install_dir="$2"
+
+    log_warning "正在重启组件: $component_name"
+    
+    # 先执行卸载脚本
+    local uninstall_script="$install_dir/uninstall.sh"
+    if [[ -f "$uninstall_script" ]]; then
+        log_info "$component_name: 执行卸载脚本..."
+        chmod +x "$uninstall_script" 2>/dev/null || true
+        # 使用 yes 命令自动回答所有确认提示
+        yes 2>/dev/null | (cd "$install_dir" && "$uninstall_script") || true
+        log_info "$component_name: 卸载完成"
+    fi
+    
+    # 执行安装脚本
+    local install_script="$install_dir/install.sh"
+    if [[ ! -f "$install_script" ]]; then
+        log_error "$component_name: 安装脚本不存在: $install_script"
+        return 1
+    fi
+    
+    chmod +x "$install_script" 2>/dev/null || true
+    log_info "$component_name: 执行安装脚本..."
+    
+    # 使用 yes 命令自动回答所有确认提示，传递 SCRIPT_DIR 作为参数
+    yes 2>/dev/null | (cd "$install_dir" && "$install_script" "$SCRIPT_DIR") || true
+    
+    log_info "$component_name: 安装脚本执行完成"
+    return 0
+}
+
+# 查找组件进程 PID
+find_component_pid() {
+    local component_name="$1"
+    local component_pid=""
+    
+    case "$component_name" in
+        "node-exporter")
+            component_pid=$(pgrep -f "node_exporter" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(pgrep -f "node-exporter" | head -1)
+            fi
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "node_exporter" | awk '{print $2}' | head -1)
+            fi
+            ;;
+        "dcgm-exporter")
+            component_pid=$(pgrep -f "dcgm-exporter" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(pgrep -f "dcgm_exporter" | head -1)
+            fi
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "dcgm-exporter" | awk '{print $2}' | head -1)
+            fi
+            ;;
+        "fluent-bit")
+            component_pid=$(pgrep -f "fluent-bit" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(pgrep -f "fluent_bit" | head -1)
+            fi
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "fluent-bit" | awk '{print $2}' | head -1)
+            fi
+            ;;
+        "argus-agent")
+            component_pid=$(pgrep -f "argus-agent" | head -1)
+            if [[ -z "$component_pid" ]]; then
+                component_pid=$(ps aux | grep -v grep | grep "argus-agent" | awk '{print $2}' | head -1)
+            fi
+            ;;
+    esac
+    
+    echo "$component_pid"
+}
+
+# 更新安装记录文件中的 PID
+update_install_record_pid() {
+    local component_name="$1"
+    local new_pid="$2"
+    
+    if [[ ! -f "$INSTALL_RECORD_FILE" ]]; then
+        log_error "安装记录文件不存在: $INSTALL_RECORD_FILE"
+        return 1
+    fi
+    
+    # 读取当前 PID
+    local current_pid=""
+    if command -v jq &> /dev/null; then
+        current_pid=$(jq -r --arg comp "$component_name" '.components[$comp].pid // ""' "$INSTALL_RECORD_FILE" 2>/dev/null)
+    fi
+    
+    if [[ -z "$current_pid" ]]; then
+        log_warning "$component_name: 无法读取当前 PID，跳过更新"
+        return 1
+    fi
+    
+    # 使用 sed 精确替换 PID，保持原有格式不变
+    # 只替换指定组件块中的 pid 字段
+    local temp_file="${INSTALL_RECORD_FILE}.tmp"
+    local in_component=0
+    local updated=0
+    
+    while IFS= read -r line; do
+        if [[ "$line" =~ \"$component_name\":[[:space:]]*\{ ]]; then
+            in_component=1
+            echo "$line"
+        elif [[ $in_component -eq 1 && "$line" =~ \"pid\":[[:space:]]*\"$current_pid\" ]]; then
+            echo "$line" | sed "s/\"pid\": \"$current_pid\"/\"pid\": \"$new_pid\"/"
+            updated=1
+            in_component=0
+        else
+            echo "$line"
+            if [[ "$line" =~ ^[[:space:]]*\}[[:space:]]*$ ]]; then
+                in_component=0
+            fi
+        fi
+    done < "$INSTALL_RECORD_FILE" > "$temp_file"
+    
+    # 验证替换是否成功
+    if [[ $updated -eq 1 ]]; then
+        mv "$temp_file" "$INSTALL_RECORD_FILE"
+        log_success "$component_name: PID 已更新为 $new_pid（原值: $current_pid）"
+        return 0
+    else
+        log_error "$component_name: PID 替换失败"
+        rm -f "$temp_file"
+        return 1
+    fi
+}
+
+# 从安装记录文件中读取组件信息
+read_install_record() {
+    local install_record_file="$1"
+
+    if [[ ! -f "$install_record_file" ]]; then
+        log_error "安装记录文件不存在: $install_record_file"
+        return 1
+    fi
+
+    # 检查是否有 jq 命令来解析 JSON
+    if command -v jq &> /dev/null; then
+        # 使用 jq 解析 JSON
+        local components_json
+        if components_json=$(jq -r '.components | to_entries[] | "\(.key):\(.value.install_dir)"' "$install_record_file" 2>/dev/null); then
+            echo "$components_json"
+            return 0
+        else
+            log_error "无法解析安装记录文件 JSON 格式: $install_record_file"
+            return 1
+        fi
+    else
+        # 如果没有 jq，尝试简单的文本解析
+        log_warning "jq 命令不可用，尝试简单文本解析"
+
+        # 查找所有 install_dir 行
+        local components=()
+        while IFS= read -r line; do
+            if [[ "$line" =~ \"install_dir\":[[:space:]]*\"([^\"]+)\" ]]; then
+                local install_dir="${BASH_REMATCH[1]}"
+                # 从路径中提取组件名称
+                local component_name=$(basename "$install_dir")
+                components+=("$component_name:$install_dir")
+            fi
+        done < "$install_record_file"
+
+        if [[ ${#components[@]} -gt 0 ]]; then
+            printf '%s\n' "${components[@]}"
+            return 0
+        else
+            log_error "无法从安装记录文件中提取组件信息"
+            return 1
+        fi
+    fi
+}
+
+# 主函数
+main() {
+    log_info "=========================================="
+    log_info "    组件自动重启检查"
+    log_info "=========================================="
+
+    # 检查是否是root用户
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        exit 1
+    fi
+
+    # 加载配置文件
+    load_config
+
+    # 从安装记录文件中读取组件信息
+    log_info "从安装记录文件读取组件信息: $INSTALL_RECORD_FILE"
+    local components_info
+    if ! components_info=$(read_install_record "$INSTALL_RECORD_FILE"); then
+        log_error "无法读取安装记录文件，自动重启检查终止"
+        exit 1
+    fi
+
+    local restart_count=0
+    local check_count=0
+
+    # 逐个检查组件
+    while IFS= read -r component_info; do
+        if [[ -n "$component_info" ]]; then
+            IFS=':' read -r component_name install_dir <<< "$component_info"
+            check_count=$((check_count + 1))
+            
+            local check_script_path="$install_dir/check_health.sh"
+
+            log_info "检查组件: $component_name"
+            
+            # 检查健康状态
+            if check_component_health "$component_name" "$check_script_path"; then
+                log_success "$component_name: 运行正常"
+            else
+                log_warning "$component_name: 健康检查失败，尝试重启"
+                restart_count=$((restart_count + 1))
+                
+                # 执行重启
+                restart_component "$component_name" "$install_dir"
+                
+                # 等待服务启动
+                log_info "$component_name: 等待进程启动..."
+                sleep 10
+                
+                # 查找新的进程 PID
+                local new_pid=$(find_component_pid "$component_name")
+                if [[ -n "$new_pid" ]]; then
+                    log_info "$component_name: 找到新进程 PID: $new_pid"
+                    update_install_record_pid "$component_name" "$new_pid"
+                else
+                    log_warning "$component_name: 未找到新进程 PID"
+                fi
+                
+                # 再次检查健康状态
+                if check_component_health "$component_name" "$check_script_path"; then
+                    log_success "$component_name: 重启成功"
+                else
+                    log_warning "$component_name: 重启后仍不健康，可能需要手动检查"
+                fi
+            fi
+        fi
+    done <<< "$components_info"
+
+    log_info "=========================================="
+    log_info "检查完成: 共检查 $check_count 个组件，尝试重启 $restart_count 个"
+    log_info "=========================================="
+
+    exit 0
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi
+

src/metric/client-plugins/all-in-one-demo/scripts/setup.sh

@@ -0,0 +1,931 @@
+#!/bin/bash
+
+set -e
+
+# 加载配置文件（仅在解压后的目录中可用）
+load_config() {
+    # setup.sh 脚本不需要配置文件，FTP参数通过命令行参数或环境变量提供
+    log_info "setup.sh 脚本使用命令行参数或环境变量获取FTP配置"
+}
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+FTP_SERVER="${FTP_SERVER}"
+FTP_USER="${FTP_USER}"
+FTP_PASS="${FTP_PASS}"
+FTP_PORT="${FTP_PORT:-21}"
+BASE_URL=""                                  # FTP基础URL (将在check_ftp_params中设置)
+LATEST_VERSION_URL=""                        # 版本文件URL (将在check_ftp_params中设置)
+TEMP_DIR="/tmp/argus-metric-install-$$"
+
+# 安装目录配置
+DEFAULT_INSTALL_DIR="/opt/argus-metric"      # 默认安装目录
+INSTALL_DIR="${INSTALL_DIR:-$DEFAULT_INSTALL_DIR}"  # 可通过环境变量覆盖
+VERSIONS_DIR="$INSTALL_DIR/versions"         # 版本目录
+BACKUPS_DIR="$INSTALL_DIR/backups"           # 备份目录
+CURRENT_LINK="$INSTALL_DIR/current"          # 当前版本软链接
+LATEST_VERSION_FILE="$INSTALL_DIR/LATEST_VERSION"  # 当前版本记录文件
+
+# 检查必需的FTP参数
+check_ftp_params() {
+    local missing_params=()
+    
+    if [[ -z "$FTP_SERVER" ]]; then
+        missing_params+=("FTP_SERVER")
+    fi
+    
+    if [[ -z "$FTP_USER" ]]; then
+        missing_params+=("FTP_USER")
+    fi
+    
+    if [[ -z "$FTP_PASS" ]]; then
+        missing_params+=("FTP_PASS")
+    fi
+    
+    if [[ ${#missing_params[@]} -gt 0 ]]; then
+        log_error "缺少必需的FTP参数: ${missing_params[*]}"
+        log_error "请通过以下方式之一设置FTP参数:"
+        log_error "  1. 命令行参数: --server <地址> --user <用户名> --password <密码>"
+        log_error "  2. 环境变量: FTP_SERVER=<地址> FTP_USER=<用户名> FTP_PASS=<密码>"
+        log_error ""
+        log_error "示例:"
+        log_error "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234"
+        log_error "  FTP_SERVER=10.211.55.4 FTP_USER=ftpuser FTP_PASS=admin1234 sudo sh setup.sh"
+        exit 1
+    fi
+    
+    # 设置BASE_URL和LATEST_VERSION_URL
+    BASE_URL="ftp://${FTP_SERVER}:${FTP_PORT}"
+    LATEST_VERSION_URL="$BASE_URL/LATEST_VERSION"
+    
+    log_info "FTP配置:"
+    log_info "  服务器: $FTP_SERVER:$FTP_PORT"
+    log_info "  用户: $FTP_USER"
+}
+
+# 获取最新版本号的函数
+get_latest_version() {
+    log_info "获取最新版本信息..." >&2
+    log_info "尝试从URL获取: $LATEST_VERSION_URL" >&2
+    
+    # 先测试FTP连接
+    log_info "测试FTP连接..." >&2
+    if ! curl -u "${FTP_USER}:${FTP_PASS}" -sfI "$LATEST_VERSION_URL" >/dev/null 2>&1; then
+        log_error "无法连接到FTP服务器或文件不存在" >&2
+        log_error "URL: $LATEST_VERSION_URL" >&2
+        log_error "请检查:" >&2
+        log_error "  1. FTP服务器是否运行: $FTP_SERVER:$FTP_PORT" >&2
+        log_error "  2. 用户名密码是否正确: $FTP_USER" >&2
+        log_error "  3. LATEST_VERSION文件是否存在" >&2
+        log_error "手动测试命令: curl -u ${FTP_USER}:${FTP_PASS} ftp://${FTP_SERVER}/LATEST_VERSION" >&2
+        exit 1
+    fi
+    
+    # 获取文件内容
+    if ! LATEST_VERSION=$(curl -u "${FTP_USER}:${FTP_PASS}" -sfL "$LATEST_VERSION_URL" 2>/dev/null | tr -d '[:space:]'); then
+        log_error "下载LATEST_VERSION文件失败" >&2
+        exit 1
+    fi
+    
+    log_info "原始获取内容: '$LATEST_VERSION'" >&2
+    
+    if [[ -z "$LATEST_VERSION" ]]; then
+        log_error "获取到的版本信息为空" >&2
+        log_error "可能的原因:" >&2
+        log_error "  1. LATEST_VERSION文件为空" >&2
+        log_error "  2. 文件内容格式不正确" >&2
+        log_error "  3. 网络传输问题" >&2
+        log_error "请检查FTP服务器上的 /srv/ftp/share/LATEST_VERSION 文件" >&2
+        exit 1
+    fi
+    
+    log_info "检测到最新版本: $LATEST_VERSION" >&2
+    echo "$LATEST_VERSION"
+}
+
+# 解析参数
+ARGUS_VERSION=""  # 使用不同的变量名避免与系统VERSION冲突
+ACTION="install"
+FORCE_INSTALL=false
+
+while [[ $# -gt 0 ]]; do
+    case $1 in
+        --version)
+            ARGUS_VERSION="$2"
+            shift 2
+            ;;
+        --server)
+            FTP_SERVER="$2"
+            shift 2
+            ;;
+        --user)
+            FTP_USER="$2"
+            shift 2
+            ;;
+        --password)
+            FTP_PASS="$2"
+            shift 2
+            ;;
+        --port)
+            FTP_PORT="$2"
+            shift 2
+            ;;
+        --uninstall)
+            ACTION="uninstall"
+            shift
+            ;;
+        --install-dir)
+            INSTALL_DIR="$2"
+            shift 2
+            ;;
+        # 简化安装逻辑：不再支持回滚和备份列表功能
+        # --rollback)
+        #     ACTION="rollback"
+        #     shift
+        #     ;;
+        # --backup-list)
+        #     ACTION="backup-list"
+        #     shift
+        #     ;;
+        --status)
+            ACTION="status"
+            shift
+            ;;
+        --force)
+            FORCE_INSTALL=true
+            shift
+            ;;
+        --help)
+            echo "Argus Metric FTP在线安装脚本"
+            echo
+            echo "用法: curl -u <用户名>:<密码> ftp://<服务器>/setup.sh -o setup.sh && sh setup.sh [选项]"
+            echo
+            echo "必需参数 (必须通过命令行参数或环境变量设置):"
+            echo "  --server SERVER       FTP服务器地址 (必须)"
+            echo "  --user USER           FTP用户名 (必须)"
+            echo "  --password PASS       FTP密码 (必须)"
+            echo
+            echo "可选参数:"
+            echo "  --version VERSION     指定版本 (默认: 自动获取最新版本)"
+            echo "  --port PORT           FTP端口 (默认: 21)"
+            echo "  --install-dir DIR     安装目录 (默认: /opt/argus-metric)"
+            echo "  --force               强制重新安装 (即使相同版本)"
+            echo "  --uninstall           卸载 (自动确认)"
+            # echo "  --rollback            回滚到上一个备份版本"
+            # echo "  --backup-list         列出所有备份版本"
+            echo "  --status              显示当前安装状态"
+            echo "  --help                显示帮助"
+            echo
+            echo "环境变量:"
+            echo "  FTP_SERVER            FTP服务器地址 (必须)"
+            echo "  FTP_USER              FTP用户名 (必须)"
+            echo "  FTP_PASS              FTP密码 (必须)"
+            echo "  FTP_PORT              FTP端口 (默认: 21)"
+            echo
+            echo "示例:"
+            echo "  # 方式1: 使用命令行参数"
+            echo "  curl -u ftpuser:admin1234 ftp://10.211.55.4/setup.sh -o setup.sh"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234"
+            echo "  "
+            echo "  # 方式2: 使用环境变量"
+            echo "  FTP_SERVER=10.211.55.4 FTP_USER=ftpuser FTP_PASS=admin1234 sudo sh setup.sh"
+            echo "  "
+            echo "  # 指定版本安装"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234 --version 1.30.0"
+            echo "  "
+            echo "  # 强制重新安装"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234 --force"
+            echo "  "
+            echo "  # 卸载"
+            echo "  sudo sh setup.sh --server 10.211.55.4 --user ftpuser --password admin1234 --uninstall"
+            exit 0
+            ;;
+        *)
+            log_error "未知参数: $1"
+            echo "使用 --help 查看帮助信息"
+            exit 1
+            ;;
+    esac
+done
+
+# 清理函数
+cleanup() {
+    if [[ -d "$TEMP_DIR" ]]; then
+        rm -rf "$TEMP_DIR"
+    fi
+}
+
+trap cleanup EXIT
+
+# 创建安装目录结构
+create_install_directories() {
+    log_info "创建安装目录结构..."
+    
+    # 创建主要目录
+    mkdir -p "$VERSIONS_DIR"
+    mkdir -p "$BACKUPS_DIR"
+    
+    log_success "安装目录结构创建完成: $INSTALL_DIR"
+}
+
+# 获取当前安装的版本
+get_current_version() {
+    # 优先从LATEST_VERSION文件读取
+    if [[ -f "$LATEST_VERSION_FILE" ]]; then
+        local version_from_file=$(cat "$LATEST_VERSION_FILE" 2>/dev/null | tr -d '[:space:]')
+        if [[ -n "$version_from_file" ]]; then
+            # 确保版本号格式一致（不带v前缀）
+            echo "$version_from_file"
+            return 0
+        fi
+    fi
+    
+    # 如果文件不存在或为空，从软链接读取
+    if [[ -L "$CURRENT_LINK" ]]; then
+        local current_path=$(readlink "$CURRENT_LINK")
+        # 从版本目录名中提取版本号（现在不带v前缀）
+        basename "$current_path"
+    else
+        echo ""
+    fi
+}
+
+# 检查是否已安装
+check_installed() {
+    if [[ -L "$CURRENT_LINK" ]] && [[ -d "$CURRENT_LINK" ]]; then
+        local current_version=$(get_current_version)
+        if [[ -n "$current_version" ]]; then
+            log_info "检测到已安装版本: v$current_version"
+            return 0
+        fi
+    fi
+    return 1
+}
+
+# 更新LATEST_VERSION文件
+update_latest_version_file() {
+    local version="$1"
+    log_info "更新LATEST_VERSION文件: $version"
+    
+    if echo "$version" > "$LATEST_VERSION_FILE"; then
+        log_success "LATEST_VERSION文件已更新"
+    else
+        log_error "更新LATEST_VERSION文件失败"
+        return 1
+    fi
+}
+
+# 初始化 DNS 配置文件到系统目录
+init_dns_config_to_system() {
+    log_info "初始化 DNS 配置文件到系统目录..."
+    
+    # 系统 DNS 配置文件
+    local system_dns_conf="$INSTALL_DIR/dns.conf"
+    
+    # 如果系统目录中还没有 dns.conf，创建一个空的占位文件
+    if [[ ! -f "$system_dns_conf" ]]; then
+        touch "$system_dns_conf"
+        chmod 644 "$system_dns_conf"
+        log_success "DNS 配置文件占位文件已创建: $system_dns_conf"
+        log_info "DNS 同步脚本将从 FTP 服务器下载实际的 DNS 配置"
+    else
+        log_info "DNS 配置文件已存在: $system_dns_conf"
+    fi
+}
+
+# 备份当前版本
+backup_current_version() {
+    local current_version=$(get_current_version)
+    if [[ -z "$current_version" ]]; then
+        log_info "没有当前版本需要备份"
+        return 0
+    fi
+    
+    # 确保备份目录存在
+    mkdir -p "$BACKUPS_DIR"
+    
+    local backup_name="$current_version"
+    local backup_path="$BACKUPS_DIR/$backup_name"
+    
+    log_info "备份当前版本 $current_version 到: $backup_path"
+    
+    # 如果备份已存在，先删除
+    if [[ -d "$backup_path" ]]; then
+        log_info "备份版本已存在，覆盖: $backup_path"
+        rm -rf "$backup_path"
+    fi
+    
+    # 复制当前版本目录（跟随软链接复制实际内容）
+    if cp -rL "$CURRENT_LINK" "$backup_path"; then
+        log_success "版本备份完成: $backup_name"
+
+    else
+        log_error "版本备份失败"
+        exit 1
+    fi
+}
+
+# 回滚到备份版本
+rollback_to_backup() {
+    local backup_name="$1"
+    
+    # 确保备份目录存在
+    mkdir -p "$BACKUPS_DIR"
+    
+    local backup_path="$BACKUPS_DIR/$backup_name"
+    
+    if [[ ! -d "$backup_path" ]]; then
+        log_error "备份不存在: $backup_path"
+        return 1
+    fi
+    
+    log_info "回滚到备份版本: $backup_name"
+    
+    # 停止当前服务
+    stop_services
+    
+    # 检查是否存在对应的版本目录
+    local version_dir="$VERSIONS_DIR/$backup_name"
+    
+    if [[ ! -d "$version_dir" ]]; then
+        log_info "版本目录不存在，从备份恢复版本目录: $version_dir"
+        # 从备份目录恢复到版本目录
+        mkdir -p "$VERSIONS_DIR"
+        cp -r "$backup_path" "$version_dir"
+    fi
+    
+    # 恢复软链接指向版本目录
+    if ln -sfn "$version_dir" "$CURRENT_LINK"; then
+        log_success "版本回滚完成: $backup_name"
+        
+        # 更新LATEST_VERSION文件
+        update_latest_version_file "$backup_name"
+        
+        return 0
+    else
+        log_error "版本回滚失败"
+        return 1
+    fi
+}
+
+# 停止服务
+stop_services() {
+    log_info "停止当前服务..."
+    
+    # 检查服务是否正在运行
+    if ! check_services_running; then
+        log_info "服务未运行，无需停止"
+        return 0
+    fi
+    
+    # 尝试使用卸载脚本停止服务
+    if [[ -f "$CURRENT_LINK/uninstall.sh" ]]; then
+        cd "$CURRENT_LINK"
+        chmod +x uninstall.sh
+        
+        # 自动确认停止服务（避免交互式确认）
+        echo "y" | ./uninstall.sh >/dev/null 2>&1
+        local stop_exit_code=$?
+        
+        if [[ $stop_exit_code -eq 0 ]]; then
+            log_success "服务停止完成"
+        else
+            log_warning "停止服务时出现警告，尝试手动停止"
+            manual_stop_services
+        fi
+    else
+        log_warning "未找到卸载脚本，尝试手动停止服务"
+        manual_stop_services
+    fi
+}
+
+# 手动停止服务
+manual_stop_services() {
+    log_info "手动停止服务..."
+    
+    # 停止 node_exporter
+    if pgrep -f "node_exporter" >/dev/null 2>&1; then
+        pkill -f "node_exporter" && log_info "node_exporter 已停止"
+    fi
+    
+    # 停止 dcgm_exporter
+    if pgrep -f "dcgm_exporter" >/dev/null 2>&1; then
+        pkill -f "dcgm_exporter" && log_info "dcgm_exporter 已停止"
+    fi
+    
+    # 等待进程完全停止
+    sleep 2
+    
+    # 检查是否还有残留进程
+    if pgrep -f "node_exporter\|dcgm_exporter" >/dev/null 2>&1; then
+        log_warning "仍有服务进程运行，尝试强制停止"
+        pkill -9 -f "node_exporter\|dcgm_exporter" 2>/dev/null || true
+    fi
+    
+    log_success "手动停止服务完成"
+}
+
+# 启动服务
+start_services() {
+    log_info "启动服务..."
+    
+    # 检查服务是否已经在运行
+    if check_services_running; then
+        log_info "服务已在运行，跳过启动"
+        return 0
+    fi
+    
+    # 由于 install_artifact.sh 已经安装了所有组件并设置了健康检查定时任务
+    # 这里只需要简单验证服务状态即可
+    log_info "组件已安装完成，健康检查定时任务已设置"
+    log_info "服务将在健康检查时自动启动（每5分钟检查一次）"
+    
+    # 等待一下让服务有时间启动
+    sleep 3
+    
+    # 验证服务状态
+    if check_services_running; then
+        log_success "服务启动成功"
+    else
+        log_info "服务可能正在启动中，健康检查机制将自动监控"
+    fi
+    
+    return 0
+}
+
+# 检查服务是否正在运行
+check_services_running() {
+    # 检查常见的服务端口是否在监听
+    local ports=(9100 9400)  # node-exporter 和 dcgm-exporter 的默认端口
+    
+    for port in "${ports[@]}"; do
+        if netstat -tlnp 2>/dev/null | grep -q ":$port "; then
+            log_info "检测到服务正在端口 $port 上运行"
+            return 0
+        fi
+    done
+    
+    # 检查相关进程
+    if pgrep -f "node_exporter\|dcgm_exporter" >/dev/null 2>&1; then
+        log_info "检测到相关服务进程正在运行"
+        return 0
+    fi
+    
+    return 1
+}
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo sh setup.sh"
+        exit 1
+    fi
+}
+
+# 检查系统要求
+check_system() {
+    log_info "检查系统要求..."
+    
+    # 检查操作系统
+    if [[ ! -f /etc/os-release ]]; then
+        log_error "无法检测操作系统版本"
+        exit 1
+    fi
+    
+    # 读取系统信息，使用子shell避免污染当前环境变量
+    local OS_INFO=$(source /etc/os-release && echo "$NAME $VERSION_ID")
+    log_info "检测到操作系统: $OS_INFO"
+    
+    # 检查系统架构
+    arch=$(uname -m)
+    log_info "系统架构: $arch"
+    
+    # 检查磁盘空间
+    available_space=$(df / | awk 'NR==2 {print $4}')
+    if [[ $available_space -lt 1024 ]]; then
+        log_warning "可用磁盘空间不足 1GB，当前可用: $(($available_space / 1024 / 1024))GB"
+    fi
+}
+
+# 下载并安装
+install_argus_metric() {
+    # 如果没有指定版本，获取最新版本
+    if [[ -z "$ARGUS_VERSION" ]]; then
+        ARGUS_VERSION=$(get_latest_version)
+    fi
+    
+    log_info "开始安装 Argus Metric v$ARGUS_VERSION..."
+    log_info "安装目录: $INSTALL_DIR"
+    
+    # 创建安装目录结构（必须先创建，以便备份时目录存在）
+    create_install_directories
+    
+    # 检查是否已安装
+    local is_upgrade=false
+    if check_installed; then
+        local current_version=$(get_current_version)
+        if [[ "$current_version" == "$ARGUS_VERSION" ]]; then
+            if [[ "$FORCE_INSTALL" == true ]]; then
+                log_info "检测到相同版本 v$ARGUS_VERSION，但使用了 --force 参数，将强制重新安装"
+                is_upgrade=true
+                # 简化安装逻辑：不再备份当前版本
+                # backup_current_version
+            else
+                log_info "版本 v$ARGUS_VERSION 已安装，无需重复安装"
+                log_info "如需强制重新安装，请使用 --force 参数"
+                return 0
+            fi
+        else
+            log_info "检测到版本升级: v$current_version -> v$ARGUS_VERSION"
+            is_upgrade=true
+            
+            # 简化安装逻辑：不再备份当前版本
+            # backup_current_version
+        fi
+    fi
+    
+    # 创建临时目录
+    mkdir -p "$TEMP_DIR"
+    cd "$TEMP_DIR"
+    
+    # 下载发布包，使用新的命名规范
+    TAR_NAME="argus-metric_$(echo $ARGUS_VERSION | tr '.' '_').tar.gz"
+    log_info "下载发布包: $TAR_NAME"
+    log_info "从FTP服务器下载: $FTP_SERVER:$FTP_PORT, 用户: $FTP_USER"
+    
+    # 构造curl命令并显示（隐藏密码）
+    CURL_CMD="curl -u \"${FTP_USER}:***\" -sfL \"$BASE_URL/$TAR_NAME\" -o \"$TAR_NAME\""
+    log_info "执行命令: $CURL_CMD"
+    
+    if ! curl -u "${FTP_USER}:${FTP_PASS}" -sfL "$BASE_URL/$TAR_NAME" -o "$TAR_NAME"; then
+        log_error "下载发布包失败: $BASE_URL/$TAR_NAME"
+        log_error "完整命令: curl -u \"${FTP_USER}:${FTP_PASS}\" -sfL \"$BASE_URL/$TAR_NAME\" -o \"$TAR_NAME\""
+        log_error "请检查FTP服务器连接、用户名密码是否正确"
+        exit 1
+    fi
+    
+    # 解压发布包到当前目录
+    log_info "解压发布包..."
+    if ! tar -xzf "$TAR_NAME"; then
+        log_error "解压发布包失败"
+        exit 1
+    fi
+    
+    # 显示解压后的文件结构
+    log_info "解压后的文件结构:"
+    ls -la "$TEMP_DIR"
+    
+    # 准备版本目录
+    local version_dir="$VERSIONS_DIR/$ARGUS_VERSION"
+    log_info "安装到版本目录: $version_dir"
+    
+    # 如果升级，先停止服务
+    if [[ "$is_upgrade" == true ]]; then
+        stop_services
+    fi
+    
+    # 创建版本目录
+    if [[ -d "$version_dir" ]]; then
+        log_info "版本目录已存在，备份后更新"
+        rm -rf "$version_dir"
+    fi
+    
+    # 创建新的版本目录
+    mkdir -p "$version_dir"
+    
+    # 移动解压的文件到版本目录
+    log_info "移动文件到版本目录: $TEMP_DIR/* -> $version_dir/"
+    
+    # 检查源目录是否有内容
+    if [[ ! "$(ls -A "$TEMP_DIR" 2>/dev/null)" ]]; then
+        log_error "临时目录为空，无法移动文件"
+        exit 1
+    fi
+    
+    # 检查目标目录是否存在
+    if [[ ! -d "$version_dir" ]]; then
+        log_error "目标版本目录不存在: $version_dir"
+        exit 1
+    fi
+    
+    # 执行文件移动
+    if mv "$TEMP_DIR"/* "$version_dir" 2>/dev/null; then
+        log_success "文件移动到版本目录完成"
+    else
+        log_error "移动文件到版本目录失败"
+        log_error "源目录内容:"
+        ls -la "$TEMP_DIR" || true
+        log_error "目标目录状态:"
+        ls -la "$version_dir" || true
+        log_error "权限检查:"
+        ls -ld "$TEMP_DIR" "$version_dir" || true
+        exit 1
+    fi
+    
+    # 执行安装脚本
+    log_info "执行安装脚本..."
+    cd "$version_dir"
+    if [[ -f "install.sh" ]]; then
+        chmod +x install.sh
+        # 传递安装根目录给安装脚本，让install_artifact.sh安装到正确的版本目录
+        if ./install.sh "$version_dir"; then
+            log_success "安装脚本执行完成"
+        else
+            log_error "安装脚本执行失败"
+            # 简化安装逻辑：不再自动回滚
+            # if [[ "$is_upgrade" == true ]]; then
+            #     log_warning "升级失败，尝试回滚到之前版本..."
+            #     # 确保备份目录存在
+            #     mkdir -p "$BACKUPS_DIR"
+            #     local latest_backup=$(ls -1t "$BACKUPS_DIR" 2>/dev/null | head -n 1)
+            #     if [[ -n "$latest_backup" ]]; then
+            #         rollback_to_backup "$latest_backup"
+            #         return 1
+            #     fi
+            # fi
+            exit 1
+        fi
+    else
+        log_error "未找到安装脚本 install.sh"
+        exit 1
+    fi
+    
+    # 更新软链接指向新版本
+    log_info "更新当前版本链接..."
+    
+    # 如果 current 已经存在且是目录，先删除它
+    if [[ -d "$CURRENT_LINK" ]] && [[ ! -L "$CURRENT_LINK" ]]; then
+        log_warning "发现 current 是目录而不是符号链接，正在删除..."
+        rm -rf "$CURRENT_LINK"
+    fi
+    
+    if ln -sfn "$version_dir" "$CURRENT_LINK"; then
+        log_success "版本链接更新完成: $CURRENT_LINK -> $version_dir"
+    else
+        log_error "版本链接更新失败"
+        exit 1
+    fi
+    
+    # 更新LATEST_VERSION文件
+    update_latest_version_file "$ARGUS_VERSION"
+    
+    # 初始化 DNS 配置文件到系统目录
+    init_dns_config_to_system
+    
+    # 启动服务
+    # start_services
+    
+    log_success "Argus Metric v$ARGUS_VERSION 安装完成！"
+    
+    # 显示安装信息
+    echo
+    log_info "安装信息:"
+    log_info "  版本: $ARGUS_VERSION"
+    log_info "  安装目录: $INSTALL_DIR"
+    log_info "  版本目录: $version_dir"
+    log_info "  当前链接: $CURRENT_LINK"
+    if [[ "$is_upgrade" == true ]]; then
+        log_info "  升级类型: 版本升级"
+    else
+        log_info "  安装类型: 全新安装"
+    fi
+}
+
+# 卸载
+uninstall_argus_metric() {
+    log_info "开始卸载 Argus Metric..."
+    log_info "安装目录: $INSTALL_DIR"
+    
+    # 检查是否已安装
+    if ! check_installed; then
+        log_info "未检测到已安装的 Argus Metric"
+        return 0
+    fi
+    
+    local current_version=$(get_current_version)
+    log_info "检测到当前版本: v$current_version"
+    
+    # 停止服务
+    stop_services
+    
+    # 执行卸载脚本
+    log_info "执行卸载脚本..."
+    if [[ -f "$CURRENT_LINK/uninstall.sh" ]]; then
+        cd "$CURRENT_LINK"
+        chmod +x uninstall.sh
+        
+        # 自动确认卸载（因为用户已经明确使用了 --uninstall 参数）
+        log_info "自动确认卸载操作..."
+        echo "y" | ./uninstall.sh
+        local uninstall_exit_code=$?
+        
+        if [[ $uninstall_exit_code -eq 0 ]]; then
+            log_success "卸载脚本执行完成"
+        else
+            log_error "卸载脚本执行失败 (退出码: $uninstall_exit_code)"
+            exit 1
+        fi
+    else
+        log_warning "未找到卸载脚本，执行基本清理"
+    fi
+    
+    # 清理安装目录
+    log_info "清理安装目录..."
+    if [[ -d "$INSTALL_DIR" ]]; then
+        # 询问是否完全删除安装目录
+        log_warning "这将删除整个安装目录: $INSTALL_DIR"
+        log_warning "包括所有版本、备份和配置文件"
+        
+        # 在自动化环境中，直接删除
+        if rm -rf "$INSTALL_DIR"; then
+            log_success "安装目录已完全清理: $INSTALL_DIR"
+        else
+            log_error "清理安装目录失败"
+            exit 1
+        fi
+    else
+        log_info "安装目录不存在，无需清理"
+    fi
+    
+    log_success "Argus Metric 卸载完成！"
+}
+
+# 显示状态
+show_status() {
+    echo "=========================================="
+    echo "    Argus Metric 安装状态"
+    echo "=========================================="
+    echo
+    
+    if check_installed; then
+        local current_version=$(get_current_version)
+        log_info "当前版本: $current_version"
+        log_info "安装目录: $INSTALL_DIR"
+        log_info "当前链接: $CURRENT_LINK"
+        log_info "版本目录: $VERSIONS_DIR/$current_version"
+        log_info "版本文件: $LATEST_VERSION_FILE"
+        
+        # 显示LATEST_VERSION文件内容
+        if [[ -f "$LATEST_VERSION_FILE" ]]; then
+            local file_version=$(cat "$LATEST_VERSION_FILE" 2>/dev/null | tr -d '[:space:]')
+            log_info "版本文件内容: $file_version"
+        fi
+        
+        echo
+        log_info "目录结构:"
+        if [[ -d "$INSTALL_DIR" ]]; then
+            tree -L 2 "$INSTALL_DIR" 2>/dev/null || ls -la "$INSTALL_DIR"
+        fi
+        
+        echo
+        log_info "可用版本:"
+        if [[ -d "$VERSIONS_DIR" ]]; then
+            ls -1 "$VERSIONS_DIR" 2>/dev/null | sed 's/^/  - /'
+        else
+            echo "  无"
+        fi
+        
+        # 简化安装逻辑：不再显示备份版本信息
+        # echo
+        # log_info "备份版本:"
+        # if [[ -d "$BACKUPS_DIR" ]] && [[ $(ls -1 "$BACKUPS_DIR" 2>/dev/null | wc -l) -gt 0 ]]; then
+        #     ls -1t "$BACKUPS_DIR" 2>/dev/null | sed 's/^/  - /'
+        # else
+        #     echo "  无"
+        # fi
+    else
+        log_warning "Argus Metric 未安装"
+        log_info "安装目录: $INSTALL_DIR"
+    fi
+}
+
+# 列出备份
+list_backups() {
+    echo "=========================================="
+    echo "    Argus Metric 备份列表"
+    echo "=========================================="
+    echo
+    
+    if [[ -d "$BACKUPS_DIR" ]] && [[ $(ls -1 "$BACKUPS_DIR" 2>/dev/null | wc -l) -gt 0 ]]; then
+        log_info "可用备份版本:"
+        ls -1t "$BACKUPS_DIR" 2>/dev/null | while read backup; do
+            local backup_time=$(stat -c %y "$BACKUPS_DIR/$backup" 2>/dev/null | cut -d' ' -f1-2)
+            echo "  - $backup (创建时间: $backup_time)"
+        done
+    else
+        log_warning "没有可用的备份版本"
+    fi
+}
+
+# 回滚功能
+rollback_version() {
+    log_info "开始回滚操作..."
+    
+    if ! check_installed; then
+        log_error "没有检测到已安装的版本，无法回滚"
+        exit 1
+    fi
+    
+    # 确保备份目录存在
+    mkdir -p "$BACKUPS_DIR"
+    
+    # 获取最新的备份
+    local latest_backup=$(ls -1t "$BACKUPS_DIR" 2>/dev/null | head -n 1)
+    if [[ -z "$latest_backup" ]]; then
+        log_error "没有找到可用的备份版本"
+        exit 1
+    fi
+    
+    log_info "将回滚到备份版本: $latest_backup"
+    
+    if rollback_to_backup "$latest_backup"; then
+        log_success "回滚完成！"
+        
+        # 显示当前状态
+        echo
+        show_status
+    else
+        log_error "回滚失败"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus Metric 在线安装脚本 v1.0"
+    echo "=========================================="
+    echo
+    
+    # 加载配置文件
+    load_config
+    
+    # 对于状态操作，不需要FTP参数和root权限
+    # 简化安装逻辑：不再支持备份列表操作
+    if [[ "$ACTION" == "status" ]]; then
+        show_status
+        return 0
+    fi
+    # if [[ "$ACTION" == "status" || "$ACTION" == "backup-list" ]]; then
+    #     if [[ "$ACTION" == "status" ]]; then
+    #         show_status
+    #     elif [[ "$ACTION" == "backup-list" ]]; then
+    #         list_backups
+    #     fi
+    #     return 0
+    # fi
+    
+    check_root
+    
+    # 更新目录配置变量（在设置INSTALL_DIR后）
+    VERSIONS_DIR="$INSTALL_DIR/versions"
+    BACKUPS_DIR="$INSTALL_DIR/backups"
+    CURRENT_LINK="$INSTALL_DIR/current"
+    LATEST_VERSION_FILE="$INSTALL_DIR/LATEST_VERSION"
+    
+    # 简化安装逻辑：不再支持回滚操作
+    # if [[ "$ACTION" == "rollback" ]]; then
+    #     rollback_version
+    #     return 0
+    # fi
+    
+    check_ftp_params
+    check_system
+    
+    if [[ "$ACTION" == "uninstall" ]]; then
+        uninstall_argus_metric
+    else
+        install_argus_metric
+    fi
+    
+    echo
+    log_info "操作完成！"
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/sync_dns.sh

@@ -0,0 +1,143 @@
+#!/bin/bash
+set -e
+
+# 颜色
+RED='\033[0;31m'; GREEN='\033[0;32m'; YELLOW='\033[1;33m'; BLUE='\033[0;34m'; NC='\033[0m'
+
+# 日志函数
+log_info() { echo -e "${BLUE}[INFO]${NC} $1" >&2; }
+log_success() { echo -e "${GREEN}[SUCCESS]${NC} $1" >&2; }
+log_warning() { echo -e "${YELLOW}[WARNING]${NC} $1" >&2; }
+log_error() { echo -e "${RED}[ERROR]${NC} $1" >&2; }
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+LOCAL_DNS_CONF="/opt/argus-metric/dns.conf"
+RESOLV_CONF="/etc/resolv.conf"
+ALT_RESOLV_CONF="/run/resolv.conf"
+LOG_FILE="/opt/argus-metric/.dns_sync.log"
+REMOTE_DNS_CONF_URL=""
+
+# 获取 FTP 配置
+get_ftp_config() {
+    log_info "获取 FTP 配置信息..."
+    if [[ -z "$FTP_SERVER" || -z "$FTP_USER" || -z "$FTP_PASSWORD" ]]; then
+        [[ -f "$SCRIPT_DIR/config.env" ]] && source "$SCRIPT_DIR/config.env"
+    fi
+    FTP_SERVER="${FTP_SERVER:-localhost}"
+    FTP_USER="${FTP_USER:-ftpuser}"
+    FTP_PASSWORD="${FTP_PASSWORD:-ZGClab1234!}"
+    REMOTE_DNS_CONF_URL="ftp://${FTP_USER}:${FTP_PASSWORD}@${FTP_SERVER}/dns.conf"
+}
+
+# 下载远程 dns.conf
+download_remote_dns_conf() {
+    local tmp="/tmp/dns.remote.$$"
+    log_info "测试 FTP 连接..."
+    if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sfI "ftp://${FTP_SERVER}/" >/dev/null; then
+        log_error "无法连接到 FTP 服务器: $FTP_SERVER"; return 1
+    fi
+    if ! curl -u "${FTP_USER}:${FTP_PASSWORD}" -sf "ftp://${FTP_SERVER}/dns.conf" -o "$tmp" 2>/dev/null; then
+        log_error "下载 dns.conf 失败"; rm -f "$tmp"; return 1
+    fi
+    echo "$tmp"
+}
+
+# 文件比较
+compare_files() { diff -q "$1" "$2" >/dev/null 2>&1; }
+
+# 从 dns.conf 提取有效 IP
+get_dns_ips() {
+    grep -Eo '^[0-9]{1,3}(\.[0-9]{1,3}){3}$' "$1" | sort -u
+}
+
+# 安全更新 resolv.conf（保留符号链接）
+update_resolv_conf() {
+    local dns_conf="$1"
+    local dns_ips
+    mapfile -t dns_ips < <(get_dns_ips "$dns_conf")
+    [[ ${#dns_ips[@]} -eq 0 ]] && { log_warning "未检测到有效 DNS"; return; }
+
+    local target_file="$RESOLV_CONF"
+    if [[ ! -w "$RESOLV_CONF" ]]; then
+        log_warning "/etc/resolv.conf 不可写，使用兜底路径 $ALT_RESOLV_CONF"
+        target_file="$ALT_RESOLV_CONF"
+    fi
+
+    local temp="/tmp/resolv.new.$$"
+    cp "$target_file" "${target_file}.backup.$(date +%Y%m%d_%H%M%S)" 2>/dev/null || true
+    log_info "更新 DNS 配置文件: $target_file"
+
+    # 写入新的 nameserver 行
+    for ip in "${dns_ips[@]}"; do
+        echo "nameserver $ip"
+    done >"$temp"
+
+    # 追加原内容（去掉重复 nameserver）
+    grep -v '^nameserver' "$target_file" >>"$temp" 2>/dev/null || true
+    awk '!a[$0]++' "$temp" >"${temp}.uniq"
+
+    # ⚙️ 使用 cat 原地覆盖，避免 mv 引发 “设备忙”
+    if cat "${temp}.uniq" >"$target_file" 2>/dev/null; then
+        chmod 644 "$target_file"
+        log_success "DNS 更新完成: ${dns_ips[*]}"
+    else
+        log_error "无法写入 $target_file，可能被系统锁定"
+    fi
+
+    rm -f "$temp" "${temp}.uniq"
+}
+
+# 检查 resolv.conf 是否包含 dns.conf 内容
+ensure_dns_in_resolv() {
+    local dns_conf="$1"
+    local dns_ips
+    mapfile -t dns_ips < <(get_dns_ips "$dns_conf")
+    [[ ${#dns_ips[@]} -eq 0 ]] && return
+
+    for ip in "${dns_ips[@]}"; do
+        if ! grep -q "nameserver $ip" "$RESOLV_CONF" 2>/dev/null; then
+            log_warning "检测到 /etc/resolv.conf 缺少 $ip，执行兜底修复"
+            update_resolv_conf "$dns_conf"
+            return
+        fi
+    done
+    log_info "/etc/resolv.conf 已包含所有 DNS"
+}
+
+log_sync() { echo "[$(date '+%F %T')] $1" >>"$LOG_FILE"; }
+
+main() {
+    log_info "开始 DNS 同步检查..."
+    mkdir -p /opt/argus-metric
+
+    get_ftp_config
+    local remote_file
+    if ! remote_file=$(download_remote_dns_conf); then
+        log_error "下载失败"; log_sync "同步失败"; exit 1
+    fi
+
+    if [[ ! -f "$LOCAL_DNS_CONF" ]]; then
+        log_info "本地 dns.conf 不存在，初始化..."
+        cp "$remote_file" "$LOCAL_DNS_CONF"
+        update_resolv_conf "$LOCAL_DNS_CONF"
+        log_sync "首次同步完成"
+    else
+        if compare_files "$LOCAL_DNS_CONF" "$remote_file"; then
+            log_info "dns.conf 无变化"
+            ensure_dns_in_resolv "$LOCAL_DNS_CONF"
+            log_sync "dns.conf 无变化，执行兜底检查"
+        else
+            log_info "检测到 DNS 配置更新"
+            cp "$remote_file" "$LOCAL_DNS_CONF"
+            update_resolv_conf "$LOCAL_DNS_CONF"
+            log_sync "DNS 配置同步完成"
+        fi
+    fi
+
+    rm -f "$remote_file"
+    log_success "DNS 同步流程完成"
+}
+
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/uninstall_artifact.sh

@@ -0,0 +1,274 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 配置变量
+INSTALL_DIR="/opt/argus-metric"
+TEMP_DIR="/tmp/argus-metric-uninstall-$$"
+VERSION_FILE="version.json"
+
+# 检查是否为 root 用户
+check_root() {
+    if [[ $EUID -ne 0 ]]; then
+        log_error "此脚本需要 root 权限运行"
+        log_info "请使用: sudo $0"
+        exit 1
+    fi
+}
+
+# 查找版本文件
+find_version_file() {
+    log_info "查找版本信息文件..."
+    
+    # 在当前目录查找
+    if [[ -f "$VERSION_FILE" ]]; then
+        VERSION_FILE_PATH="$VERSION_FILE"
+        log_success "找到版本文件: $VERSION_FILE"
+        return 0
+    fi
+    
+    # 在 artifact 目录查找
+    for version_dir in artifact/*/; do
+        if [[ -f "${version_dir}${VERSION_FILE}" ]]; then
+            VERSION_FILE_PATH="${version_dir}${VERSION_FILE}"
+            log_success "找到版本文件: $VERSION_FILE_PATH"
+            return 0
+        fi
+    done
+    
+    log_error "未找到版本信息文件 $VERSION_FILE"
+    log_info "请确保在正确的目录下运行此脚本"
+    exit 1
+}
+
+# 解析版本信息
+parse_version_info() {
+    log_info "解析版本信息..."
+    
+    if [[ ! -f "$VERSION_FILE_PATH" ]]; then
+        log_error "版本文件不存在: $VERSION_FILE_PATH"
+        exit 1
+    fi
+    
+    # 使用 jq 解析 JSON（如果可用）
+    if command -v jq &> /dev/null; then
+        VERSION=$(jq -r '.version' "$VERSION_FILE_PATH")
+        BUILD_TIME=$(jq -r '.build_time' "$VERSION_FILE_PATH")
+        
+        # 解析 install_order（现在包含完整的文件名）
+        if jq -e '.install_order' "$VERSION_FILE_PATH" > /dev/null 2>&1; then
+            jq -r '.install_order[]' "$VERSION_FILE_PATH" > "$TEMP_DIR/install_order.txt"
+        else
+            log_error "version.json 中缺少 install_order 字段"
+            exit 1
+        fi
+    else
+        log_warning "jq 未安装，使用简单的 JSON 解析"
+        VERSION=$(grep '"version"' "$VERSION_FILE_PATH" | sed 's/.*"version": *"\([^"]*\)".*/\1/')
+        BUILD_TIME=$(grep '"build_time"' "$VERSION_FILE_PATH" | sed 's/.*"build_time": *"\([^"]*\)".*/\1/')
+        
+        # 解析 install_order
+        grep -A 100 '"install_order"' "$VERSION_FILE_PATH" | grep -E '^\s*"[^"]+"' | while read line; do
+            component=$(echo "$line" | sed 's/.*"\([^"]*\)".*/\1/')
+            echo "$component" >> "$TEMP_DIR/install_order.txt"
+        done
+    fi
+    
+    log_success "版本信息解析完成"
+    log_info "  版本: $VERSION"
+    log_info "  构建时间: $BUILD_TIME"
+}
+
+# 创建临时目录
+create_temp_dirs() {
+    log_info "创建临时目录..."
+    mkdir -p "$TEMP_DIR"
+    log_success "临时目录创建完成: $TEMP_DIR"
+}
+
+# 卸载组件
+uninstall_components() {
+    log_info "开始卸载组件..."
+    
+    artifact_dir=$(dirname "$VERSION_FILE_PATH")
+    uninstall_count=0
+    total_count=0
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        total_count=$(wc -l < "$TEMP_DIR/install_order.txt")
+    fi
+    
+    if [[ -f "$TEMP_DIR/install_order.txt" ]]; then
+        while IFS= read -r filename; do
+            uninstall_count=$((uninstall_count + 1))
+            
+            # 从文件名中提取组件名（去掉时间戳后缀）
+            component=$(echo "$filename" | sed 's/-[0-9]\{8\}-[0-9]\{6\}\.tar\.gz$//')
+            
+            log_info "[$uninstall_count/$total_count] 卸载 $component..."
+            
+            # 直接使用完整的文件名
+            tar_file="$artifact_dir/$filename"
+            
+            if [[ ! -f "$tar_file" ]]; then
+                log_error "找不到组件文件: $filename"
+                exit 1
+            fi
+            
+            # 解压到临时目录
+            component_temp_dir="$TEMP_DIR/$component"
+            mkdir -p "$component_temp_dir"
+            
+            if tar -xzf "$tar_file" -C "$component_temp_dir"; then
+                log_success "  $component 解压完成"
+            else
+                log_error "  $component 解压失败"
+                exit 1
+            fi
+            
+            # 查找解压后的目录
+            extracted_dir=""
+            for dir in "$component_temp_dir"/*; do
+                if [[ -d "$dir" ]]; then
+                    extracted_dir="$dir"
+                    break
+                fi
+            done
+            
+            if [[ -z "$extracted_dir" ]]; then
+                log_error "  $component 解压后未找到目录"
+                exit 1
+            fi
+            
+            # 执行卸载脚本
+            if [[ -f "$extracted_dir/uninstall.sh" ]]; then
+                log_info "  执行 $component 卸载脚本..."
+                # 所有组件都只需要一个确认
+                if (cd "$extracted_dir" && echo "y" | ./uninstall.sh); then
+                    log_success "  $component 卸载完成"
+                else
+                    log_error "  $component 卸载失败"
+                    exit 1
+                fi
+            else
+                log_warning "  $component 缺少 uninstall.sh 文件，跳过卸载"
+            fi
+            
+            # 清理临时文件
+            rm -rf "$component_temp_dir"
+        done < "$TEMP_DIR/install_order.txt"
+    fi
+    
+    log_success "所有组件卸载完成"
+}
+
+# 清理全局文件
+cleanup_global_files() {
+    log_info "清理全局文件..."
+    
+    # 清理安装目录
+    if [[ -d "$INSTALL_DIR" ]]; then
+        rm -rf "$INSTALL_DIR"
+        log_success "安装目录已清理: $INSTALL_DIR"
+    else
+        log_info "安装目录不存在: $INSTALL_DIR"
+    fi
+    
+    # 清理可能的全局配置文件
+    local global_configs=(
+        "/etc/argus-metric"
+        "/var/log/argus-metric"
+    )
+    
+    for config in "${global_configs[@]}"; do
+        if [[ -d "$config" ]]; then
+            rm -rf "$config"
+            log_success "全局配置已清理: $config"
+        fi
+    done
+}
+
+# 显示卸载信息
+show_uninstall_info() {
+    log_success "Argus-Metrics All-in-One 卸载完成！"
+    echo
+    echo "卸载信息:"
+    echo "  版本: $VERSION"
+    echo "  构建时间: $BUILD_TIME"
+    echo
+    echo "清理内容:"
+    echo "  - 二进制文件"
+    echo "  - 配置文件"
+    echo "  - 数据目录"
+    echo "  - 进程和服务"
+    echo "  - 全局安装目录"
+    echo
+    echo "注意:"
+    echo "  - 系统依赖包可能仍然存在"
+    echo "  - 如需完全清理，请手动检查并删除相关文件"
+    echo
+}
+
+# 清理函数
+cleanup() {
+    if [[ -d "$TEMP_DIR" ]]; then
+        rm -rf "$TEMP_DIR"
+    fi
+}
+
+# 设置清理陷阱
+trap cleanup EXIT
+
+# 主函数
+main() {
+    echo "=========================================="
+    echo "    Argus-Metrics All-in-One 卸载脚本"
+    echo "=========================================="
+    echo
+    
+    check_root
+    find_version_file
+    create_temp_dirs
+    parse_version_info
+    
+    log_warning "此操作将完全卸载 Argus-Metrics All-in-One"
+    read -p "确认继续？(y/N): " confirm
+    
+    if [[ "$confirm" != "y" && "$confirm" != "Y" ]]; then
+        log_info "取消卸载操作"
+        exit 0
+    fi
+    
+    uninstall_components
+    cleanup_global_files
+    show_uninstall_info
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/client-plugins/all-in-one-demo/scripts/version-manager.sh

@@ -0,0 +1,350 @@
+#!/bin/bash
+
+set -e
+
+# 颜色定义
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# 日志函数
+log_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+log_success() {
+    echo -e "${GREEN}[SUCCESS]${NC} $1"
+}
+
+log_warning() {
+    echo -e "${YELLOW}[WARNING]${NC} $1"
+}
+
+log_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+# 显示帮助信息
+show_help() {
+    echo "AIOps 版本管理工具"
+    echo
+    echo "用法: $0 <command> [options]"
+    echo
+    echo "命令:"
+    echo "  bump <type>     - 升级版本号 (major|minor|patch)"
+    echo "  set <version>   - 设置指定版本号"
+    echo "  show            - 显示当前版本信息"
+    echo "  list            - 列出所有版本"
+    echo "  clean           - 清理旧版本"
+    echo "  validate        - 验证版本配置"
+    echo
+    echo "示例:"
+    echo "  $0 bump minor    # 升级次版本号 1.0.0 -> 1.1.0"
+    echo "  $0 set 2.0.0     # 设置版本为 2.0.0"
+    echo "  $0 show          # 显示当前版本"
+    echo "  $0 list          # 列出所有版本"
+}
+
+# 获取当前版本
+get_current_version() {
+    if [[ -f "config/VERSION" ]]; then
+        cat config/VERSION
+    else
+        echo "0.0.0"
+    fi
+}
+
+# 设置版本号
+set_version() {
+    local new_version="$1"
+    
+    # 验证版本号格式
+    if [[ ! "$new_version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+        log_error "无效的版本号格式: $new_version"
+        log_info "版本号格式应为: major.minor.patch (如: 1.2.3)"
+        exit 1
+    fi
+    
+    echo "$new_version" > config/VERSION
+    log_success "版本号已设置为: $new_version"
+}
+
+# 升级版本号
+bump_version() {
+    local bump_type="$1"
+    local current_version=$(get_current_version)
+    
+    # 解析当前版本号
+    IFS='.' read -r major minor patch <<< "$current_version"
+    
+    case "$bump_type" in
+        "major")
+            major=$((major + 1))
+            minor=0
+            patch=0
+            ;;
+        "minor")
+            minor=$((minor + 1))
+            patch=0
+            ;;
+        "patch")
+            patch=$((patch + 1))
+            ;;
+        *)
+            log_error "无效的升级类型: $bump_type"
+            log_info "支持的类型: major, minor, patch"
+            exit 1
+            ;;
+    esac
+    
+    local new_version="$major.$minor.$patch"
+    set_version "$new_version"
+    log_success "版本号已从 $current_version 升级到 $new_version"
+}
+
+# 显示当前版本信息
+show_version() {
+    local current_version=$(get_current_version)
+    log_info "当前版本: $current_version"
+    
+    if [[ -f "config/checklist" ]]; then
+        echo
+        echo "组件清单:"
+        while IFS= read -r line; do
+            [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+            read -r component version dep order <<< "$line"
+            if [[ -n "$component" && -n "$version" ]]; then
+                echo "  - $component v$version"
+            fi
+        done < config/checklist
+    fi
+    
+    # 检查是否有对应的 artifact
+    local artifact_dir="artifact/$current_version"
+    if [[ -d "$artifact_dir" ]]; then
+        echo
+        echo "已构建的组件:"
+        for file in "$artifact_dir"/*.tar.gz; do
+            if [[ -f "$file" ]]; then
+                local filename=$(basename "$file")
+                local size=$(du -h "$file" | cut -f1)
+                echo "  - $filename ($size)"
+            fi
+        done
+        
+        if [[ -f "$artifact_dir/version.json" ]]; then
+            echo
+            echo "版本信息文件: $artifact_dir/version.json"
+        fi
+    else
+        echo
+        log_warning "未找到对应的构建目录: $artifact_dir"
+        log_info "运行 ./package.sh 进行构建"
+    fi
+}
+
+# 列出所有版本
+list_versions() {
+    log_info "所有版本列表:"
+    echo
+    
+    if [[ ! -d "artifact" ]]; then
+        log_warning "artifact 目录不存在"
+        return
+    fi
+    
+    for version_dir in artifact/*/; do
+        if [[ -d "$version_dir" ]]; then
+            local version=$(basename "$version_dir")
+            local current_version=$(get_current_version)
+            
+            if [[ "$version" == "$current_version" ]]; then
+                echo "  * $version (当前版本)"
+            else
+                echo "    $version"
+            fi
+            
+            # 显示该版本的组件
+            local component_count=0
+            for file in "$version_dir"/*.tar.gz; do
+                if [[ -f "$file" ]]; then
+                    component_count=$((component_count + 1))
+                fi
+            done
+            
+            if [[ $component_count -gt 0 ]]; then
+                echo "      包含 $component_count 个组件"
+            fi
+        fi
+    done
+}
+
+# 清理旧版本
+clean_versions() {
+    local current_version=$(get_current_version)
+    local keep_versions=5  # 保留最近5个版本
+    
+    log_info "清理旧版本 (保留最近 $keep_versions 个版本)..."
+    
+    if [[ ! -d "artifact" ]]; then
+        log_warning "artifact 目录不存在"
+        return
+    fi
+    
+    # 获取所有版本目录，按修改时间排序
+    local versions=()
+    while IFS= read -r -d '' version_dir; do
+        versions+=("$(basename "$version_dir")")
+    done < <(find artifact -maxdepth 1 -type d -name "[0-9]*" -print0 | sort -z)
+    
+    local total_versions=${#versions[@]}
+    local versions_to_remove=$((total_versions - keep_versions))
+    
+    if [[ $versions_to_remove -le 0 ]]; then
+        log_info "无需清理，当前只有 $total_versions 个版本"
+        return
+    fi
+    
+    log_info "将删除 $versions_to_remove 个旧版本..."
+    
+    for ((i=0; i<versions_to_remove; i++)); do
+        local version="${versions[i]}"
+        if [[ "$version" != "$current_version" ]]; then
+            log_info "删除版本: $version"
+            rm -rf "artifact/$version"
+        fi
+    done
+    
+    log_success "旧版本清理完成"
+}
+
+# 验证版本配置
+validate_version() {
+    log_info "验证版本配置..."
+    
+    local errors=0
+    
+    # 检查 VERSION 文件
+    if [[ ! -f "config/VERSION" ]]; then
+        log_error "VERSION 文件不存在"
+        errors=$((errors + 1))
+    else
+        local version=$(get_current_version)
+        if [[ ! "$version" =~ ^[0-9]+\.[0-9]+\.[0-9]+$ ]]; then
+            log_error "VERSION 文件格式无效: $version"
+            errors=$((errors + 1))
+        else
+            log_success "VERSION 文件格式正确: $version"
+        fi
+    fi
+    
+    # 检查 checklist 文件
+    if [[ ! -f "config/checklist" ]]; then
+        log_error "checklist 文件不存在"
+        errors=$((errors + 1))
+    else
+        local component_count=0
+        while IFS= read -r line; do
+            [[ -z "$line" || "$line" =~ ^[[:space:]]*# ]] && continue
+            read -r component version dep order <<< "$line"
+            if [[ -n "$component" && -n "$version" ]]; then
+                component_count=$((component_count + 1))
+                
+                # 检查组件目录是否存在
+                if [[ ! -d "plugins/$component" ]]; then
+                    log_error "组件目录不存在: plugins/$component"
+                    errors=$((errors + 1))
+                fi
+            fi
+        done < config/checklist
+        
+        if [[ $component_count -gt 0 ]]; then
+            log_success "checklist 包含 $component_count 个组件"
+        else
+            log_error "checklist 中没有有效组件"
+            errors=$((errors + 1))
+        fi
+    fi
+    
+    # 检查 package.sh 文件
+    if [[ ! -f "scripts/package_artifact.sh" ]]; then
+        log_error "package_artifact.sh 文件不存在"
+        errors=$((errors + 1))
+    else
+        if [[ -x "scripts/package_artifact.sh" ]]; then
+            log_success "package_artifact.sh 可执行"
+        else
+            log_warning "package_artifact.sh 不可执行，请运行: chmod +x scripts/package_artifact.sh"
+        fi
+    fi
+    
+    # 检查 install.sh 文件
+    if [[ ! -f "scripts/install_artifact.sh" ]]; then
+        log_error "install_artifact.sh 文件不存在"
+        errors=$((errors + 1))
+    else
+        if [[ -x "scripts/install_artifact.sh" ]]; then
+            log_success "install_artifact.sh 可执行"
+        else
+            log_warning "install_artifact.sh 不可执行，请运行: chmod +x scripts/install_artifact.sh"
+        fi
+    fi
+    
+    if [[ $errors -eq 0 ]]; then
+        log_success "版本配置验证通过"
+    else
+        log_error "发现 $errors 个配置问题"
+        exit 1
+    fi
+}
+
+# 主函数
+main() {
+    case "${1:-}" in
+        "bump")
+            if [[ -z "${2:-}" ]]; then
+                log_error "请指定升级类型: major, minor, patch"
+                exit 1
+            fi
+            bump_version "$2"
+            ;;
+        "set")
+            if [[ -z "${2:-}" ]]; then
+                log_error "请指定版本号"
+                exit 1
+            fi
+            set_version "$2"
+            ;;
+        "show")
+            show_version
+            ;;
+        "list")
+            list_versions
+            ;;
+        "clean")
+            clean_versions
+            ;;
+        "validate")
+            validate_version
+            ;;
+        "help"|"-h"|"--help")
+            show_help
+            ;;
+        "")
+            show_help
+            ;;
+        *)
+            log_error "未知命令: $1"
+            echo
+            show_help
+            exit 1
+            ;;
+    esac
+}
+
+# 脚本入口
+if [[ "${BASH_SOURCE[0]}" == "${0}" ]]; then
+    main "$@"
+fi

src/metric/ftp/build/Dockerfile

@@ -0,0 +1,76 @@
+FROM ubuntu:22.04
+
+USER root
+
+ARG USE_INTRANET=false
+
+# 内网 apt 源配置
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+        echo "Configuring intranet apt sources..." && \
+        cp /etc/apt/sources.list /etc/apt/sources.list.bak && \
+        echo "deb [trusted=yes] http://10.68.64.1/ubuntu2204/ jammy main" > /etc/apt/sources.list && \
+        echo 'Acquire::https::Verify-Peer "false";' > /etc/apt/apt.conf.d/99disable-ssl-check && \
+        echo 'Acquire::https::Verify-Host "false";' >> /etc/apt/apt.conf.d/99disable-ssl-check; \
+    fi
+
+# 安装常用工具和FTP服务
+RUN apt-get update && \
+    apt-get install -y supervisor net-tools inetutils-ping vim vsftpd && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 如果是部署环境替换 apt 源
+RUN if [ "$USE_INTRANET" = "true" ]; then \
+    echo "deb [trusted=yes] https://10.92.132.52/mirrors/ubuntu2204/ jammy main" > /etc/apt/sources.list; \
+    fi
+
+# supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+# 设置 FTP 基础路径环境变量
+ENV FTP_BASE_PATH=/private/argus/ftp
+
+# 设置域名环境变量
+ENV DOMAIN=ftp.metric.argus.com
+
+# 设置FTP用户密码环境变量
+ENV FTP_PASSWORD=ZGClab1234!
+
+# 设置用户和组ID环境变量
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# 创建FTP用户和目录结构
+RUN groupadd -g ${ARGUS_BUILD_GID} ftpuser && \
+    useradd -u ${ARGUS_BUILD_UID} -g ${ARGUS_BUILD_GID} -d ${FTP_BASE_PATH}/share -s /bin/bash ftpuser && \
+    mkdir -p ${FTP_BASE_PATH}/share \
+    && mkdir -p /private/argus/etc \
+    && mkdir -p /var/log/vsftpd \
+    && chown -R ftpuser:ftpuser ${FTP_BASE_PATH} \
+    && mkdir -p /var/run/vsftpd/empty
+
+# 创建vsftpd配置目录和用户列表文件
+RUN mkdir -p /etc/vsftpd && \
+    echo "ftpuser" > /etc/vsftpd.userlist
+
+# supervisor 配置
+COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 启动脚本
+COPY start-ftp-supervised.sh /usr/local/bin/start-ftp-supervised.sh
+RUN chmod +x /usr/local/bin/start-ftp-supervised.sh
+
+# vsftpd 配置文件
+COPY vsftpd.conf /etc/vsftpd/vsftpd.conf
+
+COPY dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+USER root
+
+EXPOSE 21 20 21100-21110
+
+ENTRYPOINT ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf", "-n"]

src/metric/ftp/build/README.md

@@ -0,0 +1,159 @@
+# FTP 镜像配置
+
+## 环境变量配置
+
+### FTP_BASE_PATH
+
+设置 FTP 数据的基础路径。
+
+**默认值**: `/private/argus/ftp`
+
+**用途**:
+- 共享目录路径: `${FTP_BASE_PATH}/share` (用于版本发布)
+- 配置文件存储路径: `/private/argus/etc/`
+
+### DOMAIN
+
+设置 FTP 服务的域名。
+
+**默认值**: `ftp.metric.argus.com`
+
+**用途**:
+- 容器IP记录文件: `/private/argus/etc/${DOMAIN}`
+
+### FTP_PASSWORD
+
+设置 ftpuser 用户的密码。
+
+**默认值**: `ZGClab1234!`
+
+**用途**:
+- ftpuser 用户的登录密码
+
+## 使用示例
+
+### 1. 使用默认配置
+```bash
+docker run -d \
+  --name ftp-server \
+  -p 21:21 \
+  -p 21100-21110:21100-21110 \
+  -v /host/ftp/data:/private/argus/ftp \
+  argus-metric-ftp:1.0.0
+```
+
+### 2. 自定义配置（运行时环境变量）
+```bash
+docker run -d \
+  --name ftp-server \
+  -p 21:21 \
+  -p 21100-21110:21100-21110 \
+  -e FTP_BASE_PATH=/custom/ftp/path \
+  -e DOMAIN=custom.ftp.domain.com \
+  -e FTP_PASSWORD=MySecurePassword123! \
+  -v /host/ftp/data:/custom/ftp/path \
+  argus-metric-ftp:1.0.0
+```
+
+## 目录结构
+
+容器启动后会在 `${FTP_BASE_PATH}` 下创建以下目录结构：
+
+```
+${FTP_BASE_PATH}/
+└── share/                    # FTP根目录（直接挂载）
+    └── (用户上传的文件)
+
+/private/argus/etc/
+└── ${DOMAIN}                 # 容器IP记录文件
+```
+
+## vsftpd 配置说明
+
+### 核心配置参数
+
+根据README中的推荐配置，vsftpd.conf包含以下关键设置：
+
+```bash
+# 基本设置
+local_enable=YES          # 允许本地用户登录
+write_enable=YES          # 允许写操作（上传/删除/修改）
+chroot_local_user=YES     # 限制用户在自己目录中
+allow_writeable_chroot=YES # 防止 chroot 错误（重要！）
+
+# 被动模式配置
+pasv_enable=YES           # 启用被动模式
+pasv_min_port=21100       # 被动模式最小端口
+pasv_max_port=21110       # 被动模式最大端口
+
+# 用户访问控制
+userlist_enable=YES       # 启用用户列表
+userlist_file=/etc/vsftpd.userlist  # 用户列表文件
+userlist_deny=NO          # 只允许列表中的用户登录
+```
+
+### 用户管理
+
+#### 默认用户
+- **用户名**: ftpuser
+- **密码**: ZGClab1234! (可通过 FTP_PASSWORD 环境变量修改)
+- **UID**: 2133 (与prometheus用户保持一致，可通过 FTP_UID 环境变量修改)
+- **GID**: 2015 (与prometheus用户保持一致，可通过 FTP_GID 环境变量修改)
+- **主目录**: ${FTP_BASE_PATH}/share (直接指向挂载目录)
+- **Shell**: /bin/bash
+- **用户列表**: 已添加到 `/etc/vsftpd.userlist`
+
+#### 添加新用户
+```bash
+# 进入容器
+docker exec -it ftp-server bash
+
+# 添加新用户
+useradd -d ${FTP_BASE_PATH}/share/newuser -s /bin/bash newuser
+echo "newuser" >> /etc/vsftpd.userlist
+passwd newuser
+
+# 创建用户目录
+mkdir -p ${FTP_BASE_PATH}/share/newuser
+chown newuser:newuser ${FTP_BASE_PATH}/share/newuser
+```
+
+## 端口配置
+
+- **21**: FTP 控制端口
+- **20**: FTP 数据端口 (主动模式)
+- **21100-21110**: 被动模式数据端口范围
+
+### 日志文件位置
+- **vsftpd 日志**: `/var/log/vsftpd/vsftpd.log`
+- **supervisor 日志**: `/var/log/supervisor/`
+  - `supervisord.log`: supervisor 主日志
+  - `vsftpd.log`: vsftpd 标准输出
+  - `vsftpd_error.log`: vsftpd 错误输出
+
+```bash
+# 在宿主机上配置 logrotate
+cat > /etc/logrotate.d/ftp-docker << EOF
+/var/lib/docker/containers/*/ftp-server-*.log {
+    daily
+    rotate 7
+    compress
+    delaycompress
+    missingok
+    notifempty
+    copytruncate
+}
+EOF
+```
+
+### FTP连接测试
+```bash
+# 本地测试连接
+ftp localhost
+
+curl -fsS 'ftp://ftpuser:ZGClab1234!@177.177.70.200/setup.sh' -o setup.sh
+
+# root用户直接执行，非root用户需要使用sudo
+chmod +x setup.sh
+bash setup.sh --server {$域名} --user ftpuser --password 'ZGClab1234!'
+```

src/metric/ftp/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/metric/ftp/build/start-ftp-supervised.sh

@@ -0,0 +1,40 @@
+#!/bin/bash
+set -euo pipefail
+
+echo "[INFO] Starting FTP server under supervisor..."
+
+FTP_BASE_PATH=${FTP_BASE_PATH:-/private/argus/ftp}
+DOMAIN=${DOMAIN:-ftp.metric.argus.com}
+FTP_PASSWORD=${FTP_PASSWORD:-ZGClab1234!}
+
+echo "[INFO] FTP base path: ${FTP_BASE_PATH}"
+echo "[INFO] Domain: ${DOMAIN}"
+echo "[INFO] Setting ftpuser password..."
+
+# 设置ftpuser密码
+echo "ftpuser:${FTP_PASSWORD}" | chpasswd
+
+# 确保目录存在
+mkdir -p ${FTP_BASE_PATH}/share
+mkdir -p /private/argus/etc
+mkdir -p /var/run/vsftpd/empty
+
+# 直接使用挂载目录作为FTP根目录，无需软链接
+echo "[INFO] Using ${FTP_BASE_PATH}/share as FTP root directory"
+
+# 生成vsftpd配置文件
+echo "[INFO] Generating vsftpd.conf with base path: ${FTP_BASE_PATH}"
+sed "s|\${FTP_BASE_PATH}|${FTP_BASE_PATH}|g" \
+    /etc/vsftpd/vsftpd.conf > /tmp/vsftpd.conf
+
+# 记录容器 IP
+IP=$(ifconfig eth0 | awk '/inet /{print $2}' || hostname -i)
+echo "current IP: ${IP}"
+echo "${IP}" > /private/argus/etc/${DOMAIN}
+
+chown ${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID} /private/argus/etc/${DOMAIN}
+chmod +x /private/argus/etc/${DOMAIN}
+
+# 启动vsftpd
+echo "[INFO] Starting vsftpd..."
+exec /usr/sbin/vsftpd /tmp/vsftpd.conf

src/metric/ftp/build/supervisord.conf

@@ -0,0 +1,39 @@
+[supervisord]
+nodaemon=true
+logfile=/var/log/supervisor/supervisord.log
+pidfile=/var/run/supervisord.pid
+user=root
+
+[program:vsftpd]
+command=/usr/local/bin/start-ftp-supervised.sh
+user=root
+stdout_logfile=/var/log/supervisor/vsftpd.log
+stderr_logfile=/var/log/supervisor/vsftpd_error.log
+autorestart=true
+startretries=3
+startsecs=10
+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/metric/ftp/build/vsftpd-config-README.md

@@ -0,0 +1,111 @@
+# vsftpd 配置
+
+配置 vsftpd FTP 服务器。
+
+# 安装deps下 vsftpd 的离线安装包
+
+sudo dpkg -i vsftpd_3.0.5-0ubuntu1.1_amd64.deb
+
+# 有依赖问题，修复依赖
+
+sudo apt-get install -f
+
+## 启动服务
+
+sudo service vsftpd start
+
+# 重启服务
+
+sudo service vsftpd restart
+
+# 查看状态
+
+sudo service vsftpd status
+
+## 备份配置文件
+
+先备份默认配置，出问题能恢复：
+
+```bash
+sudo cp /etc/vsftpd.conf /etc/vsftpd.conf.bak
+```
+
+## 修改配置文件
+
+编辑配置：
+
+```bash
+sudo vim /etc/vsftpd.conf
+```
+
+### 基本配置参数
+
+```bash
+# 允许本地用户登录
+local_enable=YES
+
+# 允许写操作（上传/删除/修改）
+write_enable=YES
+
+# 限制用户在自己目录中，不能访问整个系统
+chroot_local_user=YES
+
+# 防止 chroot 错误（重要！）
+allow_writeable_chroot=YES
+
+# 被动模式配置
+pasv_enable=YES
+pasv_min_port=30000
+pasv_max_port=31000
+```
+
+## 创建 FTP 目录和用户
+
+### 创建共享目录
+
+```bash
+sudo mkdir -p /srv/ftp/share
+sudo chmod 755 /srv/ftp/share
+```
+
+### 创建专用用户
+
+```bash
+sudo adduser ftpuser
+
+# 修改用户主目录
+sudo usermod -d /srv/ftp/share ftpuser
+```
+
+## 重启服务
+
+```bash
+sudo service vsftpd restart
+```
+
+## 防火墙配置
+
+### 开放基本端口
+
+```bash
+sudo ufw allow 21/tcp
+```
+
+### 开放被动模式端口
+
+```bash
+sudo ufw allow 30000:31000/tcp
+```
+
+## 测试连接
+
+```bash
+# 本地测试
+ftp localhost
+
+# 远程测试
+ftp 你的服务器IP
+```
+
+用户名：ftpuser  
+密码：设置的密码

src/metric/ftp/build/vsftpd-offline-install.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+
+# vsftpd 离线安装脚本
+# 使用方法：./vsftpd-offline-install.sh
+
+set -e
+
+echo "开始 vsftpd 离线安装..."
+
+# 检查是否为 root 用户
+if [ "$EUID" -ne 0 ]; then
+    echo "请使用 root 权限运行此脚本"
+    exit 1
+fi
+
+# 定义离线包目录
+OFFLINE_DIR="./vsftpd-offline"
+DEB_DIR="$OFFLINE_DIR/debs"
+
+# 检查离线包是否存在
+if [ ! -d "$OFFLINE_DIR" ]; then
+    echo "错误：找不到离线包目录 $OFFLINE_DIR"
+    echo "请先准备离线包，方法："
+    echo "1. 在有网络的机器上运行："
+    echo "   mkdir -p $DEB_DIR"
+    echo "   cd $DEB_DIR"
+    echo "   apt download vsftpd"
+    echo "   apt download \$(apt-cache depends vsftpd | grep Depends | cut -d: -f2 | tr -d ' ')"
+    echo "2. 将整个 $OFFLINE_DIR 目录拷贝到目标机器"
+    exit 1
+fi
+
+# 安装 deb 包
+echo "安装 vsftpd 及依赖包..."
+cd "$DEB_DIR"
+dpkg -i *.deb || apt-get install -f -y
+
+# 检查安装状态
+if systemctl is-active --quiet vsftpd; then
+    echo "vsftpd 安装成功并已启动"
+else
+    echo "启动 vsftpd 服务..."
+    systemctl start vsftpd
+    systemctl enable vsftpd
+fi
+
+echo "vsftpd 离线安装完成！"
+echo "配置文件位置: /etc/vsftpd.conf"
+echo "服务状态: $(systemctl is-active vsftpd)"

src/metric/ftp/build/vsftpd.conf

@@ -0,0 +1,56 @@
+# vsftpd 配置文件
+
+# 基本设置
+listen=YES
+listen_ipv6=NO
+anonymous_enable=NO
+local_enable=YES
+write_enable=YES
+local_umask=022
+dirmessage_enable=YES
+use_localtime=YES
+xferlog_enable=YES
+connect_from_port_20=YES
+
+# 安全设置
+chroot_local_user=YES
+allow_writeable_chroot=YES
+secure_chroot_dir=/var/run/vsftpd/empty
+pam_service_name=vsftpd
+rsa_cert_file=/etc/ssl/certs/ssl-cert-snakeoil.pem
+rsa_private_key_file=/etc/ssl/private/ssl-cert-snakeoil.key
+ssl_enable=NO
+
+# 用户设置
+userlist_enable=YES
+userlist_file=/etc/vsftpd.userlist
+userlist_deny=NO
+
+# 目录设置
+local_root=${FTP_BASE_PATH}/share
+
+# 被动模式设置
+pasv_enable=YES
+pasv_min_port=21100
+pasv_max_port=21110
+pasv_address=0.0.0.0
+
+# 日志设置
+xferlog_file=/var/log/vsftpd/vsftpd.log
+log_ftp_protocol=YES
+
+# 其他设置
+hide_ids=YES
+tcp_wrappers=YES
+
+# 文件上传设置
+file_open_mode=0666
+local_umask=022
+
+# 超时设置
+idle_session_timeout=300
+data_connection_timeout=300
+
+# 限制设置
+max_clients=50
+max_per_ip=5

src/metric/grafana/build/Dockerfile

@@ -0,0 +1,69 @@
+FROM grafana/grafana:11.1.0
+
+USER root
+
+# 安装必要的工具
+RUN apk add --no-cache \
+        supervisor \
+        net-tools \
+        iputils \
+        vim \
+        bash
+
+# supervisor 日志目录
+RUN mkdir -p /var/log/supervisor
+
+# 设置 Grafana 基础路径环境变量
+ENV GRAFANA_BASE_PATH=/private/argus/metric/grafana
+
+# 设置用户和组ID环境变量
+ARG ARGUS_BUILD_UID=2133
+ARG ARGUS_BUILD_GID=2015
+
+ENV ARGUS_BUILD_UID=${ARGUS_BUILD_UID} \
+    ARGUS_BUILD_GID=${ARGUS_BUILD_GID}
+
+# 创建基本目录结构
+RUN mkdir -p /private/argus/etc \
+    && mkdir -p ${GRAFANA_BASE_PATH}/data \
+    && mkdir -p ${GRAFANA_BASE_PATH}/logs \
+    && mkdir -p ${GRAFANA_BASE_PATH}/plugins \
+    && mkdir -p ${GRAFANA_BASE_PATH}/provisioning/datasources \
+    && mkdir -p ${GRAFANA_BASE_PATH}/provisioning/dashboards \
+    && mkdir -p ${GRAFANA_BASE_PATH}/data/sessions \
+    && mkdir -p ${GRAFANA_BASE_PATH}/data/dashboards \
+    && mkdir -p ${GRAFANA_BASE_PATH}/config \
+    && mkdir -p /etc/grafana \
+    && mkdir -p /var/lib/grafana \
+    && mkdir -p /var/log/grafana
+
+# 修改 Grafana 用户 UID/GID 并授权
+RUN deluser grafana && \
+    addgroup -g ${ARGUS_BUILD_GID} grafana && \
+    adduser -u ${ARGUS_BUILD_UID} -G grafana -s /bin/sh -D grafana && \
+    chown -R grafana:grafana /var/lib/grafana /etc/grafana /var/log/grafana ${GRAFANA_BASE_PATH}
+
+# 复制配置文件到容器内临时位置
+COPY grafana.ini /tmp/grafana.ini
+COPY datasources/datasources.yml /tmp/datasources.yml
+COPY dashboards/dashboards.yml /tmp/dashboards.yml
+COPY dashboards/default_dashboard_by_hostname.json /tmp/default_dashboard.json
+
+# supervisor 配置
+COPY supervisord.conf /etc/supervisor/conf.d/supervisord.conf
+
+# 启动脚本
+COPY start-grafana-supervised.sh /usr/local/bin/start-grafana-supervised.sh
+RUN chmod +x /usr/local/bin/start-grafana-supervised.sh
+
+# 确保配置文件权限正确
+RUN chown -R grafana:grafana /etc/grafana
+
+COPY dns-monitor.sh /usr/local/bin/dns-monitor.sh
+RUN chmod +x /usr/local/bin/dns-monitor.sh
+
+USER root
+
+EXPOSE 3000
+
+ENTRYPOINT ["/usr/bin/supervisord", "-c", "/etc/supervisor/conf.d/supervisord.conf", "-n"]

src/metric/grafana/build/README.md

@@ -0,0 +1,100 @@
+# Grafana 构建配置
+
+基于 `grafana/grafana:11.1.0` 构建的自定义镜像，主要做了用户 ID 适配和配置自动化。
+
+## 快速开始
+
+```bash
+# 构建镜像
+docker build -t argus-metric-grafana:1.0.0 .
+
+# 启动容器（主机网络模式）
+docker run -d \
+  --name grafana \
+  --network=host \
+  -v /private/argus:/private/argus \
+  argus-metric-grafana:1.0.0
+```
+
+访问：`http://localhost:3001/private/argus/metric/grafana/`  
+默认账号：`admin` / `admin`
+
+## 用户 ID 配置
+
+镜像默认使用特殊的用户 ID 以适配主机权限：
+- `GRAFANA_UID=2133`
+- `GRAFANA_GID=2015`
+
+如果需要修改，构建时传入参数：
+
+```bash
+docker build \
+  --build-arg GRAFANA_UID=1000 \
+  --build-arg GRAFANA_GID=1000 \
+  -t argus-metric-grafana:1.0.0 .
+```
+
+## 配置说明
+
+### 数据源配置
+
+修改 `datasources/datasources.yml` 中的 Prometheus 地址：
+
+```yaml
+datasources:
+  - name: Prometheus
+    type: prometheus
+    url: http://10.211.55.5:9090  # 改成你的 Prometheus 地址
+    isDefault: true
+```
+
+**注意**：确保 Grafana 容器能访问到 Prometheus 服务，网络要通。
+
+### Dashboard 导入
+
+配置好数据源后，手动导入默认 dashboard：
+
+1. 登录 Grafana
+2. 左侧菜单 → Dashboards → Import
+3. 上传 `dashboards/default_dashboard.json`
+4. 选择 Prometheus 数据源
+5. Import
+
+或者直接把 dashboard 放到持久化目录：
+
+```bash
+cp dashboards/default_dashboard.json /private/argus/metric/grafana/provisioning/dashboards/
+```
+
+重启容器会自动加载（因为 `dashboards.yml` 配置了自动扫描该目录）。
+
+## 目录结构
+
+持久化目录都在 `/private/argus` 下：
+
+```
+/private/argus/
+├── etc/
+│   └── grafana.metric.argus.com       # 容器 IP 记录
+└── metric/grafana/
+    ├── config/
+    │   └── grafana.ini                 # 主配置文件
+    ├── data/                           # 数据库、会话等
+    ├── logs/                           # 日志
+    ├── plugins/                        # 插件
+    └── provisioning/
+        ├── datasources/
+        │   └── datasources.yml         # 数据源配置
+        └── dashboards/
+            ├── dashboards.yml          # dashboard 配置
+            └── *.json                  # dashboard JSON 文件
+```
+
+## 启动流程
+
+容器启动时 `start-grafana-supervised.sh` 会：
+
+1. 记录容器 IP 到 `/private/argus/etc/grafana.metric.argus.com`
+2. 创建必要的目录
+3. 从 `/tmp/` 复制配置文件到持久化目录（首次启动或配置不存在时）
+4. 用 `grafana:grafana` (UID:GID=2133:2015) 启动 Grafana 服务

src/metric/grafana/build/dashboards/dashboards.yml

@@ -0,0 +1,15 @@
+# 仪表板配置文件
+# 这个文件定义了仪表板的自动配置
+
+apiVersion: 1
+
+providers:
+  - name: 'default'
+    orgId: 1
+    folder: ''
+    type: file
+    disableDeletion: false
+    updateIntervalSeconds: 10
+    allowUiUpdates: true
+    options:
+      path: /private/argus/metric/grafana/provisioning/dashboards

src/metric/grafana/build/dashboards/default_cluster_dashboard.json

@@ -0,0 +1,570 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": 3,
+  "links": [],
+  "panels": [
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 8,
+        "x": 0,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "none",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "mean"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "100 * (1 - avg(rate(node_cpu_seconds_total{mode='idle'}[5m])))",
+          "refId": "A"
+        }
+      ],
+      "title": "CPU 平均利用率（%）",
+      "type": "stat"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 8,
+        "x": 8,
+        "y": 0
+      },
+      "id": 2,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "none",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "mean"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "avg(1 - ((node_memory_MemFree_bytes + node_memory_Buffers_bytes + node_memory_Cached_bytes) / node_memory_MemTotal_bytes)) * 100",
+          "refId": "A"
+        }
+      ],
+      "title": "内存平均利用率（%）",
+      "type": "stat"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 5,
+        "w": 8,
+        "x": 16,
+        "y": 0
+      },
+      "id": 4,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "none",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "last"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "count(count by(hostname) (up{job='node'} == 1))",
+          "refId": "A"
+        }
+      ],
+      "title": "节点在线数",
+      "type": "stat"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 6,
+        "x": 0,
+        "y": 5
+      },
+      "id": 6,
+      "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true,
+        "sizing": "auto"
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "avg by (hostname) (DCGM_FI_DEV_GPU_UTIL)",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 平均利用率 (%)",
+      "type": "gauge"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 6,
+        "x": 6,
+        "y": 5
+      },
+      "id": 12,
+      "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true,
+        "sizing": "auto"
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "round(avg(DCGM_FI_DEV_FB_USED{job='dcgm'}/(DCGM_FI_DEV_FB_USED{job='dcgm'} + DCGM_FI_DEV_FB_FREE{job='dcgm'})) * 100)",
+          "refId": "A"
+        }
+      ],
+      "title": "显存平均利用率 (%)",
+      "type": "gauge"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "max": 100,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 6,
+        "x": 12,
+        "y": 5
+      },
+      "id": 7,
+      "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": false,
+        "showThresholdMarkers": true,
+        "sizing": "auto"
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "avg by (hostname) (DCGM_FI_DEV_GPU_TEMP)",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 温度 (℃)",
+      "type": "gauge"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "mappings": [],
+          "max": 300,
+          "min": 0,
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "orange",
+                "value": 200
+              },
+              {
+                "color": "red",
+                "value": 300
+              }
+            ]
+          },
+          "unit": "watt"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 6,
+        "w": 6,
+        "x": 18,
+        "y": 5
+      },
+      "id": 8,
+      "options": {
+        "minVizHeight": 75,
+        "minVizWidth": 75,
+        "orientation": "auto",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showThresholdLabels": true,
+        "showThresholdMarkers": true,
+        "sizing": "auto"
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "avg by (hostname) (DCGM_FI_DEV_POWER_USAGE)",
+          "refId": "A"
+        }
+      ],
+      "title": "GPU 平均实时功耗 (W)",
+      "type": "gauge"
+    },
+    {
+      "datasource": "prometheus",
+      "fieldConfig": {
+        "defaults": {
+          "custom": {
+            "align": "center",
+            "cellOptions": {
+              "type": "auto"
+            },
+            "inspect": false
+          },
+          "decimals": 1,
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green"
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 12,
+        "w": 24,
+        "x": 0,
+        "y": 11
+      },
+      "id": 11,
+      "options": {
+        "cellHeight": "sm",
+        "cellLinks": [
+          {
+            "title": "跳转至节点详情",
+            "url": "http://127.0.0.1:3000/d/node_gpu_metrics/node-and-gpu-metrics?orgId=1&refresh=15s&var-hostname=${__data.fields.hostname}"
+          }
+        ],
+        "footer": {
+          "countRows": false,
+          "fields": "",
+          "reducer": [
+            "sum"
+          ],
+          "show": false
+        },
+        "showHeader": true,
+        "sortBy": [
+          {
+            "desc": true,
+            "displayName": "GPU 使用率"
+          }
+        ]
+      },
+      "pluginVersion": "11.1.0",
+      "targets": [
+        {
+          "expr": "up{job=\"dcgm\"} + on(hostname) group_left(ip, node_id) up{job=\"dcgm\"}*0",
+          "format": "table",
+          "instant": true,
+          "refId": "node_info"
+        },
+        {
+          "expr": "round(100 - avg by(hostname)(rate(node_cpu_seconds_total{job=\"node\",mode=\"idle\"}[5m])) * 100, 0.1)",
+          "format": "table",
+          "instant": true,
+          "refId": "CPU"
+        },
+        {
+          "expr": "round((1 - avg by(hostname)(node_memory_MemAvailable_bytes{job=\"node\"} / node_memory_MemTotal_bytes{job=\"node\"})) * 100, 0.1)",
+          "format": "table",
+          "instant": true,
+          "refId": "MEM"
+        },
+        {
+          "expr": "round(avg by(hostname)(DCGM_FI_DEV_GPU_UTIL{job=\"dcgm\"}), 0.1)",
+          "format": "table",
+          "instant": true,
+          "refId": "GPU_UTIL"
+        },
+        {
+          "expr": "round(avg by(hostname)(DCGM_FI_DEV_FB_USED{job=\"dcgm\"} / (DCGM_FI_DEV_FB_USED{job=\"dcgm\"} + DCGM_FI_DEV_FB_FREE{job=\"dcgm\"}) * 100), 0.1)",
+          "format": "table",
+          "instant": true,
+          "refId": "GPU_MEM"
+        }
+      ],
+      "title": "节点列表（CPU / 内存 / GPU）",
+      "transformations": [
+        {
+          "id": "seriesToColumns",
+          "options": {
+            "byField": "hostname"
+          }
+        },
+        {
+          "id": "organize",
+          "options": {
+            "excludeByName": {
+              "Time": true,
+              "Value #node_info": true,
+              "hostname_1": true,
+              "hostname_2": true,
+              "hostname_3": true,
+              "instance": true,
+              "ip_1": true,
+              "job": true,
+              "node_id_1": true
+            },
+            "indexByName": {
+              "CPU 使用率": 3,
+              "GPU 使用率": 5,
+              "GPU 显存占用": 6,
+              "IP 地址": 1,
+              "主机名": 0,
+              "内存使用率": 4,
+              "节点 ID": 2
+            },
+            "renameByName": {
+              "Value #CPU": "CPU 使用率",
+              "Value #GPU_MEM": "GPU 显存占用",
+              "Value #GPU_UTIL": "GPU 使用率",
+              "Value #MEM": "内存使用率",
+              "hostname": "主机名",
+              "ip": "IP 地址",
+              "node_id": "节点 ID",
+              "user_id": "用户ID"
+            }
+          }
+        }
+      ],
+      "type": "table"
+    }
+  ],
+  "refresh": "5s",
+  "schemaVersion": 39,
+  "tags": [
+    "cluster",
+    "gpu",
+    "system"
+  ],
+  "templating": {
+    "list": []
+  },
+  "time": {
+    "from": "now-1h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "Cluster Dashboard",
+  "uid": "cluster-dashboard",
+  "version": 34,
+  "weekStart": ""
+}

src/metric/grafana/build/dashboards/default_dashboard_by_hostname.json

@@ -0,0 +1,629 @@
+{
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": 9,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Load",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 0
+      },
+      "id": 101,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "node_load1{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} load1",
+          "refId": "A"
+        },
+        {
+          "expr": "node_load5{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} load5",
+          "refId": "B"
+        },
+        {
+          "expr": "node_load15{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} load15",
+          "refId": "C"
+        }
+      ],
+      "title": "System Load",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 0
+      },
+      "id": 1,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "100 * (1 - avg by(hostname) (irate(node_cpu_seconds_total{mode=\"idle\",hostname=\"$hostname\"}[5m])))",
+          "legendFormat": "{{hostname}}",
+          "refId": "A"
+        }
+      ],
+      "title": "CPU Usage",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "%",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 70
+              },
+              {
+                "color": "red",
+                "value": 90
+              }
+            ]
+          },
+          "unit": "percent"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 8
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "100 * (1 - (node_memory_MemAvailable_bytes{hostname=\"$hostname\"} / node_memory_MemTotal_bytes{hostname=\"$hostname\"}))",
+          "legendFormat": "{{hostname}}",
+          "refId": "B"
+        }
+      ],
+      "title": "Node Memory Usage",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Bytes/s",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 20,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 8
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum by(hostname) (rate(node_disk_read_bytes_total{device!~\"^(loop|ram|sr0).*\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} read",
+          "refId": "A"
+        },
+        {
+          "expr": "sum by(hostname) (rate(node_disk_written_bytes_total{device!~\"^(loop|ram|sr0).*\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} write",
+          "refId": "B"
+        }
+      ],
+      "title": "Node Disk I/O (Bytes/s)",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Bytes/s",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          },
+          "unit": "Bps"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 16
+      },
+      "id": 102,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "sum by(hostname)(rate(node_network_receive_bytes_total{device!~\"^(lo|docker.*)\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} RX",
+          "refId": "A"
+        },
+        {
+          "expr": "sum by(hostname)(rate(node_network_transmit_bytes_total{device!~\"^(lo|docker.*)\",hostname=\"$hostname\"}[5m]))",
+          "legendFormat": "{{hostname}} TX",
+          "refId": "B"
+        }
+      ],
+      "title": "Network Traffic",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "Processes",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 2,
+            "pointSize": 4,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": false,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "orange",
+                "value": 200
+              },
+              {
+                "color": "red",
+                "value": 500
+              }
+            ]
+          },
+          "unit": "short"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 12,
+        "y": 16
+      },
+      "id": 104,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "multi",
+          "sort": "none"
+        }
+      },
+      "targets": [
+        {
+          "expr": "node_procs_running{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} Running",
+          "refId": "A"
+        },
+        {
+          "expr": "node_procs_blocked{hostname=\"$hostname\"}",
+          "legendFormat": "{{hostname}} Blocked",
+          "refId": "B"
+        }
+      ],
+      "title": "Node Process Count",
+      "type": "timeseries"
+    }
+  ],
+  "refresh": "15s",
+  "schemaVersion": 39,
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "current": {
+          "selected": true,
+          "text": "node-exporter-A1",
+          "value": "node-exporter-A1"
+        },
+        "datasource": {
+          "type": "prometheus"
+        },
+        "definition": "label_values(node_cpu_seconds_total,hostname)",
+        "hide": 0,
+        "includeAll": false,
+        "label": "hostname",
+        "multi": false,
+        "name": "hostname",
+        "options": [],
+        "query": {
+          "qryType": 1,
+          "query": "label_values(node_cpu_seconds_total,hostname)",
+          "refId": "PrometheusVariableQueryEditor-VariableQuery"
+        },
+        "refresh": 1,
+        "regex": "",
+        "skipUrlSync": false,
+        "sort": 0,
+        "type": "query"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-12h",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "",
+  "title": "Node and GPU Metrics",
+  "uid": "node_gpu_metrics",
+  "weekStart": ""
+}