[#13 ] 增加debug模式系统集成测试，使用external network和指定private路径

[#15 ] 增加镜像构建 --no-cache选项
2025-10-13 15:18:41 +08:00 · 2025-10-13 15:17:33 +08:00
19 changed files with 1275 additions and 1 deletions
--- a/build/build_images.sh
+++ b/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:
@ -23,6 +24,7 @@ EOF
 use_intranet=false
 build_master=true
 build_master_offline=false
+no_cache=false

 while [[ $# -gt 0 ]]; do
  case $1 in
@ -39,6 +41,10 @@ while [[ $# -gt 0 ]]; do
      build_master_offline=true
      shift
      ;;
+    --no-cache)
+      no_cache=true
+      shift
+      ;;
    -h|--help)
      show_help
      exit 0
@ -65,6 +71,10 @@ cd "$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"
@ -159,6 +169,9 @@ if [[ "$build_master" == true ]]; then
  if [[ "$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")
--- a/src/master/scripts/build_images.sh
+++ b/src/master/scripts/build_images.sh
@ -3,12 +3,13 @@ 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:latest。
+  --no-cache           不使用 Docker 构建缓存。
 USAGE
 }

@ -19,6 +20,7 @@ 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
--- a/src/sys/debug/.env.example
+++ b/src/sys/debug/.env.example
@ -0,0 +1,12 @@
+# Generated by 01_bootstrap.sh
+SYS_DEBUG_PRIVATE_CORE=/absolute/path/to/private
+SYS_DEBUG_PRIVATE_NODEA=/absolute/path/to/private-nodea
+SYS_DEBUG_PRIVATE_NODEB=/absolute/path/to/private-nodeb
+SYS_DEBUG_TMP_DIR=/absolute/path/to/tmp
+SYS_DEBUG_NETWORK_NAME=argus-debug-net
+SYS_DEBUG_NETWORK_SUBNET=172.30.0.0/16
+SYS_DEBUG_NETWORK_GATEWAY=172.30.0.1
+SYS_DEBUG_PROJECT_NAME=argus-debug
+SYS_DEBUG_CONTAINER_PREFIX=argus-debug
+ARGUS_BUILD_UID=2133
+ARGUS_BUILD_GID=2015
--- a/src/sys/debug/README.md
+++ b/src/sys/debug/README.md
@ -0,0 +1,67 @@
+# ARGUS 系统调试部署模式
+
+该目录提供基于系统级 E2E 测试构建的调试部署流程，便于本地快速复现与排查问题。核心特性：
+
+- 独立 docker 网络 `argus-debug-net`（默认子网 `172.30.0.0/16`），避免与 `src/sys/tests` 冲突。
+- 私有数据目录可通过参数自定义，例如 `--private-root /tmp/argus-debug`。
+- 默认保留调试过程生成的文件，避免 `down`/`bootstrap` 自动删除。
+
+## 快速开始
+
+```bash
+cd src/sys/debug
+
+# 仅首次需要，创建 external 网络
+./scripts/network-create.sh
+
+# 初始化目录/构建 agent/写入 .env
+./scripts/01_bootstrap.sh --private-root /tmp/argus-debug
+
+# 启动调试栈
+./scripts/02_up.sh
+
+# 根据需要执行验证脚本（03～08）
+./scripts/03_wait_ready.sh
+...
+
+# 调试结束停止服务
+./scripts/09_down.sh
+
+# 若需移除网络或数据
+./scripts/network-destroy.sh
+./scripts/clean-data.sh
+```
+
+> **提示**：调试与测试栈不能同时运行，应保持 `src/sys/tests` 中的 `argus-sys` 栈已停止。
+
+## 参数与环境变量
+
+- `--private-root <path>`：同时指定核心服务与两个节点的私有目录根，脚本自动派生 `private`、`private-nodea`、`private-nodeb`。
+- `--private-core <path>`、`--private-nodea <path>`、`--private-nodeb <path>`：分别覆盖单独目录。
+- 环境变量可覆盖 `.env` 中写入的值，例如 `export SYS_DEBUG_NETWORK_NAME=my-debug-net`。
+- `.env` 文件字段：
+  - `SYS_DEBUG_PRIVATE_CORE`
+  - `SYS_DEBUG_PRIVATE_NODEA`
+  - `SYS_DEBUG_PRIVATE_NODEB`
+  - `SYS_DEBUG_TMP_DIR`
+  - `SYS_DEBUG_NETWORK_NAME`
+  - `SYS_DEBUG_NETWORK_SUBNET`
+  - `SYS_DEBUG_NETWORK_GATEWAY`
+  - `SYS_DEBUG_PROJECT_NAME`
+  - `SYS_DEBUG_CONTAINER_PREFIX`
+  - `ARGUS_BUILD_UID` / `ARGUS_BUILD_GID`
+
+## 脚本说明
+
+- `scripts/common.sh`：通用函数与环境加载。
+- `scripts/network-create.sh` / `network-destroy.sh`：管理 external 网络。
+- `scripts/00_debug_all.sh`：顺序执行 01～08（默认不执行 09）。
+- `scripts/clean-data.sh`：选择性清理宿主机私有数据。
+- `scripts/08_restart_agent_reregister.sh`：将 node-b 切换到 `SYS_DEBUG_NODEB_FIXED_IP`（默认 `172.30.0.200`），如果目标地址与当前 IP 相同脚本会报错提醒重新选择地址。
+- 其它 `01～09` 与测试目录对应，但针对参数化路径及网络做了调整。
+
+## 注意事项
+
+- 若宿主机未安装 Docker，脚本将提示错误并退出。
+- 当指定的私有目录已存在数据时，脚本不会清理，请确认内容安全后再复用。
+- 与测试环境共用镜像：请提前执行仓库根目录的 `./build/build_images.sh`。
--- a/src/sys/debug/docker-compose.yml
+++ b/src/sys/debug/docker-compose.yml
@ -0,0 +1,147 @@
+version: "3.8"
+
+networks:
+  argus-debug-net:
+    external: true
+    name: ${SYS_DEBUG_NETWORK_NAME:-argus-debug-net}
+
+services:
+  bind:
+    image: ${BIND_IMAGE_TAG:-argus-bind9:latest}
+    container_name: ${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-bind
+    networks:
+      argus-debug-net:
+        ipv4_address: ${SYS_DEBUG_BIND_IP:-172.30.0.2}
+    volumes:
+      - ${SYS_DEBUG_PRIVATE_CORE}:/private
+    restart: unless-stopped
+
+  master:
+    image: ${MASTER_IMAGE_TAG:-argus-master:latest}
+    container_name: ${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-master
+    depends_on:
+      - bind
+    environment:
+      - OFFLINE_THRESHOLD_SECONDS=6
+      - ONLINE_THRESHOLD_SECONDS=2
+      - SCHEDULER_INTERVAL_SECONDS=1
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    ports:
+      - "32300:3000"
+    volumes:
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/master:/private/argus/master
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/metric/prometheus:/private/argus/metric/prometheus
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/etc:/private/argus/etc
+    networks:
+      argus-debug-net:
+        ipv4_address: ${SYS_DEBUG_MASTER_IP:-172.30.0.10}
+    restart: unless-stopped
+
+  es:
+    image: ${ES_IMAGE_TAG:-argus-elasticsearch:latest}
+    container_name: ${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-es
+    environment:
+      - discovery.type=single-node
+      - xpack.security.enabled=false
+      - ES_JAVA_OPTS=-Xms512m -Xmx512m
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    volumes:
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/log/elasticsearch:/private/argus/log/elasticsearch
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/etc:/private/argus/etc
+    ports:
+      - "9200:9200"
+    networks:
+      argus-debug-net:
+        ipv4_address: ${SYS_DEBUG_ES_IP:-172.30.0.20}
+    restart: unless-stopped
+
+  kibana:
+    image: ${KIBANA_IMAGE_TAG:-argus-kibana:latest}
+    container_name: ${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-kibana
+    environment:
+      - ELASTICSEARCH_HOSTS=http://es.log.argus.com:9200
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+    volumes:
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/log/kibana:/private/argus/log/kibana
+      - ${SYS_DEBUG_PRIVATE_CORE}/argus/etc:/private/argus/etc
+    depends_on:
+      - es
+    ports:
+      - "5601:5601"
+    networks:
+      argus-debug-net:
+        ipv4_address: ${SYS_DEBUG_KIBANA_IP:-172.30.0.30}
+    restart: unless-stopped
+
+  node-a:
+    image: ubuntu:22.04
+    container_name: ${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-node-a
+    hostname: ${SYS_DEBUG_NODEA_HOST:-dev-yyrshare-nbnyx10-cp2f-pod-0}
+    depends_on:
+      - master
+      - bind
+      - es
+    environment:
+      - MASTER_ENDPOINT=http://master.argus.com:3000
+      - REPORT_INTERVAL_SECONDS=2
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      - ES_HOST=es
+      - ES_PORT=9200
+      - CLUSTER=local
+      - RACK=dev
+    volumes:
+      - ${SYS_DEBUG_PRIVATE_NODEA}/argus/agent/${SYS_DEBUG_NODEA_HOST:-dev-yyrshare-nbnyx10-cp2f-pod-0}:/private/argus/agent/${SYS_DEBUG_NODEA_HOST:-dev-yyrshare-nbnyx10-cp2f-pod-0}
+      - ../../agent/dist/argus-agent:/usr/local/bin/argus-agent:ro
+      - ../tests/scripts/node_entrypoint.sh:/usr/local/bin/node-entrypoint.sh:ro
+      - ../../log/fluent-bit/build/start-fluent-bit.sh:/assets/start-fluent-bit.sh:ro
+      - ../../log/fluent-bit/build/etc:/assets/fluent-bit/etc:ro
+      - ../../log/fluent-bit/build/packages:/assets/fluent-bit/packages:ro
+    entrypoint:
+      - /usr/local/bin/node-entrypoint.sh
+    dns:
+      - ${SYS_DEBUG_BIND_IP:-172.30.0.2}
+    ports:
+      - "2020:2020"
+    networks:
+      argus-debug-net:
+        ipv4_address: ${SYS_DEBUG_NODEA_IP:-172.30.0.101}
+    restart: unless-stopped
+
+  node-b:
+    image: ubuntu:22.04
+    container_name: ${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-node-b
+    hostname: ${SYS_DEBUG_NODEB_HOST:-dev-yyrshare-uuuu10-ep2f-pod-0}
+    depends_on:
+      - master
+      - bind
+      - es
+    environment:
+      - MASTER_ENDPOINT=http://master.argus.com:3000
+      - REPORT_INTERVAL_SECONDS=2
+      - ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+      - ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+      - ES_HOST=es
+      - ES_PORT=9200
+      - CLUSTER=local
+      - RACK=dev
+    volumes:
+      - ${SYS_DEBUG_PRIVATE_NODEB}/argus/agent/${SYS_DEBUG_NODEB_HOST:-dev-yyrshare-uuuu10-ep2f-pod-0}:/private/argus/agent/${SYS_DEBUG_NODEB_HOST:-dev-yyrshare-uuuu10-ep2f-pod-0}
+      - ../../agent/dist/argus-agent:/usr/local/bin/argus-agent:ro
+      - ../tests/scripts/node_entrypoint.sh:/usr/local/bin/node-entrypoint.sh:ro
+      - ../../log/fluent-bit/build/start-fluent-bit.sh:/assets/start-fluent-bit.sh:ro
+      - ../../log/fluent-bit/build/etc:/assets/fluent-bit/etc:ro
+      - ../../log/fluent-bit/build/packages:/assets/fluent-bit/packages:ro
+    entrypoint:
+      - /usr/local/bin/node-entrypoint.sh
+    dns:
+      - ${SYS_DEBUG_BIND_IP:-172.30.0.2}
+    ports:
+      - "2021:2020"
+    networks:
+      argus-debug-net:
+        ipv4_address: ${SYS_DEBUG_NODEB_IP:-172.30.0.102}
+    restart: unless-stopped
--- a/src/sys/debug/scripts/00_debug_all.sh
+++ b/src/sys/debug/scripts/00_debug_all.sh
@ -0,0 +1,24 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+SCRIPTS=(
+  "01_bootstrap.sh"
+  "02_up.sh"
+  "03_wait_ready.sh"
+  "04_verify_dns_routing.sh"
+  "05_agent_register.sh"
+  "06_write_health_and_assert.sh"
+  "07_logs_send_and_assert.sh"
+  "08_restart_agent_reregister.sh"
+)
+
+for script in "${SCRIPTS[@]}"; do
+  echo "[SYS-DEBUG] Running $script"
+  "$SCRIPT_DIR/$script"
+  echo "[SYS-DEBUG] $script completed"
+  echo
+done
+
+echo "[SYS-DEBUG] Complete. Run scripts/09_down.sh when finished (data retained)."
--- a/src/sys/debug/scripts/01_bootstrap.sh
+++ b/src/sys/debug/scripts/01_bootstrap.sh
@ -0,0 +1,210 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+PRIVATE_ROOT=""
+PRIVATE_CORE="$SYS_DEBUG_PRIVATE_CORE"
+PRIVATE_NODEA="$SYS_DEBUG_PRIVATE_NODEA"
+PRIVATE_NODEB="$SYS_DEBUG_PRIVATE_NODEB"
+TMP_DIR_VAL="$SYS_DEBUG_TMP_DIR"
+NETWORK_NAME="$SYS_DEBUG_NETWORK_NAME"
+NETWORK_SUBNET="$SYS_DEBUG_NETWORK_SUBNET"
+NETWORK_GATEWAY="$SYS_DEBUG_NETWORK_GATEWAY"
+PROJECT_NAME="$SYS_DEBUG_PROJECT_NAME"
+CONTAINER_PREFIX="$SYS_DEBUG_CONTAINER_PREFIX"
+NODEB_FIXED_IP=${SYS_DEBUG_NODEB_FIXED_IP:-172.30.0.200}
+
+usage() {
+  cat <<EOF
+Usage: ${0##*/} [--private-root PATH] [--private-core PATH] \
+                 [--private-nodea PATH] [--private-nodeb PATH] \
+                 [--tmp-dir PATH] [--network-name NAME] \
+                 [--network-subnet CIDR] [--network-gateway IP]
+
+Prepare directories, build agent binary, and write .env for debug stack.
+EOF
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --private-root)
+      shift; [[ $# -gt 0 ]] || { echo "--private-root requires value" >&2; exit 1; }
+      PRIVATE_ROOT="$1"
+      ;;
+    --private-root=*)
+      PRIVATE_ROOT="${1#*=}"
+      ;;
+    --private-core)
+      shift; [[ $# -gt 0 ]] || { echo "--private-core requires value" >&2; exit 1; }
+      PRIVATE_CORE="$1"
+      ;;
+    --private-core=*)
+      PRIVATE_CORE="${1#*=}"
+      ;;
+    --private-nodea)
+      shift; [[ $# -gt 0 ]] || { echo "--private-nodea requires value" >&2; exit 1; }
+      PRIVATE_NODEA="$1"
+      ;;
+    --private-nodea=*)
+      PRIVATE_NODEA="${1#*=}"
+      ;;
+    --private-nodeb)
+      shift; [[ $# -gt 0 ]] || { echo "--private-nodeb requires value" >&2; exit 1; }
+      PRIVATE_NODEB="$1"
+      ;;
+    --private-nodeb=*)
+      PRIVATE_NODEB="${1#*=}"
+      ;;
+    --tmp-dir)
+      shift; [[ $# -gt 0 ]] || { echo "--tmp-dir requires value" >&2; exit 1; }
+      TMP_DIR_VAL="$1"
+      ;;
+    --tmp-dir=*)
+      TMP_DIR_VAL="${1#*=}"
+      ;;
+    --network-name)
+      shift; [[ $# -gt 0 ]] || { echo "--network-name requires value" >&2; exit 1; }
+      NETWORK_NAME="$1"
+      ;;
+    --network-name=*)
+      NETWORK_NAME="${1#*=}"
+      ;;
+    --network-subnet)
+      shift; [[ $# -gt 0 ]] || { echo "--network-subnet requires value" >&2; exit 1; }
+      NETWORK_SUBNET="$1"
+      ;;
+    --network-subnet=*)
+      NETWORK_SUBNET="${1#*=}"
+      ;;
+    --network-gateway)
+      shift; [[ $# -gt 0 ]] || { echo "--network-gateway requires value" >&2; exit 1; }
+      NETWORK_GATEWAY="$1"
+      ;;
+    --network-gateway=*)
+      NETWORK_GATEWAY="${1#*=}"
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage >&2
+      exit 1
+      ;;
+  esac
+  shift
+done
+
+if [[ -n "$PRIVATE_ROOT" ]]; then
+  PRIVATE_CORE="$PRIVATE_ROOT/private"
+  PRIVATE_NODEA="$PRIVATE_ROOT/private-nodea"
+  PRIVATE_NODEB="$PRIVATE_ROOT/private-nodeb"
+fi
+
+PRIVATE_CORE=$(abs_path "$PRIVATE_CORE")
+PRIVATE_NODEA=$(abs_path "$PRIVATE_NODEA")
+PRIVATE_NODEB=$(abs_path "$PRIVATE_NODEB")
+TMP_DIR_VAL=$(abs_path "$TMP_DIR_VAL")
+
+log "Preparing directories under $PRIVATE_CORE"
+mkdir -p \
+  "$PRIVATE_CORE/argus/etc" \
+  "$PRIVATE_CORE/argus/bind" \
+  "$PRIVATE_CORE/argus/master" \
+  "$PRIVATE_CORE/argus/metric/prometheus" \
+  "$PRIVATE_CORE/argus/log/elasticsearch" \
+  "$PRIVATE_CORE/argus/log/kibana" \
+  "$PRIVATE_NODEA/argus/agent/$HOST_A/health" \
+  "$PRIVATE_NODEB/argus/agent/$HOST_B/health" \
+  "$TMP_DIR_VAL"
+
+log "Aligning ownership for core directories"
+chown -R "${ARGUS_BUILD_UID}:${ARGUS_BUILD_GID}" \
+  "$PRIVATE_CORE/argus/log/elasticsearch" \
+  "$PRIVATE_CORE/argus/log/kibana" \
+  "$PRIVATE_CORE/argus/etc" 2>/dev/null || true
+
+log "Distributing update-dns.sh"
+BIND_UPDATE_SRC="$REPO_ROOT/src/bind/build/update-dns.sh"
+BIND_UPDATE_DEST="$PRIVATE_CORE/argus/etc/update-dns.sh"
+if [[ -f "$BIND_UPDATE_SRC" ]]; then
+  cp "$BIND_UPDATE_SRC" "$BIND_UPDATE_DEST"
+  chmod +x "$BIND_UPDATE_DEST"
+else
+  echo "[WARN] Missing $BIND_UPDATE_SRC" >&2
+fi
+
+require_docker
+
+ensure_image() {
+  local image="$1"
+  if ! docker image inspect "$image" >/dev/null 2>&1; then
+    echo "[ERR] Missing image: $image. Run ./build/build_images.sh" >&2
+    exit 1
+  fi
+}
+
+log "Ensuring required images exist"
+ensure_image "${ES_IMAGE_TAG:-argus-elasticsearch:latest}"
+ensure_image "${KIBANA_IMAGE_TAG:-argus-kibana:latest}"
+ensure_image "${BIND_IMAGE_TAG:-argus-bind9:latest}"
+ensure_image "${MASTER_IMAGE_TAG:-argus-master:latest}"
+
+log "Building agent binary"
+pushd "$REPO_ROOT/src/agent" >/dev/null
+./scripts/build_binary.sh
+popd >/dev/null
+
+AGENT_BIN="$REPO_ROOT/src/agent/dist/argus-agent"
+if [[ ! -x "$AGENT_BIN" ]]; then
+  echo "[ERR] Agent binary not found at $AGENT_BIN" >&2
+  exit 1
+fi
+echo "$AGENT_BIN" > "$TMP_DIR_VAL/agent_binary_path"
+
+log "Preparing environment file contents"
+tmp_env="$(mktemp)"
+cat > "$tmp_env" <<EOF
+SYS_DEBUG_PRIVATE_CORE=$PRIVATE_CORE
+SYS_DEBUG_PRIVATE_NODEA=$PRIVATE_NODEA
+SYS_DEBUG_PRIVATE_NODEB=$PRIVATE_NODEB
+SYS_DEBUG_TMP_DIR=$TMP_DIR_VAL
+SYS_DEBUG_NETWORK_NAME=$NETWORK_NAME
+SYS_DEBUG_NETWORK_SUBNET=$NETWORK_SUBNET
+SYS_DEBUG_NETWORK_GATEWAY=$NETWORK_GATEWAY
+SYS_DEBUG_PROJECT_NAME=$PROJECT_NAME
+SYS_DEBUG_CONTAINER_PREFIX=$CONTAINER_PREFIX
+SYS_DEBUG_NODEA_HOST=$HOST_A
+SYS_DEBUG_NODEB_HOST=$HOST_B
+SYS_DEBUG_BIND_IP=${SYS_DEBUG_BIND_IP:-172.30.0.2}
+SYS_DEBUG_MASTER_IP=${SYS_DEBUG_MASTER_IP:-172.30.0.10}
+SYS_DEBUG_ES_IP=${SYS_DEBUG_ES_IP:-172.30.0.20}
+SYS_DEBUG_KIBANA_IP=${SYS_DEBUG_KIBANA_IP:-172.30.0.30}
+SYS_DEBUG_NODEA_IP=${SYS_DEBUG_NODEA_IP:-172.30.0.101}
+SYS_DEBUG_NODEB_IP=${SYS_DEBUG_NODEB_IP:-172.30.0.102}
+SYS_DEBUG_NODEB_FIXED_IP=$NODEB_FIXED_IP
+ARGUS_BUILD_UID=$ARGUS_BUILD_UID
+ARGUS_BUILD_GID=$ARGUS_BUILD_GID
+EOF
+
+if [[ -f "$ENV_FILE" ]]; then
+  if cmp -s "$tmp_env" "$ENV_FILE"; then
+    log ".env already up-to-date"
+    rm -f "$tmp_env"
+    if [[ ! -f "$DEBUG_ROOT/.env.lock" ]]; then
+      cp "$ENV_FILE" "$DEBUG_ROOT/.env.lock"
+    fi
+  else
+    mv "$ENV_FILE" "$ENV_FILE.bak"
+    mv "$tmp_env" "$ENV_FILE"
+    cp "$ENV_FILE" "$DEBUG_ROOT/.env.lock"
+    log "Bootstrap updated .env (previous saved at ${ENV_FILE}.bak)"
+  fi
+else
+  mv "$tmp_env" "$ENV_FILE"
+  cp "$ENV_FILE" "$DEBUG_ROOT/.env.lock"
+  log "Bootstrap created .env at $ENV_FILE"
+fi
--- a/src/sys/debug/scripts/02_up.sh
+++ b/src/sys/debug/scripts/02_up.sh
@ -0,0 +1,19 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+require_docker
+
+if ! docker network inspect "$SYS_DEBUG_NETWORK_NAME" >/dev/null 2>&1; then
+  echo "[ERR] Network $SYS_DEBUG_NETWORK_NAME not found. Run scripts/network-create.sh first." >&2
+  exit 1
+fi
+
+log "Starting debug stack on project $SYS_DEBUG_PROJECT_NAME"
+compose up -d
+
+log "Services started: master:32300 es:9200 kibana:5601 node-a:2020 node-b:2021"
--- a/src/sys/debug/scripts/03_wait_ready.sh
+++ b/src/sys/debug/scripts/03_wait_ready.sh
@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+service_id() {
+  compose ps -q "$1"
+}
+
+wait_http() {
+  local url="$1"; local attempts="${2:-120}"; local i=1
+  while (( i <= attempts )); do
+    if curl -fsS "$url" >/dev/null 2>&1; then
+      return 0
+    fi
+    echo "[..] waiting $url ($i/$attempts)"
+    sleep 5
+    ((i++))
+  done
+  echo "[ERR] Timeout waiting for $url" >&2
+  return 1
+}
+
+log "Waiting for ES/Kibana/Master/Fluent Bit/Bind"
+
+attempt=1; max=120
+while (( attempt <= max )); do
+  if curl -fsS "http://localhost:9200/_cluster/health?wait_for_status=yellow&timeout=1s" >/dev/null 2>&1; then
+    break
+  fi
+  echo "[..] waiting ES ($attempt/$max)"
+  sleep 5
+  ((attempt++))
+done
+if (( attempt > max )); then
+  echo "[ERR] ES not ready" >&2
+  exit 1
+fi
+
+log "Waiting for Kibana to be available (HTTP 200)"
+kb_attempt=1; kb_max=180
+while (( kb_attempt <= kb_max )); do
+  body=$(curl -sS "http://localhost:5601/api/status" 2>/dev/null || true)
+  code=$(curl -s -o /dev/null -w "%{http_code}" "http://localhost:5601/api/status" || echo 000)
+  if [[ "$code" == "200" ]] && echo "$body" | grep -q '"level":"available"'; then
+    log "Kibana available"
+    break
+  fi
+  echo "[..] waiting kibana 200 ($kb_attempt/$kb_max), last_code=$code"
+  sleep 5
+  ((kb_attempt++))
+done
+if (( kb_attempt > kb_max )); then
+  echo "[ERR] Kibana did not reach HTTP 200" >&2
+  exit 1
+fi
+
+wait_http "http://localhost:32300/readyz" 120
+wait_http "http://localhost:2020/api/v2/metrics" 120
+wait_http "http://localhost:2021/api/v2/metrics" 120
+
+BIND_ID="$(service_id bind)"
+if [[ -n "$BIND_ID" ]]; then
+  docker exec "$BIND_ID" named-checkconf >/dev/null
+else
+  echo "[WARN] bind container id not found" >&2
+fi
+
+log "All services are ready"
--- a/src/sys/debug/scripts/04_verify_dns_routing.sh
+++ b/src/sys/debug/scripts/04_verify_dns_routing.sh
@ -0,0 +1,51 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+service_id() {
+  compose ps -q "$1"
+}
+
+log "Verifying DNS routing via bind"
+
+MASTER_FILE="$SYS_DEBUG_PRIVATE_CORE/argus/etc/master.argus.com"
+if [[ ! -f "$MASTER_FILE" ]]; then
+  echo "[ERR] master.argus.com file missing at $MASTER_FILE" >&2
+  exit 1
+fi
+MASTER_IP_HOST="$(tr -d '\r\n' < "$MASTER_FILE" || true)"
+log "master.argus.com file content: $MASTER_IP_HOST"
+
+BIN_ID="$(service_id bind)"
+if [[ -n "$BIN_ID" ]]; then
+  DIG_IP="$(docker exec "$BIN_ID" dig +short master.argus.com A | tail -n1 || true)"
+  log "dig(master.argus.com) from bind container -> $DIG_IP"
+  if [[ -z "$DIG_IP" ]]; then
+    echo "[ERR] bind did not resolve master.argus.com" >&2
+    exit 1
+  fi
+else
+  echo "[WARN] bind container not found; skip dig" >&2
+fi
+
+for node in node-a node-b; do
+  CID="$(service_id "$node")"
+  if [[ -z "$CID" ]]; then
+    echo "[ERR] Container for $node not found" >&2
+    exit 1
+  fi
+  log "Checking resolution inside $node"
+  if ! docker exec "$CID" getent hosts master.argus.com >/dev/null 2>&1; then
+    echo "[ERR] $node cannot resolve master.argus.com" >&2
+    exit 1
+  fi
+  RES="$(docker exec "$CID" getent hosts master.argus.com | awk '{print $1}' | head -n1)"
+  log "$node resolved master.argus.com -> $RES"
+done
+
+log "DNS routing verified"
--- a/src/sys/debug/scripts/05_agent_register.sh
+++ b/src/sys/debug/scripts/05_agent_register.sh
@ -0,0 +1,84 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+TMP_DIR_LOCAL="$TMP_DIR"
+mkdir -p "$TMP_DIR_LOCAL"
+
+API_BASE="http://localhost:32300/api/v1/master"
+
+log "Waiting for agent nodes to register"
+
+extract_node() {
+  local name="$1"; local output="$2"; local json_file="$3"
+  python3 - "$name" "$output" "$json_file" <<'PY'
+import json, sys, pathlib
+name = sys.argv[1]
+out = pathlib.Path(sys.argv[2])
+json_file = sys.argv[3]
+with open(json_file, 'r') as fh:
+    data = json.load(fh)
+node = next((n for n in data if n.get("name") == name), None)
+if node:
+    out.write_text(node["id"])
+    print(node["id"])
+PY
+}
+
+ID_A=""; ID_B=""
+for _ in {1..60}; do
+  sleep 2
+  resp=$(curl -fsS "$API_BASE/nodes" 2>/dev/null || true)
+  [[ -z "$resp" ]] && continue
+  if ! echo "$resp" | head -c1 | grep -q '\['; then
+    continue
+  fi
+  echo "$resp" > "$TMP_DIR_LOCAL/nodes_list.json"
+  ID_A=$(extract_node "$HOST_A" "$TMP_DIR_LOCAL/node_id_a" "$TMP_DIR_LOCAL/nodes_list.json" 2>/dev/null || true)
+  ID_B=$(extract_node "$HOST_B" "$TMP_DIR_LOCAL/node_id_b" "$TMP_DIR_LOCAL/nodes_list.json" 2>/dev/null || true)
+  if [[ -s "$TMP_DIR_LOCAL/node_id_a" && -s "$TMP_DIR_LOCAL/node_id_b" ]]; then
+    break
+  fi
+done
+
+if [[ ! -s "$TMP_DIR_LOCAL/node_id_a" || ! -s "$TMP_DIR_LOCAL/node_id_b" ]]; then
+  echo "[ERR] Agents did not register in time" >&2
+  exit 1
+fi
+
+node_detail() {
+  local id="$1"; local out="$2"
+  curl -fsS "$API_BASE/nodes/$id" -o "$out"
+}
+
+node_detail "$(cat "$TMP_DIR_LOCAL/node_id_a")" "$TMP_DIR_LOCAL/detail_a.json"
+node_detail "$(cat "$TMP_DIR_LOCAL/node_id_b")" "$TMP_DIR_LOCAL/detail_b.json"
+
+python3 - "$TMP_DIR_LOCAL/detail_a.json" "$TMP_DIR_LOCAL/initial_ip_a" <<'PY'
+import json, sys, pathlib
+node=json.load(open(sys.argv[1]))
+ip=node.get("meta_data",{}).get("ip")
+assert ip, "missing ip"
+pathlib.Path(sys.argv[2]).write_text(ip)
+PY
+
+python3 - "$TMP_DIR_LOCAL/detail_b.json" "$TMP_DIR_LOCAL/initial_ip_b" <<'PY'
+import json, sys, pathlib
+node=json.load(open(sys.argv[1]))
+ip=node.get("meta_data",{}).get("ip")
+assert ip, "missing ip"
+pathlib.Path(sys.argv[2]).write_text(ip)
+PY
+
+NODE_JSON_A="$SYS_DEBUG_PRIVATE_NODEA/argus/agent/$HOST_A/node.json"
+NODE_JSON_B="$SYS_DEBUG_PRIVATE_NODEB/argus/agent/$HOST_B/node.json"
+
+[[ -f "$NODE_JSON_A" ]] || { echo "[ERR] node.json missing for $HOST_A" >&2; exit 1; }
+[[ -f "$NODE_JSON_B" ]] || { echo "[ERR] node.json missing for $HOST_B" >&2; exit 1; }
+
+log "Agents registered: $(cat "$TMP_DIR_LOCAL/node_id_a") , $(cat "$TMP_DIR_LOCAL/node_id_b")"
--- a/src/sys/debug/scripts/06_write_health_and_assert.sh
+++ b/src/sys/debug/scripts/06_write_health_and_assert.sh
@ -0,0 +1,78 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+API_BASE="http://localhost:32300/api/v1/master"
+
+HEALTH_A="$SYS_DEBUG_PRIVATE_NODEA/argus/agent/$HOST_A/health"
+HEALTH_B="$SYS_DEBUG_PRIVATE_NODEB/argus/agent/$HOST_B/health"
+
+write_health() {
+  local dir="$1"; mkdir -p "$dir"
+  cat > "$dir/log-fluentbit.json" <<JSON
+{ "status": "healthy", "timestamp": "2025-10-13T12:05:00Z" }
+JSON
+  cat > "$dir/metric-node-exporter.json" <<JSON
+{ "status": "healthy", "timestamp": "2025-10-13T12:05:00Z" }
+JSON
+}
+
+log "Writing health files for both nodes"
+write_health "$HEALTH_A"
+write_health "$HEALTH_B"
+
+ID_A="$TMP_DIR/node_id_a"
+ID_B="$TMP_DIR/node_id_b"
+
+[[ -f "$ID_A" && -f "$ID_B" ]] || { echo "[ERR] node id files missing in $TMP_DIR" >&2; exit 1; }
+
+ID_A_VAL="$(cat "$ID_A")"
+ID_B_VAL="$(cat "$ID_B")"
+
+check_health() {
+  local id="$1"; local tries=40
+  for _ in $(seq 1 $tries); do
+    sleep 2
+    resp=$(curl -fsS "$API_BASE/nodes/$id" 2>/dev/null || true)
+    [[ -z "$resp" ]] && continue
+    echo "$resp" > "$TMP_DIR/node_${id}_detail.json"
+    if python3 - "$TMP_DIR/node_${id}_detail.json" <<'PY'
+import json,sys
+node=json.load(open(sys.argv[1]))
+h=node.get("health",{})
+if "log-fluentbit" in h and "metric-node-exporter" in h:
+    sys.exit(0)
+sys.exit(1)
+PY
+    then
+      return 0
+    fi
+  done
+  return 1
+}
+
+check_health "$ID_A_VAL" || { echo "[ERR] health keys not reported for node A" >&2; exit 1; }
+check_health "$ID_B_VAL" || { echo "[ERR] health keys not reported for node B" >&2; exit 1; }
+
+NODES_JSON="$SYS_DEBUG_PRIVATE_CORE/argus/metric/prometheus/nodes.json"
+if [[ ! -f "$NODES_JSON" ]]; then
+  echo "[ERR] nodes.json missing at $NODES_JSON" >&2
+  exit 1
+fi
+
+python3 - "$NODES_JSON" <<'PY'
+import json,sys
+with open(sys.argv[1]) as h:
+  nodes=json.load(h)
+if not isinstance(nodes, list):
+    raise SystemExit("nodes.json expected list")
+if len(nodes) != 2:
+    raise SystemExit(f"expected 2 nodes online, got {len(nodes)}")
+PY
+
+log "Health reported and nodes.json has 2 online nodes"
--- a/src/sys/debug/scripts/07_logs_send_and_assert.sh
+++ b/src/sys/debug/scripts/07_logs_send_and_assert.sh
@ -0,0 +1,73 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+log "Sending logs and asserting ES counts"
+
+get_count() {
+  local idx="$1"
+  curl -s "http://localhost:9200/${idx}/_count?ignore_unavailable=true&allow_no_indices=true" | sed -E 's/.*"count":([0-9]+).*/\1/' | awk 'NF{print $0;exit} END{if(NR==0)print 0}'
+}
+
+train0=$(get_count "train-*")
+infer0=$(get_count "infer-*")
+base=$((train0 + infer0))
+log "initial counts: train=${train0} infer=${infer0} total=${base}"
+
+service_id() {
+  compose ps -q "$1"
+}
+
+send_logs() {
+  local sid="$1"; local hosttag="$2"
+  docker exec "$sid" sh -lc 'mkdir -p /logs/train /logs/infer'
+  docker exec "$sid" sh -lc "ts=\
+\$(date '+%F %T'); echo \"\$ts INFO [$hosttag] training step=1 loss=1.23 model=bert\" >> /logs/train/train-demo.log"
+  docker exec "$sid" sh -lc "ts=\
+\$(date '+%F %T'); echo \"\$ts INFO [$hosttag] training step=2 loss=1.10 model=bert\" >> /logs/train/train-demo.log"
+  docker exec "$sid" sh -lc "ts=\
+\$(date '+%F %T'); echo \"\$ts WARN [$hosttag] inference slow on batch=2 latency=1.9s\" >> /logs/infer/infer-demo.log"
+}
+
+CID_A="$(service_id node-a)"
+CID_B="$(service_id node-b)"
+
+[[ -n "$CID_A" && -n "$CID_B" ]] || { echo "[ERR] node containers not found" >&2; exit 1; }
+
+send_logs "$CID_A" "host01"
+send_logs "$CID_B" "host02"
+
+log "Waiting for ES to ingest"
+sleep 10
+
+train1=$(get_count "train-*")
+infer1=$(get_count "infer-*")
+final=$((train1 + infer1))
+log "final counts: train=${train1} infer=${infer1} total=${final}"
+
+if (( final <= base )); then
+  echo "[ERR] ES total did not increase (${base} -> ${final})" >&2
+  exit 1
+fi
+
+if (( final < 4 )); then
+  echo "[ERR] ES total below expected threshold: ${final} < 4" >&2
+  exit 1
+fi
+
+es_health=$(curl -s "http://localhost:9200/_cluster/health" | grep -o '"status":"[^"]*"' | cut -d'"' -f4)
+if [[ "$es_health" != "green" && "$es_health" != "yellow" ]]; then
+  echo "[ERR] ES health not green/yellow: $es_health" >&2
+  exit 1
+fi
+
+if ! curl -fs "http://localhost:5601/api/status" >/dev/null 2>&1; then
+  echo "[WARN] Kibana status endpoint not available"
+fi
+
+log "ES counts increased and services healthy"
--- a/src/sys/debug/scripts/08_restart_agent_reregister.sh
+++ b/src/sys/debug/scripts/08_restart_agent_reregister.sh
@ -0,0 +1,110 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+API_BASE="http://localhost:32300/api/v1/master"
+NODE_ENTRYPOINT="$DEBUG_ROOT/../tests/scripts/node_entrypoint.sh"
+[[ -f "$NODE_ENTRYPOINT" ]] || { echo "[ERR] node entrypoint script missing at $NODE_ENTRYPOINT" >&2; exit 1; }
+
+TARGET_FIXED_IP="${SYS_DEBUG_NODEB_FIXED_IP:-172.30.0.200}"
+
+ID_B_FILE="$TMP_DIR/node_id_b"
+IP_INIT_FILE="$TMP_DIR/initial_ip_b"
+[[ -f "$ID_B_FILE" && -f "$IP_INIT_FILE" ]] || { echo "[ERR] Required node id/ip files missing in $TMP_DIR" >&2; exit 1; }
+
+ID_B="$(cat "$ID_B_FILE")"
+IP0_B="$(cat "$IP_INIT_FILE")"
+
+DETAIL_BEFORE="$TMP_DIR/node_b_before.json"
+curl -fsS "$API_BASE/nodes/$ID_B" -o "$DETAIL_BEFORE"
+LAST0=$(python3 - "$DETAIL_BEFORE" <<'PY'
+import json,sys
+node=json.load(open(sys.argv[1]))
+print(node.get("last_updated",""))
+PY
+)
+IP_BEFORE=$(python3 - "$DETAIL_BEFORE" <<'PY'
+import json,sys
+node=json.load(open(sys.argv[1]))
+print(node.get("meta_data",{}).get("ip",""))
+PY
+)
+
+if [[ "$IP_BEFORE" != "$IP0_B" ]]; then
+  echo "[ERR] Expected initial IP $IP0_B for node-b, got $IP_BEFORE" >&2
+  exit 1
+fi
+
+if [[ "$IP_BEFORE" == "$TARGET_FIXED_IP" ]]; then
+  echo "[ERR] node-b current IP $IP_BEFORE already matches target $TARGET_FIXED_IP. Configure SYS_DEBUG_NODEB_FIXED_IP to a different address before rerun." >&2
+  exit 1
+fi
+
+service_id() {
+  compose ps -q "$1"
+}
+
+log "Recreating node-b (old IP $IP_BEFORE) with static IP $TARGET_FIXED_IP"
+compose rm -sf node-b >/dev/null 2>&1 || true
+
+CONTAINER_NAME="${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}-node-b"
+docker rm -f "$CONTAINER_NAME" >/dev/null 2>&1 || true
+
+AGENT_BIN_PATH="$(cat "$TMP_DIR/agent_binary_path")"
+[[ -f "$AGENT_BIN_PATH" ]] || { echo "[ERR] Agent binary path missing in $TMP_DIR" >&2; exit 1; }
+
+require_docker
+
+docker run -d \
+  --name "$CONTAINER_NAME" \
+  --hostname "$HOST_B" \
+  --network "$SYS_DEBUG_NETWORK_NAME" \
+  --ip "$TARGET_FIXED_IP" \
+  --dns "${SYS_DEBUG_BIND_IP:-172.30.0.2}" \
+  -e MASTER_ENDPOINT=http://master.argus.com:3000 \
+  -e REPORT_INTERVAL_SECONDS=2 \
+  -e ARGUS_BUILD_UID=$ARGUS_BUILD_UID \
+  -e ARGUS_BUILD_GID=$ARGUS_BUILD_GID \
+  -e ES_HOST=es \
+  -e ES_PORT=9200 \
+  -e CLUSTER=local \
+  -e RACK=dev \
+  -p 2021:2020 \
+  -v "$SYS_DEBUG_PRIVATE_NODEB/argus/agent/$HOST_B:/private/argus/agent/$HOST_B" \
+  -v "$AGENT_BIN_PATH:/usr/local/bin/argus-agent:ro" \
+  -v "$NODE_ENTRYPOINT:/usr/local/bin/node-entrypoint.sh:ro" \
+  -v "$REPO_ROOT/src/log/fluent-bit/build/start-fluent-bit.sh:/assets/start-fluent-bit.sh:ro" \
+  -v "$REPO_ROOT/src/log/fluent-bit/build/etc:/assets/fluent-bit/etc:ro" \
+  -v "$REPO_ROOT/src/log/fluent-bit/build/packages:/assets/fluent-bit/packages:ro" \
+  --entrypoint /usr/local/bin/node-entrypoint.sh \
+  ubuntu:22.04 >/dev/null
+
+log "Waiting for node-b to re-register with new IP"
+for _ in {1..40}; do
+  sleep 3
+  if curl -fsS "$API_BASE/nodes/$ID_B" -o "$TMP_DIR/node_b_after.json"; then
+    if python3 - "$TMP_DIR/node_b_after.json" "$LAST0" "$TARGET_FIXED_IP" <<'PY'
+import json,sys
+node=json.load(open(sys.argv[1]))
+last0=sys.argv[2]
+expected_ip=sys.argv[3]
+ip=node.get("meta_data",{}).get("ip")
+lu=node.get("last_updated")
+if ip == expected_ip and lu and lu != last0:
+    sys.exit(0)
+sys.exit(1)
+PY
+    then
+      log "node-b IP updated: $IP_BEFORE -> $TARGET_FIXED_IP"
+      exit 0
+    fi
+  fi
+done
+
+echo "[ERR] node-b did not update to IP $TARGET_FIXED_IP in time" >&2
+exit 1
--- a/src/sys/debug/scripts/09_down.sh
+++ b/src/sys/debug/scripts/09_down.sh
@ -0,0 +1,13 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+require_docker
+
+log "Stopping debug stack (project $SYS_DEBUG_PROJECT_NAME)"
+compose down --remove-orphans >/dev/null 2>&1 || true
+
+log "Containers stopped. No host directories were removed."
--- a/src/sys/debug/scripts/clean-data.sh
+++ b/src/sys/debug/scripts/clean-data.sh
@ -0,0 +1,66 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+ensure_env_file
+ensure_paths_defined
+
+FORCE=false
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    -y|--yes)
+      FORCE=true
+      ;;
+    -h|--help)
+      cat <<USAGE
+Usage: ${0##*/} [--yes]
+
+Safely remove debug private directories after adjusting ownership.
+USAGE
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      exit 1
+      ;;
+  esac
+  shift
+done
+
+if [[ $FORCE == false ]]; then
+  read -r -p "This will delete debug private directories. Continue? [y/N] " reply
+  case "$reply" in
+    y|Y|yes|YES)
+      ;;
+    *)
+      echo "Aborted"
+      exit 0
+      ;;
+  esac
+fi
+
+paths=(
+  "$SYS_DEBUG_PRIVATE_CORE"
+  "$SYS_DEBUG_PRIVATE_NODEA"
+  "$SYS_DEBUG_PRIVATE_NODEB"
+  "$SYS_DEBUG_TMP_DIR"
+)
+
+require_docker
+
+image="ubuntu:22.04"
+
+for dir in "${paths[@]}"; do
+  [[ -d "$dir" ]] || continue
+  log "Fixing ownership for $dir"
+  if ! docker run --rm -v "$dir:/target" "$image" chown -R "$(id -u):$(id -g)" /target >/dev/null 2>&1; then
+    echo "[WARN] Failed to adjust ownership via $image, attempting local chown" >&2
+    chown -R "$(id -u):$(id -g)" "$dir" >/dev/null 2>&1 || true
+  fi
+  log "Removing $dir"
+  rm -rf "$dir"
+done
+
+log "Clean data completed"
--- a/src/sys/debug/scripts/common.sh
+++ b/src/sys/debug/scripts/common.sh
@ -0,0 +1,96 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+DEBUG_ROOT="$(cd "$SCRIPT_DIR/.." && pwd)"
+REPO_ROOT="$(cd "$DEBUG_ROOT/../../.." && pwd)"
+ENV_FILE="$DEBUG_ROOT/.env"
+
+source "$REPO_ROOT/scripts/common/build_user.sh"
+load_build_user
+
+if [[ -f "$ENV_FILE" ]]; then
+  set -a
+  # shellcheck disable=SC1090
+  source "$ENV_FILE"
+  set +a
+fi
+
+SYS_DEBUG_NETWORK_NAME=${SYS_DEBUG_NETWORK_NAME:-argus-debug-net}
+SYS_DEBUG_NETWORK_SUBNET=${SYS_DEBUG_NETWORK_SUBNET:-172.30.0.0/16}
+SYS_DEBUG_NETWORK_GATEWAY=${SYS_DEBUG_NETWORK_GATEWAY:-172.30.0.1}
+SYS_DEBUG_PROJECT_NAME=${SYS_DEBUG_PROJECT_NAME:-argus-debug}
+SYS_DEBUG_CONTAINER_PREFIX=${SYS_DEBUG_CONTAINER_PREFIX:-argus-debug}
+SYS_DEBUG_PRIVATE_CORE=${SYS_DEBUG_PRIVATE_CORE:-$DEBUG_ROOT/private}
+SYS_DEBUG_PRIVATE_NODEA=${SYS_DEBUG_PRIVATE_NODEA:-$DEBUG_ROOT/private-nodea}
+SYS_DEBUG_PRIVATE_NODEB=${SYS_DEBUG_PRIVATE_NODEB:-$DEBUG_ROOT/private-nodeb}
+SYS_DEBUG_TMP_DIR=${SYS_DEBUG_TMP_DIR:-$DEBUG_ROOT/tmp}
+ARGUS_BUILD_UID=${ARGUS_BUILD_UID:-2133}
+ARGUS_BUILD_GID=${ARGUS_BUILD_GID:-2015}
+
+SYS_DEBUG_NODEA_HOST=${SYS_DEBUG_NODEA_HOST:-dev-yyrshare-nbnyx10-cp2f-pod-0}
+SYS_DEBUG_NODEB_HOST=${SYS_DEBUG_NODEB_HOST:-dev-yyrshare-uuuu10-ep2f-pod-0}
+
+HOST_A="$SYS_DEBUG_NODEA_HOST"
+HOST_B="$SYS_DEBUG_NODEB_HOST"
+
+COMPOSE_FILE="$DEBUG_ROOT/docker-compose.yml"
+
+abs_path() {
+  python3 - "$1" <<'PY'
+import os, sys
+path = sys.argv[1]
+print(os.path.abspath(path))
+PY
+}
+
+ensure_command() {
+  local cmd="$1"
+  if ! command -v "$cmd" >/dev/null 2>&1; then
+    echo "[ERR] Required command '$cmd' not found" >&2
+    exit 1
+  fi
+}
+
+require_docker() {
+  ensure_command docker
+}
+
+compose() {
+  require_docker
+  local bin
+  if docker compose version >/dev/null 2>&1; then
+    bin=(docker compose)
+  else
+    bin=(docker-compose)
+  fi
+  "${bin[@]}" -p "$SYS_DEBUG_PROJECT_NAME" -f "$COMPOSE_FILE" "$@"
+}
+
+ensure_paths_defined() {
+  local missing=()
+  for name in SYS_DEBUG_PRIVATE_CORE SYS_DEBUG_PRIVATE_NODEA SYS_DEBUG_PRIVATE_NODEB SYS_DEBUG_TMP_DIR; do
+    if [[ -z "${!name:-}" ]]; then
+      missing+=("$name")
+    fi
+  done
+  if (( ${#missing[@]} > 0 )); then
+    echo "[ERR] Missing required environment variables: ${missing[*]}" >&2
+    echo "      Run 01_bootstrap.sh first." >&2
+    exit 1
+  fi
+}
+
+ensure_env_file() {
+  if [[ ! -f "$ENV_FILE" ]]; then
+    echo "[ERR] Missing .env at $ENV_FILE. Run 01_bootstrap.sh first." >&2
+    exit 1
+  fi
+}
+
+log() {
+  echo "[INFO] $*"
+}
+
+TMP_DIR="$SYS_DEBUG_TMP_DIR"
+mkdir -p "$TMP_DIR"
--- a/src/sys/debug/scripts/network-create.sh
+++ b/src/sys/debug/scripts/network-create.sh
@ -0,0 +1,76 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+NAME="$SYS_DEBUG_NETWORK_NAME"
+SUBNET="$SYS_DEBUG_NETWORK_SUBNET"
+GATEWAY="$SYS_DEBUG_NETWORK_GATEWAY"
+
+usage() {
+  cat <<EOF
+Usage: ${0##*/} [--name NAME] [--subnet CIDR] [--gateway IP]
+
+Create (if missing) the external debug docker network.
+
+Defaults derived from .env or:
+  name    = $NAME
+  subnet  = $SUBNET
+  gateway = $GATEWAY
+EOF
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --name)
+      shift; [[ $# -gt 0 ]] || { echo "--name requires value" >&2; exit 1; }
+      NAME="$1"
+      ;;
+    --name=*)
+      NAME="${1#*=}"
+      ;;
+    --subnet)
+      shift; [[ $# -gt 0 ]] || { echo "--subnet requires value" >&2; exit 1; }
+      SUBNET="$1"
+      ;;
+    --subnet=*)
+      SUBNET="${1#*=}"
+      ;;
+    --gateway)
+      shift; [[ $# -gt 0 ]] || { echo "--gateway requires value" >&2; exit 1; }
+      GATEWAY="$1"
+      ;;
+    --gateway=*)
+      GATEWAY="${1#*=}"
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage >&2
+      exit 1
+      ;;
+  esac
+  shift
+done
+
+require_docker
+
+if docker network inspect "$NAME" >/dev/null 2>&1; then
+  log "Network $NAME already exists"
+  exit 0
+fi
+
+log "Creating network $NAME (subnet=$SUBNET gateway=$GATEWAY)"
+docker network create \
+  --driver bridge \
+  --subnet "$SUBNET" \
+  --gateway "$GATEWAY" \
+  "$NAME"
+
+mkdir -p "$TMP_DIR"
+echo "$NAME" > "$TMP_DIR/network.created"
+log "Network $NAME created"
--- a/src/sys/debug/scripts/network-destroy.sh
+++ b/src/sys/debug/scripts/network-destroy.sh
@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# shellcheck source=common.sh
+source "$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)/common.sh"
+
+NAME="$SYS_DEBUG_NETWORK_NAME"
+
+usage() {
+  cat <<EOF
+Usage: ${0##*/} [--name NAME]
+
+Destroy the debug docker network if no containers are attached.
+EOF
+}
+
+while [[ $# -gt 0 ]]; do
+  case "$1" in
+    --name)
+      shift; [[ $# -gt 0 ]] || { echo "--name requires value" >&2; exit 1; }
+      NAME="$1"
+      ;;
+    --name=*)
+      NAME="${1#*=}"
+      ;;
+    -h|--help)
+      usage
+      exit 0
+      ;;
+    *)
+      echo "Unknown argument: $1" >&2
+      usage >&2
+      exit 1
+      ;;
+  esac
+  shift
+done
+
+require_docker
+
+if ! docker network inspect "$NAME" >/dev/null 2>&1; then
+  log "Network $NAME not found; nothing to do"
+  exit 0
+fi
+
+attached=$(docker network inspect -f '{{range $id, $conf := .Containers}}{{printf "%s " $conf.Name}}{{end}}' "$NAME")
+if [[ -n "${attached// }" ]]; then
+  echo "[ERR] Cannot remove network $NAME: still connected containers -> $attached" >&2
+  exit 1
+fi
+
+log "Deleting network $NAME"
+docker network rm "$NAME" >/dev/null
+rm -f "$TMP_DIR/network.created"
+log "Network $NAME removed"
Author	SHA1	Message	Date
yuyr	3d9b229ac0	[#13 ] 增加debug模式系统集成测试，使用external network和指定private路径	2025-10-13 15:18:41 +08:00
yuyr	0e96c5bcb0	[#15 ] 增加镜像构建 --no-cache选项	2025-10-13 15:17:33 +08:00