[#37] 修复dcgm exporter启动

src/sys/build/node-bundle/node-bootstrap.sh

@@ -40,7 +40,15 @@ else
         # run component installer within version dir
         if [[ -f "$version_dir/install.sh" ]]; then
           chmod +x "$version_dir/install.sh" 2>/dev/null || true
-          (cd "$version_dir" && ./install.sh "$version_dir")
+          # 传递运行时开关：容器内缺省启用 AUTO_START_DCGM=1、禁用 Profiling（可通过环境变量覆盖）
+          # 注意：不能用 `VAR=.. VAR2=.. (cmd)` 前缀到子 shell；bash 不允许 env 赋值直接修饰 `(` 复合命令。
+          # 因此改为在子 subshell 中 export 后再执行。
+          (
+            export AUTO_START_DCGM="${AUTO_START_DCGM:-1}"
+            export DCGM_EXPORTER_DISABLE_PROFILING="${DCGM_EXPORTER_DISABLE_PROFILING:-1}"
+            export DCGM_EXPORTER_LISTEN="${DCGM_EXPORTER_LISTEN:-:9400}"
+            cd "$version_dir" && ./install.sh "$version_dir"
+          )
           echo "$ver" > "$target_root/LATEST_VERSION" 2>/dev/null || true
           ln -sfn "$version_dir" "$target_root/current" 2>/dev/null || true
           if [[ -L "$target_root/current" && -d "$target_root/current" ]]; then
@@ -75,7 +83,19 @@ if ! pgrep -x argus-agent >/dev/null 2>&1; then
   setsid /usr/local/bin/argus-agent >/var/log/argus-agent.log 2>&1 < /dev/null &
 fi
 
-# 5) post-install selfcheck (best-effort) and wait for node.json
+# 5) 若 dcgm-exporter 未监听（可能因 Profiling 崩溃），尝试无 Profiling 清单回退启动
+if ! ss -tlnp 2>/dev/null | grep -q ":9400 "; then
+  echo "[BOOT] dcgm-exporter not listening; trying no-prof fallback"
+  pgrep -f nv-hostengine >/dev/null || (nohup nv-hostengine >/var/log/nv-hostengine.log 2>&1 & sleep 2)
+  cfg_dir="/etc/dcgm-exporter"; default_cfg="$cfg_dir/default-counters.csv"; no_prof_cfg="$cfg_dir/no-prof.csv"
+  if [[ -f "$default_cfg" ]]; then
+    grep -v 'DCGM_FI_PROF_' "$default_cfg" > "$no_prof_cfg" || true
+    pkill -f dcgm-exporter >/dev/null 2>&1 || true
+    nohup /usr/local/bin/dcgm-exporter --address="${DCGM_EXPORTER_LISTEN:-:9400}" --collectors "$no_prof_cfg" >/var/log/dcgm-exporter.log 2>&1 &
+  fi
+fi
+
+# 6) post-install selfcheck (best-effort) and wait for node.json
 for i in {1..30}; do
   if compgen -G "$INSTALL_DIR/versions/*/check_health.sh" > /dev/null; then
     bash "$INSTALL_DIR"/versions/*/check_health.sh || true