[#49] swarm test重启测试通过

src/sys/build/node-bundle/Dockerfile

@@ -11,6 +11,7 @@ WORKDIR /
 # bundle files are provided at build time into ./bundle in build context
 COPY bundle/ /bundle/
 COPY node-bootstrap.sh /usr/local/bin/node-bootstrap.sh
-RUN chmod +x /usr/local/bin/node-bootstrap.sh
+COPY health-watcher.sh /usr/local/bin/health-watcher.sh
+RUN chmod +x /usr/local/bin/node-bootstrap.sh /usr/local/bin/health-watcher.sh
 
 ENTRYPOINT ["/usr/local/bin/node-bootstrap.sh"]

src/sys/build/node-bundle/health-watcher.sh

@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+# health-watcher.sh
+# 周期执行 check_health.sh 与 restart_unhealthy.sh，用于容器内节点自愈。
+
+INSTALL_ROOT="/opt/argus-metric"
+INTERVAL="${HEALTH_WATCH_INTERVAL:-60}"
+VER_DIR="${1:-}"
+
+log(){ echo "[HEALTH-WATCHER] $*"; }
+
+resolve_ver_dir() {
+  local dir=""
+  if [[ -n "${VER_DIR:-}" && -d "$VER_DIR" ]]; then
+    dir="$VER_DIR"
+  elif [[ -L "$INSTALL_ROOT/current" ]]; then
+    dir="$(readlink -f "$INSTALL_ROOT/current" 2>/dev/null || true)"
+  fi
+  if [[ -z "$dir" ]]; then
+    dir="$(ls -d "$INSTALL_ROOT"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
+  fi
+  echo "$dir"
+}
+
+main() {
+  log "starting with interval=${INTERVAL}s"
+  local dir
+  dir="$(resolve_ver_dir)"
+  if [[ -z "$dir" || ! -d "$dir" ]]; then
+    log "no valid install dir found under $INSTALL_ROOT; exiting"
+    exit 0
+  fi
+
+  local chk="$dir/check_health.sh"
+  local rst="$dir/restart_unhealthy.sh"
+
+  if [[ ! -x "$chk" && ! -x "$rst" ]]; then
+    log "neither check_health.sh nor restart_unhealthy.sh is executable under $dir; exiting"
+    exit 0
+  fi
+
+  log "watching install dir: $dir"
+
+  while :; do
+    if [[ -x "$chk" ]]; then
+      log "running check_health.sh"
+      "$chk" >> "$dir/.health_check.watch.log" 2>&1 || log "check_health.sh reported issues (see .health_check.watch.log)"
+    fi
+    if [[ -x "$rst" ]]; then
+      log "running restart_unhealthy.sh"
+      "$rst" >> "$dir/.restart.watch.log" 2>&1 || log "restart_unhealthy.sh reported issues (see .restart.watch.log)"
+    fi
+    sleep "$INTERVAL"
+  done
+}
+
+main "$@"
+

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

@@ -115,5 +115,21 @@ for i in {1..60}; do
   sleep 2
 done
 
+# 7) spawn health watcher (best-effort, non-blocking)
+ver_dir=""
+if [[ -L "$INSTALL_DIR/current" ]]; then
+  ver_dir="$(readlink -f "$INSTALL_DIR/current" 2>/dev/null || true)"
+fi
+if [[ -z "$ver_dir" ]]; then
+  ver_dir="$(ls -d "$INSTALL_DIR"/versions/* 2>/dev/null | sort -V | tail -n1 || true)"
+fi
+
+if command -v /usr/local/bin/health-watcher.sh >/dev/null 2>&1; then
+  echo "[BOOT] starting health watcher for $ver_dir"
+  setsid /usr/local/bin/health-watcher.sh "${ver_dir:-}" >/var/log/health-watcher.log 2>&1 < /dev/null || true &
+else
+  echo "[BOOT][WARN] health-watcher.sh not found; skip health watcher"
+fi
+
 echo "[BOOT] ready; entering sleep"
 exec sleep infinity