From f23745d18b2ab954d4e4def50109e73146c18d37 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Vin=C3=ADcius=20Ferr=C3=A3o?=
 <2031761+viniciusferrao@users.noreply.github.com>
Date: Sat, 29 Aug 2026 21:01:02 -0300
Subject: [PATCH] fix(remoteshell): wait for the ssh daemon to end before a new
 one starts

A kill only asks the kernel to end a process, so it returns before the process
is gone. The fallback started a new daemon on the next line, which could find
the port still held by the old one, fail to start, and leave the node with no
daemon at all.

Wait for the processes to end, for up to ten seconds, before the new daemon
starts. The test that a process is still there sends no signal.
---
 xCAT/postscripts/remoteshell | 14 +++++++++++++-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/xCAT/postscripts/remoteshell b/xCAT/postscripts/remoteshell
index 54390fd93..3378b9253 100755
--- a/xCAT/postscripts/remoteshell
+++ b/xCAT/postscripts/remoteshell
@@ -648,7 +648,19 @@ fi
 #try to kill the process and start
 if [ "$?" != "0" ];then
    PIDLIST=`ps aux | grep -v grep | grep "/usr/sbin/sshd"|awk -F" " '{print $2}'|xargs`
-   [ -n "$PIDLIST" ] && kill -9 $PIDLIST
+   if [ -n "$PIDLIST" ]; then
+      kill -9 $PIDLIST
+      waited=0
+      while [ $waited -lt 10 ]; do
+         alive=0
+         for pid in $PIDLIST; do
+            if kill -0 $pid 2>/dev/null; then alive=1; fi
+         done
+         if [ $alive -eq 0 ]; then break; fi
+         sleep 1
+         waited=`expr $waited + 1`
+      done
+   fi
    /usr/sbin/sshd
 fi
 kill -9 $CREDPID