From 1b533794aa18ea25e3c90090bb83eb7bcb3984f0 Mon Sep 17 00:00:00 2001
From: Paulo Zulato <paulozulato@gmail.com>
Date: Sun, 17 Sep 2023 21:53:37 -0300
Subject: [PATCH] fix: handle case that zombie process terminated

When emqx is stopped, sometimes it found out that the process is at
zombie state and tries to get the parent PID but the process has already
finished in the meanwhile, printing an error message like this:

```
error: process ID list syntax error

Usage:
 ps [options]

 Try 'ps --help <simple|list|output|threads|misc|all>'
  or 'ps --help <s|l|o|t|m|a>'
 for additional help text.

For more details see ps(1).
WARNING: 281777 is marked <defunct>, parent:
ok
```
---
 bin/emqx | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/bin/emqx b/bin/emqx
index b65b5b431..5484a82e5 100755
--- a/bin/emqx
+++ b/bin/emqx
@@ -805,6 +805,12 @@ generate_config() {
     mv -f "$TMP_ARG_FILE" "$ARGS_FILE"
 }
 
+# check if a PID is defunct
+is_defunct() {
+    local PID="$1"
+    ps -fp "$PID" | $GREP -q 'defunct'
+}
+
 # check if a PID is down
 # shellcheck disable=SC2317 # call in func `nodetool_shutdown()`
 is_down() {
@@ -812,9 +818,13 @@ is_down() {
     if ps -p "$PID" >/dev/null; then
         # still around
         # shellcheck disable=SC2009 # this grep pattern is not a part of the program names
-        if ps -fp "$PID" | $GREP -q 'defunct'; then
+        if is_defunct "$PID"; then
             # zombie state, print parent pid
             parent="$(ps -o ppid= -p "$PID" | tr -d ' ')"
+            if [ -z "$parent" ] && ! is_defunct "$PID"; then
+                # process terminated in the meanwhile
+                return 0;
+            fi
             logwarn "$PID is marked <defunct>, parent: $(ps -p "$parent")"
             return 0
         fi