From 428d6da9f96f42db7bb06a84b340c9e329cad4e6 Mon Sep 17 00:00:00 2001
From: abdosi <58047199+abdosi@users.noreply.github.com>
Date: Thu, 26 Dec 2024 23:42:20 +0530
Subject: [PATCH] Fix monit connection failure when doing
 routeCheck/contianerCheck  monitor enable after config reload (#3698)

Fix:
sonic-net/sonic-buildimage#21268

How I did:
Reorder the sequence of doing enabling container_cheek and routeCheck before doing monit reload to avoid transient issue of monit sock error.

Also I add a sleep of 1 sec to make sure monitor enable configuration takes effect before we do reload.
---
 config/main.py       | 11 +++++------
 tests/config_test.py |  2 +-
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/config/main.py b/config/main.py
index ea915fca97..dbd574ff01 100644
--- a/config/main.py
+++ b/config/main.py
@@ -949,18 +949,17 @@ def _restart_services():
     # If load_minigraph exit before eth0 restart, commands after load_minigraph may failed
     wait_service_restart_finish('interfaces-config', last_interface_config_timestamp)
     wait_service_restart_finish('networking', last_networking_timestamp)
-
-    # Reload Monit configuration to pick up new hostname in case it changed
-    click.echo("Reloading Monit configuration ...")
-    clicommon.run_command(['sudo', 'monit', 'reload'])
-
     try:
         subprocess.check_call(['sudo', 'monit', 'status'], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
         click.echo("Enabling container and routeCheck monitoring ...")
-        clicommon.run_command(['sudo', 'monit', 'monitor', 'container_checker'])
         clicommon.run_command(['sudo', 'monit', 'monitor', 'routeCheck'])
+        clicommon.run_command(['sudo', 'monit', 'monitor', 'container_checker'])
+        time.sleep(1)
     except subprocess.CalledProcessError as err:
         pass
+    # Reload Monit configuration to pick up new hostname in case it changed
+    click.echo("Reloading Monit configuration ...")
+    clicommon.run_command(['sudo', 'monit', 'reload'])
 
 def _per_namespace_swss_ready(service_name):
     out, _ = clicommon.run_command(['systemctl', 'show', str(service_name), '--property', 'ActiveState', '--value'], return_cmd=True)
diff --git a/tests/config_test.py b/tests/config_test.py
index eaa4ea0874..bd38011b5c 100644
--- a/tests/config_test.py
+++ b/tests/config_test.py
@@ -56,8 +56,8 @@
 Running command: config qos reload --no-dynamic-buffer --no-delay
 Running command: pfcwd start_default
 Restarting SONiC target ...
-Reloading Monit configuration ...
 Enabling container and routeCheck monitoring ...
+Reloading Monit configuration ...
 Please note setting loaded from minigraph will be lost after system reboot. To preserve setting, run `config save`.
 Released lock on {0}
 """