From a1c9100063811e7b653eb2a709d100974e5d578d Mon Sep 17 00:00:00 2001
From: saksarav-nokia <sakthivadivu.saravanaraj@nokia.com>
Date: Thu, 18 Apr 2024 01:19:49 -0400
Subject: [PATCH] Wait till CHASIS_APP_DB PING is successful,  host_name and
 asic_name are valid in CONIFG_DB before starting chassis-db-cleanup (#17962)

This PR fixes the issue reported in Issu #17945
We noticed that chassis db clean up is skipped sometimes when the CHASSIS_APP_DB PING fails. Also if host_name and asic_name are not written to CONIG_DB, it could pass the empty strings to CHASSIS_APP_DB EVAL commands.
The service hostname-config.service is restarted whenever the config-reload or load-minigraph is done and this services renames the file /etc/hosts to updates it with the new file. This interferes with swss@.service and when swss.sh script CHASSIS_APP_DPP when the /etc/hosts file is renamed, the error "Unable to connect to redis: Cannot assign requested address" is seen and the CHASSIS_APP_DB EVAL command fails. This causes the chassis db entries not getting cleaned up and causes orchagent crash in remote LC's.

---------

Signed-off-by: saksarav <sakthivadivu.saravanaraj@nokia.com>
---
 files/image_config/hostname/hostname-config.sh |  8 +++++++-
 files/scripts/swss.sh                          | 17 ++++++++++++++---
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/files/image_config/hostname/hostname-config.sh b/files/image_config/hostname/hostname-config.sh
index c2a4f1e546ce..5f4bfede2097 100755
--- a/files/image_config/hostname/hostname-config.sh
+++ b/files/image_config/hostname/hostname-config.sh
@@ -11,10 +11,16 @@ fi
 echo $HOSTNAME > /etc/hostname
 hostname -F /etc/hostname
 
+#Don't update the /etc/hosts if hostname is not changed
+#This is to prevent intermittent redis_chassis.server reachability issue
+if [ $CURRENT_HOSTNAME == $HOSTNAME ] ;  then
+    exit 0
+fi
+
 # Remove the old hostname entry from hosts file.
 # But, 'localhost' entry is used by multiple applications. Don't remove it altogether.
 # Edit contents of /etc/hosts and put in /etc/hosts.new
-if [ $CURRENT_HOSTNAME  != "localhost" ] || [ $CURRENT_HOSTNAME == $HOSTNAME ] ;  then
+if [ $CURRENT_HOSTNAME  != "localhost" ] ;  then
     sed "/\s$CURRENT_HOSTNAME$/d" /etc/hosts > /etc/hosts.new
 else
     cp -f /etc/hosts /etc/hosts.new
diff --git a/files/scripts/swss.sh b/files/scripts/swss.sh
index 912461ba9ad9..16849cdffa74 100755
--- a/files/scripts/swss.sh
+++ b/files/scripts/swss.sh
@@ -132,12 +132,23 @@ function clean_up_chassis_db_tables()
         return
     fi
 
-    if [[ !($($SONIC_DB_CLI CHASSIS_APP_DB PING | grep -c True) -gt 0) ]]; then
-        return
-    fi
+    until [[ $($SONIC_DB_CLI CHASSIS_APP_DB PING | grep -c True) -gt 0 ]]; do
+        sleep 1
+    done
 
     lc=`$SONIC_DB_CLI CONFIG_DB  hget 'DEVICE_METADATA|localhost' 'hostname'`
+    until [[ -n "${lc}" ]]; do
+        lc=`$SONIC_DB_CLI CONFIG_DB  hget 'DEVICE_METADATA|localhost' 'hostname'`
+        sleep 1
+    done
+    debug "Chassis db clean up for ${SERVICE}$DEV. hostname=$lc"
+
     asic=`$SONIC_DB_CLI CONFIG_DB  hget 'DEVICE_METADATA|localhost' 'asic_name'`
+    until [[ -n "${asic}" ]]; do
+        asic=`$SONIC_DB_CLI CONFIG_DB  hget 'DEVICE_METADATA|localhost' 'asic_name'`
+        sleep 1
+    done
+    debug "Chassis db clean up for ${SERVICE}$DEV. asic=$asic"
 
     # First, delete SYSTEM_NEIGH entries
     num_neigh=`$SONIC_DB_CLI CHASSIS_APP_DB EVAL "