From c20abb9e28d93cd0b9ecab8d77881ff7a4934b5a Mon Sep 17 00:00:00 2001
From: prabhataravind <108555774+prabhataravind@users.noreply.github.com>
Date: Wed, 3 Jan 2024 17:44:22 -0800
Subject: [PATCH] [docker_image_ctl.j2]: swss docker initialization
 improvements (#17628)

* [docker_image_ctl.j2]: swss docker initialization improvements

This commit attempts to address the following:
 * Make sure swss container is indeed up and running before running any commands
   on it. In case where swss container is not fully up when swss.sh attempts to
   create swss:/ready file using "docker exec swss$DEV touch", the command can
   fail silently and can cause swssconfig to wait forever leading to missing IP
   decap configuration among other things. Add a wait so that docker commands
   are run only after swss container status is "Running"
*  Add a log when swss:/ready file is created or if the file creation fails so
   that it becomes easier to debug such scenarios in the future
* [docker_image_ctl.j2]: Use swss$DEV to accommodate multi ASIC platforms as well

Signed-off-by: Prabhat Aravind <paravind@microsoft.com>
---
 files/build_templates/docker_image_ctl.j2 | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/files/build_templates/docker_image_ctl.j2 b/files/build_templates/docker_image_ctl.j2
index 2093622daa..95c2e1fa52 100644
--- a/files/build_templates/docker_image_ctl.j2
+++ b/files/build_templates/docker_image_ctl.j2
@@ -283,6 +283,12 @@ function postStartAction()
     fi
     chgrp -f redis $REDIS_SOCK && chmod -f 0760 $REDIS_SOCK
 {%- elif docker_container_name == "swss" %}
+    # Wait until swss container state is Running
+    until [[ ($(docker inspect -f {{"'{{.State.Running}}'"}} swss$DEV) == "true") ]]; do
+        sleep 0.1
+    done
+    echo "swss container is up and running"
+
     docker exec swss$DEV rm -f /ready   # remove cruft
     if [[ "$BOOT_TYPE" == "fast" ]] && [[ -d /host/fast-reboot ]]; then
         test -e /host/fast-reboot/fdb.json && docker cp /host/fast-reboot/fdb.json swss$DEV:/
@@ -292,6 +298,9 @@ function postStartAction()
         rm -fr /host/fast-reboot
     fi
     docker exec swss$DEV touch /ready # signal swssconfig.sh to go
+    # Re-confirm that file is indeed created and log an error if not
+    docker exec swss$DEV test -f /ready && echo "File swss:/ready created" || echo "Error: File swss:/ready doesn't exist"
+
 {%- elif docker_container_name == "pmon" %}
 
     DEVPATH="/usr/share/sonic/device"