Delay pmon non-critical daemon (#18907)

- Why I did it After this pull request #19190 , the pmon has been added to the start list in fast/warm reboot scenarios. However, certain non-critical daemons of pmon could be delayed, resulting in a saving of approximately 1 second in the reboot process. For performance considerations, especially as the current time usage of fast reboot is closer to 30 seconds limitation, this change could ease the pressure. - How I did it add a script as fast/warm reboot monitor and relative supervisord rlues. once the script exited means the reboot process has ended, other delayed daemon would then initialize. - How to verify it check the fast/warm reboot time usage Signed-off-by: Yuanzhe, Liu <[email protected]>
sonic-net · Nov 20, 2024 · 99eaa84 · 99eaa84
1 parent 71fd069
commit 99eaa84
Show file tree

Hide file tree

Showing 3 changed files with 25 additions and 7 deletions.
diff --git a/device/mellanox/x86_64-mlnx_msn2700-r0/pmon_daemon_control.json b/device/mellanox/x86_64-mlnx_msn2700-r0/pmon_daemon_control.json
@@ -2,6 +2,7 @@
     "skip_ledd": true,
     "skip_fancontrol": true,
     "delay_xcvrd": true,
-    "skip_xcvrd_cmis_mgr": true
+    "skip_xcvrd_cmis_mgr": true,
+    "delay_non_critical_daemon": true
 }
 
diff --git a/dockers/docker-platform-monitor/delay.py b/dockers/docker-platform-monitor/delay.py
@@ -0,0 +1,7 @@
+#!/usr/bin/env python3
+
+# This file serves as a monitor for advanced reboot. 
+# Once it exits, the delayed daemon will initiate.
+
+from swsscommon.swsscommon import RestartWaiter
+RestartWaiter.waitAdvancedBootDone()
diff --git a/dockers/docker-platform-monitor/docker-pmon.supervisord.conf.j2 b/dockers/docker-platform-monitor/docker-pmon.supervisord.conf.j2
@@ -28,6 +28,16 @@ stdout_logfile=syslog
 stderr_logfile=syslog
 dependent_startup=true
 
+
+{% if delay_non_critical_daemon %}
+[program:delay]
+command=python3 /usr/bin/delay.py
+autostart=false
+autorestart=false
+startsecs=0
+dependent_startup=true
+{% endif %}
+
 {% if not skip_chassisd and (IS_MODULAR_CHASSIS == 1 or is_smartswitch) %}
 [program:chassisd]
 command=/usr/local/bin/chassisd
@@ -64,7 +74,7 @@ stdout_logfile=syslog
 stderr_logfile=syslog
 startsecs=0
 dependent_startup=true
-dependent_startup_wait_for=rsyslogd:running
+dependent_startup_wait_for=rsyslogd:running {% if delay_non_critical_daemon %}delay:exited{% endif %}
 {% endif %}
 
 {% if not skip_fancontrol and HAVE_FANCONTROL_CONF == 1 %}
@@ -151,7 +161,7 @@ stdout_logfile=syslog
 stderr_logfile=syslog
 startsecs=10
 dependent_startup=true
-dependent_startup_wait_for=rsyslogd:running
+dependent_startup_wait_for=rsyslogd:running {% if delay_non_critical_daemon %}delay:exited{% endif %}
 {% endif %}
 
 {% if not skip_syseepromd %}
@@ -164,7 +174,7 @@ stdout_logfile=syslog
 stderr_logfile=syslog
 startsecs=10
 dependent_startup=true
-dependent_startup_wait_for=rsyslogd:running
+dependent_startup_wait_for=rsyslogd:running {% if delay_non_critical_daemon %}delay:exited{% endif %}
 {% endif %}
 
 {% if not skip_thermalctld %}
@@ -178,7 +188,7 @@ stderr_logfile=syslog
 startsecs=10
 startretries=50
 dependent_startup=true
-dependent_startup_wait_for=rsyslogd:running
+dependent_startup_wait_for=rsyslogd:running {% if delay_non_critical_daemon %}delay:exited{% endif %}
 {% endif %}
 
 {% if not skip_pcied %}
@@ -191,7 +201,7 @@ stdout_logfile=syslog
 stderr_logfile=syslog
 startsecs=10
 dependent_startup=true
-dependent_startup_wait_for=rsyslogd:running
+dependent_startup_wait_for=rsyslogd:running {% if delay_non_critical_daemon %}delay:exited{% endif %}
 {% endif %}
 
 {% if include_sensormond %}
@@ -204,7 +214,7 @@ stdout_logfile=syslog
 stderr_logfile=syslog
 startsecs=10
 dependent_startup=true
-dependent_startup_wait_for=rsyslogd:running
+dependent_startup_wait_for=rsyslogd:running {% if delay_non_critical_daemon %}delay:exited{% endif %}
 {% endif %}
 
 {% if not skip_stormond %}