From 89f091eded92dbe100d2ec8cebd1e01ee1a17f49 Mon Sep 17 00:00:00 2001
From: mssonicbld <79238446+mssonicbld@users.noreply.github.com>
Date: Wed, 6 Sep 2023 12:53:08 +0800
Subject: [PATCH] [Mellanox] set select timeout to no more than 1 sec to make
 sure fast shutdown (#13611) (#16449)

- Why I did it
Commit sonic-net/sonic-platform-daemons@153ea47 changed SfpStateUpdateTask from Process to Thread. In this commit, it raises an exception in SfpStateUpdateTask to make shutdown flow fast. But it does not work on Nvidia platform as Nvidia platform is passing timeout parameter of get_change_event to select. Linux select function can not be interrupted by a Python exception. There is no such issue on Nvidia platform before that commit. However, in order to comply with the commit and make shutdown flow fast, we decided to change Nvidia platform API implementation.

To fix issue #13591.

- How I did it
The select call in get_change_event should use no more than 1 second as timeout parameter.
Outside the select call, add a while loop to make sure timeout parameter of get_change_event work as expected

- How to verify it
Manual test

Co-authored-by: Junchao-Mellanox <57339448+Junchao-Mellanox@users.noreply.github.com>
---
 .../sonic_platform/chassis.py                 | 24 +++++++++++--------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/platform/mellanox/mlnx-platform-api/sonic_platform/chassis.py b/platform/mellanox/mlnx-platform-api/sonic_platform/chassis.py
index e13b90d6c0ca..17d66b2e8f64 100644
--- a/platform/mellanox/mlnx-platform-api/sonic_platform/chassis.py
+++ b/platform/mellanox/mlnx-platform-api/sonic_platform/chassis.py
@@ -31,10 +31,10 @@
     from . import utils
     from .device_data import DeviceDataManager
     import re
+    import time
 except ImportError as e:
     raise ImportError (str(e) + "- required module not found")
 
-MAX_SELECT_DELAY = 3600
 
 RJ45_TYPE = "RJ45"
 
@@ -387,26 +387,30 @@ def get_change_event(self, timeout=0):
             self.sfp_event.initialize()
 
         wait_for_ever = (timeout == 0)
+        # select timeout should be no more than 1000ms to ensure fast shutdown flow
+        select_timeout = 1000.0 if timeout >= 1000 else float(timeout)
         port_dict = {}
         error_dict = {}
-        if wait_for_ever:
-            timeout = MAX_SELECT_DELAY
-            while True:
-                status = self.sfp_event.check_sfp_status(port_dict, error_dict, timeout)
-                if bool(port_dict):
+        begin = time.time()
+        while True:
+            status = self.sfp_event.check_sfp_status(port_dict, error_dict, select_timeout)
+            if bool(port_dict):
+                break
+
+            if not wait_for_ever:
+                elapse = time.time() - begin
+                if elapse * 1000 > timeout:
                     break
-        else:
-            status = self.sfp_event.check_sfp_status(port_dict, error_dict, timeout)
 
         if status:
             if port_dict:
                 self.reinit_sfps(port_dict)
-            result_dict = {'sfp':port_dict}
+            result_dict = {'sfp': port_dict}
             if error_dict:
                 result_dict['sfp_error'] = error_dict
             return True, result_dict
         else:
-            return True, {'sfp':{}}
+            return True, {'sfp': {}}
 
     def reinit_sfps(self, port_dict):
         """