CLI support for SmartSwitch PMON

config/chassis_modules.py

@@ -5,6 +5,7 @@
 import re
 import subprocess
 import utilities_common.cli as clicommon
+from utilities_common.chassis import is_smartswitch, get_all_dpus
 
 TIMEOUT_SECS = 10
 
@@ -27,7 +28,10 @@ def get_config_module_state(db, chassis_module_name):
     config_db = db.cfgdb
     fvs = config_db.get_entry('CHASSIS_MODULE', chassis_module_name)
     if not fvs:
-        return 'up'
+        if is_smartswitch():
+            return 'down'
+        else:
+            return 'up'
     else:
         return fvs['admin_status']
 
@@ -102,16 +106,21 @@ def fabric_module_set_admin_status(db, chassis_module_name, state):
 #
 @modules.command('shutdown')
 @clicommon.pass_db
-@click.argument('chassis_module_name', metavar='<module_name>', required=True)
+@click.argument('chassis_module_name',
+                metavar='<module_name>',
+                required=True,
+                type=click.Choice(get_all_dpus(), case_sensitive=False) if is_smartswitch() else str
+                )
 def shutdown_chassis_module(db, chassis_module_name):
     """Chassis-module shutdown of module"""
     config_db = db.cfgdb
     ctx = click.get_current_context()
 
     if not chassis_module_name.startswith("SUPERVISOR") and \
        not chassis_module_name.startswith("LINE-CARD") and \
-       not chassis_module_name.startswith("FABRIC-CARD"):
-        ctx.fail("'module_name' has to begin with 'SUPERVISOR', 'LINE-CARD' or 'FABRIC-CARD'")
+       not chassis_module_name.startswith("FABRIC-CARD") and \
+       not chassis_module_name.startswith("DPU"):
+        ctx.fail("'module_name' has to begin with 'SUPERVISOR', 'LINE-CARD', 'FABRIC-CARD', 'DPU'")
 
     # To avoid duplicate operation
     if get_config_module_state(db, chassis_module_name) == 'down':
@@ -130,7 +139,11 @@ def shutdown_chassis_module(db, chassis_module_name):
 #
 @modules.command('startup')
 @clicommon.pass_db
-@click.argument('chassis_module_name', metavar='<module_name>', required=True)
+@click.argument('chassis_module_name',
+                metavar='<module_name>',
+                required=True,
+                type=click.Choice(get_all_dpus(), case_sensitive=False) if is_smartswitch() else str
+                )
 def startup_chassis_module(db, chassis_module_name):
     """Chassis-module startup of module"""
     config_db = db.cfgdb
@@ -142,7 +155,12 @@ def startup_chassis_module(db, chassis_module_name):
         return
 
     click.echo("Starting up chassis module {}".format(chassis_module_name))
-    config_db.set_entry('CHASSIS_MODULE', chassis_module_name, None)
+    if is_smartswitch():
+        fvs = {'admin_status': 'up'}
+        config_db.set_entry('CHASSIS_MODULE', chassis_module_name, fvs)
+    else:
+        config_db.set_entry('CHASSIS_MODULE', chassis_module_name, None)
+
     if chassis_module_name.startswith("FABRIC-CARD"):
         if not check_config_module_state_with_timeout(ctx, db, chassis_module_name, 'up'):
             fabric_module_set_admin_status(db, chassis_module_name, 'up')

doc/Command-Reference.md

@@ -713,6 +713,32 @@ This command displays the cause of the previous reboot
   User issued reboot command [User: admin, Time: Mon Mar 25 01:02:03 UTC 2019]
   ```
 
+```
+Note: The CLI extensions shown in this block are applicable only to smartswitch platforms. When these extensions are used on a regular switch the extension will be ignored and the output will be the same irrespective of the options.
+
+CLI Extensions Applicable to Smartswtich
+  - show reboot-cause all
+  - show reboot-cause history all
+  - show reboot-cause history DPUx
+```
+**show reboot-cause all**
+
+This command displays the cause of the previous reboot for the Switch and the DPUs for which the midplane interfaces are up.
+
+- Usage:
+  ```
+  show reboot-cause all
+  ```
+
+- Example:
+  ```
+  root@MtFuji:~$  show reboot-cause all
+  Device    Name                 Cause                      Time    User
+  --------  -------------------  ----------                 ------  ------
+  NPU       2024_07_24_20_43_22  Power Loss                 N/A     N/A
+  DPU2      2024_07_24_20_43_22  Software causes (Reboot)   N/A     N/A
+  DPU1      2024_07_24_20_43_22  Software causes (Reboot)   N/A     N/A
+  ```
 **show reboot-cause history**
 
 This command displays the history of the previous reboots up to 10 entry
@@ -733,6 +759,42 @@ This command displays the history of the previous reboots up to 10 entry
   2020_10_09_04_53_58  warm-reboot  Fri Oct  9 04:51:47 UTC 2020  admin
   ```
 
+**show reboot-cause history all**
+
+This command displays the history of the previous reboots up to 10 entry of the Switch and the DPUs for which the midplane interfaces are up.
+
+- Usage:
+  ```
+  show reboot-cause history all
+  ```
+
+- Example:
+  ```
+  root@MtFuji:~# show reboot-cause history all
+  Device    Name                 Cause                                      Time                             User    Comment
+  --------  -------------------  -----------------------------------------  -------------------------------  ------  -------
+  NPU       2024_07_23_23_06_57  Kernel Panic                               Tue Jul 23 11:02:27 PM UTC 2024  N/A     N/A
+  NPU       2024_07_23_11_21_32  Power Loss                                 N/A                              N/A     Unknown
+  ```
+
+**show reboot-cause history DPU1**
+
+This command displays the history of the previous reboots up to 10 entry of DPU1. If DPU1 is powered down then there won't be any data in the DB and the "show reboot-cause history DPU1" output will be blank.
+
+- Usage:
+  ```
+  show reboot-cause history DPU1
+  ```
+
+- Example:
+  ```
+  root@MtFuji:~# show reboot-cause history DPU1
+  Device    Name    Cause                                      Time    User    Comment
+  --------  ------  -----------------------------------------  ------  ------  ---------
+  DPU1      DPU1    Software causes (Hardware watchdog reset)  N/A     N/A     N/A
+  ```
+
+
 **show uptime**
 
 This command displays the current system uptime
@@ -11165,6 +11227,36 @@ In addition, displays a list of all current 'Services' and 'Hardware' being moni
   psu.voltage  Ignored   Device
   ```
 
+**show system-health dpu <option>**
+
+This is a smartswitch specific cli.  This cli shows the midplane, control plane and data plane health of the DPU modules in the smartswitch.
+
+This can take two forms of "<option>" 1. DPU module name (ex: DPU0) 2. all, which will list all the DPUs in the smartswitch
+
+- Usage:
+  ```
+  show system-health dpu DPU0
+  ```
+
+- Example:
+  ```
+root@MtFuji-dut:/home/cisco# show system-health dpu DPU0
+Name    Oper-Status    State-Detail             State-Value    Time                             Reason
+------  -------------  -----------------------  -------------  -------------------------------  ------------------------------------------------------------------------------------
+DPU0    Online         dpu_midplane_link_state  up             Mon Dec 23 05:12:17 PM UTC 2024
+                       dpu_control_plane_state  up             Mon Dec 23 05:12:17 PM UTC 2024 All containers are up and running, host-ethlink-status: Uplink1/1 is UP
+                       dpu_data_plane_state     up             Mon Dec 23 05:12:17 PM UTC 2024 DPU container named polaris is running, pdsagent running : OK, pciemgrd running : OK
+
+root@MtFuji-dut:/home/cisco# show system-health dpu all
+Name    Oper-Status    State-Detail             State-Value    Time                             Reason
+------  -------------  -----------------------  -------------  -------------------------------  ------------------------------------------------------------------------------------
+DPU0    Online         dpu_midplane_link_state  up             Mon Dec 23 05:12:17 PM UTC 2024
+                       dpu_control_plane_state  up             Mon Dec 23 05:12:17 PM UTC 2024 All containers are up and running, host-ethlink-status: Uplink1/1 is UP
+                       dpu_data_plane_state     up             Mon Dec 23 05:12:17 PM UTC 2024 DPU container named polaris is running, pdsagent running : OK, pciemgrd running : OK
+DPU1    Online         dpu_midplane_link_state  up             Mon Dec 23 05:12:17 PM UTC 2024
+                       dpu_control_plane_state  up             Mon Dec 23 05:12:17 PM UTC 2024 All containers are up and running, host-ethlink-status: Uplink1/1 is UP
+                       dpu_data_plane_state     up             Mon Dec 23 05:12:17 PM UTC 2024 DPU container named polaris is running, pdsagent running : OK, pciemgrd running : OK
+
 Go Back To [Beginning of the document](#) or [Beginning of this section](#System-Health)
 
 ## VLAN & FDB

show/chassis_modules.py

@@ -2,6 +2,7 @@
 from natsort import natsorted
 from tabulate import tabulate
 from swsscommon.swsscommon import SonicV2Connector
+from utilities_common.chassis import is_smartswitch
 
 import utilities_common.cli as clicommon
 from sonic_py_common import multi_asic
@@ -40,11 +41,11 @@ def status(db, chassis_module_name):
     state_db = SonicV2Connector(host="127.0.0.1")
     state_db.connect(state_db.STATE_DB)
 
-    key_pattern = '*'
+    key_pattern = CHASSIS_MODULE_INFO_TABLE + '|*'
     if chassis_module_name:
-        key_pattern = '|' + chassis_module_name
+        key_pattern = CHASSIS_MODULE_INFO_TABLE + '|' + chassis_module_name
 
-    keys = state_db.keys(state_db.STATE_DB, CHASSIS_MODULE_INFO_TABLE + key_pattern)
+    keys = state_db.keys(state_db.STATE_DB, key_pattern)
     if not keys:
         print('Key {} not found in {} table'.format(key_pattern, CHASSIS_MODULE_INFO_TABLE))
         return
@@ -62,7 +63,10 @@ def status(db, chassis_module_name):
         oper_status = data_dict[CHASSIS_MODULE_INFO_OPERSTATUS_FIELD]
         serial = data_dict[CHASSIS_MODULE_INFO_SERIAL_FIELD]
 
-        admin_status = 'up'
+        if is_smartswitch():
+            admin_status = 'down'
+        else:
+            admin_status = 'up'
         config_data = chassis_cfg_table.get(key_list[1])
         if config_data is not None:
             admin_status = config_data.get(CHASSIS_MODULE_INFO_ADMINSTATUS_FIELD)