SWDEV-504130 Add temperature violation status to amd-smi monitor (#2)
Added boolean temperature violation status to amd-smi monitor. Signed-off-by: Bindhiya Kanangot Balakrishnan <Bindhiya.KanangotBalakrishnan@amd.com>
Bu işleme şunda yer alıyor:
1 ebeveyn
129ad8ffad
işleme
d0e770ffbc
4 files changed
+42
-5
No files matched your search
@@ -5270,6 +5270,7 @@ class AMDSMICommands():
|
||||
violation_status = {
|
||||
"pviol": "N/A",
|
||||
"tviol": "N/A",
|
||||
"tviol_active": "N/A",
|
||||
"phot_tviol": "N/A",
|
||||
"vr_tviol": "N/A",
|
||||
"hbm_tviol": "N/A",
|
||||
@@ -5278,26 +5279,31 @@ class AMDSMICommands():
|
||||
violations = amdsmi_interface.amdsmi_get_violation_status(args.gpu)
|
||||
violation_status['pviol'] = violations['per_ppt_pwr']
|
||||
violation_status['tviol'] = violations['per_socket_thrm']
|
||||
violation_status['tviol_active'] = violations['active_socket_thrm']
|
||||
violation_status['phot_tviol'] = violations['per_prochot_thrm']
|
||||
violation_status['vr_tviol'] = violations['per_vr_thrm']
|
||||
violation_status['hbm_tviol'] = violations['per_hbm_thrm']
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
monitor_values['pviol'] = violation_status['pviol']
|
||||
monitor_values['tviol'] = violation_status['tviol']
|
||||
monitor_values['tviol_active'] = violation_status['tviol_active']
|
||||
monitor_values['phot_tviol'] = violation_status['phot_tviol']
|
||||
monitor_values['vr_tviol'] = violation_status['vr_tviol']
|
||||
monitor_values['hbm_tviol'] = violation_status['hbm_tviol']
|
||||
logging.debug("Failed to get violation status on gpu %s | %s", gpu_id, e.get_error_info())
|
||||
violation_status_unit = "%"
|
||||
kTVIOL_MAX_WIDTH = 10
|
||||
kPVIOL_MAX_WIDTH = 10
|
||||
kTVIOL_MAX_WIDTH = 7
|
||||
kTVIOL_ACTIVE_MAX_WIDTH = 14
|
||||
kPVIOL_MAX_WIDTH = 7
|
||||
kPHOT_MAX_WIDTH = 12
|
||||
kVR_MAX_WIDTH = 10
|
||||
kHBM_MAX_WIDTH = 11
|
||||
|
||||
for key, value in violation_status.items():
|
||||
monitor_values[key] = self.helpers.unit_format(self.logger, violation_status[key], violation_status_unit)
|
||||
|
||||
if key == "tviol_active":
|
||||
monitor_values[key] = value
|
||||
elif key != "tviol_active":
|
||||
monitor_values[key] = self.helpers.unit_format(self.logger, violation_status[key], violation_status_unit)
|
||||
if self.logger.is_human_readable_format():
|
||||
monitor_values['pviol'] = monitor_values['pviol'].rjust(kPVIOL_MAX_WIDTH, ' ')
|
||||
monitor_values['tviol'] = monitor_values['tviol'].rjust(kTVIOL_MAX_WIDTH, ' ')
|
||||
@@ -5306,6 +5312,7 @@ class AMDSMICommands():
|
||||
monitor_values['hbm_tviol'] = monitor_values['hbm_tviol'].rjust(kHBM_MAX_WIDTH, ' ')
|
||||
self.logger.table_header += 'PVIOL'.rjust(kPVIOL_MAX_WIDTH, ' ')
|
||||
self.logger.table_header += 'TVIOL'.rjust(kTVIOL_MAX_WIDTH, ' ')
|
||||
self.logger.table_header += 'TVIOL_ACTIVE'.rjust(kTVIOL_ACTIVE_MAX_WIDTH, ' ')
|
||||
self.logger.table_header += 'PHOT_TVIOL'.rjust(kPHOT_MAX_WIDTH, ' ')
|
||||
self.logger.table_header += 'VR_TVIOL'.rjust(kVR_MAX_WIDTH, ' ')
|
||||
self.logger.table_header += 'HBM_TVIOL'.rjust(kHBM_MAX_WIDTH, ' ')
|
||||
|
||||
@@ -170,6 +170,16 @@ class AMDSMILogger():
|
||||
table_values += string_value.ljust(18)
|
||||
elif key == "RW":
|
||||
table_values += string_value.ljust(57)
|
||||
elif key in ('pviol', 'tviol'):
|
||||
table_values += string_value.rjust(7)
|
||||
elif key == "tviol_active":
|
||||
table_values += string_value.rjust(14)
|
||||
elif key == "phot_tviol":
|
||||
table_values += string_value.rjust(12)
|
||||
elif key == "vr_tviol":
|
||||
table_values += string_value.rjust(10)
|
||||
elif key == "hbm_tviol":
|
||||
table_values += string_value.rjust(11)
|
||||
elif key == "process_list":
|
||||
#Add an additional padding between the first instance of GPU and NAME
|
||||
table_values += ' '
|
||||
|
||||
Reference in new issue
Bir kullanıcı engelle