AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixed log handling and exceptions

Browse Source 
Updated exceptions
	Added driver load exception
	Fixed logging override by removing previous log handlers
	Updated debug output to use gpu_id vs C-pointer
	Removed AmdSmiRetcode class in favor of using the wrapper
directly
	Added traceback limits for clean errors (Not in debug)

Change-Id: Ia02bb842b8f60d9ab4b68b7f8b1afda30b1c021c
Signed-off-by: Maisam Arif <maisarif@amd.com>
This commit is contained in:
Maisam Arif
2023-09-24 16:12:30 -05:00
parent db3e119f7d
commit 9281bfbbfa
8 changed files with 188 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files
amdsmi_cli/README.md
+9 -9
View File
@@ -102,7 +102,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
``` bash
@@ -123,7 +123,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -153,7 +153,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -176,7 +176,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -215,7 +215,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -245,7 +245,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -271,7 +271,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -296,7 +296,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
```bash
@@ -323,7 +323,7 @@ Command Modifiers:
--json Displays output in JSON format (human readable by default).
--csv Displays output in CSV format (human readable by default).
--file FILE Saves output into a file on the provided path (stdout by default).
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands
--loglevel {DEBUG,INFO,WARNING,ERROR,CRITICAL} Set the logging level for the parser commands (ERROR by default).
```
## Disclaimer
amdsmi_cli/amdsmi_cli.py
+16 -8
View File
@@ -66,14 +66,22 @@ if __name__ == "__main__":
amd_smi_commands.logger.format = amd_smi_commands.logger.LoggerFormat.csv.value
if args.file:
amd_smi_commands.logger.destination = args.file
if args.loglevel:
logging_dict = {'DEBUG' : logging.DEBUG,
'INFO' : logging.INFO,
'WARNING': logging.WARNING,
'ERROR': logging.ERROR,
'CRITICAL': logging.CRITICAL}
# Enable debug logs on amdsmi library ie. RSMI_LOGGING = 1 in environment or otherwise
logging.basicConfig(format='%(levelname)s: %(message)s', level=logging_dict[args.loglevel])
# Remove previous log handlers
for handler in logging.root.handlers[:]:
logging.root.removeHandler(handler)
logging_dict = {'DEBUG' : logging.DEBUG,
'INFO' : logging.INFO,
'WARNING': logging.WARNING,
'ERROR': logging.ERROR,
'CRITICAL': logging.CRITICAL}
# To enable debug logs on rocm-smi library set RSMI_LOGGING = 1 in environment
logging.basicConfig(format='%(levelname)s: %(message)s', level=logging_dict[args.loglevel])
# Disable traceback for non-debug log levels
if args.loglevel != "DEBUG":
sys.tracebacklimit = -1
# Execute subcommands
args.func(args)
amdsmi_cli/amdsmi_commands.py
+114 -75
View File
@@ -191,6 +191,9 @@ class AMDSMICommands():
static_dict = {}
# Get gpu_id for logging
gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
if args.asic:
try:
asic_info = amdsmi_interface.amdsmi_get_gpu_asic_info(args.gpu)
@@ -203,7 +206,7 @@ class AMDSMICommands():
static_dict['asic'] = asic_info
except amdsmi_exception.AmdSmiLibraryException as e:
static_dict['asic'] = "N/A"
logging.debug("Failed to get asic info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get asic info for gpu %s | %s", gpu_id, e.get_error_info())
if args.bus:
bus_output_info = {}
@@ -239,13 +242,13 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
bus_info = "N/A"
logging.debug("Failed to get bus info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get bus info for gpu %s | %s", gpu_id, e.get_error_info())
try:
bus_output_info['bdf'] = amdsmi_interface.amdsmi_get_gpu_device_bdf(args.gpu)
except amdsmi_exception.AmdSmiLibraryException as e:
bus_output_info['bdf'] = "N/A"
logging.debug("Failed to get bdf for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get bdf for gpu %s | %s", gpu_id, e.get_error_info())
bus_output_info.update(bus_info)
static_dict['bus'] = bus_output_info
@@ -255,7 +258,7 @@ class AMDSMICommands():
static_dict['vbios'] = vbios_info
except amdsmi_exception.AmdSmiLibraryException as e:
static_dict['vbios'] = "N/A"
logging.debug("Failed to get vbios info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get vbios info for gpu %s | %s", gpu_id, e.get_error_info())
if self.helpers.is_linux() and self.helpers.is_baremetal():
if args.board:
@@ -271,7 +274,7 @@ class AMDSMICommands():
static_dict['board'] = board_info
except amdsmi_exception.AmdSmiLibraryException as e:
static_dict['board'] = "N/A"
logging.debug("Failed to get board info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get board info for gpu %s | %s", gpu_id, e.get_error_info())
if args.limit:
# Power limits
try:
@@ -283,7 +286,7 @@ class AMDSMICommands():
power_limit_error = True
max_power_limit = "N/A"
current_power_limit = "N/A"
logging.debug("Failed to get power cap info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get power cap info for gpu %s | %s", gpu_id, e.get_error_info())
# Edge temperature limits
try:
@@ -293,7 +296,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
slowdown_temp_edge_limit_error = True
slowdown_temp_edge_limit = "N/A"
logging.debug("Failed to get edge temperature slowdown metric for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get edge temperature slowdown metric for gpu %s | %s", gpu_id, e.get_error_info())
if slowdown_temp_edge_limit == 0:
slowdown_temp_edge_limit_error = True
@@ -306,7 +309,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
shutdown_temp_edge_limit_error = True
shutdown_temp_edge_limit = "N/A"
logging.debug("Failed to get edge temperature shutdown metrics for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get edge temperature shutdown metrics for gpu %s | %s", gpu_id, e.get_error_info())
if shutdown_temp_edge_limit == 0:
shutdown_temp_edge_limit_error = True
@@ -320,7 +323,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
slowdown_temp_hotspot_limit_error = True
slowdown_temp_hotspot_limit = "N/A"
logging.debug("Failed to get hotspot temperature slowdown metrics for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get hotspot temperature slowdown metrics for gpu %s | %s", gpu_id, e.get_error_info())
try:
shutdown_temp_hotspot_limit_error = False
@@ -329,7 +332,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
shutdown_temp_hotspot_limit_error = True
shutdown_temp_hotspot_limit = "N/A"
logging.debug("Failed to get hotspot temperature shutdown metrics for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get hotspot temperature shutdown metrics for gpu %s | %s", gpu_id, e.get_error_info())
# VRAM temperature limits
@@ -340,7 +343,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
slowdown_temp_vram_limit_error = True
slowdown_temp_vram_limit = "N/A"
logging.debug("Failed to get vram temperature slowdown metrics for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get vram temperature slowdown metrics for gpu %s | %s", gpu_id, e.get_error_info())
try:
shutdown_temp_vram_limit_error = False
@@ -349,7 +352,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
shutdown_temp_vram_limit_error = True
shutdown_temp_vram_limit = "N/A"
logging.debug("Failed to get vram temperature shutdown metrics for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get vram temperature shutdown metrics for gpu %s | %s", gpu_id, e.get_error_info())
if self.logger.is_human_readable_format():
unit = 'W'
@@ -392,7 +395,7 @@ class AMDSMICommands():
static_dict['driver'] = driver_info
except amdsmi_exception.AmdSmiLibraryException as e:
static_dict['driver'] = "N/A"
logging.debug("Failed to get driver info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get driver info for gpu %s | %s", gpu_id, e.get_error_info())
if self.helpers.is_hypervisor() or self.helpers.is_baremetal():
if args.ras:
@@ -400,7 +403,7 @@ class AMDSMICommands():
static_dict['ras'] = amdsmi_interface.amdsmi_get_gpu_ras_block_features_enabled(args.gpu)
except amdsmi_exception.AmdSmiLibraryException as e:
static_dict['ras'] = "N/A"
logging.debug("Failed to get ras block features for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get ras block features for gpu %s | %s", gpu_id, e.get_error_info())
if args.vram:
try:
vram_info = amdsmi_interface.amdsmi_get_gpu_vram_info(args.gpu)
@@ -417,7 +420,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
vram_info = "N/A"
logging.debug("Failed to get vram info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get vram info for gpu %s | %s", gpu_id, e.get_error_info())
static_dict['vram'] = vram_info
@@ -427,13 +430,13 @@ class AMDSMICommands():
numa_node_number = amdsmi_interface.amdsmi_topo_get_numa_node_number(args.gpu)
except amdsmi_exception.AmdSmiLibraryException as e:
numa_node_number = "N/A"
logging.debug("Failed to get numa node number for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get numa node number for gpu %s | %s", gpu_id, e.get_error_info())
try:
numa_affinity = amdsmi_interface.amdsmi_get_gpu_topo_numa_affinity(args.gpu)
except amdsmi_exception.AmdSmiLibraryException as e:
numa_affinity = "N/A"
logging.debug("Failed to get numa affinity for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get numa affinity for gpu %s | %s", gpu_id, e.get_error_info())
static_dict['numa'] = {'node' : numa_node_number,
'affinity' : numa_affinity}
@@ -500,6 +503,10 @@ class AMDSMICommands():
args.gpu = device_handle
fw_list = {}
# Get gpu_id for logging
gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
if args.fw_list:
try:
fw_info = amdsmi_interface.amdsmi_get_fw_info(args.gpu)
@@ -519,7 +526,7 @@ class AMDSMICommands():
fw_list.update(fw_info)
except amdsmi_exception.AmdSmiLibraryException as e:
fw_list['fw_list'] = "N/A"
logging.debug("Failed to get firmware info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get firmware info for gpu %s | %s", gpu_id, e.get_error_info())
multiple_devices_csv_override = False
# Convert and store output by pid for csv format
@@ -586,13 +593,16 @@ class AMDSMICommands():
values_dict = {}
bad_page_err_output = ''
# Get gpu_id for logging
gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
try:
bad_page_info = amdsmi_interface.amdsmi_get_gpu_bad_page_info(args.gpu)
bad_page_error = False
except amdsmi_exception.AmdSmiLibraryException as e:
bad_page_error = True
bad_page_err_output = "N/A"
logging.debug("Failed to get bad page info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get bad page info for gpu %s | %s", gpu_id, e.get_error_info())
if bad_page_info == "No bad pages found.":
bad_page_error = True
@@ -798,6 +808,10 @@ class AMDSMICommands():
# Add timestamp and store values for specified arguments
values_dict = {}
# Get gpu_id for logging
gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
if self.helpers.is_linux() and self.helpers.is_baremetal():
if args.usage:
try:
@@ -818,7 +832,7 @@ class AMDSMICommands():
values_dict['usage'] = engine_usage
except amdsmi_exception.AmdSmiLibraryException as e:
values_dict['usage'] = "N/A"
logging.debug("Failed to get gpu activity for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get gpu activity for gpu %s | %s", gpu_id, e.get_error_info())
if args.power:
power_dict = {'current_power': "N/A",
'current_gfx_voltage': "N/A",
@@ -845,7 +859,7 @@ class AMDSMICommands():
power_dict['power_limit'] = power_info['power_limit']
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get power info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get power info for gpu %s | %s", gpu_id, e.get_error_info())
try:
is_power_management_enabled = amdsmi_interface.amdsmi_is_gpu_power_management_enabled(args.gpu)
@@ -854,7 +868,7 @@ class AMDSMICommands():
else:
power_dict['power_management'] = "DISABLED"
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get power management status for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get power management status for gpu %s | %s", gpu_id, e.get_error_info())
values_dict['power'] = power_dict
if args.clock:
@@ -870,20 +884,20 @@ class AMDSMICommands():
clocks['gfx'] = gfx_clock
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get gfx clock info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get gfx clock info for gpu %s | %s", gpu_id, e.get_error_info())
try:
# is_clk_locked = amdsmi_interface.amdsmi_is_clk_locked(args.gpu, amdsmi_interface.AmdSmiClkType.GFX)
is_clk_locked = "N/A"
except amdsmi_exception.AmdSmiLibraryException as e:
is_clk_locked = "N/A"
logging.debug("Failed to get gfx clock lock status info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get gfx clock lock status info for gpu %s | %s", gpu_id, e.get_error_info())
if isinstance(clocks['gfx'], dict):
clocks['gfx']['is_clk_locked'] = is_clk_locked
else:
clocks['gfx'] = {'is_clk_locked': is_clk_locked}
try:
mem_clock = amdsmi_interface.amdsmi_get_clock_info(args.gpu, amdsmi_interface.AmdSmiClkType.MEM)
@@ -894,7 +908,7 @@ class AMDSMICommands():
clocks['mem'] = mem_clock
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get mem clock info for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get mem clock info for gpu %s | %s", gpu_id, e.get_error_info())
values_dict['clock'] = clocks
if args.temperature:
@@ -903,14 +917,14 @@ class AMDSMICommands():
args.gpu, amdsmi_interface.AmdSmiTemperatureType.EDGE, amdsmi_interface.AmdSmiTemperatureMetric.CURRENT)
except amdsmi_exception.AmdSmiLibraryException as e:
temperature_edge_current = "N/A"
logging.debug("Failed to get current edge temperature for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get current edge temperature for gpu %s | %s", gpu_id, e.get_error_info())
try:
temperature_edge_limit = amdsmi_interface.amdsmi_get_temp_metric(
args.gpu, amdsmi_interface.AmdSmiTemperatureType.EDGE, amdsmi_interface.AmdSmiTemperatureMetric.CRITICAL)
except amdsmi_exception.AmdSmiLibraryException as e:
temperature_edge_limit = "N/A"
logging.debug("Failed to get edge temperature limit for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get edge temperature limit for gpu %s | %s", gpu_id, e.get_error_info())
# If edge limit is reporting 0 then set the current edge temp to N/A
if temperature_edge_limit == 0:
@@ -921,14 +935,14 @@ class AMDSMICommands():
args.gpu, amdsmi_interface.AmdSmiTemperatureType.HOTSPOT, amdsmi_interface.AmdSmiTemperatureMetric.CURRENT)
except amdsmi_exception.AmdSmiLibraryException as e:
temperature_hotspot_current = "N/A"
logging.debug("Failed to get current hotspot temperature for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get current hotspot temperature for gpu %s | %s", gpu_id, e.get_error_info())
try:
temperature_vram_current = amdsmi_interface.amdsmi_get_temp_metric(
args.gpu, amdsmi_interface.AmdSmiTemperatureType.VRAM, amdsmi_interface.AmdSmiTemperatureMetric.CURRENT)
except amdsmi_exception.AmdSmiLibraryException as e:
temperature_vram_current = "N/A"
logging.debug("Failed to get current vram temperature for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get current vram temperature for gpu %s | %s", gpu_id, e.get_error_info())
temperatures = {'edge': temperature_edge_current,
'hotspot': temperature_hotspot_current,
@@ -950,7 +964,7 @@ class AMDSMICommands():
except amdsmi_exception.AmdSmiLibraryException as e:
ecc_count['correctable'] = "N/A"
ecc_count['uncorrectable'] = "N/A"
logging.debug("Failed to get ecc count for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get ecc count for gpu %s | %s", gpu_id, e.get_error_info())
values_dict['ecc'] = ecc_count
if args.ecc_block:
@@ -966,14 +980,14 @@ class AMDSMICommands():
'uncorrectable': ecc_count['uncorrectable_count']}
except amdsmi_exception.AmdSmiLibraryException as e:
ecc_count = "N/A"
logging.debug("Failed to get ecc count for gpu %s at block %s | %s", args.gpu, gpu_block, e.get_error_info())
logging.debug("Failed to get ecc count for gpu %s at block %s | %s", gpu_id, gpu_block, e.get_error_info())
ecc_dict[state['block']] = {'correctable' : ecc_count,
'uncorrectable': ecc_count}
values_dict['ecc_block'] = ecc_dict
except amdsmi_exception.AmdSmiLibraryException as e:
values_dict['ecc_block'] = "N/A"
logging.debug("Failed to get ecc block features for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get ecc block features for gpu %s | %s", gpu_id, e.get_error_info())
if args.pcie:
pcie_dict = {'current_width': "N/A",
'current_speed': "N/A",
@@ -997,13 +1011,13 @@ class AMDSMICommands():
unit = 'GT/s'
pcie_link_status['current_speed'] = f"{pcie_link_status['pcie_speed']} {unit}"
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get pcie link status for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get pcie link status for gpu %s | %s", gpu_id, e.get_error_info())
try:
pci_replay_counter = amdsmi_interface.amdsmi_get_gpu_pci_replay_counter(args.gpu)
pcie_dict['replay_count'] = pci_replay_counter
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get pci replay counter for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get pci replay counter for gpu %s | %s", gpu_id, e.get_error_info())
try:
pcie_bw = amdsmi_interface.amdsmi_get_gpu_pci_throughput(args.gpu)
@@ -1024,7 +1038,7 @@ class AMDSMICommands():
pcie_dict['current_bandwith_received'] = received
pcie_dict['max_packet_size'] = pcie_bw['max_pkt_sz']
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get pcie bandwidth for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get pcie bandwidth for gpu %s | %s", gpu_id, e.get_error_info())
values_dict['pcie'] = pcie_dict
if args.fan:
@@ -1077,7 +1091,7 @@ class AMDSMICommands():
values_dict['voltage_curve'] = voltage_point_dict
except amdsmi_exception.AmdSmiLibraryException as e:
values_dict['voltage_curve'] = "N/A"
logging.debug("Failed to get voltage curve for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get voltage curve for gpu %s | %s", gpu_id, e.get_error_info())
if args.overdrive:
try:
overdrive_level = amdsmi_interface.amdsmi_get_gpu_overdrive_level(args.gpu)
@@ -1089,14 +1103,14 @@ class AMDSMICommands():
values_dict['overdrive'] = overdrive_level
except amdsmi_exception.AmdSmiLibraryException as e:
values_dict['overdrive'] = "N/A"
logging.debug("Failed to get overdrive level for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get overdrive level for gpu %s | %s", gpu_id, e.get_error_info())
if args.perf_level:
try:
perf_level = amdsmi_interface.amdsmi_get_gpu_perf_level(args.gpu)
values_dict['perf_level'] = perf_level
except amdsmi_exception.AmdSmiLibraryException as e:
values_dict['perf_level'] = "N/A"
logging.debug("Failed to get perf level for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get perf level for gpu %s | %s", gpu_id, e.get_error_info())
if self.helpers.is_linux() and self.helpers.is_baremetal():
if args.xgmi_err:
@@ -1104,7 +1118,7 @@ class AMDSMICommands():
values_dict['xgmi_err'] = amdsmi_interface.amdsmi_gpu_xgmi_error_status(args.gpu)
except amdsmi_interface.AmdSmiLibraryException as e:
values_dict['xgmi_err'] = "N/A"
logging.debug("Failed to get xgmi error status for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get xgmi error status for gpu %s | %s", gpu_id, e.get_error_info())
if args.energy:
try:
energy_dict = amdsmi_interface.amdsmi_get_energy_count(args.gpu)
@@ -1140,19 +1154,19 @@ class AMDSMICommands():
total_vram = amdsmi_interface.amdsmi_get_gpu_memory_total(args.gpu, amdsmi_interface.AmdSmiMemoryType.VRAM)
memory_usage['total_vram'] = total_vram // (1024*1024)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get total VRAM memory for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get total VRAM memory for gpu %s | %s", gpu_id, e.get_error_info())
try:
total_visible_vram = amdsmi_interface.amdsmi_get_gpu_memory_total(args.gpu, amdsmi_interface.AmdSmiMemoryType.VIS_VRAM)
memory_usage['total_visible_vram'] = total_visible_vram // (1024*1024)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get total VIS VRAM memory for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get total VIS VRAM memory for gpu %s | %s", gpu_id, e.get_error_info())
try:
total_gtt = amdsmi_interface.amdsmi_get_gpu_memory_total(args.gpu, amdsmi_interface.AmdSmiMemoryType.GTT)
memory_usage['total_gtt'] = total_gtt // (1024*1024)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get total GTT memory for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get total GTT memory for gpu %s | %s", gpu_id, e.get_error_info())
# Used VRAM
try:
@@ -1160,19 +1174,19 @@ class AMDSMICommands():
memory_usage['used_vram'] = used_vram // (1024*1024)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get used VRAM memory for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get used VRAM memory for gpu %s | %s", gpu_id, e.get_error_info())
try:
used_visible_vram = amdsmi_interface.amdsmi_get_gpu_memory_usage(args.gpu, amdsmi_interface.AmdSmiMemoryType.VIS_VRAM)
memory_usage['used_visible_vram'] = used_visible_vram // (1024*1024)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get used VIS VRAM memory for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get used VIS VRAM memory for gpu %s | %s", gpu_id, e.get_error_info())
try:
used_gtt = amdsmi_interface.amdsmi_get_gpu_memory_usage(args.gpu, amdsmi_interface.AmdSmiMemoryType.GTT)
memory_usage['used_gtt'] = used_gtt // (1024*1024)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get used GTT memory for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get used GTT memory for gpu %s | %s", gpu_id, e.get_error_info())
# Free VRAM
if memory_usage['total_vram'] != "N/A" and memory_usage['used_vram'] != "N/A":
@@ -1288,11 +1302,14 @@ class AMDSMICommands():
else:
raise IndexError("args.gpu should not be an empty list")
# Get gpu_id for logging
gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
# Populate initial processes
try:
process_list = amdsmi_interface.amdsmi_get_gpu_process_list(args.gpu)
except amdsmi_exception.AmdSmiLibraryException as e:
logging.debug("Failed to get process list for gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to get process list for gpu %s | %s", gpu_id, e.get_error_info())
raise e
filtered_process_values = []
@@ -1301,7 +1318,7 @@ class AMDSMICommands():
process_info = amdsmi_interface.amdsmi_get_gpu_process_info(args.gpu, process_handle)
except amdsmi_exception.AmdSmiLibraryException as e:
process_info = "N/A"
logging.debug("Failed to get process info for gpu %s on process_handle %s | %s", args.gpu, process_handle, e.get_error_info())
logging.debug("Failed to get process info for gpu %s on process_handle %s | %s", gpu_id, process_handle, e.get_error_info())
filtered_process_values.append({'process_info': process_info})
continue
@@ -1467,7 +1484,10 @@ class AMDSMICommands():
src_gpu_links[dest_gpu_key] = bool(dest_gpu_link_status)
except amdsmi_exception.AmdSmiLibraryException as e:
src_gpu_links[dest_gpu_key] = "N/A"
logging.debug("Failed to get link status for %s to %s | %s", src_gpu, dest_gpu, e.get_error_info())
logging.debug("Failed to get link status for %s to %s | %s",
self.helpers.get_gpu_id_from_device_handle(src_gpu),
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
e.get_error_info())
topo_values[src_gpu_index]['link_accessibility'] = src_gpu_links
@@ -1487,7 +1507,10 @@ class AMDSMICommands():
src_gpu_weight[dest_gpu_key] = dest_gpu_link_weight
except amdsmi_exception.AmdSmiLibraryException as e:
src_gpu_weight[dest_gpu_key] = "N/A"
logging.debug("Failed to get link weight for %s to %s | %s", src_gpu, dest_gpu, e.get_error_info())
logging.debug("Failed to get link weight for %s to %s | %s",
self.helpers.get_gpu_id_from_device_handle(src_gpu),
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
e.get_error_info())
topo_values[src_gpu_index]['weight'] = src_gpu_weight
@@ -1507,7 +1530,10 @@ class AMDSMICommands():
src_gpu_hops[dest_gpu_key] = dest_gpu_hops
except amdsmi_exception.AmdSmiLibraryException as e:
src_gpu_hops[dest_gpu_key] = "N/A"
logging.debug("Failed to get link hops for %s to %s | %s", src_gpu, dest_gpu, e.get_error_info())
logging.debug("Failed to get link hops for %s to %s | %s",
self.helpers.get_gpu_id_from_device_handle(src_gpu),
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
e.get_error_info())
topo_values[src_gpu_index]['hops'] = src_gpu_hops
@@ -1532,7 +1558,10 @@ class AMDSMICommands():
src_gpu_link_type[dest_gpu_key] = "XGMI"
except amdsmi_exception.AmdSmiLibraryException as e:
src_gpu_link_type[dest_gpu_key] = "N/A"
logging.debug("Failed to get link type for %s to %s | %s", src_gpu, dest_gpu, e.get_error_info())
logging.debug("Failed to get link type for %s to %s | %s",
self.helpers.get_gpu_id_from_device_handle(src_gpu),
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
e.get_error_info())
topo_values[src_gpu_index]['link_type'] = src_gpu_link_type
@@ -1556,7 +1585,10 @@ class AMDSMICommands():
continue
except amdsmi_exception.AmdSmiLibraryException as e:
src_gpu_link_type[dest_gpu_key] = "N/A"
logging.debug("Failed to get link type for %s to %s | %s", src_gpu, dest_gpu, e.get_error_info())
logging.debug("Failed to get link type for %s to %s | %s",
self.helpers.get_gpu_id_from_device_handle(src_gpu),
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
e.get_error_info())
try:
min_bw = amdsmi_interface.amdsmi_get_minmax_bandwidth_between_processors(src_gpu, dest_gpu)['min_bandwidth']
@@ -1565,6 +1597,10 @@ class AMDSMICommands():
src_gpu_link_type[dest_gpu_key] = f'{min_bw}-{max_bw}'
except amdsmi_exception.AmdSmiLibraryException as e:
src_gpu_link_type[dest_gpu_key] = e.get_error_info()
logging.debug("Failed to get min max bandwidth for %s to %s | %s",
self.helpers.get_gpu_id_from_device_handle(src_gpu),
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
e.get_error_info())
topo_values[src_gpu_index]['numa_bandwidth'] = src_gpu_link_type
@@ -1638,7 +1674,7 @@ class AMDSMICommands():
try:
amdsmi_interface.amdsmi_set_gpu_fan_speed(args.gpu, 0, args.fan)
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
raise ValueError(f"Unable to set fan speed {args.fan} on {gpu_string}") from e
@@ -1648,7 +1684,7 @@ class AMDSMICommands():
try:
amdsmi_interface.amdsmi_set_gpu_perf_level(args.gpu, perf_level)
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
raise ValueError(f"Unable to set performance level {args.perflevel} on {gpu_string}") from e
@@ -1659,7 +1695,7 @@ class AMDSMICommands():
try:
amdsmi_interface.amdsmi_set_gpu_perf_determinism_mode(args.gpu, args.perfdeterminism)
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
raise ValueError(f"Unable to set performance determinism and clock frequency to {args.perfdeterminism} on {gpu_string}") from e
@@ -1721,13 +1757,16 @@ class AMDSMICommands():
args.gpu = device_handle
# Get gpu_id for logging
gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
if args.gpureset:
if self.helpers.is_amd_device(args.gpu):
try:
amdsmi_interface.amdsmi_reset_gpu(args.gpu)
result = 'Successfully reset GPU'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
result = "Failed to reset GPU"
else:
@@ -1742,30 +1781,30 @@ class AMDSMICommands():
amdsmi_interface.amdsmi_set_gpu_overdrive_level(args.gpu, 0)
reset_clocks_results['overdrive'] = 'Overdrive set to 0'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
reset_clocks_results['overdrive'] = "N/A"
logging.debug("Failed to reset overdrive on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset overdrive on gpu %s | %s", gpu_id, e.get_error_info())
try:
level_auto = amdsmi_interface.AmdSmiDevPerfLevel.AUTO
amdsmi_interface.amdsmi_set_gpu_perf_level(args.gpu, level_auto)
reset_clocks_results['clocks'] = 'Successfully reset clocks'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
reset_clocks_results['clocks'] = "N/A"
logging.debug("Failed to reset perf level on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset perf level on gpu %s | %s", gpu_id, e.get_error_info())
try:
level_auto = amdsmi_interface.AmdSmiDevPerfLevel.AUTO
amdsmi_interface.amdsmi_set_gpu_perf_level(args.gpu, level_auto)
reset_clocks_results['performance'] = 'Performance level reset to auto'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
reset_clocks_results['performance'] = "N/A"
logging.debug("Failed to reset perf level on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset perf level on gpu %s | %s", gpu_id, e.get_error_info())
self.logger.store_output(args.gpu, 'reset_clocks', reset_clocks_results)
if args.fans:
@@ -1773,10 +1812,10 @@ class AMDSMICommands():
amdsmi_interface.amdsmi_reset_gpu_fan(args.gpu, 0)
result = 'Successfully reset fan speed to driver control'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
result = "N/A"
logging.debug("Failed to reset fans on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset fans on gpu %s | %s", gpu_id, e.get_error_info())
self.logger.store_output(args.gpu, 'reset_fans', result)
if args.profile:
@@ -1787,20 +1826,20 @@ class AMDSMICommands():
amdsmi_interface.amdsmi_set_gpu_power_profile(args.gpu, 0, power_profile_mask)
reset_profile_results['power_profile'] = 'Successfully reset Power Profile'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
reset_profile_results['power_profile'] = "N/A"
logging.debug("Failed to reset power profile on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset power profile on gpu %s | %s", gpu_id, e.get_error_info())
try:
level_auto = amdsmi_interface.AmdSmiDevPerfLevel.AUTO
amdsmi_interface.amdsmi_set_gpu_perf_level(args.gpu, level_auto)
reset_profile_results['performance_level'] = 'Successfully reset Performance Level'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
reset_profile_results['performance_level'] = "N/A"
logging.debug("Failed to reset perf level on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset perf level on gpu %s | %s", gpu_id, e.get_error_info())
self.logger.store_output(args.gpu, 'reset_profile', reset_profile_results)
if args.xgmierr:
@@ -1808,10 +1847,10 @@ class AMDSMICommands():
amdsmi_interface.amdsmi_reset_gpu_xgmi_error(args.gpu)
result = 'Successfully reset XGMI Error count'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
result = "N/A"
logging.debug("Failed to reset xgmi error count on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to reset xgmi error count on gpu %s | %s", gpu_id, e.get_error_info())
self.logger.store_output(args.gpu, 'reset_xgmi_err', result)
if args.perfdeterminism:
try:
@@ -1819,10 +1858,10 @@ class AMDSMICommands():
amdsmi_interface.amdsmi_set_gpu_perf_level(args.gpu, level_auto)
result = 'Successfully disabled performance determinism'
except amdsmi_exception.AmdSmiLibraryException as e:
if e.get_error_code() == amdsmi_exception.AmdSmiRetCode.STATUS_NO_PERM:
if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
raise PermissionError('Command requires elevation') from e
result = "N/A"
logging.debug("Failed to set perf level on gpu %s | %s", args.gpu, e.get_error_info())
logging.debug("Failed to set perf level on gpu %s | %s", gpu_id, e.get_error_info())
self.logger.store_output(args.gpu, 'reset_perf_determinism', result)
@@ -1857,7 +1896,7 @@ class AMDSMICommands():
commands.logger.store_output(device, 'values', values_dict)
commands.logger.print_output()
except amdsmi_exception.AmdSmiLibraryException as e:
if e.err_code != amdsmi_exception.AmdSmiRetCode.STATUS_NO_DATA:
if e.err_code != amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_DATA:
print(e)
except Exception as e:
print(e)
amdsmi_cli/amdsmi_init.py
+3 -2
View File
@@ -37,6 +37,8 @@ from amdsmi import amdsmi_exception
# Using basic python logging for user errors and development
logging.basicConfig(format='%(levelname)s: %(message)s', level=logging.ERROR) # User level logging
# This traceback limit only affects this file, once the code hit's the cli portion it get's reset to the user's preference
sys.tracebacklimit = -1 # Disable traceback for user errors
# On initial import set initialized variable
AMDSMI_INITIALIZED = False
@@ -66,8 +68,7 @@ def init_amdsmi(flag=amdsmi_interface.AmdSmiInitFlags.INIT_AMD_GPUS):
amdsmi_interface.amdsmi_init(flag)
except (amdsmi_interface.AmdSmiLibraryException, amdsmi_interface.AmdSmiParameterException) as err:
raise err
logging.info('AMDSMI initialized successfully') # without errors really
logging.debug('AMDSMI initialized successfully')
else:
logging.error('Driver not initialized (amdgpu not found in modules)')
exit(-1)
amdsmi_cli/amdsmi_parser.py
+1 -1
View File
@@ -209,7 +209,7 @@ class AMDSMIParser(argparse.ArgumentParser):
json_help = "Displays output in JSON format (human readable by default)."
csv_help = "Displays output in CSV format (human readable by default)."
file_help = "Saves output into a file on the provided path (stdout by default)."
loglevel_help = "Set the logging level for the parser commands"
loglevel_help = "Set the logging level for the parser commands (ERROR by default)."
command_modifier_group = subcommand_parser.add_argument_group('Command Modifiers')
py-interface/README.md
+1 -1
View File
@@ -60,7 +60,7 @@ try:
print("No GPUs on machine")
except AmdSmiException as e:
print("Error code: {}".format(e.err_code))
if e.err_code == AmdSmiRetCode.STATUS_RETRY:
if e.err_code == amdsmi_wrapper.AMDSMI_STATUS_RETRY:
print("Error info: {}".format(e.err_info))
```
py-interface/__init__.py
-1
View File
@@ -194,4 +194,3 @@ from .amdsmi_exception import AmdSmiKeyException
from .amdsmi_exception import AmdSmiBdfFormatException
from .amdsmi_exception import AmdSmiTimeoutException
from .amdsmi_exception import AmdSmiException
from .amdsmi_exception import AmdSmiRetCode
py-interface/amdsmi_exception.py
+44 -60
View File
@@ -22,40 +22,9 @@
from enum import IntEnum
from . import amdsmi_wrapper
class AmdSmiRetCode(IntEnum):
SUCCESS = amdsmi_wrapper.AMDSMI_STATUS_SUCCESS
STATUS_INVAL = amdsmi_wrapper.AMDSMI_STATUS_INVAL
STATUS_NOT_SUPPORTED = amdsmi_wrapper.AMDSMI_STATUS_NOT_SUPPORTED
STATUS_FILE_ERROR = amdsmi_wrapper.AMDSMI_STATUS_FILE_ERROR
STATUS_NO_PERM = amdsmi_wrapper.AMDSMI_STATUS_NO_PERM
STATUS_OUT_OF_RESOURCES = amdsmi_wrapper.AMDSMI_STATUS_OUT_OF_RESOURCES
STATUS_INTERNAL_EXCEPTION = amdsmi_wrapper.AMDSMI_STATUS_INTERNAL_EXCEPTION
STATUS_INPUT_OUT_OF_BOUNDS = amdsmi_wrapper.AMDSMI_STATUS_INPUT_OUT_OF_BOUNDS
STATUS_INIT_ERROR = amdsmi_wrapper.AMDSMI_STATUS_INIT_ERROR
STATUS_NOT_YET_IMPLEMENTED = amdsmi_wrapper.AMDSMI_STATUS_NOT_YET_IMPLEMENTED
STATUS_NOT_FOUND = amdsmi_wrapper.AMDSMI_STATUS_NOT_FOUND
STATUS_INSUFFICIENT_SIZE = amdsmi_wrapper.AMDSMI_STATUS_INSUFFICIENT_SIZE
STATUS_INTERRUPT = amdsmi_wrapper.AMDSMI_STATUS_INTERRUPT
STATUS_UNEXPECTED_SIZE = amdsmi_wrapper.AMDSMI_STATUS_UNEXPECTED_SIZE
STATUS_NO_DATA = amdsmi_wrapper.AMDSMI_STATUS_NO_DATA
STATUS_UNEXPECTED_DATA = amdsmi_wrapper.AMDSMI_STATUS_UNEXPECTED_DATA
STATUS_BUSY = amdsmi_wrapper.AMDSMI_STATUS_BUSY
STATUS_REFCOUNT_OVERFLOW = amdsmi_wrapper.AMDSMI_STATUS_REFCOUNT_OVERFLOW
STATUS_FAIL_LOAD_MODULE = amdsmi_wrapper.AMDSMI_STATUS_FAIL_LOAD_MODULE
STATUS_FAIL_LOAD_SYMBOL = amdsmi_wrapper.AMDSMI_STATUS_FAIL_LOAD_SYMBOL
STATUS_DRM_ERROR = amdsmi_wrapper.AMDSMI_STATUS_DRM_ERROR
STATUS_IO = amdsmi_wrapper.AMDSMI_STATUS_IO
STATUS_API_FAILED = amdsmi_wrapper.AMDSMI_STATUS_API_FAILED
STATUS_TIMEOUT = amdsmi_wrapper.AMDSMI_STATUS_TIMEOUT
STATUS_NO_SLOT = amdsmi_wrapper.AMDSMI_STATUS_NO_SLOT
STATUS_RETRY = amdsmi_wrapper.AMDSMI_STATUS_RETRY
STATUS_NOT_INIT = amdsmi_wrapper.AMDSMI_STATUS_NOT_INIT
UNKNOWN_ERROR = amdsmi_wrapper.AMDSMI_STATUS_UNKNOWN_ERROR
class AmdSmiException(Exception):
"""Base smi exception class"""
pass
@@ -67,7 +36,7 @@ class AmdSmiLibraryException(AmdSmiException):
self.set_err_info()
def __str__(self):
return "An error occured with code: {err_code}({err_info})".format(
return "Error code:\n\t{err_code} | {err_info}".format(
err_code=self.err_code, err_info=self.err_info
)
@@ -77,34 +46,49 @@ class AmdSmiLibraryException(AmdSmiException):
def get_error_code(self):
return self.err_code
# Translate error codes to error strings
def set_err_info(self):
switch = {
AmdSmiRetCode.STATUS_INVAL: "AMDSMI_STATUS_INVAL - Invalid parameters",
AmdSmiRetCode.STATUS_NOT_SUPPORTED: "AMDSMI_STATUS_NOT_SUPPORTED - Feature not supported",
AmdSmiRetCode.STATUS_FILE_ERROR: "AMDSMI_STATUS_FILE_ERROR - Error opening file",
AmdSmiRetCode.STATUS_OUT_OF_RESOURCES: "AMDSMI_STATUS_OUT_OF_RESOURCES - Not enough memory",
AmdSmiRetCode.STATUS_INTERNAL_EXCEPTION: "AMDSMI_STATUS_INTERNAL_EXCEPTION - Internal error",
AmdSmiRetCode.STATUS_NO_PERM: "AMDSMI_STATUS_NO_PERM - Permission Denied",
AmdSmiRetCode.STATUS_INPUT_OUT_OF_BOUNDS: "AMDSMI_STATUS_INPUT_OUT_OF_BOUNDS - Out of bounds",
AmdSmiRetCode.STATUS_INIT_ERROR: "AMDSMI_STATUS_INIT_ERROR - Initialization error",
AmdSmiRetCode.STATUS_BUSY: "AMDSMI_STATUS_BUSY - Device busy",
AmdSmiRetCode.STATUS_NOT_FOUND: "AMDSMI_STATUS_NOT_FOUND - Device Not found",
AmdSmiRetCode.STATUS_IO: "AMDSMI_STATUS_IO - I/O Error",
AmdSmiRetCode.STATUS_NOT_YET_IMPLEMENTED: "AMDSMI_STATUS_NOT_YET_IMPLEMENTED - Feature not yet implemented",
AmdSmiRetCode.STATUS_INSUFFICIENT_SIZE: "AMDSMI_STATUS_INSUFFICIENT_SIZE - Insufficient size for operation",
AmdSmiRetCode.STATUS_INTERRUPT: "AMDSMI_STATUS_INTERRUPT - Interrupt ocurred during execution",
AmdSmiRetCode.STATUS_UNEXPECTED_SIZE: "AMDSMI_STATUS_UNEXPECTED_SIZE - unexpected size of data was read",
AmdSmiRetCode.STATUS_NO_DATA: "AMDSMI_STATUS_NO_DATA - No data was found for given input",
AmdSmiRetCode.STATUS_UNEXPECTED_DATA: "AMDSMI_STATUS_UNEXPECTED_DATA - The data read or provided was unexpected",
AmdSmiRetCode.STATUS_REFCOUNT_OVERFLOW: "AMDSMI_STATUS_REFCOUNT_OVERFLOW - Internal reference counter exceeded INT32_MAX",
AmdSmiRetCode.STATUS_FAIL_LOAD_MODULE: "AMDSMI_STATUS_FAIL_LOAD_MODULE - Fail to load lib",
AmdSmiRetCode.STATUS_FAIL_LOAD_SYMBOL: "AMDSMI_STATUS_FAIL_LOAD_SYMBOL - Fail to load symbol",
AmdSmiRetCode.STATUS_DRM_ERROR: "AMDSMI_STATUS_DRM_ERROR - Error when called libdrm",
AmdSmiRetCode.STATUS_API_FAILED: "AMDSMI_STATUS_API_FAILED - API call failed",
AmdSmiRetCode.STATUS_TIMEOUT: "AMDSMI_STATUS_TIMEOUT - Timeout in API call",
AmdSmiRetCode.STATUS_NO_SLOT: "AMDSMI_STATUS_NO_SLOT - No more free slot",
AmdSmiRetCode.STATUS_RETRY: "AMDSMI_STATUS_RETRY - Retry operation",
AmdSmiRetCode.STATUS_NOT_INIT: "AMDSMI_STATUS_NOT_INIT - Device not initialized",
amdsmi_wrapper.AMDSMI_STATUS_INVAL : "AMDSMI_STATUS_INVAL - Invalid parameters",
amdsmi_wrapper.AMDSMI_STATUS_NOT_SUPPORTED : "AMDSMI_STATUS_NOT_SUPPORTED - Feature not supported",
amdsmi_wrapper.AMDSMI_STATUS_NOT_YET_IMPLEMENTED : "AMDSMI_STATUS_NOT_YET_IMPLEMENTED - Feature not yet implemented",
amdsmi_wrapper.AMDSMI_STATUS_FAIL_LOAD_MODULE : "AMDSMI_STATUS_FAIL_LOAD_MODULE - Fail to load lib",
amdsmi_wrapper.AMDSMI_STATUS_FAIL_LOAD_SYMBOL : "AMDSMI_STATUS_FAIL_LOAD_SYMBOL - Fail to load symbol",
amdsmi_wrapper.AMDSMI_STATUS_DRM_ERROR : "AMDSMI_STATUS_DRM_ERROR - Error when called libdrm",
amdsmi_wrapper.AMDSMI_STATUS_API_FAILED : "AMDSMI_STATUS_API_FAILED - API call failed",
amdsmi_wrapper.AMDSMI_STATUS_TIMEOUT : "AMDSMI_STATUS_TIMEOUT - Timeout in API call",
amdsmi_wrapper.AMDSMI_STATUS_RETRY : "AMDSMI_STATUS_RETRY - Retry operation",
amdsmi_wrapper.AMDSMI_STATUS_NO_PERM : "AMDSMI_STATUS_NO_PERM - Permission Denied",
amdsmi_wrapper.AMDSMI_STATUS_INTERRUPT : "AMDSMI_STATUS_INTERRUPT - Interrupt ocurred during execution",
amdsmi_wrapper.AMDSMI_STATUS_IO : "AMDSMI_STATUS_IO - I/O Error",
amdsmi_wrapper.AMDSMI_STATUS_ADDRESS_FAULT : "AMDSMI_STATUS_ADDRESS_FAULT - Bad address",
amdsmi_wrapper.AMDSMI_STATUS_FILE_ERROR : "AMDSMI_STATUS_FILE_ERROR - Error opening file",
amdsmi_wrapper.AMDSMI_STATUS_OUT_OF_RESOURCES : "AMDSMI_STATUS_OUT_OF_RESOURCES - Not enough memory",
amdsmi_wrapper.AMDSMI_STATUS_INTERNAL_EXCEPTION : "AMDSMI_STATUS_INTERNAL_EXCEPTION - Internal error",
amdsmi_wrapper.AMDSMI_STATUS_INPUT_OUT_OF_BOUNDS : "AMDSMI_STATUS_INPUT_OUT_OF_BOUNDS - Out of bounds",
amdsmi_wrapper.AMDSMI_STATUS_INIT_ERROR : "AMDSMI_STATUS_INIT_ERROR - Initialization error",
amdsmi_wrapper.AMDSMI_STATUS_REFCOUNT_OVERFLOW : "AMDSMI_STATUS_REFCOUNT_OVERFLOW - Internal reference counter exceeded INT32_MAX",
amdsmi_wrapper.AMDSMI_STATUS_BUSY : "AMDSMI_STATUS_BUSY - Device busy",
amdsmi_wrapper.AMDSMI_STATUS_NOT_FOUND : "AMDSMI_STATUS_NOT_FOUND - Device Not found",
amdsmi_wrapper.AMDSMI_STATUS_NOT_INIT : "AMDSMI_STATUS_NOT_INIT - Device not initialized",
amdsmi_wrapper.AMDSMI_STATUS_NO_SLOT : "AMDSMI_STATUS_NO_SLOT - No more free slot",
amdsmi_wrapper.AMDSMI_STATUS_DRIVER_NOT_LOADED : "AMDSMI_STATUS_DRIVER_NOT_LOADED - Processor driver not loaded",
amdsmi_wrapper.AMDSMI_STATUS_NO_DATA : "AMDSMI_STATUS_NO_DATA - No data was found for given input",
amdsmi_wrapper.AMDSMI_STATUS_INSUFFICIENT_SIZE : "AMDSMI_STATUS_INSUFFICIENT_SIZE - Insufficient size for operation",
amdsmi_wrapper.AMDSMI_STATUS_UNEXPECTED_SIZE : "AMDSMI_STATUS_UNEXPECTED_SIZE - unexpected size of data was read",
amdsmi_wrapper.AMDSMI_STATUS_UNEXPECTED_DATA : "AMDSMI_STATUS_UNEXPECTED_DATA - The data read or provided was unexpected",
amdsmi_wrapper.AMDSMI_STATUS_NON_AMD_CPU : "AMDSMI_STATUS_NON_AMD_CPU - System has non-AMD CPU",
amdsmi_wrapper.AMDSMI_NO_ENERGY_DRV : "AMD_SMI_NO_ENERGY_DRV - Energy driver not found",
amdsmi_wrapper.AMDSMI_NO_MSR_DRV : "AMDSMI_NO_MSR_DRV - MSR driver not found",
amdsmi_wrapper.AMDSMI_NO_HSMP_DRV : "AMD_SMI_NO_HSMP_DRV - HSMP driver not found",
amdsmi_wrapper.AMDSMI_NO_HSMP_SUP : "AMD_SMI_NO_HSMP_SUP - HSMP not supported",
amdsmi_wrapper.AMDSMI_NO_HSMP_MSG_SUP : "AMD_SMI_NO_HSMP_MSG_SUP - HSMP message/feature not supported",
amdsmi_wrapper.AMDSMI_HSMP_TIMEOUT : "AMD_SMI_HSMP_TIMEOUT - HSMP message timeout",
amdsmi_wrapper.AMDSMI_NO_DRV : "AMDSMI_NO_DRV - No Energy and HSMP driver present",
amdsmi_wrapper.AMDSMI_FILE_NOT_FOUND : "AMDSMI_FILE_NOT_FOUND - File or directory not found",
amdsmi_wrapper.AMDSMI_ARG_PTR_NULL : "AMDSMI_ARG_PTR_NULL - Parsed argument is invalid",
amdsmi_wrapper.AMDSMI_STATUS_MAP_ERROR : "AMDSMI_STATUS_MAP_ERROR - The internal library error did not map to a status code",
amdsmi_wrapper.AMDSMI_STATUS_UNKNOWN_ERROR : "AMDSMI_STATUS_UNKNOWN_ERROR - An unknown error occurred"
}
self.err_info = switch.get(self.err_code, "AMDSMI_STATUS_UNKNOWN_ERROR - An unknown error occurred")
@@ -112,12 +96,12 @@ class AmdSmiLibraryException(AmdSmiException):
class AmdSmiRetryException(AmdSmiLibraryException):
def __init__(self):
super().__init__(AmdSmiRetCode.RETRY)
super().__init__(amdsmi_wrapper.AMDSMI_STATUS_RETRY)
class AmdSmiTimeoutException(AmdSmiLibraryException):
def __init__(self):
super().__init__(AmdSmiRetCode.TIMEOUT)
super().__init__(amdsmi_wrapper.AMDSMI_STATUS_TIMEOUT)
class AmdSmiParameterException(AmdSmiException):