Fixed log handling and exceptions

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
+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))
```
-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
+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):