[SWDEV-529266] [MI308][AMDSMI][RAS CPER] CPER dump not working on CPX mode (#319)
* Do not raise excepction for cper status not found, but keep iterating to next gpu
* Do not raise excepction for cper status not found, but keep iterating to next gpu
* use partition id and skip if non-zero
* reverting un-needed change
* Do not raise excepction for cper status not found, but keep iterating to next gpu
* use partition id and skip if non-zero
---------
Co-authored-by: Oosman Saeed <oossaeed@amd.com>
[ROCm/amdsmi commit: 9c297639f3]
This commit is contained in:
کامیت شده توسط
Maisam Arif
والد
7201649fbf
کامیت
2391516ced
@@ -6381,6 +6381,20 @@ class AMDSMICommands():
|
|||||||
if args.follow and not getattr(self, "_cper_follow_prompted", False):
|
if args.follow and not getattr(self, "_cper_follow_prompted", False):
|
||||||
print("Press CTRL + C to stop.")
|
print("Press CTRL + C to stop.")
|
||||||
self._cper_follow_prompted = True
|
self._cper_follow_prompted = True
|
||||||
|
|
||||||
|
partition_id = -1
|
||||||
|
try:
|
||||||
|
kfd_info = amdsmi_interface.amdsmi_get_gpu_kfd_info(args.gpu)
|
||||||
|
kfd_id = kfd_info['kfd_id']
|
||||||
|
node_id = kfd_info['node_id']
|
||||||
|
partition_id = kfd_info['current_partition_id']
|
||||||
|
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||||
|
logging.debug("Failed to get kfd info for gpu %s | %s", gpu_id, e.get_error_info())
|
||||||
|
|
||||||
|
if partition_id != 0:
|
||||||
|
logging.debug(f"Skipping gpu {gpu_id} on non zero partition {partition_id}")
|
||||||
|
return
|
||||||
|
|
||||||
if args.folder and args.gpu:
|
if args.folder and args.gpu:
|
||||||
print(f"Dumping CPER file header entries for GPU {gpu_id} in folder {args.folder}")
|
print(f"Dumping CPER file header entries for GPU {gpu_id} in folder {args.folder}")
|
||||||
elif args.folder:
|
elif args.folder:
|
||||||
|
|||||||
مرجع در شماره جدید
Block a user