大佬们,请问一下。我们在2509使用默认的300I A2 sr文件,在web界面-系统信息-FRU信息中无法正常看到Atlas 300I A2的FRU信息。我们将sr文件中的NPU_1删除后发现FRU信息显示正常,请问一下你们是否也会遇到这个问题?
方便查看一下删除前后NPU卡的相关属性吗?具体操作可以使用mdbctl进行
使用默认的sr文件
NPU卡FruData:
openUBMC:/->mdbctl lsprop FruData_NPUCard_010101010107
bmc.kepler.Object.Properties
ClassName="FruData"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="FruData_NPUCard_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.FruData.Board
BoardCustomInfo=""
BoardFRUFileID="53.09.00.23"
BoardManufacturer="Huawei"
BoardPartNumber=""
BoardProductName=""
BoardSerialNumber=""
MfgDate="1996/01/01 Mon 00:00:00"
bmc.kepler.Systems.FruData.Chassis
ChassisCustomInfo=""
ChassisPartNumber=""
ChassisSerialNumber=""
ChassisType=""
bmc.kepler.Systems.FruData.Overview
FruId=12
FruName="Atlas 300I-3000"
FruType="8"
bmc.kepler.Systems.FruData.Product
AssetTag=""
ManufacturerName="Huawei"
ProductCustomInfo=""
ProductFRUFileID="53.09.00.23"
ProductName=""
ProductPartNumber=""
ProductSerialNumber=""
ProductVersion=""
bmc.kepler.Systems.FruData.System
SystemManufacturer=""
SystemProductName=""
SystemSerialNumber=""
SystemVersion=""
openUBMC:/->
NPU卡Fru:
openUBMC:/->mdbctl lsprop Fru_NPUCard_010101010107
bmc.kepler.Object.Properties
ClassName="Fru"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="Fru_NPUCard_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.Fru
BoardId=65535
ConnectorGroupId=0
EepStatus=1
FruDataId="FruData_NPUCard_010101010107"
FruId=12
FruName="Atlas 300I-3000"
GroupPosition="010101010107"
Health=0
PcbId=0
PcbVersion=".A"
PowerState=1
Type=8
UniqueId=""
openUBMC:/->
NPU卡PCIeCard:
openUBMC:/->mdbctl lsprop PCIeCard_1_010101010107
bmc.kepler.Object.Properties
ClassName="PCIeCard"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="PCIeCard_1_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.Board.Unit
CurrentUpgradeStatus=0
HWSRVersion=""
Type=""
UID=""
bmc.kepler.Systems.PCIeDevices.PCIeCard
BoardID=164
BoardName="IT22PDHB"
CardForServers=[1]
CardManufacturer=""
CardModel=""
Description="Atlas 300I A2 Inference Card PCI-E 1*16x(FHFL)"
DeviceID=55298
DeviceName="PCIe Card 7 (Atlas 300I A2)"
FirmwareVersion=""
FunctionClass=9
Health=0
LaneOwner=0
LinkSpeed="32.0GT/s"
LinkSpeedCapability="32.0GT/s"
LinkWidth="X16"
LinkWidthAbility="X16"
Manufacturer="Huawei"
Model="Atlas_300I_A2"
Name="Atlas 300I A2 Inference Card"
NodeID="PCIeCard7"
PartNumber="02314RAL"
PcbVersion=".A"
Position="PCIeSwitch"
Presence=0
RefComponent=""
SerialNumber=""
SlotID=7
SubDeviceID=16384
SubVendorID=6629
VendorID=6629
NPU卡NPUCard:
openUBMC:/->mdbctl lsprop NPUCard_1_010101010107
bmc.kepler.Inventory.Hardware
AssetName="PCIeCard7"
AssetTag="N/A"
AssetType="PCIe NPU Card"
FirmwareVersion=""
ManufactureDate="N/A"
Manufacturer="Huawei"
Model="Atlas_300I_A2"
PCBVersion=""
PartNumber="02314RAL"
SerialNumber="10259B863824"
Slot="7"
UUID=""
bmc.kepler.Object.Properties
ClassName="NPUCard"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="NPUCard_1_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.NPUCard
BoardID=164
ChipFaultDescription=""
ChipHealthStatus=0
Core0TemperatureCelsius=255
Core1TemperatureCelsius=255
FaultCode="Error code: NA"
FaultState=0
FirmwareVersion=""
InletTemperatureCelsius=0
McuFirmwareVersion="25.52.38"
MemoryCapacityMiB=0
Name="Atlas 300I A2 Inference Card"
OutletTemperatureCelsius=0
PcbVersion=".A"
PowerState=0
PowerWatts=32767
SerialNumber="10259B863824"
SlotNumber=7
openUBMC:/->
NPU卡NPU_1:
openUBMC:/->mdbctl lsprop NPU_1_010101010107
bmc.kepler.Inventory.Hardware
AssetName="NPU7-1"
AssetTag="N/A"
AssetType="NPU"
FirmwareVersion=""
ManufactureDate="N/A"
Manufacturer="Huawei"
Model="Atlas_300I_A2"
PCBVersion="N/A"
PartNumber="N/A"
SerialNumber="10259B863824"
Slot="7"
UUID=""
bmc.kepler.Object.Properties
ClassName="NPU"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="NPU_1_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.Processor
Architecture=""
Family="N/A"
FirmwareVersion=""
Health=0
Id=13
InstructionSet=""
Manufacturer="Huawei"
Model="Atlas_300I_A2"
Name="NPU7-1"
PartNumber="Unknown"
Position="PCIe Card 7 (Atlas 300I A2)"
Presence=1
ProcessorType=""
Replaceable=false
SN="10259B863824"
SocketDesignation=""
SystemId=1
ThermalTrip=0
bmc.kepler.Systems.Processor.NPU
AiCPUUsagePercent=0
AiCoreCurrentSpeedMHz=0
AiCoreMaxSpeedMHz=0
AiCoreTemp=32767
AiCoreUsagePercent=0
BDF=""
CapabilitySupportMask=0
ComputeCapability=""
CtrlCPUUsagePercent=0
DiagnosticFault=0
DriverVersion=""
ECCAlarmStatus=0
FaultCode=""
FlashIds=[]
HBMBWUsagePercent=0
HBMMultiBitIsolatedPages=0
HBMSingleBitIsolatedPages=0
HBMTemp=32767
HBMUsagePercent=0
IErrFlag=0
Ierr=0
Location=""
MemBWUsagePercent=0
MemUsagePercent=0
MemoryBandWidth=0
MemoryCapacityKiB=0
MemoryFreeKiB=0
MemoryUsageKiB=0
MultiBitEcc=""
NimBusTemp=32767
Power=32767
PowerCapWatts=0
PowerCapacityWatts=0
PowerConsumedWatts=0
PowerOn=1
PowerState="On"
PredictiveFault=0
ReadingCelsius=0
RootBDF=""
SingleBitEcc=""
Slot=7
TotalCores=0
TotalMemoryKiB=0
VRDChipTemp=32767
VendorID=0
Version=""
Volt=0
openUBMC:/->
删除了NPU_1对象后的sr文件
NPU卡FruData:
~ ~ $ mdbctl lsprop FruData_NPUCard_010101010107
bmc.kepler.Object.Properties
ClassName="FruData"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="FruData_NPUCard_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.FruData.Board
BoardCustomInfo=""
BoardFRUFileID="3.19.00.03"
BoardManufacturer="Huawei"
BoardPartNumber=""
BoardProductName="IT22PDHB"
BoardSerialNumber="10259B863824"
MfgDate="2025/09/29 Mon 20:01:00"
bmc.kepler.Systems.FruData.Chassis
ChassisCustomInfo=""
ChassisPartNumber=""
ChassisSerialNumber=""
ChassisType=""
bmc.kepler.Systems.FruData.Overview
FruId=12
FruName="Atlas 300I-3000"
FruType="8"
bmc.kepler.Systems.FruData.Product
AssetTag=""
ManufacturerName="Huawei"
ProductCustomInfo=""
ProductFRUFileID="3.19.00.03"
ProductName=""
ProductPartNumber=""
ProductSerialNumber=""
ProductVersion=""
bmc.kepler.Systems.FruData.System
SystemManufacturer=""
SystemProductName=""
SystemSerialNumber=""
SystemVersion=""
Private
EepromWp=0
FruAreaSizeBytes=2048
FruDev="Chip_Dmini_Elabel_010101010107"
HeaderOffset=0
StorageLoc=""
StorageType="MCU"
NPU卡Fru:
~ ~ $ mdbctl lsprop Fru_NPUCard_010101010107
bmc.kepler.Object.Properties
ClassName="Fru"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="Fru_NPUCard_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.Fru
BoardId=65535
ConnectorGroupId=0
EepStatus=1
FruDataId="FruData_NPUCard_010101010107"
FruId=12
FruName="Atlas 300I-3000"
GroupPosition="010101010107"
Health=0
PcbId=0
PcbVersion=".A"
PowerState=1
Type=8
UniqueId=""
~ ~ $
NPU卡PCIeCard:
~ ~ $ mdbctl lsprop PCIeCard_1_010101010107
bmc.kepler.Object.Properties
ClassName="PCIeCard"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="PCIeCard_1_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.Board.Unit
CurrentUpgradeStatus=0
HWSRVersion=""
Type=""
UID=""
bmc.kepler.Systems.PCIeDevices.PCIeCard
BoardID=164
BoardName="IT22PDHB"
CardForServers=[1]
CardManufacturer=""
CardModel=""
Description="Atlas 300I A2 Inference Card PCI-E 1*16x(FHFL)"
DeviceID=55298
DeviceName="PCIe Card 7 (Atlas 300I A2)"
FirmwareVersion=""
FunctionClass=9
Health=0
LaneOwner=0
LinkSpeed="32.0GT/s"
LinkSpeedCapability="32.0GT/s"
LinkWidth="X16"
LinkWidthAbility="X16"
Manufacturer="Huawei"
Model="Atlas_300I_A2"
Name="Atlas 300I A2 Inference Card"
NodeID="PCIeCard7"
PartNumber="02314RAL"
PcbVersion=".A"
Position="PCIeSwitch"
Presence=0
RefComponent=""
SerialNumber=""
SlotID=7
SubDeviceID=16384
SubVendorID=6629
VendorID=6629
Private
DevBus=12
DevDevice=0
DevFunction=0
MaxFrameLen=32
PcbID=0
Protocol=""
RefChip=[]
NPU卡NPUCard:
~ ~ $ mdbctl lsprop NPUCard_1_010101010107
bmc.kepler.Inventory.Hardware
AssetName="PCIeCard7"
AssetTag="N/A"
AssetType="PCIe NPU Card"
FirmwareVersion=""
ManufactureDate="N/A"
Manufacturer="Huawei"
Model="Atlas_300I_A2"
PCBVersion=""
PartNumber="02314RAL"
SerialNumber="10259B863824"
Slot="7"
UUID=""
bmc.kepler.Object.Properties
ClassName="NPUCard"
ObjectIdentifier=[1,"1","1","010101010107"]
ObjectName="NPUCard_1_010101010107"
TraceSamplingRate=0
bmc.kepler.Systems.NPUCard
BoardID=164
ChipFaultDescription=""
ChipHealthStatus=0
Core0TemperatureCelsius=255
Core1TemperatureCelsius=255
FaultCode="Error code: NA"
FaultState=0
FirmwareVersion=""
InletTemperatureCelsius=0
McuFirmwareVersion="25.52.38"
MemoryCapacityMiB=0
Name="Atlas 300I A2 Inference Card"
OutletTemperatureCelsius=0
PcbVersion=".A"
PowerState=0
PowerWatts=32767
SerialNumber="10259B863824"
SlotNumber=7
Private
CardDescription="Atlas 300I A2 Inference Card PCI-E 1*16x(FHFL)"
CardPartNumber="02314RAL"
DeviceName="PCIe Card 7 (Atlas 300I A2)"
LockChip="Chip_Dmini_010101010107"
RefChip="Chip_Dmini_010101010107"
RefEeprom="Chip_Dmini_Elabel_010101010107"
RefFrudata="FruData_NPUCard_010101010107"
NPU卡NPU_1:
~ ~ $ mdbctl lsprop NPU_1_010101010107
Failed: Object does not exist.
一些可疑的日志:
app.log
2025-12-26 08:46:24.715918 compute ERROR: handler_npu.lua(63): find_object nil [repeated 14 times in 120s from 2025-12-26 08:39:04.632346 to 2025-12-26 08:41:04.718692][flush]
2025-12-26 08:46:24.716740 compute NOTICE: handler_base.lua(83): c_handler_base: regist_object end, path=/bmc/kepler/Systems/1/Sms/1/ComputerSystem/Systems/1/NPUs/0000:80:00.0_0000:8e:00.0/Summary [repeated 11 times in 200s from 2025-12-26 08:37:44.690830 to 2025-12-26 08:41:04.742946][flush]
2025-12-26 08:46:24.717614 compute NOTICE: handler_base.lua(83): c_handler_base: regist_object end, path=/bmc/kepler/Systems/1/Sms/1/ComputerSystem/Systems/1/NPUs/0000:0b:00.0_0000:0c:00.0 [repeated 10 times in 180s from 2025-12-26 08:38:04.638701 to 2025-12-26 08:41:04.645621][flush]
2025-12-26 08:46:24.718363 compute NOTICE: handler_base.lua(83): c_handler_base: regist_object end, path=/bmc/kepler/Systems/1/Sms/1/ComputerSystem/Systems/1/NPUs/0000:0b:00.0_0000:0c:00.0/Summary [repeated 10 times in 180s from 2025-12-26 08:38:04.665716 to 2025-12-26 08:41:04.664153][flush]
2025-12-26 08:46:24.719236 compute NOTICE: handler_base.lua(83): c_handler_base: regist_object end, path=/bmc/kepler/Systems/1/Sms/1/ComputerSystem/Systems/1/NPUs/0000:80:00.0_0000:8e:00.0 [repeated 10 times in 180s from 2025-12-26 08:38:04.697099 to 2025-12-26 08:41:04.718935][flush]
2025-12-26 08:31:00.697055 firmware_mgmt NOTICE: init.lua(178): Add firmware inventory successfully, Id:MCU_NPUCard_010101010107, Name:PCIe7 MCU, Version:, BuildNum:, ReleaseDate:
2025-12-26 08:31:00.699385 firmware_mgmt NOTICE: persist_client_lib.lua(170): persist saving large data, op: insert, table: t_fw_inventory_objs, primary_key: [["Id","MCU_NPUCard_010101010107"]], data_size: 1069
2025-12-26 08:31:00.725190 frudata NOTICE: object_manage.lua(284): start to add objects, path: /bmc/kepler/ObjectGroup/01013B, life cycle id: 1, count: 3
2025-12-26 08:31:00.744007 cooling NOTICE: wave_record_init.lua(208): Now up time is 133, CPU 2 wave record will begin in 9 seconds.
2025-12-26 08:31:00.765409 compute NOTICE: NPUCard.lua(1016): [NPUCard]PluginRequest start
2025-12-26 08:31:00.931763 redfish NOTICE: key_client_lib.lua(187): start listen on change of keyid from path: /bmc/kepler/KeyService/Kmc/Keys/7
2025-12-26 08:31:01.075500 tpcm ERROR: mdb_set_value(484): Property /bmc/kepler/Systems/1/Events.MaxEventCount signature not match, get: u, need: q
2025-12-26 08:31:01.075531 tpcm ERROR: mdb_set_value(484): Property /bmc/kepler/Systems/1/Events.CurEventCount signature not match, get: u, need: q
2025-12-26 08:31:01.075554 tpcm ERROR: mdb_set_value(484): Property /bmc/kepler/Systems/1/Events.MinorCount signature not match, get: u, need: q
2025-12-26 08:31:01.075566 tpcm ERROR: mdb_set_value(484): Property /bmc/kepler/Systems/1/Events.MajorCount signature not match, get: u, need: q
2025-12-26 08:31:01.075578 tpcm ERROR: mdb_set_value(484): Property /bmc/kepler/Systems/1/Events.CriticalCount signature not match, get: u, need: q
2025-12-26 08:31:01.075603 tpcm WARN: iter_property_values(1501): Unkown property /bmc/kepler/Systems/1/Events.EventMode get, intf:bmc.kepler.Systems.Events
2025-12-26 08:31:01.088305 power_strategy NOTICE: base.lua(137): Add NPU_Card(/bmc/kepler/Systems/1/Processors/NPU/NPU_1_010101010107), interface: bmc.kepler.Systems.Processor.NPU
2025-12-26 08:31:01.099735 cooling NOTICE: base.lua(140): Add Single NPU(/bmc/kepler/Systems/1/Processors/NPU/NPU_1_010101010107), interface: bmc.kepler.Systems.Processor.NPU
2025-12-26 08:31:01.226835 storage NOTICE: nvme_object.lua(497): get disk8 NVMe MI 1.0
2025-12-26 08:31:01.282849 power_strategy NOTICE: base.lua(131): Add object(/bmc/kepler/Systems/1/Processors/NPU/NPU_1_010101010107) completed, interface: bmc.kepler.Systems.Processor.NPU
2025-12-26 08:31:01.311840 event ERROR: event_management.lua(1148): repeated add event [System_TPCM.BootMeasurement_["BIOS"]_1_1_00] failed
2025-12-26 08:31:01.313676 tpcm NOTICE: do_add_event(138): [TPCM] Call add event success
2025-12-26 08:31:01.313702 tpcm ERROR: add_event(151): [TPCM] is_repeat = 0, Add event the 1 time successfully.
2025-12-26 08:31:01.313708 tpcm ERROR: add_event(160): [TPCM] Add Bios event repeatly finished successfully.
2025-12-26 08:31:01.319536 fault_diagnosis ERROR: npu_ras.lua(390): npu ras obj id is nil
2025-12-26 08:31:01.380681 mctpd NOTICE: mctp_engine.lua(320): mctp_engine: set owner_eid=8, owner_phy_addr=152
2025-12-26 08:31:01.419947 cooling NOTICE: base.lua(134): Add object(/bmc/kepler/Systems/1/Processors/NPU/NPU_1_010101010107) completed, interface: bmc.kepler.Systems.Processor.NPU
2025-12-26 08:31:01.447021 fault_diagnosis ERROR: npu_ras.lua(390): npu ras obj id is nil
2025-12-26 08:31:01.451715 storage NOTICE: nvme_object.lua(497): get disk11 NVMe MI 1.0
2025-12-26 08:31:01.481975 cooling NOTICE: wave_record_init.lua(208): Now up time is 134, NPU 13 wave record will begin in 18 seconds.
2025-12-26 08:33:44.610978 compute ERROR: handler_npu.lua(63): find_object nil
2025-12-26 08:33:44.671196 compute ERROR: handler_npu.lua(63): find_object nil
2025-12-26 08:33:47.575228 general_hardware NOTICE: fructl_handler.lua(76): get_power_state: get power power ON
2025-12-26 08:33:50.568157 bmc_time ERROR: ntp.lua(714): Sync to NTP server failed, count = 2
2025-12-26 08:33:51.836509 power_mgmt ERROR: psu.lua(435): Update power[01013D] level failed
2025-12-26 08:33:59.425331 bmc_core ERROR: lldp_proc.c(318): Can't find port name from LLDP
2025-12-26 08:34:00.701061 power_mgmt ERROR: psu.lua(435): Update power[01013C] level failed
2025-12-26 08:34:01.459070 fault_diagnosis ERROR: npu_ras.lua(573): invalid local_npu_id = 13
2025-12-26 08:34:01.468751 fault_diagnosis ERROR: npu_ras.lua(573): invalid local_npu_id = 13
2025-12-26 08:31:20.249238 frudata NOTICE: frudata_app.lua(74): frudata add object, obj.FruId = 12, frudata name = FruData_NPUCard_010101010107, type = MCU
2025-12-26 08:31:20.253489 power_strategy NOTICE: fan_listening.lua(73): Add object(/bmc/kepler/Systems/1/Thermal/Fans/Fan_10_010103) completed, interface: bmc.kepler.Systems.Fan
2025-12-26 08:31:20.253518 frudata NOTICE: frudata_app.lua(102): fru_mdb_obj.FruDataId = FruData_NPUCard_010101010107
2025-12-26 08:31:20.253840 frudata NOTICE: frudata_app.lua(105): Fru [Id: 12, Name: Atlas 300I-3000] emit added signal start
2025-12-26 08:31:20.255374 frudata NOTICE: object_manage.lua(304): add objects callback, path: /bmc/kepler/ObjectGroup/010101010107, life cycle id: 1, count: 3, took 560ms
2025-12-26 08:31:20.257061 frudata NOTICE: object_manage.lua(315): add objects completely, path: /bmc/kepler/ObjectGroup/010101010107, life cycle id: 1, took 0ms
2025-12-26 08:31:20.260954 frudata NOTICE: manage.lua(40): init non standard frudata, bmc_ver = 53.09.00.23, obj.FruId = 12
2025-12-26 08:31:20.270363 frudata NOTICE: frudata_service.lua(93): read MCU data successfully, break loop. fru_id = 12
2025-12-26 08:31:20.270900 frudata NOTICE: manage.lua(207): update_fru_data_to_dbus bmc_ver = 53.09.00.23, fru_id = 12
2025-12-26 08:31:20.275808 power_strategy NOTICE: fan_listening.lua(79): Add fan(/bmc/kepler/Systems/1/Thermal/Fans/Fan_4_010103), interface: bmc.kepler.Systems.Fan
2025-12-26 08:31:20.277131 frudata NOTICE: manage.lua(255): update_sys_data_to_dbus sys_ver = 0, fru_id = 12
2025-12-26 08:31:04.422759 frudata NOTICE: frudata_app.lua(102): fru_mdb_obj.FruDataId = FruData_IEU_0101010101
2025-12-26 08:31:04.427947 frudata NOTICE: frudata_app.lua(105): Fru [Id: 7, Name: Switch] emit added signal start
2025-12-26 08:31:04.456054 frudata NOTICE: object_manage.lua(304): add objects callback, path: /bmc/kepler/ObjectGroup/0101010101, life cycle id: 1, count: 3, took 720ms
2025-12-26 08:31:04.456499 frudata NOTICE: object_manage.lua(315): add objects completely, path: /bmc/kepler/ObjectGroup/0101010101, life cycle id: 1, took 10ms
2025-12-26 08:31:04.524148 compute NOTICE: npu_event_handler.lua(29): "NPUToSwitchModuleLinkAbnormal"
2025-12-26 08:31:04.551594 frudata NOTICE: object_manage.lua(284): start to add objects, path: /bmc/kepler/ObjectGroup/010109, life cycle id: 1, count: 10
完整的app.log:
app.txt (749.3 KB)
方便发一下一键收集下的compute组件的资源协作接口吗?具体路径如下
dump_info\AppDump\compute\mdb_info.log
在一键收集的日志里没有dump_info\AppDump\compute\ 这个文件夹
mdb_info.txt (275.2 KB)
刚刚因为一些电脑问题找不到该文件,现在找到了,感谢你看下。
这个对应的是删除了csr内NPU_1还是没删除的版本?麻烦把两者都发一下。
目前来看删除CSR内NPU前后NPU卡的信息获取是没有问题的,现在确认一下NPU卡的FRU信息获取在删除前后是否有区别。麻烦发送一下删除前后一键收集中以下文件。方便确认是否有区别。
dump_info\AppDump\frudata\mdb_info.log
dump_info\LogDump\app.log
方便提供一下您的邮箱吗?我将两份完整日志打包发送给您。
这个问题当前有结论了吗
web的FRU信息显示跟NPU没关系
如果没有结论的话 发一下FRU的CSR配置
目前还没有结论。
vendor/Huawei/Gpu/14140130_19e5d802_19e54000.sr:
{
"FormatVersion": "3.00",
"DataVersion": "3.00",
"Unit": {
"Type": "PCIeCard",
"Name": "PCIeCard_1"
},
"ManagementTopology": {
"Anchor": {
"Buses": [
"I2cMux_Chan"
]
},
"I2cMux_Chan": {
"Chips": [
"Chip_Dmini",
"Chip_Dmini_Elabel"
]
}
},
"Objects": {
"DftMcu_1": {
"Id": 172,
"Type": 2,
"Slot": "${Slot}",
"DeviceNum": 5,
"ItemName": "MCU Log Clear Test",
"PrompteReady": "",
"PrompteFinish": ""
},
"DftMcu_2": {
"Id": 172,
"Type": 1,
"Slot": "${Slot}",
"DeviceNum": 7,
"ItemName": "MCU self interrupt Test",
"PrompteReady": "",
"PrompteFinish": ""
},
"Chip_Dmini": {
"OffsetWidth": 1,
"AddrWidth": 1,
"Address": 216,
"WriteTmout": 100,
"ReadTmout": 100,
"HealthStatus": 0,
"WriteRetryTimes": 2,
"ReadRetryTimes": 0
},
"Chip_Dmini_Elabel": {
"OffsetWidth": 1,
"AddrWidth": 1,
"Address": 0,
"WriteTmout": 100,
"ReadTmout": 100,
"HealthStatus": 0,
"WriteRetryTimes": 2,
"ReadRetryTimes": 216
},
"Entity_GPUCard": {
"Id": 11,
"Name": "PCIe Card",
"PowerState": 1,
"Presence": 1,
"Instance": 101
},
"PCIeDevice_1": {
"Segment": 1,
"DeviceName": "PCIe Card $ (Atlas 300I A2)",
"DiagnosticFault": 0,
"PredictiveFault": 0,
"FunctionClass": 9,
"LinkSpeedReduced": 0,
"CorrectableError": 0,
"UncorrectableError": 0,
"FatalError": 0,
"Position": "",
"Container": "${Container}",
"GroupPosition": "PCIeDevice_${GroupPosition}",
"DeviceType": 8,
"PCIeDeviceType": "SingleFunction",
"SlotType": "FullLength",
"FunctionProtocol": "PCIe",
"FunctionType": "Physical"
},
"FruData_NPUCard": {
"FruId": 2,
"StorageType": "MCU",
"FruDev": "#/Chip_Dmini_Elabel"
},
"Fru_NPUCard": {
"PcbVersion": ".A",
"FruId": 2,
"PowerState": 1,
"FruName": "Atlas 300I-3000",
"Health": 0,
"EepStatus": 1,
"Type": 8,
"FruDataId": "#/FruData_NPUCard"
},
"NPUCard_1":{
"Name": "Atlas 300I A2 Inference Card",
"CardDescription": "Atlas 300I A2 Inference Card PCI-E 1*16x(FHFL)",
"DeviceName": "<=/PCIeDevice_1.DeviceName",
"RefChip":"#/Chip_Dmini",
"LockChip":"#/Chip_Dmini",
"RefEeprom":"#/Chip_Dmini_Elabel",
"RefFrudata": "#/FruData_NPUCard",
"Model": "Atlas_300I_A2",
"SlotNumber": "${Slot}",
"PcbVersion": ".A",
"BoardID": 170,
"FirmwareVersion": "N/A",
"CardPartNumber": "02314RAL"
},
"NPU_1":{
"Name": "NPU${Slot}-1",
"Id": "${Slot} |> expr($1 * 2 - 1)",
"SystemId": 1,
"Presence": 1,
"Slot": "${Slot}",
"Position": "<=/PCIeDevice_1.DeviceName",
"ComputeCapability": "",
"Architecture": "",
"InstructionSet": "",
"Version": "",
"Model": "Atlas_300I_A2",
"CapabilitySupportMask": 0,
"TotalCores": 0,
"Location": "",
"ECCAlarmState": 0,
"DiagnosticFaule": 0,
"PredictiveFault": 0,
"PowerOn": 1,
"ThermalTrip": 0,
"PowerState": "On",
"SN": "",
"PartNumber": "02314RAL",
"PcbVersion": "#/NPUCard_1.PcbVersion",
"Manufacturer": "<=/PCIeCard_1.Manufacturer",
"Health": "<=/Component_PCIeCard.Health"
},
"PCIeCard_1": {
"DeviceName": "<=/PCIeDevice_1.DeviceName",
"SlotID": "<=/PCIeDevice_1.SlotID",
"NodeID": "<=/PCIeDevice_1.SlotID |> string.format('PCIeCard%s',$1)",
"Health": "<=/Component_PCIeCard.Health",
"Name": "Atlas 300I A2 Inference Card",
"BoardName": "<=/FruData_NPUCard.BoardProductName |> expr($1 == '' ? 'IT22PDHB' : $1)",
"Description": "Atlas 300I A2 Inference Card PCI-E 1*16x(FHFL)",
"FunctionClass": 9,
"VendorID": 6629,
"DeviceID": 55298,
"SubVendorID": 6629,
"SubDeviceID": 16384,
"Position": "<=/PCIeDevice_1.Position",
"LaneOwner": "<=/PCIeDevice_1.SocketID",
"FirmwareVersion": "#/NPUCard_1.FirmwareVersion",
"Manufacturer": "Huawei",
"PartNumber": "02314RAL",
"MaxFrameLen": 32,
"LinkSpeed": "N/A",
"LinkSpeedCapability": "N/A",
"PcbVersion": "#/NPUCard_1.PcbVersion",
"BoardID": "#/NPUCard_1.BoardID",
"Bus": "<=/PCIeDevice_1.Bus",
"Device": "<=/PCIeDevice_1.Device",
"Function": "<=/PCIeDevice_1.Function",
"DevBus": "<=/PCIeDevice_1.DevBus",
"DevDevice": "<=/PCIeDevice_1.DevDevice",
"SerialNumber": "",
"Model": "Atlas_300I_A2",
"DevFunction": "<=/PCIeDevice_1.DevFunction"
},
"Event_PCIeCardUCE": {
"EventKeyId": "PCIeCard.PCIeCardUncorrectableErr",
"Condition": 1,
"LedFaultCode": "q$$"
},
"Event_PCIeCardCE": {
"EventKeyId": "PCIeCard.PCIeCardCEHardFailure",
"Condition": 1,
"LedFaultCode": "q$$"
},
"Event_PcieCardReplaceMntr": {
"EventKeyId": "PcieCard.PcieCardReplace",
"Condition": 1
},
"Event_PCIeLinkSpeed": {
"EventKeyId": "PCIeCard.PCIeCardLinkSpeedReduced",
"Condition": 1
},
"ThresholdSensor_GPUHBMTemp": {
"OwnerId": 32,
"OwnerLun": 0,
"EntityId": "<=/Entity_GPUCard.Id",
"EntityInstance": "<=/Entity_GPUCard.Instance",
"Initialization": 127,
"Capabilities": 104,
"SensorType": 1,
"ReadingType": 1,
"SensorName": "NPU${Slot} HBM Temp",
"AssertMask": 0,
"DeassertMask": 0,
"ReadingMask": 2056,
"UpperNoncritical": 105,
"PositiveHysteresis": 2,
"Unit": 128,
"BaseUnit": 1,
"ModifierUnit": 0,
"Linearization": 0,
"M": 1,
"RBExp": 0,
"Analog": 1,
"NominalReading": 25,
"NormalMaximum": 0,
"NormalMinimum": 0,
"MaximumReading": 127,
"MinimumReading": 128,
"Reading": "<=/NPU_1.HBMTemp",
"ReadingStatus": "<=/NPU_1.HBMTemp |> expr($1 >= 255 ? (($1 == 32767 || $1 == 32768 || $1 == 255) ? 3 : 1) : 0)",
"SensorNumber": 255
},
"ThresholdSensor_GPUPREDEVTemp": {
"OwnerId": 32,
"OwnerLun": 0,
"EntityId": "<=/Entity_GPUCard.Id",
"EntityInstance": "<=/Entity_GPUCard.Instance",
"Initialization": 127,
"Capabilities": 104,
"SensorType": 1,
"ReadingType": 1,
"SensorName": "NPU${Slot} PREDEV Temp",
"AssertMask": 0,
"DeassertMask": 0,
"ReadingMask": 2056,
"UpperNoncritical": 105,
"PositiveHysteresis": 2,
"Unit": 128,
"BaseUnit": 1,
"ModifierUnit": 0,
"Linearization": 0,
"M": 1,
"RBExp": 0,
"Analog": 1,
"NominalReading": 25,
"NormalMaximum": 0,
"NormalMinimum": 0,
"MaximumReading": 127,
"MinimumReading": 128,
"Reading": "<=/NPU_1.NimBusTemp",
"ReadingStatus": "<=/NPU_1.NimBusTemp |> expr($1 >= 255 ? (($1 == 32767 || $1 == 32768 || $1 == 255) ? 3 : 1) : 0)"
},
"ThresholdSensor_GPUVRDTemp": {
"OwnerId": 32,
"OwnerLun": 0,
"EntityId": "<=/Entity_GPUCard.Id",
"EntityInstance": "<=/Entity_GPUCard.Instance",
"Initialization": 127,
"Capabilities": 104,
"SensorType": 1,
"ReadingType": 1,
"SensorName": "NPU${Slot} VRD Temp",
"AssertMask": 0,
"DeassertMask": 0,
"ReadingMask": 2056,
"UpperNoncritical": 118,
"PositiveHysteresis": 2,
"Unit": 128,
"BaseUnit": 1,
"ModifierUnit": 0,
"Linearization": 0,
"M": 1,
"RBExp": 0,
"Analog": 1,
"NominalReading": 25,
"NormalMaximum": 0,
"NormalMinimum": 0,
"MaximumReading": 127,
"MinimumReading": 128,
"Reading": "<=/NPU_1.VRDChipTemp",
"ReadingStatus": "<=/NPU_1.VRDChipTemp |> expr($1 >= 255 ? (($1 == 32767 || $1 == 32768 || $1 == 255) ? 3 : 1) : 0)"
},
"ThresholdSensor_GPUAICoreTemp": {
"OwnerId": 32,
"OwnerLun": 0,
"EntityId": "<=/Entity_GPUCard.Id",
"EntityInstance": "<=/Entity_GPUCard.Instance",
"Initialization": 127,
"Capabilities": 104,
"SensorType": 1,
"ReadingType": 1,
"SensorName": "NPU${Slot} AICORE Temp",
"AssertMask": 0,
"DeassertMask": 0,
"ReadingMask": 2056,
"UpperNoncritical": 105,
"PositiveHysteresis": 2,
"Unit": 128,
"BaseUnit": 1,
"ModifierUnit": 0,
"Linearization": 0,
"M": 1,
"RBExp": 0,
"Analog": 1,
"NominalReading": 25,
"NormalMaximum": 0,
"NormalMinimum": 0,
"MaximumReading": 127,
"MinimumReading": 128,
"Reading": "<=/NPU_1.AiCoreTemp",
"ReadingStatus": "<=/NPU_1.AiCoreTemp |> expr($1 >= 255 ? (($1 == 32767 || $1 == 32768 || $1 == 255) ? 3 : 1) : 0)"
},
"ThresholdSensor_GPUPower": {
"OwnerId": 32,
"OwnerLun": 0,
"EntityId": "<=/Entity_GPUCard.Id",
"EntityInstance": "<=/Entity_GPUCard.Instance",
"Initialization": 127,
"Capabilities": 104,
"SensorType": 11,
"ReadingType": 1,
"SensorName": "NPU${Slot} Power",
"AssertMask": 0,
"DeassertMask": 0,
"ReadingMask": 0,
"Unit": 0,
"BaseUnit": 6,
"ModifierUnit": 0,
"Linearization": 0,
"M": 15,
"RBExp": 240,
"Analog": 1,
"NominalReading": 0,
"NormalMaximum": 0,
"NormalMinimum": 0,
"MaximumReading": 255,
"MinimumReading": 0,
"Reading": "<=/NPU_1.Power |> expr($1 // 15)",
"ReadingStatus": "<=/NPU_1.Power |> expr($1 >= 16384 ? 1 : 0)"
},
"Event_PCIeBandWidth": {
"EventKeyId": "PCIeCard.PCIeCardBandWidthDecreased",
"Condition": 1
},
"Event_AiCoreOverTemp": {
"EventKeyId": "PCIeCard.PCIeCardOverTemp",
"Condition": "#/ThresholdSensor_GPUAICoreTemp.UpperNoncritical",
"Hysteresis": "#/ThresholdSensor_GPUAICoreTemp.PositiveHysteresis"
},
"Event_HBMOverTemp": {
"EventKeyId": "PCIeCard.PCIeCardOverTemp",
"Condition": "#/ThresholdSensor_GPUHBMTemp.UpperNoncritical",
"Hysteresis": "#/ThresholdSensor_GPUHBMTemp.PositiveHysteresis"
},
"Event_PREDEVOverTemp": {
"EventKeyId": "PCIeCard.PCIeCardOverTemp",
"Condition": "#/ThresholdSensor_GPUPREDEVTemp.UpperNoncritical",
"Hysteresis": "#/ThresholdSensor_GPUPREDEVTemp.PositiveHysteresis"
},
"Event_VRDOverTemp": {
"EventKeyId": "PCIeCard.PCIeCardOverTemp",
"Condition": "#/ThresholdSensor_GPUVRDTemp.UpperNoncritical",
"Hysteresis": "#/ThresholdSensor_GPUVRDTemp.PositiveHysteresis"
},
"Event_AirTempFail": {
"EventKeyId": "PcieCard.PCIeCardTempFail",
"Condition": 1
},
"Event_FirmwareFailure": {
"EventKeyId": "PcieCard.PCIeCardFirmwareFailure",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 8192) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "NPU",
"DescArg5": "(SPI Flash)",
"DescArg6": "#/NPUCard_1.FaultCode"
},
"Event_InspectFail": {
"EventKeyId": "PcieCard.PCIeCardInspectionFailure",
"Reading": "<=/NPUCard_1.FaultState;<=/NPUCard_1.PowerWatts |> expr((($1 & 4) == 0) && (($2 & 32768) == 0) ? 0 : 1)",
"Condition": 0,
"OperatorId": 6,
"AdditionalInfo": "2",
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name"
},
"Event_VoltFail": {
"EventKeyId": "PcieCard.PCIeCardAccessVoltFailure",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 256) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg5": "#/NPUCard_1.FaultCode"
},
"Event_VoltUpper": {
"EventKeyId": "PcieCard.PCIeCardVoltageUpper",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 512) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"Event_VoltLower": {
"EventKeyId": "PcieCard.PCIeCardVoltageLower",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 1024) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"Event_HealthFail": {
"EventKeyId": "PcieCard.PCIeCardHealthFail",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 2097152) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"Event_MiniFail": {
"EventKeyId": "PcieCard.PCIeCardMiniFail",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 4194304) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"Event_PowerUpDown": {
"EventKeyId": "PcieCard.PCIeCardPowerUpDown",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 33554432) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"Event_HardwareFail": {
"EventKeyId": "PcieCard.PCIeCardHardwareFail",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 65536) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg1": "#/NPUCard_1.FaultCode",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name"
},
"Event_PwrFail": {
"EventKeyId": "PcieCard.PCIeCardPwrFail",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 128) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"Event_OverCurrent": {
"EventKeyId": "PcieCard.PCIeCardOverCurrent",
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 1073741824) == 0 ? 0 : 1)",
"Condition": 1,
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "#/PCIeCard_1.Name",
"DescArg4": "#/NPUCard_1.FaultCode"
},
"CoolingRequirement_1_77": {
"RequirementId": 77,
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 90,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
},
"CoolingRequirement_1_80": {
"RequirementId": "${Slot} |> expr(($1 >= 1 && $1 <= 8) ? 80 : 0)",
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 85,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
},
"CoolingRequirement_1_81": {
"RequirementId": "${Slot} |> expr(($1 >= 7 && $1 <= 14) ? 81 : 0)",
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 85,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
},
"CoolingRequirement_1_82": {
"RequirementId": "${Slot} |> expr(($1 >= 13 && $1 <= 20) ? 82 : 0)",
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 85,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
},
"CoolingRequirement_1_83": {
"RequirementId": "${Slot} |> expr(($1 >= 1 && $1 <= 10) ? 83 : 0)",
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 85,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
},
"CoolingRequirement_1_84": {
"RequirementId": "${Slot} |> expr(($1 >= 11 && $1 <= 20) ? 84 : 0)",
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 85,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
},
"CoolingRequirement_1_85": {
"RequirementId": 85,
"Description": "Atlas 300I A2芯片温度调速",
"MonitoringStatus": "<=/NPU_1.AiCoreTemp |> expr($1 == 32768 ? 1 : 0)",
"MonitoringValue": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"FailedValue": 0,
"MaxAllowedTemperatureCelsius": 90,
"SensorName": "#/ThresholdSensor_GPUAICoreTemp.SensorName"
}
}
}
vendor/Huawei/Gpu/14140130_19e5d802_19e54000_soft.sr:
{
"FormatVersion": "3.00",
"DataVersion": "3.00",
"Unit": {
"Type": "PCIeCard",
"Name": "PCIeCard_1"
},
"Objects": {
"Component_PCIeCard": {
"Instance": "<=/PCIeDevice_1.SlotID",
"UniqueId": "N/A",
"FruId": 255,
"BoardId": 65535,
"Manufacturer": "Huawei",
"Type": 8,
"Presence": 1,
"Health": 0,
"PowerState": 1,
"GroupId": 1,
"Name": "<=/PCIeDevice_1.DeviceName",
"ReplaceFlag": 0,
"PreviousSN": "",
"SerialNumber": "<=/PCIeCard_1.SerialNumber"
},
"Event_PCIeCardUCE": {
"Reading": "<=/PCIeDevice_1.DiagnosticFault;<=/PCIeDevice_1.UCEByBIOS |> expr(($1 + $2) == 0 ? 0 : 1)",
"OperatorId": 5,
"Enabled": true,
"AdditionalInfo": "2",
"DescArg2": "#/Component_PCIeCard.Name",
"DescArg4": "NA",
"Component": "#/Component_PCIeCard"
},
"Event_PCIeCardCE": {
"Reading": "<=/PCIeDevice_1.PredictiveFault",
"OperatorId": 5,
"Enabled": true,
"AdditionalInfo": "2",
"DescArg2": "#/Component_PCIeCard.Name",
"Component": "#/Component_PCIeCard"
},
"Event_PcieCardReplaceMntr": {
"Reading": "<=/Component_PCIeCard.ReplaceFlag",
"OperatorId": 5,
"Enabled": true,
"AdditionalInfo": "1",
"DescArg1": "#/Component_PCIeCard.Name",
"DescArg2": "#/Component_PCIeCard.PreviousSN",
"DescArg3": "#/Component_PCIeCard.SerialNumber",
"Component": "#/Component_PCIeCard"
},
"Event_PCIeLinkSpeed": {
"Reading": "<=/PCIeDevice_1.LinkSpeedReduced",
"OperatorId": 5,
"Enabled": true,
"AdditionalInfo": "2",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "(Atlas 300I A2 Inference Card)",
"Component": "#/Component_PCIeCard"
},
"Event_PCIeBandWidth": {
"Reading": "<=/PCIeDevice_1.BandwidthReduction",
"OperatorId": 5,
"Enabled": true,
"AdditionalInfo": "2",
"DescArg2": "#/PCIeDevice_1.SlotID",
"DescArg3": "(Atlas 300I A2 Inference Card)",
"Component": "#/Component_PCIeCard"
},
"Event_AiCoreOverTemp": {
"Reading": "<=/NPU_1.AiCoreTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"@Default": {
"Reading": 40
},
"OperatorId": 4,
"Component": "#/Component_PCIeCard",
"AdditionalInfo": "3",
"DescArg2": "#/Component_PCIeCard.Name",
"DescArg3": "AICORE",
"DescArg4": "#/Event_AiCoreOverTemp.Reading",
"DescArg5": "#/Event_AiCoreOverTemp.Condition"
},
"Event_HBMOverTemp": {
"Reading": "<=/NPU_1.HBMTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"@Default": {
"Reading": 40
},
"OperatorId": 4,
"Component": "#/Component_PCIeCard",
"AdditionalInfo": "3",
"DescArg2": "#/Component_PCIeCard.Name",
"DescArg3": "HBM",
"DescArg4": "#/Event_HBMOverTemp.Reading",
"DescArg5": "#/Event_HBMOverTemp.Condition"
},
"Event_PREDEVOverTemp": {
"Reading": "<=/NPU_1.NimBusTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"@Default": {
"Reading": 40
},
"OperatorId": 4,
"Component": "#/Component_PCIeCard",
"AdditionalInfo": "3",
"DescArg2": "#/Component_PCIeCard.Name",
"DescArg3": "PREDEV",
"DescArg4": "#/Event_PREDEVOverTemp.Reading",
"DescArg5": "#/Event_PREDEVOverTemp.Condition"
},
"Event_VRDOverTemp": {
"Reading": "<=/NPU_1.VRDChipTemp |> expr(($1 >= 255) ? 40 : ($1 & 255))",
"@Default": {
"Reading": 40
},
"OperatorId": 4,
"Component": "#/Component_PCIeCard",
"AdditionalInfo": "3",
"DescArg2": "#/Component_PCIeCard.Name",
"DescArg3": "VRD",
"DescArg4": "#/Event_VRDOverTemp.Reading",
"DescArg5": "#/Event_VRDOverTemp.Condition"
},
"Event_AirTempFail": {
"Reading": "<=/NPUCard_1.FaultState |> expr(($1 & 268435456) == 0 ? 0 : 1)",
"OperatorId": 5,
"Component": "#/Component_PCIeCard",
"DescArg2": "#/Component_PCIeCard.Name",
"DescArg3": "inlet or outlet",
"DescArg4": "#/NPUCard_1.FaultCode"
}
}
}
没看到FruData_NPUCard配置呢
web界面是查看的这个对象
麻烦将当时的一键收集日志发送到邮箱
zhangzhiyang22@huawei.com
请分别标明是否有删除NPU的相关sr
两份日志已发送。
好的,我先看看


