已关闭
【修改描述】: 适配Nvidia 5090GPU #765
luzhenying103创建于 5月21日关闭于 5月27日
【修改描述】: 适配Nvidia 5090GPU #765
已关闭
共 3 个文件变更+299-1
| @@ -282,4 +282,6 @@ LRLINK/Nic/OCP/14220247_80880103_8088c401.sr | |||
| 282 | LRLINK/Nic/OCP/14220247_80861521_ffff0000.sr | 282 | LRLINK/Nic/OCP/14220247_80861521_ffff0000.sr |
| 283 | Huawei/TianChi/SEU/14140224_POLICY_1e49.sr | 283 | Huawei/TianChi/SEU/14140224_POLICY_1e49.sr |
| 284 | Broadcom/Raid/14140130_100010e2_10004020.sr | 284 | Broadcom/Raid/14140130_100010e2_10004020.sr |
| 285 | -Huawei/TianChi/SEU/14140224_POLICY_1ee4.sr | 285 | +Huawei/TianChi/SEU/14140224_POLICY_1ee4.sr |
| 286 | +Nvidia/Gpu/14140130_10de2b85_1458419e.sr | ||
| 287 | +Nvidia/Gpu/14140130_10de2b85_1458419e_soft.sr | ||
| @@ -0,0 +1,182 @@ | |||
| 1 | +{ | ||
| 2 | + "FormatVersion": "3.00", | ||
| 3 | + "DataVersion": "3.00", | ||
| 4 | + "Unit": { | ||
| 5 | + "Type": "PCIeCard", | ||
| 6 | + "Name": "PCIeCard_1" | ||
| 7 | + }, | ||
| 8 | + "ManagementTopology": { | ||
| 9 | + "Anchor": { | ||
| 10 | + "Buses": [ | ||
| 11 | + "I2cMux_Chan" | ||
| 12 | + ] | ||
| 13 | + }, | ||
| 14 | + "I2cMux_Chan": { | ||
| 15 | + "Chips": [ | ||
| 16 | + "Chip_TempChip" | ||
| 17 | + ] | ||
| 18 | + } | ||
| 19 | + }, | ||
| 20 | + "Objects": { | ||
| 21 | + "Chip_TempChip": { | ||
| 22 | + "Address": 159, | ||
| 23 | + "AddrWidth": 1, | ||
| 24 | + "OffsetWidth": 1, | ||
| 25 | + "WriteTmout": 100, | ||
| 26 | + "ReadTmout": 100, | ||
| 27 | + "HealthStatus": 0 | ||
| 28 | + }, | ||
| 29 | + "MidAvg_GPUTemp": { | ||
| 30 | + "WindowSize": 4, | ||
| 31 | + "DefaultValue": 20, | ||
| 32 | + "IsSigned": true | ||
| 33 | + }, | ||
| 34 | + "Scanner_GPUTemp": { | ||
| 35 | + "Chip": "#/Chip_TempChip", | ||
| 36 | + "Size": 1, | ||
| 37 | + "Offset": 0, | ||
| 38 | + "Mask": 255, | ||
| 39 | + "Period": 1000, | ||
| 40 | + "Debounce": "#/MidAvg_GPUTemp", | ||
| 41 | + "Type": 0 | ||
| 42 | + }, | ||
| 43 | + "GPU_1": { | ||
| 44 | + "SystemId": 1, | ||
| 45 | + "Id": 1, | ||
| 46 | + "Name": "NVIDIA 5090", | ||
| 47 | + "Presence": 1, | ||
| 48 | + "Manufacturer": "Nvidia", | ||
| 49 | + "Model": "NVIDIA 5090", | ||
| 50 | + "SN": "", | ||
| 51 | + "SocketDesignation": "1", | ||
| 52 | + "Position": "<=/PCIeDevice_1.Position", | ||
| 53 | + "ProcessorType": "2", | ||
| 54 | + "Health": "#/Component_PCIeCard.Health", | ||
| 55 | + "Slot": "<=/PCIeDevice_1.SlotID", | ||
| 56 | + "VendorID": 4318, | ||
| 57 | + "DeviceID": 11141, | ||
| 58 | + "SubVendorID": 5208, | ||
| 59 | + "SubDeviceID": 16798, | ||
| 60 | + "DevBus": "<=/PCIeDevice_1.DevBus", | ||
| 61 | + "DevDevice": "<=/PCIeDevice_1.DevDevice", | ||
| 62 | + "DevFunction": "<=/PCIeDevice_1.DevFunction", | ||
| 63 | + "RefChip": "#/Chip_TempChip", | ||
| 64 | + "SerialNumber": "#/PCIeCard_1.SerialNumber", | ||
| 65 | + "CardFirmwareVersion": "#/PCIeCard_1.FirmwareVersion", | ||
| 66 | + "CardPartNumber": "", | ||
| 67 | + "PrimaryGPUTemperatureCelsius": "<=/Scanner_GPUTemp.Value" | ||
| 68 | + }, | ||
| 69 | + "Entity_GPUCard": { | ||
| 70 | + "Id": 11, | ||
| 71 | + "Name": "GPUCard", | ||
| 72 | + "PowerState": 1, | ||
| 73 | + "Presence": 1, | ||
| 74 | + "Instance": 101 | ||
| 75 | + }, | ||
| 76 | + "PCIeDevice_1": { | ||
| 77 | + "Segment": 1, | ||
| 78 | + "DeviceName": "PCIe Card $ (NVIDIA 5090)", | ||
| 79 | + "DiagnosticFault": 0, | ||
| 80 | + "PredictiveFault": 0, | ||
| 81 | + "FunctionClass": 3, | ||
| 82 | + "Position": "", | ||
| 83 | + "Container": "${Container}", | ||
| 84 | + "GroupPosition": "PCIeDevice_${GroupPosition}", | ||
| 85 | + "BandwidthReduction": 0, | ||
| 86 | + "CorrectableError": 0, | ||
| 87 | + "UncorrectableError": 0, | ||
| 88 | + "FatalError": 0, | ||
| 89 | + "LinkSpeedReduced": 0, | ||
| 90 | + "DeviceType": 8, | ||
| 91 | + "PCIeDeviceType": "SingleFunction", | ||
| 92 | + "SlotType": "FullLength", | ||
| 93 | + "FunctionProtocol": "PCIe", | ||
| 94 | + "FunctionType": "Physical" | ||
| 95 | + }, | ||
| 96 | + "PCIeCard_1": { | ||
| 97 | + "SlotID": "<=/PCIeDevice_1.SlotID", | ||
| 98 | + "NodeID": "<=/PCIeDevice_1.SlotID |> string.format('PCIeCard%s',$1)", | ||
| 99 | + "Name": "NVIDIA 5090", | ||
| 100 | + "DeviceName": "<=/PCIeDevice_1.DeviceName", | ||
| 101 | + "BoardName": "NVIDIA 5090", | ||
| 102 | + "Model": "NVIDIA 5090", | ||
| 103 | + "Description": "NVIDIA 5090", | ||
| 104 | + "FunctionClass": 3, | ||
| 105 | + "VendorID": 4318, | ||
| 106 | + "DeviceID": 11141, | ||
| 107 | + "SubVendorID": 5208, | ||
| 108 | + "SubDeviceID": 16798, | ||
| 109 | + "Position": "<=/PCIeDevice_1.Position", | ||
| 110 | + "LaneOwner": "<=/PCIeDevice_1.SocketID", | ||
| 111 | + "FirmwareVersion": "N/A", | ||
| 112 | + "Manufacturer": "Nvidia", | ||
| 113 | + "PartNumber": "", | ||
| 114 | + "Protocol": "", | ||
| 115 | + "MaxFrameLen": 64, | ||
| 116 | + "LinkSpeed": "N/A", | ||
| 117 | + "LinkSpeedCapability": "N/A", | ||
| 118 | + "PcbVersion": "N/A", | ||
| 119 | + "Health": "<=/Component_PCIeCard.Health", | ||
| 120 | + "Bus": "<=/PCIeDevice_1.Bus", | ||
| 121 | + "Device": "<=/PCIeDevice_1.Device", | ||
| 122 | + "Function": "<=/PCIeDevice_1.Function", | ||
| 123 | + "DevBus": "<=/PCIeDevice_1.DevBus", | ||
| 124 | + "DevDevice": "<=/PCIeDevice_1.DevDevice", | ||
| 125 | + "SerialNumber": "", | ||
| 126 | + "DevFunction": "<=/PCIeDevice_1.DevFunction", | ||
| 127 | + "CardManufacturer": "Nvidia", | ||
| 128 | + "CardModel": "NVIDIA 5090" | ||
| 129 | + }, | ||
| 130 | + "Event_PCIeCardUCE": { | ||
| 131 | + "EventKeyId": "PCIeCard.PCIeCardUncorrectableErr", | ||
| 132 | + "Condition": 1, | ||
| 133 | + "LedFaultCode": "q$$" | ||
| 134 | + }, | ||
| 135 | + "Event_PCIeCardCE": { | ||
| 136 | + "EventKeyId": "PCIeCard.PCIeCardCEHardFailure", | ||
| 137 | + "Condition": 1, | ||
| 138 | + "LedFaultCode": "q$$" | ||
| 139 | + }, | ||
| 140 | + "Event_PcieCardReplaceMntr": { | ||
| 141 | + "EventKeyId": "PcieCard.PcieCardReplace", | ||
| 142 | + "Condition": 1 | ||
| 143 | + }, | ||
| 144 | + "ThresholdSensor_GPUTemp": { | ||
| 145 | + "AssertMask": 128, | ||
| 146 | + "DeassertMask": 28800, | ||
| 147 | + "ReadingMask": 2056, | ||
| 148 | + "Linearization": 0, | ||
| 149 | + "M": 100, | ||
| 150 | + "RBExp": 224, | ||
| 151 | + "UpperNoncritical": 93, | ||
| 152 | + "PositiveHysteresis": 2, | ||
| 153 | + "NegativeHysteresis": 2 | ||
| 154 | + }, | ||
| 155 | + "CoolingRequirement_1_58": { | ||
| 156 | + "RequirementId": "${Slot} |> expr((58 << 8) | $1)", | ||
| 157 | + "MonitoringStatus": "<=/Scanner_GPUTemp.Value |> expr($1 >= 255 ? 1 : 0)", | ||
| 158 | + "MonitoringValue": "<=/Scanner_GPUTemp.Value |> expr($1 >= 255 ? 30 : ($1 & 255))", | ||
| 159 | + "FailedValue": 80, | ||
| 160 | + "TargetTemperatureCelsius": 73, | ||
| 161 | + "MaxAllowedTemperatureCelsius": 79, | ||
| 162 | + "SensorName": "#/ThresholdSensor_GPUTemp.SensorName" | ||
| 163 | + }, | ||
| 164 | + "Event_OverTemp": { | ||
| 165 | + "EventKeyId": "PCIeCard.PCIeCardOverTemp", | ||
| 166 | + "Condition": "<=/ThresholdSensor_GPUTemp.UpperNoncritical", | ||
| 167 | + "Hysteresis": "<=/ThresholdSensor_GPUTemp.PositiveHysteresis" | ||
| 168 | + }, | ||
| 169 | + "Event_TempFail": { | ||
| 170 | + "EventKeyId": "PcieCard.PCIeCardTempFail", | ||
| 171 | + "Condition": 1 | ||
| 172 | + }, | ||
| 173 | + "Event_PCIeBandWidth": { | ||
| 174 | + "EventKeyId": "PCIeCard.PCIeCardBandWidthDecreased", | ||
| 175 | + "Condition": 1 | ||
| 176 | + }, | ||
| 177 | + "Event_PCIeLinkSpeed": { | ||
| 178 | + "EventKeyId": "PCIeCard.PCIeCardLinkSpeedReduced", | ||
| 179 | + "Condition": 1 | ||
| 180 | + } | ||
| 181 | + } | ||
| 182 | +} | ||
| @@ -0,0 +1,114 @@ | |||
| 1 | +{ | ||
| 2 | + "FormatVersion": "3.00", | ||
| 3 | + "DataVersion": "3.00", | ||
| 4 | + "Unit": { | ||
| 5 | + "Type": "PCIeCard", | ||
| 6 | + "Name": "PCIeCard_1" | ||
| 7 | + }, | ||
| 8 | + "Objects": { | ||
| 9 | + "Component_PCIeCard": { | ||
| 10 | + "FruId": 255, | ||
| 11 | + "Name": "<=/PCIeDevice_1.DeviceName", | ||
| 12 | + "Instance": "<=/PCIeDevice_1.SlotID", | ||
| 13 | + "BoardId": 65535, | ||
| 14 | + "Type": 8, | ||
| 15 | + "Presence": 1, | ||
| 16 | + "Health": 0, | ||
| 17 | + "PowerState": 1, | ||
| 18 | + "UniqueId": "N/A", | ||
| 19 | + "Manufacturer": "Nvidia", | ||
| 20 | + "ReplaceFlag": 0, | ||
| 21 | + "PreviousSN": "", | ||
| 22 | + "SerialNumber": "<=/PCIeCard_1.SerialNumber", | ||
| 23 | + "GroupId": 1 | ||
| 24 | + }, | ||
| 25 | + "ThresholdSensor_GPUTemp": { | ||
| 26 | + "OwnerId": 32, | ||
| 27 | + "OwnerLun": 0, | ||
| 28 | + "EntityId": "<=/Entity_GPUCard.Id", | ||
| 29 | + "EntityInstance": "<=/Entity_GPUCard.Instance", | ||
| 30 | + "Initialization": 127, | ||
| 31 | + "Capabilities": 104, | ||
| 32 | + "SensorType": 1, | ||
| 33 | + "ReadingType": 1, | ||
| 34 | + "SensorName": "<=/PCIeDevice_1.SlotID |> string.format('GPU%s Temp',$1)", | ||
| 35 | + "Unit": 128, | ||
| 36 | + "BaseUnit": 1, | ||
| 37 | + "ModifierUnit": 0, | ||
| 38 | + "Analog": 1, | ||
| 39 | + "NominalReading": 25, | ||
| 40 | + "NormalMaximum": 0, | ||
| 41 | + "NormalMinimum": 0, | ||
| 42 | + "MaximumReading": 127, | ||
| 43 | + "MinimumReading": 128, | ||
| 44 | + "Reading": "<=/Scanner_GPUTemp.Value", | ||
| 45 | + "ReadingStatus": "<=/Scanner_GPUTemp.Value;<=/Scanner_GPUTemp.Status |> expr($1 >= 255 ? 2 : ($2 == 0 ? 0 : 2))" | ||
| 46 | + }, | ||
| 47 | + "Event_PCIeCardUCE": { | ||
| 48 | + "Reading": "<=/PCIeDevice_1.DiagnosticFault;<=/PCIeDevice_1.UCEByBIOS |> expr(($1 + $2) == 0 ? 0 : 1)", | ||
| 49 | + "OperatorId": 5, | ||
| 50 | + "Enabled": true, | ||
| 51 | + "AdditionalInfo": "2", | ||
| 52 | + "DescArg2": "#/Component_PCIeCard.Name", | ||
| 53 | + "DescArg4": "NA", | ||
| 54 | + "Component": "#/Component_PCIeCard" | ||
| 55 | + }, | ||
| 56 | + "Event_PCIeCardCE": { | ||
| 57 | + "Reading": "<=/PCIeDevice_1.PredictiveFault", | ||
| 58 | + "OperatorId": 5, | ||
| 59 | + "Enabled": true, | ||
| 60 | + "AdditionalInfo": "2", | ||
| 61 | + "DescArg2": "#/Component_PCIeCard.Name", | ||
| 62 | + "Component": "#/Component_PCIeCard" | ||
| 63 | + }, | ||
| 64 | + "Event_PcieCardReplaceMntr": { | ||
| 65 | + "Reading": "<=/Component_PCIeCard.ReplaceFlag", | ||
| 66 | + "OperatorId": 5, | ||
| 67 | + "Enabled": true, | ||
| 68 | + "AdditionalInfo": "1", | ||
| 69 | + "DescArg1": "#/Component_PCIeCard.Name", | ||
| 70 | + "DescArg2": "#/Component_PCIeCard.PreviousSN", | ||
| 71 | + "DescArg3": "#/Component_PCIeCard.SerialNumber", | ||
| 72 | + "Component": "#/Component_PCIeCard" | ||
| 73 | + }, | ||
| 74 | + "Event_OverTemp": { | ||
| 75 | + "Reading": "<=/Scanner_GPUTemp.Value |> expr(($1 >= 255) ? 30 : ($1 & 255))", | ||
| 76 | + "@Default": { | ||
| 77 | + "Condition": 93 | ||
| 78 | + }, | ||
| 79 | + "OperatorId": 4, | ||
| 80 | + "Enabled": true, | ||
| 81 | + "Component": "#/Component_PCIeCard", | ||
| 82 | + "AdditionalInfo": "2", | ||
| 83 | + "DescArg2": "#/Component_PCIeCard.Name", | ||
| 84 | + "DescArg4": "#/Event_OverTemp.Reading |> string.format('%s', $1)", | ||
| 85 | + "DescArg5": "#/ThresholdSensor_GPUTemp.UpperNoncritical" | ||
| 86 | + }, | ||
| 87 | + "Event_TempFail": { | ||
| 88 | + "Reading": "<=/Scanner_GPUTemp.Status;<=/Scanner_GPUTemp.Value |> expr($1 == 0 ? ($2 == 255 ? 1 : 0) : 0)", | ||
| 89 | + "OperatorId": 5, | ||
| 90 | + "Enabled": true, | ||
| 91 | + "Component": "#/Component_PCIeCard", | ||
| 92 | + "AdditionalInfo": "2", | ||
| 93 | + "DescArg2": "#/Component_PCIeCard.Name" | ||
| 94 | + }, | ||
| 95 | + "Event_PCIeBandWidth": { | ||
| 96 | + "Reading": "<=/PCIeDevice_1.BandwidthReduction", | ||
| 97 | + "OperatorId": 5, | ||
| 98 | + "Enabled": true, | ||
| 99 | + "AdditionalInfo": "2", | ||
| 100 | + "DescArg2": "#/PCIeDevice_1.SlotID", | ||
| 101 | + "DescArg3": "(5090)", | ||
| 102 | + "Component": "#/Component_PCIeCard" | ||
| 103 | + }, | ||
| 104 | + "Event_PCIeLinkSpeed": { | ||
| 105 | + "Reading": "<=/PCIeDevice_1.LinkSpeedReduced", | ||
| 106 | + "OperatorId": 5, | ||
| 107 | + "Enabled": true, | ||
| 108 | + "AdditionalInfo": "2", | ||
| 109 | + "DescArg2": "#/PCIeDevice_1.SlotID", | ||
| 110 | + "DescArg3": "(5090)", | ||
| 111 | + "Component": "#/Component_PCIeCard" | ||
| 112 | + } | ||
| 113 | + } | ||
| 114 | +} | ||