mindx-dl-deviceinfo-node1:
CmName: "mindx-dl-deviceinfo-node1"
DeviceList:
huawei.com/Ascend910-Fault: |
[
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-0", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-1", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-2", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-3", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-4", "fault_code": "80E01801,11111111,22222222,33333333",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" },
"11111111": { "fault_time": 100000, "fault_level": "RestartBusiness" },
"22222222": { "fault_time": 100000, "fault_level": "RestartBusiness" },
"33333333": { "fault_time": 100000, "fault_level": "RestartBusiness" } } }
]
huawei.com/Ascend910-Unhealthy: Ascend910-0,Ascend910-1,Ascend910-2,Ascend910-3,Ascend910-4
mindx-dl-deviceinfo-node2:
CmName: "mindx-dl-deviceinfo-node2"
DeviceList:
huawei.com/Ascend910-Fault: |
[
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-0", "fault_code": "80E01801,22222222",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" },
"22222222": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-1", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-2", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-3", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } },
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-4", "fault_code": "80E01801",
"fault_time_and_level_map": { "80E01801": { "fault_time": 100000, "fault_level": "RestartBusiness" } } }
]
huawei.com/Ascend910-Unhealthy: Ascend910-0,Ascend910-1,Ascend910-2,Ascend910-3,Ascend910-4
---
mindx-dl-deviceinfo-node1:
CmName: "mindx-dl-deviceinfo-node1"
DeviceList:
huawei.com/Ascend910-Fault: |
[
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-4", "fault_code": "11111111,22222222,33333333",
"large_model_fault_level":"RestartBusiness","fault_level":"RestartBusiness","fault_handling":"RestartBusiness",
"fault_time_and_level_map": { "11111111": { "fault_time": 100000, "fault_level": "RestartBusiness" },
"22222222": { "fault_time": 100000, "fault_level": "RestartBusiness" },
"33333333": { "fault_time": 100000, "fault_level": "RestartBusiness" } } }
]
huawei.com/Ascend910-Unhealthy: Ascend910-4
mindx-dl-deviceinfo-node2:
CmName: "mindx-dl-deviceinfo-node2"
DeviceList:
huawei.com/Ascend910-Fault: |
[
{ "fault_type": "CardUnhealthy", "npu_name": "Ascend910-0", "fault_code": "22222222",
"large_model_fault_level":"RestartBusiness","fault_level":"RestartBusiness","fault_handling":"RestartBusiness",
"fault_time_and_level_map": { "22222222": { "fault_time": 100000, "fault_level": "RestartBusiness" } } }
]
huawei.com/Ascend910-Unhealthy: Ascend910-0
---
node1:
NodeName: "node1"
DeviceInfo:
Ascend910-0:
DeviceName: "Ascend910-0"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-1:
DeviceName: "Ascend910-1"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-2:
DeviceName: "Ascend910-2"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-3:
DeviceName: "Ascend910-3"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-4:
DeviceName: "Ascend910-4"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
node2:
NodeName: "node2"
DeviceInfo:
Ascend910-0:
DeviceName: "Ascend910-0"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-1:
DeviceName: "Ascend910-1"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-2:
DeviceName: "Ascend910-2"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-3:
DeviceName: "Ascend910-3"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
Ascend910-4:
DeviceName: "Ascend910-4"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
---
job1:
node1:
device:
- device_id: 0
rank_id: 0
server_name: node1
node2:
device:
- device_id: 0
rank_id: 1
server_name: node2
job2:
node1:
device:
- device_id: 1
rank_id: 2
server_name: node1
node2:
device:
- device_id: 1
rank_id: 3
server_name: node2
job3:
node1:
device:
- device_id: 2
rank_id: 4
server_name: node1
node2:
device:
- device_id: 2
rank_id: 5
server_name: node2
job4:
node1:
device:
- device_id: 3
rank_id: 6
server_name: node1
node2:
device:
- device_id: 3
rank_id: 7
server_name: node2
job5:
node1:
device:
- device_id: 4
rank_id: 8
server_name: node1
node2:
device:
- device_id: 4
rank_id: 9
server_name: node2
---
job1: true
job2: true
job3: true
job4: true
job5: true
---
job1:
JobId: job1
RetryNode:
node1:
NodeName: node1
DeviceInfo:
Ascend910-0:
DeviceName: "Ascend910-0"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
node2:
NodeName: node2
DeviceInfo:
Ascend910-0:
DeviceName: "Ascend910-0"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
job2:
JobId: job2
RetryNode:
node1:
NodeName: node1
DeviceInfo:
Ascend910-1:
DeviceName: "Ascend910-1"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
node2:
NodeName: node2
DeviceInfo:
Ascend910-1:
DeviceName: "Ascend910-1"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
job3:
JobId: job3
RetryNode:
node1:
NodeName: node1
DeviceInfo:
Ascend910-2:
DeviceName: "Ascend910-2"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
node2:
NodeName: node2
DeviceInfo:
Ascend910-2:
DeviceName: "Ascend910-2"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
job4:
JobId: job4
RetryNode:
node1:
NodeName: node1
DeviceInfo:
Ascend910-3:
DeviceName: "Ascend910-3"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
node2:
NodeName: node2
DeviceInfo:
Ascend910-3:
DeviceName: "Ascend910-3"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
job5:
JobId: job5
RetryNode:
node1:
NodeName: node1
DeviceInfo:
Ascend910-4:
DeviceName: "Ascend910-4"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"
node2:
NodeName: node2
DeviceInfo:
Ascend910-4:
DeviceName: "Ascend910-4"
FaultDetail:
FaultTime: 100000
RecoverTime: 9223372036854775807
CompleteTime: 9223372036854775807
FaultType: "0"