File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 63, in wrapper
func(*args, **kwargs)
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 264, in task_distribute
resource_proxy[SUB_PROCESS_STATE].append(True)
File "<string>", line 2, in append
File "/usr/lib64/python3.11/multiprocessing/managers.py", line 819, in _callmethod
self._connect()
File "/usr/lib64/python3.11/multiprocessing/managers.py", line 806, in _connect
conn = self._Client(self._token.address, authkey=self._authkey)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.11/multiprocessing/connection.py", line 518, in Client
c = SocketClient(address)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.11/multiprocessing/connection.py", line 646, in SocketClient
s.connect(address)
ConnectionRefusedError: [Errno 111] Connection refused
Process ForkServerProcess-8:
Traceback (most recent call last):
File "/usr/lib64/python3.11/multiprocessing/managers.py", line 815, in _callmethod
conn = self._tls.connection
^^^^^^^^^^^^^^^^^^^^
AttributeError: 'ForkAwareLocal' object has no attribute 'connection'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/usr/lib64/python3.11/multiprocessing/process.py", line 314, in _bootstrap
self.run()
File "/usr/lib64/python3.11/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 71, in wrapper
raise exp
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 63, in wrapper
func(*args, **kwargs)
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 264, in task_distribute
resource_proxy[SUB_PROCESS_STATE].append(True)
File "<string>", line 2, in append
File "/usr/lib64/python3.11/multiprocessing/managers.py", line 819, in _callmethod
self._connect()
File "/usr/lib64/python3.11/multiprocessing/managers.py", line 806, in _connect
conn = self._Client(self._token.address, authkey=self._authkey)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.11/multiprocessing/connection.py", line 518, in Client
c = SocketClient(address)
^^^^^^^^^^^^^^^^^^^^^
File "/usr/lib64/python3.11/multiprocessing/connection.py", line 646, in SocketClient
s.connect(address)
ConnectionRefusedError: [Errno 111] Connection refused
1. 环境配置
2. 多机通信环境变量设置
3. rank_table_file.json设置
{ "version": "1.0", "server_count": "2", "server_list": [ { "server_id": "172.16.144.144", "container_ip": "10.0.0.2", "device": [ { "device_id": "0", "device_ip": "29.10.189.120", "rank_id": "0" }, { "device_id": "1", "device_ip": "29.10.126.84", "rank_id": "1" }, { "device_id": "2", "device_ip": "29.10.83.192", "rank_id": "2" }, { "device_id": "3", "device_ip": "29.10.165.249", "rank_id": "3" }, { "device_id": "4", "device_ip": "29.10.184.45", "rank_id": "4" }, { "device_id": "5", "device_ip": "29.10.31.246", "rank_id": "5" }, { "device_id": "6", "device_ip": "29.10.110.72", "rank_id": "6" }, { "device_id": "7", "device_ip": "29.10.153.77", "rank_id": "7" } ] }, { "server_id": "172.16.144.161", "container_ip": "10.0.0.15", "device": [ { "device_id": "0", "device_ip": "29.10.46.97", "rank_id": "8" }, { "device_id": "1", "device_ip": "29.10.9.16", "rank_id": "9" }, { "device_id": "2", "device_ip": "29.10.113.87", "rank_id": "10" }, { "device_id": "3", "device_ip": "29.10.64.147", "rank_id": "11" }, { "device_id": "4", "device_ip": "29.10.189.233", "rank_id": "12" }, { "device_id": "5", "device_ip": "29.10.140.91", "rank_id": "13" }, { "device_id": "6", "device_ip": "29.10.82.192", "rank_id": "14" }, { "device_id": "7", "device_ip": "29.10.66.160", "rank_id": "15" } ] } ], "status": "completed" }4. mindie-server启动
5. 硬件信息
6. 报错信息
File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 63, in wrapper func(*args, **kwargs) File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 264, in task_distribute resource_proxy[SUB_PROCESS_STATE].append(True) File "<string>", line 2, in append File "/usr/lib64/python3.11/multiprocessing/managers.py", line 819, in _callmethod self._connect() File "/usr/lib64/python3.11/multiprocessing/managers.py", line 806, in _connect conn = self._Client(self._token.address, authkey=self._authkey) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib64/python3.11/multiprocessing/connection.py", line 518, in Client c = SocketClient(address) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib64/python3.11/multiprocessing/connection.py", line 646, in SocketClient s.connect(address) ConnectionRefusedError: [Errno 111] Connection refused Process ForkServerProcess-8: Traceback (most recent call last): File "/usr/lib64/python3.11/multiprocessing/managers.py", line 815, in _callmethod conn = self._tls.connection ^^^^^^^^^^^^^^^^^^^^ AttributeError: 'ForkAwareLocal' object has no attribute 'connection' During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/usr/lib64/python3.11/multiprocessing/process.py", line 314, in _bootstrap self.run() File "/usr/lib64/python3.11/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 71, in wrapper raise exp File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 63, in wrapper func(*args, **kwargs) File "/usr/local/Ascend/ascend-toolkit/latest/python/site-packages/tbe/common/repository_manager/route.py", line 264, in task_distribute resource_proxy[SUB_PROCESS_STATE].append(True) File "<string>", line 2, in append File "/usr/lib64/python3.11/multiprocessing/managers.py", line 819, in _callmethod self._connect() File "/usr/lib64/python3.11/multiprocessing/managers.py", line 806, in _connect conn = self._Client(self._token.address, authkey=self._authkey) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib64/python3.11/multiprocessing/connection.py", line 518, in Client c = SocketClient(address) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib64/python3.11/multiprocessing/connection.py", line 646, in SocketClient s.connect(address) ConnectionRefusedError: [Errno 111] Connection refused