Revert "修复ruff-check检查出来的规范性问题"-MindIE-Motor-CPP-AtomGit

Mmindie_motor/python/mindie_motor/node_manager/common/logging.py+2-2

	@@ -119,10 +119,10 @@ def _create_log_file(log_file):
119	else:	119	else:
120	clean_path = os.path.normpath(log_file)	120	clean_path = os.path.normpath(log_file)
121	if os.path.islink(clean_path):	121	if os.path.islink(clean_path):
122	- err_msg = "Check log file path failed because it's a symbolic."	122	+ err_msg = f"Check log file path failed because it's a symbolic."
		ascend-robot3月10日代码可读性与一致性: 第122行将错误消息从普通字符串改为f-string，但该字符串中没有需要格式化的变量。这种改动增加了不必要的复杂性，与第125行的改动形成了不一致的处理方式。虽然第125行使用f-string是合理的（因为包含了变量clean_path），但第122行没有变量需要插入，使用普通字符串更简洁。这种不一致性会影响代码的可读性和维护性。问题类型: 代码可读性与一致性文件路径: `mindie_motor/python/mindie_motor/node_manager/common/logging.py` 行号: 122 问题代码: err_msg = f"Check log file path failed because it's a symbolic." 修改建议: 将第122行改回普通字符串格式：err_msg = "Check log file path failed because it's a symbolic."，以保持代码简洁性和一致性。或者，如果团队有统一使用f-string的编码规范，那么第125行也应该相应地调整格式，确保两行代码风格一致。 --- 此评论由代码审查工具自动生成
123	raise ValueError(err_msg)	123	raise ValueError(err_msg)
124	if len(clean_path) > 1024:	124	if len(clean_path) > 1024:
125	- err_msg = "Path of log file is too long, it should not exceed 1024 character."	125	+ err_msg = f"Path of log file is too long, it should not exceed 1024 character."
		ascend-robot3月10日错误信息准确性: 第125行的错误消息中使用了单数形式的'character'，但实际检查的是路径长度是否超过1024个字符。当路径长度超过限制时，应该使用复数形式'characters'更符合英语语法习惯。虽然这是一个小问题，但在国际化或面向英语用户的项目中，这种细节会影响专业性。问题类型: 错误信息准确性文件路径: `mindie_motor/python/mindie_motor/node_manager/common/logging.py` 行号: 125 问题代码: err_msg = f"Path of log file is too long, it should not exceed 1024 character." 修改建议: 将错误消息中的'character'改为复数形式'characters'：err_msg = f"Path of log file is too long, it should not exceed 1024 characters." --- 此评论由代码审查工具自动生成
126	raise ValueError(err_msg)	126	raise ValueError(err_msg)
127	os.chmod(log_file, mode)	127	os.chmod(log_file, mode)
128		128

Mmindie_motor/python/mindie_motor/node_manager/common/mindie_cpu_binding.py+4-1

	@@ -1,9 +1,12 @@
1	# Copyright Huawei Technologies Co., Ltd. 2023-2024. All rights reserved.	1	# Copyright Huawei Technologies Co., Ltd. 2023-2024. All rights reserved.
		2	+import argparse
2	import os	3	import os
		4	+from itertools import accumulate
3	from dataclasses import dataclass	5	from dataclasses import dataclass
4	import logging	6	import logging
5	-from typing import List, Dict, Union	7	+from typing import List, Dict, Tuple, Union
6	import subprocess	8	import subprocess
		9	+import psutil
7		10
8		11
9	class ENV:	12	class ENV:

Mmindie_motor/python/mindie_motor/node_manager/core/config.py+5-4

	@@ -11,6 +11,7 @@
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
13	import os	13	import os
		14	+import json
14	import ipaddress	15	import ipaddress
15	from node_manager.common.utils import _SingletonMeta, validate_port_range	16	from node_manager.common.utils import _SingletonMeta, validate_port_range
16	from node_manager.common.logging import Log	17	from node_manager.common.logging import Log
	@@ -41,12 +42,12 @@ class GeneralConfig(metaclass=_SingletonMeta):
41	@staticmethod	42	@staticmethod
42	def _check_server_config_valid(config):	43	def _check_server_config_valid(config):
43	if SERVER_CONFIG not in config:	44	if SERVER_CONFIG not in config:
44	- raise KeyError("Invalid Server Engine Config File")	45	+ raise KeyError(f"Invalid Server Engine Config File")
45	server_config = config[SERVER_CONFIG]	46	server_config = config[SERVER_CONFIG]
46	if MANAGEMENT_PORT not in server_config:	47	if MANAGEMENT_PORT not in server_config:
47	- raise KeyError("Management Port is Missing in Server Engine Config File")	48	+ raise KeyError(f"Management Port is Missing in Server Engine Config File")
48	if "distDPServerEnabled" not in server_config or not isinstance(server_config["distDPServerEnabled"], bool):	49	if "distDPServerEnabled" not in server_config or not isinstance(server_config["distDPServerEnabled"], bool):
49	- raise KeyError("distDPServerEnabled is Missing or Invalid in Server Engine Config File")	50	+ raise KeyError(f"distDPServerEnabled is Missing or Invalid in Server Engine Config File")
		ascend-robot3月10日代码可读性: 异常消息使用f-string但未包含变量，与前两行问题相同。原字符串'distDPServerEnabled is Missing or Invalid in Server Engine Config File'已经足够清晰。问题类型: 代码可读性文件路径: `mindie_motor/python/mindie_motor/node_manager/core/config.py` 行号: 50 问题代码: raise KeyError(f"distDPServerEnabled is Missing or Invalid in Server Engine Config File") 修改建议: 移除f-string前缀：raise KeyError("distDPServerEnabled is Missing or Invalid in Server Engine Config File") --- 此评论由代码审查工具自动生成
50		51
51	@staticmethod	52	@staticmethod
52	def _load_server_engine_ip():	53	def _load_server_engine_ip():
	@@ -55,7 +56,7 @@ class GeneralConfig(metaclass=_SingletonMeta):
55	raise KeyError("[Config] Please Check Environment Variable Configuration of POD_IP")	56	raise KeyError("[Config] Please Check Environment Variable Configuration of POD_IP")
56	address = ipaddress.ip_address(pod_ip)	57	address = ipaddress.ip_address(pod_ip)
57	if address.version != IPV4 and address.version != IPV6:	58	if address.version != IPV4 and address.version != IPV6:
58	- raise Exception('[Config] POD_IP is not ipv4 or ipv6.')	59	+ raise Exception(f'[Config] POD_IP is not ipv4 or ipv6.')
		ascend-robot3月10日安全编码规范: 在异常消息中使用了f-string，但消息内容为静态字符串，没有使用任何变量插值。虽然这里使用了单引号字符串，但同样存在不必要的f-string前缀问题。问题类型: 安全编码规范文件路径: `mindie_motor/python/mindie_motor/node_manager/core/config.py` 行号: 59 问题代码: raise Exception(f'[Config] POD_IP is not ipv4 or ipv6.') 修改建议: 移除不必要的f-string前缀，改为普通字符串：raise Exception('[Config] POD_IP is not ipv4 or ipv6.') --- 此评论由代码审查工具自动生成
59	return pod_ip	60	return pod_ip
60		61
61	@classmethod	62	@classmethod

Mmindie_motor/python/mindie_motor/node_manager/core/fault_mng.py+14-13

	@@ -20,6 +20,7 @@ from node_manager.common.logging import Log
20	from node_manager.models.enums import (	20	from node_manager.models.enums import (
21	EngineCmd,	21	EngineCmd,
22	NodeRunningStatus,	22	NodeRunningStatus,
		23	+ ServiceStatus,
23	ControllerCmd,	24	ControllerCmd,
24	)	25	)
25	from node_manager.common.utils import _SingletonMeta	26	from node_manager.common.utils import _SingletonMeta
	@@ -151,7 +152,7 @@ class FaultManager(metaclass=_SingletonMeta):
151	"""	152	"""
152	self.init_heartbeat_mng()	153	self.init_heartbeat_mng()
153	self.logger.info(	154	self.logger.info(
154	- "[_cmd_failed_further_action] Set running status = ABNORMAL"	155	+ f"[_cmd_failed_further_action] Set running status = ABNORMAL"
155	)	156	)
156	self.heartbeat_mng.set_running_status(NodeRunningStatus.ABNORMAL.value)	157	self.heartbeat_mng.set_running_status(NodeRunningStatus.ABNORMAL.value)
157		158
	@@ -174,7 +175,7 @@ class FaultManager(metaclass=_SingletonMeta):
174	- status (bool): Whether the command was executed successfully.	175	- status (bool): Whether the command was executed successfully.
175	- reason (str): Explanation of why the command succeeded or failed.	176	- reason (str): Explanation of why the command succeeded or failed.
176	"""	177	"""
177	- self.logger.info("FaultManager: pause engine starts.")	178	+ self.logger.info(f"FaultManager: pause engine starts.")
178	self.init_heartbeat_mng()	179	self.init_heartbeat_mng()
179	_, after_state = self._find_matching_index(	180	_, after_state = self._find_matching_index(
180	cmd=ControllerCmd.PAUSE_ENGINE.value,	181	cmd=ControllerCmd.PAUSE_ENGINE.value,
	@@ -191,14 +192,14 @@ class FaultManager(metaclass=_SingletonMeta):
191	ret_data = self._extract_info(ret_info_all, field=STATUS_STR)	192	ret_data = self._extract_info(ret_info_all, field=STATUS_STR)
192	if all(ret_data):	193	if all(ret_data):
193	self.logger.info(	194	self.logger.info(
194	- "FaultManager: Successfully executed the PAUSE ENGINE cmd."	195	+ f"FaultManager: Successfully executed the PAUSE ENGINE cmd."
195	)	196	)
196	# 发送请求成功,命令执行成功	197	# 发送请求成功,命令执行成功
197	return {STATUS_STR: True, REASON_STR: None}	198	return {STATUS_STR: True, REASON_STR: None}
198	else:	199	else:
199	# 请求发送成功,命令执行有失败	200	# 请求发送成功,命令执行有失败
200	self.logger.error(	201	self.logger.error(
201	- "FaultManager: PAUSE ENGINE cmd sent successfully, but the cmd execution failed."	202	+ f"FaultManager: PAUSE ENGINE cmd sent successfully, but the cmd execution failed."
202	)	203	)
203	self._set_heartbeat_check_allowed(	204	self._set_heartbeat_check_allowed(
204	True	205	True
	@@ -213,7 +214,7 @@ class FaultManager(metaclass=_SingletonMeta):
213	else:	214	else:
214	# 请求发送失败	215	# 请求发送失败
215	# status表明当前命令的执行状态是否成功	216	# status表明当前命令的执行状态是否成功
216	- self.logger.error("FaultManager: Sending PAUSE ENGINE cmd failed.")	217	+ self.logger.error(f"FaultManager: Sending PAUSE ENGINE cmd failed.")
217	self._set_heartbeat_check_allowed(	218	self._set_heartbeat_check_allowed(
218	True	219	True
219	) # 默认下一步指令可能不发送cmd,启动心跳检测,kill异常pod	220	) # 默认下一步指令可能不发送cmd,启动心跳检测,kill异常pod
	@@ -230,7 +231,7 @@ class FaultManager(metaclass=_SingletonMeta):
230	}	231	}
231		232
232	def _reinit_npu(self) -> dict:	233	def _reinit_npu(self) -> dict:
233	- self.logger.info("FaultManager: REINIT NPU starts.")	234	+ self.logger.info(f"FaultManager: REINIT NPU starts.")
234	self.init_heartbeat_mng()	235	self.init_heartbeat_mng()
235	_, after_state = self._find_matching_index(	236	_, after_state = self._find_matching_index(
236	cmd=ControllerCmd.REINIT_NPU.value,	237	cmd=ControllerCmd.REINIT_NPU.value,
	@@ -248,7 +249,7 @@ class FaultManager(metaclass=_SingletonMeta):
248	else:	249	else:
249	# 不在pause_engine->reinit_npu->start_engine指令流中	250	# 不在pause_engine->reinit_npu->start_engine指令流中
250	self.logger.error(	251	self.logger.error(
251	- "not supported single cmd, must in pause_engine->reinit_npu->start_engine cmd stream"	252	+ f"not supported single cmd, must in pause_engine->reinit_npu->start_engine cmd stream"
252	)	253	)
253	return {	254	return {
254	STATUS_STR: False,	255	STATUS_STR: False,
	@@ -264,13 +265,13 @@ class FaultManager(metaclass=_SingletonMeta):
264	if all(ret_data):	265	if all(ret_data):
265	# 发送请求成功,命令执行成功	266	# 发送请求成功,命令执行成功
266	self.logger.info(	267	self.logger.info(
267	- "FaultManager: Successfully executed the REINIT NPU cmd."	268	+ f"FaultManager: Successfully executed the REINIT NPU cmd."
268	)	269	)
269	self.heartbeat_mng.set_running_status(after_state)	270	self.heartbeat_mng.set_running_status(after_state)
270	else:	271	else:
271	# 发送请求成功,命令执行有失败	272	# 发送请求成功,命令执行有失败
272	self.logger.error(	273	self.logger.error(
273	- "FaultManager: REINIT NPU cmd sent successfully, but the cmd execution failed."	274	+ f"FaultManager: REINIT NPU cmd sent successfully, but the cmd execution failed."
274	)	275	)
275	self._set_heartbeat_check_allowed(	276	self._set_heartbeat_check_allowed(
276	True	277	True
	@@ -299,7 +300,7 @@ class FaultManager(metaclass=_SingletonMeta):
299		300
300		301
301	def _start_engine(self):	302	def _start_engine(self):
302	- self.logger.info("FaultManager: start engine starts.")	303	+ self.logger.info(f"FaultManager: start engine starts.")
303	self.init_heartbeat_mng()	304	self.init_heartbeat_mng()
304	_, after_state = self._find_matching_index(	305	_, after_state = self._find_matching_index(
305	cmd=ControllerCmd.START_ENGINE.value,	306	cmd=ControllerCmd.START_ENGINE.value,
	@@ -314,7 +315,7 @@ class FaultManager(metaclass=_SingletonMeta):
314	if all(ret_data):	315	if all(ret_data):
315	# 发送请求成功,命令执行成功	316	# 发送请求成功,命令执行成功
316	self.logger.info(	317	self.logger.info(
317	- "FaultManager: Successfully executed the START ENGINE cmd."	318	+ f"FaultManager: Successfully executed the START ENGINE cmd."
318	)	319	)
319	self._set_heartbeat_check_allowed(True)	320	self._set_heartbeat_check_allowed(True)
320	self.heartbeat_mng.set_running_status(after_state)	321	self.heartbeat_mng.set_running_status(after_state)
	@@ -322,7 +323,7 @@ class FaultManager(metaclass=_SingletonMeta):
322	else:	323	else:
323	# 发送请求成功,命令执行有失败	324	# 发送请求成功,命令执行有失败
324	self.logger.warning(	325	self.logger.warning(
325	- "FaultManager: START ENGINE cmd sent successfully, but the cmd execution failed."	326	+ f"FaultManager: START ENGINE cmd sent successfully, but the cmd execution failed."
326	)	327	)
327	self._set_heartbeat_check_allowed(	328	self._set_heartbeat_check_allowed(
328	True	329	True
	@@ -336,7 +337,7 @@ class FaultManager(metaclass=_SingletonMeta):
336	return {STATUS_STR: False, REASON_STR: reason_val_str}	337	return {STATUS_STR: False, REASON_STR: reason_val_str}
337	else:	338	else:
338	# 请求发送失败	339	# 请求发送失败
339	- self.logger.warning("FaultManager: Sending START ENGINE cmd failed.")	340	+ self.logger.warning(f"FaultManager: Sending START ENGINE cmd failed.")
340	self._set_heartbeat_check_allowed(	341	self._set_heartbeat_check_allowed(
341	True	342	True
342	) # 默认server不下发下一步指令,启动心跳检测,kill异常pod	343	) # 默认server不下发下一步指令,启动心跳检测,kill异常pod

Mmindie_motor/python/mindie_motor/node_manager/core/heartbeat_mng.py+10-10

Mmindie_motor/python/mindie_motor/node_manager/core/runtime_param_checker.py+5-2

	@@ -15,7 +15,6 @@ import subprocess
15	import threading	15	import threading
16	import time	16	import time
17	from datetime import datetime, timedelta, timezone	17	from datetime import datetime, timedelta, timezone
18	-import importlib.util
19		18
20	from node_manager.common.utils import _SingletonMeta	19	from node_manager.common.utils import _SingletonMeta
21	from node_manager.common.logging import Log	20	from node_manager.common.logging import Log
	@@ -46,7 +45,11 @@ class RuntimeParamChecker(metaclass=_SingletonMeta):
46		45
47	@staticmethod	46	@staticmethod
48	def has_msprechecker():	47	def has_msprechecker():
49	- return importlib.util.find_spec('msprechecker') is not None	48	+ try:
		49	+ import msprechecker
		50	+ return True
		51	+ except ImportError:
		52	+ return False
50		53
51	@staticmethod	54	@staticmethod
52	def get_check_rule_path():	55	def get_check_rule_path():

Mmindie_motor/python/mindie_motor/node_manager/daemon_manager/base_daemon_manager.py+1-1

	@@ -80,7 +80,7 @@ class BaseDaemonManager(ABC):
80	try:	80	try:
81	pid, status = os.waitpid(-1, os.WNOHANG)	81	pid, status = os.waitpid(-1, os.WNOHANG)
82	except OSError:	82	except OSError:
83	- self.logger.error("No more child processes")	83	+ self.logger.error(f"No more child processes")
84	return	84	return
85	exit_flag = pid > 0	85	exit_flag = pid > 0
86	while pid > 0:	86	while pid > 0:

Mmindie_motor/python/mindie_motor/node_manager/framework/server.py+2-0

	@@ -13,6 +13,7 @@
13	import ipaddress	13	import ipaddress
14	import os	14	import os
15	import socket	15	import socket
		16	+import ssl
16		17
17	import uvicorn	18	import uvicorn
18	from fastapi import FastAPI, Request, HTTPException	19	from fastapi import FastAPI, Request, HTTPException
	@@ -22,6 +23,7 @@ from node_manager.common.utils import _SingletonMeta
22	from node_manager.routes.server_api import router	23	from node_manager.routes.server_api import router
23	from node_manager.common.logging import Log	24	from node_manager.common.logging import Log
24	from node_manager.framework.utils import CertUtil	25	from node_manager.framework.utils import CertUtil
		26	+from node_manager.framework.utils.cert_utils import CA_CERTS, TLS_CERT, TLS_KEY
25		27
26	logger = Log(__name__).getlog()	28	logger = Log(__name__).getlog()
27		29

Mmindie_motor/python/mindie_motor/node_manager/framework/utils/cert_utils.py+2-1

	@@ -15,6 +15,7 @@ import sys
15	import stat	15	import stat
16	import ssl	16	import ssl
17	import ctypes	17	import ctypes
		18	+from ctypes import c_char_p
18	from OpenSSL import crypto	19	from OpenSSL import crypto
19		20
20	from node_manager.common.utils import PathCheck, safe_open	21	from node_manager.common.utils import PathCheck, safe_open
	@@ -38,7 +39,7 @@ def _check_invalid_ssl_filesize(ssl_options):
38	def check_size(path: str):	39	def check_size(path: str):
39	size = os.path.getsize(path)	40	size = os.path.getsize(path)
40	if size > max_size:	41	if size > max_size:
41	- raise RuntimeError("SSL file should not exceed 10MB!")	42	+ raise RuntimeError(f"SSL file should not exceed 10MB!")
42		43
43	max_size = 10 * 1024 * 1024 # 最大文件大小为10MB	44	max_size = 10 * 1024 * 1024 # 最大文件大小为10MB
44	for ssl_key in SSL_MUST_KEYS:	45	for ssl_key in SSL_MUST_KEYS:

Mmindie_motor/python/mindie_motor/om_adapter/backends/base_backend.py+1-1

	@@ -39,7 +39,7 @@ class BaseBackend(ABC):
39	def fetch_log_messages(self):	39	def fetch_log_messages(self):
40	log_data = self.log_collector.collect_handler.log_processor.get_log_data(self.identity)	40	log_data = self.log_collector.collect_handler.log_processor.get_log_data(self.identity)
41	if log_data is None:	41	if log_data is None:
42	- self.logger.debug("No log data read from backend!")	42	+ self.logger.debug(f"No log data read from backend!")
43	return None	43	return None
44	log_request_message = json.dumps(LogRequestMessage(log_data_list=[log_data], server_ip=get_local_ip()).format())	44	log_request_message = json.dumps(LogRequestMessage(log_data_list=[log_data], server_ip=get_local_ip()).format())
45	self.logger.debug(f"Log data read from backend is: {log_request_message}")	45	self.logger.debug(f"Log data read from backend is: {log_request_message}")

Mmindie_motor/python/mindie_motor/om_adapter/backends/log_collect/__init__.py+0-2

	@@ -10,7 +10,5 @@
10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
13	-__all__ = ['Collector', 'LogRequestMessage']
14	-
15	from .log_collector import Collector	13	from .log_collector import Collector
16	from .data_class import LogRequestMessage	14	from .data_class import LogRequestMessage

Mmindie_motor/python/mindie_motor/om_adapter/backends/log_collect/data_class.py+1-0

	@@ -10,6 +10,7 @@
10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
		13	+import json
13	import os	14	import os
14	from dataclasses import dataclass	15	from dataclasses import dataclass
15	from datetime import datetime, timezone	16	from datetime import datetime, timezone

Mmindie_motor/python/mindie_motor/om_adapter/backends/log_collect/log_collector.py+5-5

Mmindie_motor/python/mindie_motor/om_adapter/backends/mindie_backend.py+3-3

	@@ -29,13 +29,13 @@ class MindIEBackend(BaseBackend):
29	self.alarm_shm = CircularShareMemory("mindie_controller_alarms_sem", "mindie_controller_alarms",	29	self.alarm_shm = CircularShareMemory("mindie_controller_alarms_sem", "mindie_controller_alarms",
30	10 * 1024 * 1024)	30	10 * 1024 * 1024)
31	self.logger.info("Alarm share memory created successfully!")	31	self.logger.info("Alarm share memory created successfully!")
32	- self.alive_shm = ByteShareMemory("smu_ctrl_heartbeat_sem", "smu_ctrl_heartbeat_shm")	32	+ self.alive_shm = ByteShareMemory(f"smu_ctrl_heartbeat_sem", f"smu_ctrl_heartbeat_shm")
33	self.logger.info("Alive share memory created successfully!")	33	self.logger.info("Alive share memory created successfully!")
34	else:	34	else:
35	self.alarm_shm = CircularShareMemory("mindie_coordinator_alarms_sem", "mindie_coordinator_alarms",	35	self.alarm_shm = CircularShareMemory("mindie_coordinator_alarms_sem", "mindie_coordinator_alarms",
36	10 * 1024 * 1024)	36	10 * 1024 * 1024)
37	self.logger.info("Alarm share memory created successfully!")	37	self.logger.info("Alarm share memory created successfully!")
38	- self.alive_shm = ByteShareMemory("smu_coord_heartbeat_sem", "smu_coord_heartbeat_shm")	38	+ self.alive_shm = ByteShareMemory(f"smu_coord_heartbeat_sem", f"smu_coord_heartbeat_shm")
39	self.logger.info("Alive share memory created successfully!")	39	self.logger.info("Alive share memory created successfully!")
40		40
41	def fetch_alarm_info(self) -> list:	41	def fetch_alarm_info(self) -> list:
	@@ -66,7 +66,7 @@ class MindIEBackend(BaseBackend):
66	alive_timestamp = json.loads(chunk)["timestamp"]	66	alive_timestamp = json.loads(chunk)["timestamp"]
67	if time.time() <= alive_timestamp + 5:	67	if time.time() <= alive_timestamp + 5:
68	return True	68	return True
69	- except JSONDecodeError:	69	+ except JSONDecodeError as json_error:
70	self.logger.error(f"Failed to read timestamp json: {chunk}")	70	self.logger.error(f"Failed to read timestamp json: {chunk}")
71	except Exception as e:	71	except Exception as e:
72	self.logger.error(e)	72	self.logger.error(e)

Mmindie_motor/python/mindie_motor/om_adapter/common/cert_util.py+3-1

	@@ -12,6 +12,8 @@
12		12
13	import os	13	import os
14	import stat	14	import stat
		15	+import ctypes
		16	+from ctypes import c_char_p
15		17
16	from om_adapter.common.util import PathCheck, safe_open	18	from om_adapter.common.util import PathCheck, safe_open
17	from om_adapter.common.logging import Log	19	from om_adapter.common.logging import Log
	@@ -34,7 +36,7 @@ def _check_invalid_ssl_filesize(ssl_options):
34	def check_size(path: str):	36	def check_size(path: str):
35	size = os.path.getsize(path)	37	size = os.path.getsize(path)
36	if size > max_size:	38	if size > max_size:
37	- raise RuntimeError("SSL file should not exceed 10MB!")	39	+ raise RuntimeError(f"SSL file should not exceed 10MB!")
38		40
39	max_size = 10 * 1024 * 1024 # 最大文件大小为10MB	41	max_size = 10 * 1024 * 1024 # 最大文件大小为10MB
40	for ssl_key in SSL_MUST_KEYS:	42	for ssl_key in SSL_MUST_KEYS:

Mmindie_motor/python/mindie_motor/om_adapter/common/logging.py+2-2

	@@ -118,10 +118,10 @@ def _create_log_file(log_file):
118	else:	118	else:
119	clean_path = os.path.normpath(log_file)	119	clean_path = os.path.normpath(log_file)
120	if os.path.islink(clean_path):	120	if os.path.islink(clean_path):
121	- err_msg = "Check log file path failed because it's a symbolic."	121	+ err_msg = f"Check log file path failed because it's a symbolic."
122	raise ValueError(err_msg)	122	raise ValueError(err_msg)
123	if len(clean_path) > 1024:	123	if len(clean_path) > 1024:
124	- err_msg = "Path of log file is too long, it should not exceed 1024 character."	124	+ err_msg = f"Path of log file is too long, it should not exceed 1024 character."
125	raise ValueError(err_msg)	125	raise ValueError(err_msg)
126	os.chmod(log_file, mode)	126	os.chmod(log_file, mode)
127		127

Mmindie_motor/python/mindie_motor/om_adapter/monitors/ccae_monitor.py+1-1

	@@ -155,7 +155,7 @@ class CCAEMonitor(BaseMonitor):
155	"POST", url, headers=self.headers, body=json.dumps(inventory_json).encode())	155	"POST", url, headers=self.headers, body=json.dumps(inventory_json).encode())
156	response_raise_for_status(response, "inventory")	156	response_raise_for_status(response, "inventory")
157	self.logger.debug("Response from inventory is: %s", response.data.decode())	157	self.logger.debug("Response from inventory is: %s", response.data.decode())
158	- except JSONDecodeError:	158	+ except JSONDecodeError as json_error:
159	self.logger.error(f"Failed to decode inventory info: {inventories}")	159	self.logger.error(f"Failed to decode inventory info: {inventories}")
160	except Exception as e:	160	except Exception as e:
161	self.logger.error(e)	161	self.logger.error(e)

Mmindie_motor/python/mindie_motor/om_adapter/monitors/kafka_client/kafka_produce.py+1-1

	@@ -62,4 +62,4 @@ class KafkaProducer:
62	self.logger.error("[OM Adapter] message send failed, the reason is: %s" % err)	62	self.logger.error("[OM Adapter] message send failed, the reason is: %s" % err)
63	else:	63	else:
64	self.logger.debug(	64	self.logger.debug(
65	- "[OM Adapter] message send successfully topic=%s, partition=%s", msg.topic(), msg.partition())	65	+ f"[OM Adapter] message send successfully topic=%s, partition=%s", msg.topic(), msg.partition())

Mmindie_motor/python/mindie_motor/om_adapter/share_memory_utils/__init__.py+0-2

	@@ -10,7 +10,5 @@
10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
13	-__all__ = ['ByteShareMemory', 'CircularShareMemory']
14	-
15	from .byte_memory import ByteShareMemory	13	from .byte_memory import ByteShareMemory
16	from .circular_memory import CircularShareMemory	14	from .circular_memory import CircularShareMemory

Mmindie_motor/python/mindie_motor/om_adapter/share_memory_utils/abstract_memory.py+1-0

	@@ -11,6 +11,7 @@
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
13	import os	13	import os
		14	+import sys
14	from abc import ABC, abstractmethod	15	from abc import ABC, abstractmethod
15	import mmap	16	import mmap
16	import ctypes	17	import ctypes

Mmindie_motor/python/setup.py+1-1

	@@ -46,7 +46,7 @@ def use_cxx11_abi() -> str:
46	logging.info(f"Detect ABI from torch, set GLOBAL_ABI_VERSION to {abi}")	46	logging.info(f"Detect ABI from torch, set GLOBAL_ABI_VERSION to {abi}")
47	return abi	47	return abi
48	except Exception:	48	except Exception:
49	- logging.warning("No torch detected on current environment.")	49	+ logging.warning(f"No torch detected on current environment.")
50		50
51	# 3. Fallback to "0" with warning	51	# 3. Fallback to "0" with warning
52	abi = "0"	52	abi = "0"

Mmindie_motor/src/example/deploy_scripts/boot_helper/gen_config_single_container.py+8-12

	@@ -153,12 +153,12 @@ def get_server_num():
153	raise	153	raise
154		154
155	if (device_num % tp_num) != 0:	155	if (device_num % tp_num) != 0:
156	- logger.error("device_num % tp_num must equal to 0.")	156	+ logger.error(f"device_num % tp_num must equal to 0.")
157	raise ValueError("device_num % tp_num must equal to 0.")	157	raise ValueError("device_num % tp_num must equal to 0.")
158	server_num = int(device_num / tp_num)	158	server_num = int(device_num / tp_num)
159	if server_num < 1:	159	if server_num < 1:
160	- logger.error(f"server_num({server_num}) must be greater than 0.")	160	+ logger.error(f"server_num must be greater than 0.")
161	- raise ValueError(f"server_num({server_num}) must be greater than 0.")	161	+ raise ValueError(f"server_num must be greater than 0.")
162	return server_num	162	return server_num
163		163
164		164
	@@ -300,7 +300,7 @@ def check_server_config(config_file_path: str, server_id: int):
300	try:	300	try:
301	update_port_value(config_file_path, f"server{server_id}_{port_name}", port_name, port)	301	update_port_value(config_file_path, f"server{server_id}_{port_name}", port_name, port)
302	except Exception:	302	except Exception:
303	- logger.error("Update port value failed.")	303	+ logger.error(f"Update port value failed.")
304	raise	304	raise
305	if server_id == 1:	305	if server_id == 1:
306	PortHelper.cache_port(port_name, [g_ports_allocated[f"server{server_id}_{port_name}"]])	306	PortHelper.cache_port(port_name, [g_ports_allocated[f"server{server_id}_{port_name}"]])
	@@ -315,7 +315,7 @@ def get_coordinator_ip_from_config(config_path: str):
315	ms_coordinator = load_json_file(ms_coordinator_path)	315	ms_coordinator = load_json_file(ms_coordinator_path)
316	return ms_coordinator["http_config"]["manage_ip"]	316	return ms_coordinator["http_config"]["manage_ip"]
317	except Exception:	317	except Exception:
318	- logger.error("Get coordinator IP from config failed.")	318	+ logger.error(f"Get coordinator IP from config failed.")
319	raise	319	raise
320		320
321		321
	@@ -331,7 +331,7 @@ def check_json_files(config_path: str, config_json_files: List[str], is_gen_serv
331	manage_port = int(ms_coordinator["http_config"]["manage_port"])	331	manage_port = int(ms_coordinator["http_config"]["manage_port"])
332	update_port_value(ms_coordinator_path, "coordinator_manage_port", "manage_port", manage_port)	332	update_port_value(ms_coordinator_path, "coordinator_manage_port", "manage_port", manage_port)
333	except Exception:	333	except Exception:
334	- logger.error("Check and update ms_coordinator.json failed.")	334	+ logger.error(f"Check and update ms_coordinator.json failed.")
335	raise	335	raise
336		336
337	try:	337	try:
	@@ -343,7 +343,7 @@ def check_json_files(config_path: str, config_json_files: List[str], is_gen_serv
343	http_server_port = int(ms_controller["http_server"]["port"])	343	http_server_port = int(ms_controller["http_server"]["port"])
344	update_port_value(ms_controller_path, "controller_http_server_port", "port", http_server_port)	344	update_port_value(ms_controller_path, "controller_http_server_port", "port", http_server_port)
345	except Exception:	345	except Exception:
346	- logger.error("Check and update ms_controller.json failed.")	346	+ logger.error(f"Check and update ms_controller.json failed.")
347	raise	347	raise
348		348
349	# check and update server json files	349	# check and update server json files
	@@ -393,11 +393,7 @@ def update_keys_in_json(config, config_key, config_value):
393	if config_key.lower() in must_string_key:	393	if config_key.lower() in must_string_key:
394	config[key] = config_value	394	config[key] = config_value
395	else:	395	else:
396	- config[key] = (	396	+ config[key] = json.loads(config_value) if infer_type(config_value) != str else config_value
397	- json.loads(config_value)
398	- if not isinstance(infer_type(config_value), str)
399	- else config_value
400	- )
401	return (config, True)	397	return (config, True)
402		398
403	new_config, is_changed = update_keys_in_json(value, config_key, config_value)	399	new_config, is_changed = update_keys_in_json(value, config_key, config_value)

Mmindie_motor/src/example/deploy_scripts/boot_helper/mindie_cpu_binding.py+3-1

	@@ -13,7 +13,9 @@ import subprocess
13	import logging	13	import logging
14	import argparse	14	import argparse
15	from dataclasses import dataclass	15	from dataclasses import dataclass
16	-from typing import List, Dict, Union	16	+from itertools import accumulate
		17	+from typing import List, Dict, Tuple, Union
		18	+import psutil
17		19
18		20
19	class ENV:	21	class ENV:

Mmindie_motor/src/example/deploy_scripts/boot_helper/update_mindie_server_config.py+11-11

	@@ -57,30 +57,30 @@ class _FileUtils:
57	:return: check_status[True or False], err_msg[if False], real_file_path[if True]	57	:return: check_status[True or False], err_msg[if False], real_file_path[if True]
58	"""	58	"""
59	if not file_path or not isinstance(file_path, str):	59	if not file_path or not isinstance(file_path, str):
60	- err_msg = "The file path is empty or not a string type."	60	+ err_msg = f"The file path is empty or not a string type."
61	return False, err_msg, None	61	return False, err_msg, None
62		62
63	if not base_dir or not isinstance(base_dir, str):	63	if not base_dir or not isinstance(base_dir, str):
64	- err_msg = "The base dir path is empty or not a string type."	64	+ err_msg = f"The base dir path is empty or not a string type."
65	return False, err_msg, None	65	return False, err_msg, None
66		66
67	if len(file_path) > 1024:	67	if len(file_path) > 1024:
68	- err_msg = "The file path exceeds the maximum length."	68	+ err_msg = f"The file path exceeds the maximum length."
69	return False, err_msg, None	69	return False, err_msg, None
70		70
71	if not allow_symlink and os.path.islink(file_path):	71	if not allow_symlink and os.path.islink(file_path):
72	- err_msg = "The file path is a link."	72	+ err_msg = f"The file path is a link."
73	return False, err_msg, None	73	return False, err_msg, None
74		74
75	try:	75	try:
76	real_file_path = os.path.realpath(file_path)	76	real_file_path = os.path.realpath(file_path)
77	- except Exception:	77	+ except Exception as e:
78	- err_msg = "Realpath parsing failed"	78	+ err_msg = f"Realpath parsing failed"
79	return False, err_msg, None	79	return False, err_msg, None
80		80
81	base_dir = base_dir if base_dir[-1] == "/" else base_dir + '/'	81	base_dir = base_dir if base_dir[-1] == "/" else base_dir + '/'
82	if not cls.is_base_dir_path(base_dir, real_file_path):	82	if not cls.is_base_dir_path(base_dir, real_file_path):
83	- err_msg = 'the file path is not in base dir'	83	+ err_msg = f'the file path is not in base dir'
		ascend-robot3月10日代码逻辑和结构: 在错误消息字符串中不必要地使用了f-string，但字符串中没有包含任何变量插值。问题类型: 代码逻辑和结构文件路径: `mindie_motor/src/example/deploy_scripts/boot_helper/update_mindie_server_config.py` 行号: 83 问题代码: err_msg = f'the file path is not in base dir' 修改建议: 将f-string改回普通字符串：err_msg = 'the file path is not in base dir' --- 此评论由代码审查工具自动生成
84	return False, err_msg, None	84	return False, err_msg, None
85		85
86	return True, None, real_file_path	86	return True, None, real_file_path
	@@ -101,7 +101,7 @@ class _FileUtils:
101	"""	101	"""
102	# Check if the file exists	102	# Check if the file exists
103	if not cls.check_file_exists(file_path):	103	if not cls.check_file_exists(file_path):
104	- err_msg = "Error: File not found."	104	+ err_msg = f"Error: File not found."
		ascend-robot3月10日代码逻辑和结构: 在错误消息字符串中不必要地使用了f-string，但字符串中没有包含任何变量插值。问题类型: 代码逻辑和结构文件路径: `mindie_motor/src/example/deploy_scripts/boot_helper/update_mindie_server_config.py` 行号: 104 问题代码: err_msg = f"Error: File not found." 修改建议: 将f-string改回普通字符串：err_msg = "Error: File not found." --- 此评论由代码审查工具自动生成
105	return False, err_msg	105	return False, err_msg
106		106
107	# Get the real_file_path	107	# Get the real_file_path
	@@ -118,7 +118,7 @@ class _FileUtils:
118	# Get the file size	118	# Get the file size
119	file_size = fp.tell()	119	file_size = fp.tell()
120	if file_size < DEFAULT_MIN_FILE_SIZE or file_size > DEFAULT_MAX_FILE_SIZE:	120	if file_size < DEFAULT_MIN_FILE_SIZE or file_size > DEFAULT_MAX_FILE_SIZE:
121	- err_msg = "Read input file failed, file size is invalid"	121	+ err_msg = f"Read input file failed, file size is invalid"
		ascend-robot3月10日代码逻辑和结构: 在错误消息字符串中不必要地使用了f-string，但字符串中没有包含任何变量插值。问题类型: 代码逻辑和结构文件路径: `mindie_motor/src/example/deploy_scripts/boot_helper/update_mindie_server_config.py` 行号: 121 问题代码: err_msg = f"Read input file failed, file size is invalid" 修改建议: 将f-string改回普通字符串：err_msg = "Read input file failed, file size is invalid" --- 此评论由代码审查工具自动生成
122	return False, err_msg	122	return False, err_msg
123	return True, None	123	return True, None
124	except Exception as e:	124	except Exception as e:
	@@ -130,7 +130,7 @@ class _FileUtils:
130	try:	130	try:
131	file_stat = os.stat(file_path)	131	file_stat = os.stat(file_path)
132	except FileNotFoundError:	132	except FileNotFoundError:
133	- err_msg = "Error: File not found."	133	+ err_msg = f"Error: File not found."
		ascend-robot3月10日代码逻辑和结构: 在错误消息字符串中不必要地使用了f-string，但字符串中没有包含任何变量插值。问题类型: 代码逻辑和结构文件路径: `mindie_motor/src/example/deploy_scripts/boot_helper/update_mindie_server_config.py` 行号: 133 问题代码: err_msg = f"Error: File not found." 修改建议: 将f-string改回普通字符串：err_msg = "Error: File not found." --- 此评论由代码审查工具自动生成
134	return False, err_msg	134	return False, err_msg
135	except PermissionError:	135	except PermissionError:
136	err_msg = f"Error: Permission denied to access file: {file_path}"	136	err_msg = f"Error: Permission denied to access file: {file_path}"
	@@ -160,7 +160,7 @@ class _FileUtils:
160	try:	160	try:
161	file_stat = os.stat(file_path)	161	file_stat = os.stat(file_path)
162	except FileNotFoundError:	162	except FileNotFoundError:
163	- err_msg = "Error: File not found."	163	+ err_msg = f"Error: File not found."
		ascend-robot3月10日代码逻辑和结构: 在错误消息字符串中不必要地使用了f-string，但字符串中没有包含任何变量插值。问题类型: 代码逻辑和结构文件路径: `mindie_motor/src/example/deploy_scripts/boot_helper/update_mindie_server_config.py` 行号: 163 问题代码: err_msg = f"Error: File not found." 修改建议: 将f-string改回普通字符串：err_msg = "Error: File not found." --- 此评论由代码审查工具自动生成
164	return False, err_msg	164	return False, err_msg
165		165
166	current_permissions = file_stat.st_mode & 0o777	166	current_permissions = file_stat.st_mode & 0o777

Mmindie_motor/src/example/deploy_scripts/deploy_ac_job.py+4-3

	@@ -30,7 +30,7 @@ sys.path.append(os.getcwd())
30	from gen_ranktable_helper.gen_global_ranktable import generate_global_ranktable	30	from gen_ranktable_helper.gen_global_ranktable import generate_global_ranktable
31	from utils.file_utils import safe_open	31	from utils.file_utils import safe_open
32	from utils.validate_config import validate_user_config	32	from utils.validate_config import validate_user_config
33	-from utils.validate_utils import validate_identifier, validate_path_part	33	+from utils.validate_utils import validate_identifier, validate_path_part, validate_command_part
34		34
35	# 配置日志格式和级别	35	# 配置日志格式和级别
36	logging.basicConfig(	36	logging.basicConfig(
	@@ -299,7 +299,7 @@ def check_coordinator_memory_config(coordinator_yaml_data, ms_coordinator_json_p
299	else:	299	else:
300	return f"{bytes_val} bytes"	300	return f"{bytes_val} bytes"
301		301
302	- logging.info("Coordinator memory config check:")	302	+ logging.info(f"Coordinator memory config check:")
303	logging.info(f" max_requests: {max_requests}")	303	logging.info(f" max_requests: {max_requests}")
304	logging.info(f" body_limit: {body_limit_mb} MB ({body_limit_bytes} bytes)")	304	logging.info(f" body_limit: {body_limit_mb} MB ({body_limit_bytes} bytes)")
305	logging.info(f" Theoretical max memory (with 20% margin): {format_bytes(theoretical_max_memory)}")	305	logging.info(f" Theoretical max memory (with 20% margin): {format_bytes(theoretical_max_memory)}")
	@@ -334,7 +334,7 @@ def check_coordinator_memory_config(coordinator_yaml_data, ms_coordinator_json_p
334	)	334	)
335	raise ValueError(error_msg)	335	raise ValueError(error_msg)
336		336
337	- logging.info("Memory config check passed.")	337	+ logging.info(f"Memory config check passed.")
338		338
339		339
340	def check_config(config: dict):	340	def check_config(config: dict):
	@@ -1190,6 +1190,7 @@ def exec_cm_create_kubectl_multi(deploy_config, out_path):
1190		1190
1191		1191
1192	def exec_cm_elastic_kubectl(deploy_config, out_path):	1192	def exec_cm_elastic_kubectl(deploy_config, out_path):
		1193	+ job_id = deploy_config[CONFIG_JOB_ID]
1193	logging.info("Starting to execute kubectl update configmap elastic")	1194	logging.info("Starting to execute kubectl update configmap elastic")
1194	exec_cmd("kubectl delete configmap scaling-rule" + NAME_FLAG + deploy_config[CONFIG_JOB_ID])	1195	exec_cmd("kubectl delete configmap scaling-rule" + NAME_FLAG + deploy_config[CONFIG_JOB_ID])
1195	exec_cmd("kubectl create configmap scaling-rule --from-file=" +	1196	exec_cmd("kubectl create configmap scaling-rule --from-file=" +

Mmindie_motor/src/example/deploy_scripts/ras_starter.py+12-10

	@@ -231,9 +231,9 @@ def restart_service(namespace: str, boot_args):
231	time.sleep(10)	231	time.sleep(10)
232		232
233	# restart service	233	# restart service
234	- subprocess.run(["python3", "deploy_ac_job.py"] + boot_args)	234	+ deploy_ac_job_res = subprocess.run(["python3", "deploy_ac_job.py"] + boot_args)
235	if is_mindie_service_detected(namespace):	235	if is_mindie_service_detected(namespace):
236	- logging.info("Restart service successfully!")	236	+ logging.info(f"Restart service successfully!")
237		237
238		238
239	def get_metrics_from_metrics_api(http_pool_manager, params: CheckParams) -> str:	239	def get_metrics_from_metrics_api(http_pool_manager, params: CheckParams) -> str:
	@@ -279,6 +279,7 @@ def main():
279	do_inference_retries = 5	279	do_inference_retries = 5
280	do_inference_interval = 180	280	do_inference_interval = 180
281	input_content = "相对论的提出者是谁？" # Probe prompt	281	input_content = "相对论的提出者是谁？" # Probe prompt
		282	+ max_unavailable_time = 1200 # Maximum service unavailable time
282	http_timeout = 60 # urllib3 request timeout	283	http_timeout = 60 # urllib3 request timeout
283	cert_context = load_cert()	284	cert_context = load_cert()
284	if cert_context:	285	if cert_context:
	@@ -303,7 +304,7 @@ def main():
303	try:	304	try:
304	ms_coordinator_config = fetch_config(os.path.join(boot_config["--conf_path"], "ms_coordinator.json"))	305	ms_coordinator_config = fetch_config(os.path.join(boot_config["--conf_path"], "ms_coordinator.json"))
305	metric_port = ms_coordinator_config["http_config"]["external_port"]	306	metric_port = ms_coordinator_config["http_config"]["external_port"]
306	- except Exception:	307	+ except Exception as e:
307	metric_port = coordinator_http_config["manage_port"]	308	metric_port = coordinator_http_config["manage_port"]
308		309
309	params = CheckParams(	310	params = CheckParams(
	@@ -326,7 +327,7 @@ def main():
326		327
327	# Check if metrics is enabled	328	# Check if metrics is enabled
328	if not is_metrics_mode_enabled():	329	if not is_metrics_mode_enabled():
329	- raise RuntimeError("Metrics mode is disabled, please check and set MIES_SERVICE_MONITOR_MODE=1.")	330	+ raise RuntimeError(f"Metrics mode is disabled, please check and set MIES_SERVICE_MONITOR_MODE=1.")
330		331
331	logging.info(f"Start monitoring service with namespace: {params.namespace}, model_name: {params.model_name}, "	332	logging.info(f"Start monitoring service with namespace: {params.namespace}, model_name: {params.model_name}, "
332	f"coordinator_port: {params.coordinator_port}, "	333	f"coordinator_port: {params.coordinator_port}, "
	@@ -350,10 +351,11 @@ def main():
350	resp_text = get_metrics_from_metrics_api(http_pool_manager, params)	351	resp_text = get_metrics_from_metrics_api(http_pool_manager, params)
351	last_success_count = find_metric_values(resp_text, "request_success_total")	352	last_success_count = find_metric_values(resp_text, "request_success_total")
352	last_failed_count = find_metric_values(resp_text, "request_failed_total")	353	last_failed_count = find_metric_values(resp_text, "request_failed_total")
		354	+ last_running_count = find_metric_values(resp_text, "num_requests_running")
353		355
354	time.sleep(probe_interval)	356	time.sleep(probe_interval)
355		357
356	- logging.info("Start to examine service status...")	358	+ logging.info(f"Start to examine service status...")
357	resp_text = get_metrics_from_metrics_api(http_pool_manager, params)	359	resp_text = get_metrics_from_metrics_api(http_pool_manager, params)
358	cur_success_count = find_metric_values(resp_text, "request_success_total")	360	cur_success_count = find_metric_values(resp_text, "request_success_total")
359	cur_failed_count = find_metric_values(resp_text, "request_failed_total")	361	cur_failed_count = find_metric_values(resp_text, "request_failed_total")
	@@ -365,12 +367,12 @@ def main():
365	if cur_failed_count >= 0 and last_failed_count >= 0 else -1)	367	if cur_failed_count >= 0 and last_failed_count >= 0 else -1)
366		368
367	if delta_success < 0 or delta_failed < 0:	369	if delta_success < 0 or delta_failed < 0:
368	- logging.info("Metrics values decreased, continue to monitor...")	370	+ logging.info(f"Metrics values decreased, continue to monitor...")
369	continue	371	continue
370		372
371	# Fault detection logic	373	# Fault detection logic
372	if delta_success > 0:	374	if delta_success > 0:
373	- logging.info("Success inference request count increased, continue to monitor...")	375	+ logging.info(f"Success inference request count increased, continue to monitor...")
374	continue	376	continue
375	elif delta_success == 0:	377	elif delta_success == 0:
376	if delta_failed > 0:	378	if delta_failed > 0:
	@@ -379,7 +381,7 @@ def main():
379	f"with interval {do_inference_interval}s")	381	f"with interval {do_inference_interval}s")
380	if infer_with_retry(http_pool_manager, params, do_inference_retries, do_inference_interval):	382	if infer_with_retry(http_pool_manager, params, do_inference_retries, do_inference_interval):
381	continue	383	continue
382	- logging.info("Virtual inference failed in failure increase state, restart service!")	384	+ logging.info(f"Virtual inference failed in failure increase state, restart service!")
383	break	385	break
384	elif delta_failed == 0:	386	elif delta_failed == 0:
385	if cur_running_count == 0: # No request, idle state	387	if cur_running_count == 0: # No request, idle state
	@@ -388,7 +390,7 @@ def main():
388	f"with interval {do_inference_interval}s")	390	f"with interval {do_inference_interval}s")
389	if infer_with_retry(http_pool_manager, params, do_inference_retries, do_inference_interval):	391	if infer_with_retry(http_pool_manager, params, do_inference_retries, do_inference_interval):
390	continue	392	continue
391	- logging.info("Virtual inference failed in idle state, restart service!")	393	+ logging.info(f"Virtual inference failed in idle state, restart service!")
392	break	394	break
393	elif cur_running_count > 0: # Running state, e.g. long sequence inference	395	elif cur_running_count > 0: # Running state, e.g. long sequence inference
394	logging.info(f"Doing virtual inference in running state, "	396	logging.info(f"Doing virtual inference in running state, "
	@@ -396,7 +398,7 @@ def main():
396	f"with interval {do_inference_interval}s")	398	f"with interval {do_inference_interval}s")
397	if infer_with_retry(http_pool_manager, params, do_inference_retries, do_inference_interval):	399	if infer_with_retry(http_pool_manager, params, do_inference_retries, do_inference_interval):
398	continue	400	continue
399	- logging.info("Virtual inference failed in running state, restart service!")	401	+ logging.info(f"Virtual inference failed in running state, restart service!")
400	break	402	break
401		403
402	restart_service(params.namespace, boot_args)	404	restart_service(params.namespace, boot_args)

Mmindie_motor/src/example/deploy_scripts/utils/validate_utils.py+1-0

	@@ -13,6 +13,7 @@
13	import os	13	import os
14	import re	14	import re
15	import logging	15	import logging
		16	+import string
16	from typing import Tuple	17	from typing import Tuple
17		18
18	# 配置日志格式和级别	19	# 配置日志格式和级别

Mmindie_motor/src/http_client_ctl/scripts/check_npu_status.py+1-1

	@@ -37,7 +37,7 @@ def __is_npu_health():
37	return False	37	return False
38	check_file_flag = FileUtils.is_symlink(yaml_file)	38	check_file_flag = FileUtils.is_symlink(yaml_file)
39	if check_file_flag:	39	if check_file_flag:
40	- logger.error("The path is a symbolic file.")	40	+ logger.error(f"The path is a symbolic file.")
41	return False	41	return False
42	try:	42	try:
43	with open(yaml_file, 'r', encoding='utf-8') as file:	43	with open(yaml_file, 'r', encoding='utf-8') as file:

Mmindie_motor/src/http_client_ctl/scripts/get_distribute_role.py+2-1

	@@ -13,6 +13,7 @@
13	import sys	13	import sys
14	import json	14	import json
15	import os	15	import os
		16	+import time
16	import logging	17	import logging
17	from file_util import FileUtils	18	from file_util import FileUtils
18	logging.basicConfig(level=logging.INFO)	19	logging.basicConfig(level=logging.INFO)
	@@ -32,7 +33,7 @@ def get_distribute_role():
32	try:	33	try:
33	check_path_flag, err_msg, real_path = FileUtils.regular_file_path(rank_table_path)	34	check_path_flag, err_msg, real_path = FileUtils.regular_file_path(rank_table_path)
34	if not check_path_flag:	35	if not check_path_flag:
35	- logging.error("check file path failed: %s", err_msg)	36	+ logger.error(f"check file path failed: %s", err_msg)
36	return PARSE_ERROR	37	return PARSE_ERROR
37	with open(real_path, 'r', encoding='utf-8') as file:	38	with open(real_path, 'r', encoding='utf-8') as file:
38	buf = file.read()	39	buf = file.read()

Mmindie_motor/src/http_client_ctl/scripts/get_group_id.py+1-1

	@@ -44,7 +44,7 @@ def wait_global_ranktable_completed(argv):
44		44
45	try:	45	try:
46	ipaddress.ip_address(pod_ip)	46	ipaddress.ip_address(pod_ip)
47	- except ValueError as e:	47	+ except ValueError:
48	raise RuntimeError(f"Invalid POD_IP: {pod_ip}") from e	48	raise RuntimeError(f"Invalid POD_IP: {pod_ip}") from e
49	for group in server_group_list:	49	for group in server_group_list:
50	group_id = "-1"	50	group_id = "-1"

Mmindie_motor/src/http_client_ctl/scripts/get_mies_mgmt_port.py+2-2

	@@ -29,11 +29,11 @@ logger.addHandler(console_handler)
29	def __check_file_path(file_path, mode, check_permission):	29	def __check_file_path(file_path, mode, check_permission):
30	check_path_flag, err_msg, real_path = FileUtils.regular_file_path(file_path)	30	check_path_flag, err_msg, real_path = FileUtils.regular_file_path(file_path)
31	if not check_path_flag:	31	if not check_path_flag:
32	- logger.error("check file path failed: %s", err_msg)	32	+ logger.error(f"check file path failed: %s", err_msg)
33	return False	33	return False
34	check_file_flag, err_msg = FileUtils.is_file_valid(real_path, mode=mode, check_permission=check_permission)	34	check_file_flag, err_msg = FileUtils.is_file_valid(real_path, mode=mode, check_permission=check_permission)
35	if not check_file_flag:	35	if not check_file_flag:
36	- logger.error("check file path is invalid: %s", err_msg)	36	+ logger.error(f"check file path is invalid: %s", err_msg)
37	return False	37	return False
38	return True	38	return True
39		39

Mmindie_motor/src/test/adapter_test/test_ccae_monitor.py+6-6

Mmindie_motor/src/test/adapter_test/test_kafka_client.py+1-0

	@@ -13,6 +13,7 @@
13	import unittest	13	import unittest
14		14
15	from om_adapter.monitors.kafka_client.kafka_produce import KafkaProducer	15	from om_adapter.monitors.kafka_client.kafka_produce import KafkaProducer
		16	+from om_adapter.config import ConfigUtil
16		17
17		18
18	class TestKafkaProduce(unittest.TestCase):	19	class TestKafkaProduce(unittest.TestCase):

Mmindie_motor/src/test/adapter_test/test_log_collect.py+1-1

	@@ -45,7 +45,7 @@ class TestLogDataProcessor(unittest.TestCase):
45	self.log_processor = LogDataProcessor()	45	self.log_processor = LogDataProcessor()
46	self.log_processor.watch_files[self.filename] = LogFile(self.filename)	46	self.log_processor.watch_files[self.filename] = LogFile(self.filename)
47	self.log_processor.modified_log_files.add(self.filename)	47	self.log_processor.modified_log_files.add(self.filename)
48	- with patch.object(PathCheck, 'check_path_full', return_value=(True, None)):	48	+ with patch.object(PathCheck, 'check_path_full', return_value=(True, None)) as mock_fuc:
49	# 首次读文件	49	# 首次读文件
50	log_data = self.log_processor.get_log_data(component)	50	log_data = self.log_processor.get_log_data(component)
51	self.assertEqual(log_data.component_type, component)	51	self.assertEqual(log_data.component_type, component)

Mmindie_motor/src/test/nodemanager_test/__init__.py+2-1

	@@ -10,9 +10,10 @@
10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
		13	+import os
13	import sys	14	import sys
14	import types	15	import types
15	-from unittest.mock import patch	16	+from unittest.mock import patch, MagicMock
16		17
17		18
18	class FakeGeneralConfig:	19	class FakeGeneralConfig:

Mmindie_motor/src/test/nodemanager_test/test_fault_mng.py+3-0

	@@ -19,10 +19,12 @@ sys.path.append(
19	)	19	)
20	import unittest	20	import unittest
21	from unittest.mock import patch, MagicMock	21	from unittest.mock import patch, MagicMock
		22	+from unittest.mock import patch, MagicMock
22	import logging	23	import logging
23		24
24	import requests	25	import requests
25		26
		27	+from node_manager.models import NodeRunningStatus
26	from node_manager.core.fault_mng import fault_manager	28	from node_manager.core.fault_mng import fault_manager
27	from node_manager.models.enums import NodeRunningStatus	29	from node_manager.models.enums import NodeRunningStatus
28		30
	@@ -74,6 +76,7 @@ class TestFaultManager(unittest.TestCase):
74		76
75	# 下发命令 reinit npu	77	# 下发命令 reinit npu
76	self._set_response_data(mocked_request, 200, mock_data)	78	self._set_response_data(mocked_request, 200, mock_data)
		79	+ ret_true = {status_str: True, "reason": None}
77	func = self.fault_manager.get_handler("REINIT_NPU")	80	func = self.fault_manager.get_handler("REINIT_NPU")
78	response = func()	81	response = func()
79	sleep(8)	82	sleep(8)

Mmindie_motor/src/test/nodemanager_test/test_heartbeat_mng.py+3-0

	@@ -21,7 +21,10 @@ import threading
21	import unittest	21	import unittest
22	from time import sleep	22	from time import sleep
23	import logging	23	import logging
		24	+import time
24	from unittest.mock import patch, MagicMock	25	from unittest.mock import patch, MagicMock
		26	+import threading
		27	+import threading
25	from collections import deque	28	from collections import deque
26		29
27	from node_manager.models.enums import NodeRunningStatus, ServiceStatus	30	from node_manager.models.enums import NodeRunningStatus, ServiceStatus

Mmindie_motor/src/test/nodemanager_test/test_llm_daemon_starter.py+1-0

	@@ -10,6 +10,7 @@
10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
		13	+import os
13	import unittest	14	import unittest
14	import signal	15	import signal
15	from unittest.mock import patch, MagicMock	16	from unittest.mock import patch, MagicMock

Mmindie_motor/src/test/nodemanager_test/test_server.py+1-0

	@@ -9,6 +9,7 @@
9	# See the Mulan PSL v2 for more details.	9	# See the Mulan PSL v2 for more details.
10		10
11		11
		12	+import os
12	import threading	13	import threading
13	import time	14	import time
14	import unittest	15	import unittest

Mmindie_motor/src/test/nodemanager_test/test_service.py+1-0

	@@ -9,6 +9,7 @@
9	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	9	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
10	# See the Mulan PSL v2 for more details.	10	# See the Mulan PSL v2 for more details.
11		11
		12	+import os
12	import unittest	13	import unittest
13	from unittest.mock import patch, Mock	14	from unittest.mock import patch, Mock
14		15

Mtests/ms/scripts/merge_gtest_result.py+1-1

	@@ -65,7 +65,7 @@ def merge_results(product, result_dir):
65	for case in cases:	65	for case in cases:
66	merge_root.extend(case)	66	merge_root.extend(case)
67	new_tree = ET.ElementTree(merge_root)	67	new_tree = ET.ElementTree(merge_root)
68	- new_tree.write("test_detail.xml", encoding='utf-8', xml_declaration=True, short_empty_elements=True)	68	+ new_tree.write(f"test_detail.xml", encoding='utf-8', xml_declaration=True, short_empty_elements=True)
69		69
70	if __name__ == '__main__':	70	if __name__ == '__main__':
71	main()	71	main()

Mtests/ms/scripts/replace_log_macro.py+1-0

	@@ -11,6 +11,7 @@
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
13	import os	13	import os
		14	+import re
14	import stat	15	import stat
15	from pathlib import Path	16	from pathlib import Path
16		17

Mtests/sys_perf_test/command_helper.py+1-1

	@@ -140,7 +140,7 @@ class CommandHelper(object):
140	def clear_output_buffer(self, terminal_id: int) -> None:	140	def clear_output_buffer(self, terminal_id: int) -> None:
141	'''clear old output in output.txt	141	'''clear old output in output.txt
142	'''	142	'''
143	- with open(self.output[terminal_id], 'w'):	143	+ with open(self.output[terminal_id], 'w') as f:
144	pass	144	pass
145		145
146	def _add_output_command(self, command: str, terminal_id: int) -> str:	146	def _add_output_command(self, command: str, terminal_id: int) -> str:

Mtests/sys_perf_test/compile_utils.py+2-2

	@@ -45,7 +45,7 @@ def wait_compile_complete(command_helper_instance: CommandHelper, output_path: s
45	while retry_times > 0:	45	while retry_times > 0:
46	time.sleep(30 * ONE_SEC)	46	time.sleep(30 * ONE_SEC)
47	if has_output_file(command_helper_instance, output_path, terminal_id):	47	if has_output_file(command_helper_instance, output_path, terminal_id):
48	- print_to_screen('Compile completed.')	48	+ print_to_screen(f'Compile completed.')
49	break	49	break
50	retry_times -= 1	50	retry_times -= 1
51	if retry_times == 0:	51	if retry_times == 0:
	@@ -69,7 +69,7 @@ def compile_mies(command_helper_instance: CommandHelper, compile_config: dict):
69	# compile service	69	# compile service
70	# prepare dependency	70	# prepare dependency
71	command_helper_instance.exec_command(compiler_id, f'cd {mies_repo_path}', wait_time=1)	71	command_helper_instance.exec_command(compiler_id, f'cd {mies_repo_path}', wait_time=1)
72	- command_helper_instance.exec_command(compiler_id, 'mkdir -p third_party/install/MindIE-LLM', wait_time=1)	72	+ command_helper_instance.exec_command(compiler_id, f'mkdir -p third_party/install/MindIE-LLM', wait_time=1)
73	unpackage_mindie_llm = f'bash {compile_config["mindie_llm_run_path"]} --extract=third_party/install/MindIE-LLM'	73	unpackage_mindie_llm = f'bash {compile_config["mindie_llm_run_path"]} --extract=third_party/install/MindIE-LLM'
74	command_helper_instance.exec_command(compiler_id, unpackage_mindie_llm, wait_time=1)	74	command_helper_instance.exec_command(compiler_id, unpackage_mindie_llm, wait_time=1)
75	command_helper_instance.exec_command(	75	command_helper_instance.exec_command(

Mtests/sys_perf_test/sys_perf.py+4-2

	@@ -10,6 +10,7 @@
10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.	10	# MERCHANTABILITY OR FIT FOR A PARTICULAR PURPOSE.
11	# See the Mulan PSL v2 for more details.	11	# See the Mulan PSL v2 for more details.
12		12
		13	+import os
13	import atexit	14	import atexit
14	import subprocess	15	import subprocess
15	import argparse	16	import argparse
	@@ -18,6 +19,7 @@ import random
18	from command_helper import CommandHelper	19	from command_helper import CommandHelper
19	from compile_utils import compile_mies, deployment	20	from compile_utils import compile_mies, deployment
20	from utils import (	21	from utils import (
		22	+ PerfIndex,
21	print_to_screen,	23	print_to_screen,
22	load_config,	24	load_config,
23	extract_result_from_perf_csv,	25	extract_result_from_perf_csv,
	@@ -116,7 +118,7 @@ if __name__ == '__main__':
116	if args.compile or args.deployment:	118	if args.compile or args.deployment:
117	try:	119	try:
118	deployment(command_helper_instance, server_id, environment_config)	120	deployment(command_helper_instance, server_id, environment_config)
119	- except Exception:	121	+ except Exception as e:
120	print_to_screen('Deployment failed, please check the compile result and try again')	122	print_to_screen('Deployment failed, please check the compile result and try again')
121		123
122	results_of_performance_test = []	124	results_of_performance_test = []
	@@ -139,7 +141,7 @@ if __name__ == '__main__':
139	# start service	141	# start service
140	command_helper_instance.exec_command(server_id, f'export MIES_CONFIG_JSON_PATH={test_case["config_path"]}',	142	command_helper_instance.exec_command(server_id, f'export MIES_CONFIG_JSON_PATH={test_case["config_path"]}',
141	wait_time=1)	143	wait_time=1)
142	- command_helper_instance.exec_command(server_id, "mindie_llm_server",	144	+ command_helper_instance.exec_command(server_id, f"mindie_llm_server",
143	True, wait_strs=["Daemon start success"], wait_time=180)	145	True, wait_strs=["Daemon start success"], wait_time=180)
144		146
145	# start client	147	# start client

Mtests/sys_perf_test/sys_perf_multi_node.py+7-6

	@@ -112,10 +112,10 @@ class NodeStatusMonitor(metaclass=_SingletonMeta):
112	# 在当前不执行指令时候才解析, 不会出现server engine状态不一致的问题	112	# 在当前不执行指令时候才解析, 不会出现server engine状态不一致的问题
113	engine_state_cur = self.engine_state[-1] # 首字段engine_state_cur[0]是时间戳	113	engine_state_cur = self.engine_state[-1] # 首字段engine_state_cur[0]是时间戳
114	if ServiceStatus.SERVICE_READY.value in engine_state_cur[1:]:	114	if ServiceStatus.SERVICE_READY.value in engine_state_cur[1:]:
115	- self.logger.error("[parse_engine_state] Contain SERVICE_READY in engine state while no CMD executing")	115	+ self.logger.error(f"[parse_engine_state] Contain SERVICE_READY in engine state while no CMD executing")
116	return NodeRunningStatus.ABNORMAL.value	116	return NodeRunningStatus.ABNORMAL.value
117	if ServiceStatus.SERVICE_PAUSE.value in engine_state_cur[1:]:	117	if ServiceStatus.SERVICE_PAUSE.value in engine_state_cur[1:]:
118	- self.logger.error("[parse_engine_state] Contain SERVICE_PAUSE in engine state while no CMD executing")	118	+ self.logger.error(f"[parse_engine_state] Contain SERVICE_PAUSE in engine state while no CMD executing")
119	return NodeRunningStatus.ABNORMAL.value	119	return NodeRunningStatus.ABNORMAL.value
120	if ServiceStatus.SERVICE_ABNORMAL.value in engine_state_cur[1:]:	120	if ServiceStatus.SERVICE_ABNORMAL.value in engine_state_cur[1:]:
121	return NodeRunningStatus.ABNORMAL.value	121	return NodeRunningStatus.ABNORMAL.value
	@@ -137,15 +137,15 @@ class NodeStatusMonitor(metaclass=_SingletonMeta):
137		137
138	def _monitor_state(self):	138	def _monitor_state(self):
139	while self.running:	139	while self.running:
140	- self.logger.info("Monitoring EP status")	140	+ self.logger.info(f"Monitering EP status")
141	result_all = self._query_ep_status()	141	result_all = self._query_ep_status()
142	if not self.heartbeat_mng.heartbeat_check_allowed:	142	if not self.heartbeat_mng.heartbeat_check_allowed:
143	# CMD在运行或者heartbeatmng在处理异常,不做状态更新和处理	143	# CMD在运行或者heartbeatmng在处理异常,不做状态更新和处理
144	- self.logger.info("while handling cmd, not update heartbeat")	144	+ self.logger.info(f"while handling cmd, not update heartbeat")
145	time.sleep(self.query_interval)	145	time.sleep(self.query_interval)
146	continue	146	continue
147	if self.heartbeat_mng.get_running_status() == NodeRunningStatus.PAUSE.value: # 在处理异常	147	if self.heartbeat_mng.get_running_status() == NodeRunningStatus.PAUSE.value: # 在处理异常
148	- self.logger.error("heartBeatMng is Paused while no cmd is executing")	148	+ self.logger.error(f"heartBeatMng is Paused while no cmd is executing")
149	time.sleep(self.query_interval)	149	time.sleep(self.query_interval)
150	continue	150	continue
151	now = datetime.now(timezone.utc).strftime("%Y/%m/%d %H:%M:%S")	151	now = datetime.now(timezone.utc).strftime("%Y/%m/%d %H:%M:%S")
	@@ -283,10 +283,10 @@ class NodeStatusMonitor(metaclass=_SingletonMeta):
283	resp = self.client.send_alarm_info_to_ctrler(error_info)	283	resp = self.client.send_alarm_info_to_ctrler(error_info)
284		284
285	if resp.get(DATA_STR, {}).get("status", "") == str(ControllerReply.SEND_CONTROLLER_ALARM_SUCCESS.value):	285	if resp.get(DATA_STR, {}).get("status", "") == str(ControllerReply.SEND_CONTROLLER_ALARM_SUCCESS.value):
286	- self.logger.info("Has successfully send alarm to controller.")	286	+ self.logger.info(f"Has successfully send alarm to controller.")
287	elif resp.get(DATA_STR, {}).get("status", "") == \	287	elif resp.get(DATA_STR, {}).get("status", "") == \
288	str(ControllerReply.SEND_CONTROLLER_ALARM_UNREACHEABLE.value):	288	str(ControllerReply.SEND_CONTROLLER_ALARM_UNREACHEABLE.value):
289	- self.logger.info("Failed to send alarm to controller, service unreachable")	289	+ self.logger.info(f"Failed to send alarm to controller, service unreachable")
290	else:	290	else:
291	self.logger.error(f"Controller reply not found, ctrl_rpl={resp}")	291	self.logger.error(f"Controller reply not found, ctrl_rpl={resp}")
292		292
	@@ -311,14 +311,14 @@ class HeartBeatMng(metaclass=_SingletonMeta):
311		311
312	def run(self):	312	def run(self):
313	if not GeneralConfig().has_endpoint:	313	if not GeneralConfig().has_endpoint:
314	- self.logger.info("Heartbeat Manager: No endpoint configured, skipping monitoring.")	314	+ self.logger.info(f"Heartbeat Manager: No endpoint configured, skipping monitoring.")
315	return	315	return
316	- self.logger.info("Heartbeat Manager:Start monitoring engine state.")	316	+ self.logger.info(f"Heartbeat Manager:Start monitoring engine state.")
317	self._status_monitor.start_monitoring()	317	self._status_monitor.start_monitoring()
318		318
319	def stop(self):	319	def stop(self):
320	self._status_monitor.stop_monitoring()	320	self._status_monitor.stop_monitoring()
321	- self.logger.info("Heartbeat Manager: Monitoring engine state stopped.")	321	+ self.logger.info(f"Heartbeat Manager: Monitoring engine state stopped.")
322		322
323	def get_heartbeat_check_allowed(self) -> bool:	323	def get_heartbeat_check_allowed(self) -> bool:
324	return self.heartbeat_check_allowed	324	return self.heartbeat_check_allowed

	@@ -42,13 +42,13 @@ class CollectHandler(FileSystemEventHandler):
42		42
43	def on_created(self, event):	43	def on_created(self, event):
44	if self._check_valid_file(event):	44	if self._check_valid_file(event):
45	- self.logger.info("[OM Adapter] File %s is created" % event.src_path)	45	+ self.logger.info(f"[OM Adapter] File %s is created" % event.src_path)
46	self.log_processor.watch_files[event.src_path] = LogFile(file_path=event.src_path)	46	self.log_processor.watch_files[event.src_path] = LogFile(file_path=event.src_path)
47	self.log_processor.modified_log_files.add(event.src_path)	47	self.log_processor.modified_log_files.add(event.src_path)
48		48
49	def on_modified(self, event):	49	def on_modified(self, event):
50	if self._check_valid_file(event):	50	if self._check_valid_file(event):
51	- self.logger.debug("[OM Adapter] File %s is modified", event.src_path) # 文件内容更新频率高	51	+ self.logger.debug(f"[OM Adapter] File %s is modified", event.src_path) # 文件内容更新频率高
52	if event.src_path not in self.log_processor.watch_files:	52	if event.src_path not in self.log_processor.watch_files:
53	self.log_processor.watch_files[event.src_path] = LogFile(file_path=event.src_path)	53	self.log_processor.watch_files[event.src_path] = LogFile(file_path=event.src_path)
54	self.log_processor.modified_log_files.add(event.src_path)	54	self.log_processor.modified_log_files.add(event.src_path)
	@@ -61,7 +61,7 @@ class CollectHandler(FileSystemEventHandler):
61		61
62	def on_moved(self, event):	62	def on_moved(self, event):
63	if self._check_valid_file(event):	63	if self._check_valid_file(event):
64	- self.logger.info("[OM Adapter] File %s is changed to %s" % (event.src_path, event.dest_path))	64	+ self.logger.info(f"[OM Adapter] File %s is changed to %s" % (event.src_path, event.dest_path))
65	src_log_file = self.log_processor.watch_files.pop(event.src_path, LogFile(file_path=event.dest_path))	65	src_log_file = self.log_processor.watch_files.pop(event.src_path, LogFile(file_path=event.dest_path))
66	src_log_file.file_path = event.dest_path	66	src_log_file.file_path = event.dest_path
67	src_log_file.last_read_position = 0 # 文件轮转后，更新读取位置	67	src_log_file.last_read_position = 0 # 文件轮转后，更新读取位置
	@@ -72,10 +72,10 @@ class Collector:
72	def __init__(self, collect_path=DEFAULT_COLLECT_PATH):	72	def __init__(self, collect_path=DEFAULT_COLLECT_PATH):
73	self.logger = Log(__name__).getlog()	73	self.logger = Log(__name__).getlog()
74	if not collect_path:	74	if not collect_path:
75	- err_msg = "[OM Adapter] Init log monitor failed, the collect_path is empty from config.json"	75	+ err_msg = f"[OM Adapter] Init log monitor failed, the collect_path is empty from config.json"
76	self.logger.error(err_msg)	76	self.logger.error(err_msg)
77	raise Exception(err_msg)	77	raise Exception(err_msg)
78	- self.logger.info("[OM Adapter] Log monitor path is %s" % collect_path)	78	+ self.logger.info(f"[OM Adapter] Log monitor path is %s" % collect_path)
		ascend-robot3月10日代码风格与一致性: 第79行是f-string与%格式化的混合使用，与第45、51、64行是同类问题。这种模式在代码中重复出现，表明需要统一的修复方案。不一致的字符串格式化方式会影响代码的可读性和维护成本。问题类型: 代码风格与一致性文件路径: `mindie_motor/python/mindie_motor/om_adapter/backends/log_collect/log_collector.py` 行号: 78 问题代码: self.logger.info(f"[OM Adapter] Log monitor path is %s" % collect_path) 修改建议: 改为纯f-string格式：`self.logger.info(f"[OM Adapter] Log monitor path is {collect_path}")`。同时建议检查整个文件中所有字符串格式化的地方，确保风格统一。 --- 此评论由代码审查工具自动生成
79		79
80	self.collect_handler = CollectHandler(collect_path)	80	self.collect_handler = CollectHandler(collect_path)
81	self.collect_observer = Observer()	81	self.collect_observer = Observer()

	@@ -78,7 +78,7 @@ class TestCCAEMonitor(unittest.TestCase):
78	}	78	}
79	}]	79	}]
80	}	80	}
81	- with patch("urllib3.PoolManager.request", return_value=MockResponse(json.dumps(mock_heartbeat_response))):	81	+ with patch("urllib3.PoolManager.request", return_value=MockResponse(json.dumps(mock_heartbeat_response))) as p:
82	self.ccae_monitor.send_heart_beat()	82	self.ccae_monitor.send_heart_beat()
83	self.assertTrue(self.ccae_monitor.model_id_period[MODEL_ID][0])	83	self.assertTrue(self.ccae_monitor.model_id_period[MODEL_ID][0])
84	self.assertEqual(self.ccae_monitor.model_id_period[MODEL_ID][1], 2)	84	self.assertEqual(self.ccae_monitor.model_id_period[MODEL_ID][1], 2)
	@@ -89,8 +89,8 @@ class TestCCAEMonitor(unittest.TestCase):
89	"alarmId": "this is a new alarm"	89	"alarmId": "this is a new alarm"
90	}]	90	}]
91	with patch.object(AbstractShareMemoryUtil, "read",	91	with patch.object(AbstractShareMemoryUtil, "read",
92	- return_value=json.dumps(single_alarm_info)):	92	+ return_value=json.dumps(single_alarm_info)) as shm_read_p:
93	- with patch("urllib3.PoolManager.request", return_value=MockResponse("OK")):	93	+ with patch("urllib3.PoolManager.request", return_value=MockResponse("OK")) as response_p:
94	self.ccae_monitor.upload_alarm(self.ccae_monitor.backend.fetch_alarm_info()[0])	94	self.ccae_monitor.upload_alarm(self.ccae_monitor.backend.fetch_alarm_info()[0])
95	self.assertEqual(self.ccae_monitor.alarm_cache["this is a new alarm"], single_alarm_info[0])	95	self.assertEqual(self.ccae_monitor.alarm_cache["this is a new alarm"], single_alarm_info[0])
96	self.assertEqual(self.ccae_monitor.fetch_alarm_cache(), single_alarm_info)	96	self.assertEqual(self.ccae_monitor.fetch_alarm_cache(), single_alarm_info)
	@@ -101,12 +101,12 @@ class TestCCAEMonitor(unittest.TestCase):
101	"alarmId": "this is a cancel alarm"	101	"alarmId": "this is a cancel alarm"
102	}]	102	}]
103	with patch.object(AbstractShareMemoryUtil, "read",	103	with patch.object(AbstractShareMemoryUtil, "read",
104	- return_value=json.dumps(single_alarm_info)):	104	+ return_value=json.dumps(single_alarm_info)) as shm_read_p:
105	- with patch("urllib3.PoolManager.request", return_value=MockResponse("OK")):	105	+ with patch("urllib3.PoolManager.request", return_value=MockResponse("OK")) as response_p:
106	self.ccae_monitor.upload_alarm(self.ccae_monitor.backend.fetch_alarm_info()[0])	106	self.ccae_monitor.upload_alarm(self.ccae_monitor.backend.fetch_alarm_info()[0])
107	self.assertEqual(len(self.ccae_monitor.alarm_cache), 0)	107	self.assertEqual(len(self.ccae_monitor.alarm_cache), 0)
108		108
109	def test_upload_inventory(self):	109	def test_upload_inventory(self):
110	- with patch("urllib3.PoolManager.request", return_value=MockResponse("OK")):	110	+ with patch("urllib3.PoolManager.request", return_value=MockResponse("OK")) as p:
111	self.assertIsNone(self.ccae_monitor.upload_inventory(str({"inventory": None})))	111	self.assertIsNone(self.ccae_monitor.upload_inventory(str({"inventory": None})))
112		112

	@@ -18,6 +18,7 @@ import random
18		18
19	from command_helper import CommandHelper, kill_all_service	19	from command_helper import CommandHelper, kill_all_service
20	from utils import (	20	from utils import (
		21	+ PerfIndex,
21	print_to_screen,	22	print_to_screen,
22	load_config,	23	load_config,
23	extract_result_from_perf_csv,	24	extract_result_from_perf_csv,
	@@ -62,17 +63,17 @@ def set_env(command_helper_instance, terminal_id, env_config):
62	command_helper_instance.exec_command(	63	command_helper_instance.exec_command(
63	terminal_id, f'export RANK_TABLE_FILE={env_config["RankTableFile"]}', wait_time=1)	64	terminal_id, f'export RANK_TABLE_FILE={env_config["RankTableFile"]}', wait_time=1)
64	command_helper_instance.exec_command(	65	command_helper_instance.exec_command(
65	- terminal_id, 'export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True', wait_time=1)	66	+ terminal_id, f'export PYTORCH_NPU_ALLOC_CONF=expandable_segments:True', wait_time=1)
66	command_helper_instance.exec_command(	67	command_helper_instance.exec_command(
67	- terminal_id, 'export ATB_WORKSPACE_MEM_ALLOC_ALG_TYPE=3', wait_time=1)	68	+ terminal_id, f'export ATB_WORKSPACE_MEM_ALLOC_ALG_TYPE=3', wait_time=1)
68	command_helper_instance.exec_command(	69	command_helper_instance.exec_command(
69	- terminal_id, 'export NPU_MEMORY_FRACTION=0.96', wait_time=1)	70	+ terminal_id, f'export NPU_MEMORY_FRACTION=0.96', wait_time=1)
70	command_helper_instance.exec_command(	71	command_helper_instance.exec_command(
71	terminal_id, f'export MIES_CONTAINER_IP={env_config["ip"]}', wait_time=1)	72	terminal_id, f'export MIES_CONTAINER_IP={env_config["ip"]}', wait_time=1)
72	command_helper_instance.exec_command(	73	command_helper_instance.exec_command(
73	- terminal_id, 'export HCCL_CONNECT_TIMEOUT=7200', wait_time=1)	74	+ terminal_id, f'export HCCL_CONNECT_TIMEOUT=7200', wait_time=1)
74	command_helper_instance.exec_command(	75	command_helper_instance.exec_command(
75	- terminal_id, 'HCCL_EXEC_TIMEOUT=0', wait_time=1)	76	+ terminal_id, f'HCCL_EXEC_TIMEOUT=0', wait_time=1)
76		77
77		78
78	if __name__ == '__main__':	79	if __name__ == '__main__':
	@@ -128,7 +129,7 @@ if __name__ == '__main__':
128	command_helper_instance.exec_command(server_id[-1], f'docker start {container_name}', wait_time=5)	129	command_helper_instance.exec_command(server_id[-1], f'docker start {container_name}', wait_time=5)
129	command_helper_instance.exec_command(server_id[-1], f'docker exec -it {container_name} bash', wait_time=5)	130	command_helper_instance.exec_command(server_id[-1], f'docker exec -it {container_name} bash', wait_time=5)
130	time.sleep(5)	131	time.sleep(5)
131	- print_to_screen('Check if slave node is in container using command `tmux attach -t <session-name>:2`')	132	+ print_to_screen(f'Check if slave node is in container using command `tmux attach -t <session-name>:2`')
132	set_env(command_helper_instance, server_id[-1], env_config)	133	set_env(command_helper_instance, server_id[-1], env_config)
133		134
134	results_of_performance_test = []	135	results_of_performance_test = []