优化了SSH连接的管理，使用连接池来复用连接，减少连接建立的开销。

主板CPU温度获取优化，改为sensors方式获取。有主板CPU温度获取错误的情况提交issues，并带上sensors命令的输出日志，我会做适配。

custom_components/fn_nas/__init__.py

@@ -1,62 +1,89 @@
 import logging
+import asyncio
+import asyncssh
 from homeassistant.config_entries import ConfigEntry
 from homeassistant.core import HomeAssistant
-from .const import DOMAIN, DATA_UPDATE_COORDINATOR, PLATFORMS, CONF_ENABLE_DOCKER  # 导入新增常量
+from homeassistant.helpers import config_validation as cv
+
+from .const import (
+    DOMAIN, DATA_UPDATE_COORDINATOR, PLATFORMS, CONF_ENABLE_DOCKER, 
+    CONF_HOST, DEFAULT_PORT
+)
 from .coordinator import FlynasCoordinator, UPSDataUpdateCoordinator
 
 _LOGGER = logging.getLogger(__name__)
 
 async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry):
     config = {**entry.data, **entry.options}
-    
-    coordinator = FlynasCoordinator(hass, config)
-    await coordinator.async_config_entry_first_refresh()
-
-    _LOGGER.debug("协调器类型: %s", type(coordinator).__name__)
-    _LOGGER.debug("协调器是否有control_vm方法: %s", hasattr(coordinator, 'control_vm'))
-    _LOGGER.debug("协调器是否有vm_manager属性: %s", hasattr(coordinator, 'vm_manager'))
-    
-    # 检查是否启用Docker，并初始化Docker管理器（如果有）
-    enable_docker = config.get(CONF_ENABLE_DOCKER, False)
-    if enable_docker:
-        # 导入Docker管理器并初始化
-        from .docker_manager import DockerManager
-        coordinator.docker_manager = DockerManager(coordinator)
-        _LOGGER.debug("已启用Docker容器监控")
-    else:
-        coordinator.docker_manager = None
-        _LOGGER.debug("未启用Docker容器监控")
-    
-    ups_coordinator = UPSDataUpdateCoordinator(hass, config, coordinator)
-    await ups_coordinator.async_config_entry_first_refresh()
-    
+    coordinator = FlynasCoordinator(hass, config, entry)
+    # 直接初始化，不阻塞等待NAS上线
     hass.data.setdefault(DOMAIN, {})
     hass.data[DOMAIN][entry.entry_id] = {
         DATA_UPDATE_COORDINATOR: coordinator,
-        "ups_coordinator": ups_coordinator,
-        CONF_ENABLE_DOCKER: enable_docker  # 存储启用状态
+        "ups_coordinator": None,
+        CONF_ENABLE_DOCKER: coordinator.config.get(CONF_ENABLE_DOCKER, False)
     }
-
-    await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)
-    entry.async_on_unload(entry.add_update_listener(async_update_entry))
+    # 异步后台初始化
+    hass.async_create_task(async_delayed_setup(hass, entry, coordinator))
     return True
 
+async def async_delayed_setup(hass: HomeAssistant, entry: ConfigEntry, coordinator: FlynasCoordinator):
+    try:
+        # 不阻塞等待NAS上线，直接尝试刷新数据
+        await coordinator.async_config_entry_first_refresh()
+        enable_docker = coordinator.config.get(CONF_ENABLE_DOCKER, False)
+        if enable_docker:
+            from .docker_manager import DockerManager
+            coordinator.docker_manager = DockerManager(coordinator)
+            _LOGGER.debug("已启用Docker容器监控")
+        else:
+            coordinator.docker_manager = None
+            _LOGGER.debug("未启用Docker容器监控")
+        ups_coordinator = UPSDataUpdateCoordinator(hass, coordinator.config, coordinator)
+        await ups_coordinator.async_config_entry_first_refresh()
+        hass.data[DOMAIN][entry.entry_id]["ups_coordinator"] = ups_coordinator
+        await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)
+        entry.async_on_unload(entry.add_update_listener(async_update_entry))
+        _LOGGER.info("飞牛NAS集成初始化完成")
+    except Exception as e:
+        _LOGGER.error("飞牛NAS集成初始化失败: %s", str(e))
+        await coordinator.async_disconnect()
+        if hasattr(coordinator, '_ping_task') and coordinator._ping_task:
+            coordinator._ping_task.cancel()
+
 async def async_update_entry(hass: HomeAssistant, entry: ConfigEntry):
-    await hass.config_entries.async_reload(entry.entry_id)
+    """更新配置项"""
+    # 卸载现有集成
+    await async_unload_entry(hass, entry)
+    # 重新加载集成
+    await async_setup_entry(hass, entry)
 
 async def async_unload_entry(hass: HomeAssistant, entry: ConfigEntry):
-    unload_ok = await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
+    """卸载集成"""
+    # 获取集成数据
+    domain_data = hass.data.get(DOMAIN, {}).get(entry.entry_id, {})
+    unload_ok = True
     
-    if unload_ok:
-        domain_data = hass.data[DOMAIN][entry.entry_id]
+    if DATA_UPDATE_COORDINATOR in domain_data:
         coordinator = domain_data[DATA_UPDATE_COORDINATOR]
-        ups_coordinator = domain_data["ups_coordinator"]
+        ups_coordinator = domain_data.get("ups_coordinator")
         
-        # 关闭主协调器的SSH连接
-        await coordinator.async_disconnect()
-        # 关闭UPS协调器
-        await ups_coordinator.async_shutdown()
+        # 卸载平台
+        unload_ok = await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
         
-        # 从DOMAIN中移除该entry的数据
-        hass.data[DOMAIN].pop(entry.entry_id)
+        if unload_ok:
+            # 关闭主协调器的SSH连接
+            await coordinator.async_disconnect()
+            
+            # 关闭UPS协调器（如果存在）
+            if ups_coordinator:
+                await ups_coordinator.async_shutdown()
+            
+            # 取消监控任务（如果存在）
+            if hasattr(coordinator, '_ping_task') and coordinator._ping_task and not coordinator._ping_task.done():
+                coordinator._ping_task.cancel()
+                
+            # 从DOMAIN中移除该entry的数据
+            hass.data[DOMAIN].pop(entry.entry_id, None)
+    
     return unload_ok

custom_components/fn_nas/coordinator.py

@@ -1,6 +1,7 @@
 import logging
-import re
+import asyncio
 import asyncssh
+import re
 from datetime import timedelta
 from homeassistant.core import HomeAssistant
 from homeassistant.helpers.update_coordinator import DataUpdateCoordinator, UpdateFailed
@@ -20,8 +21,10 @@ from .docker_manager import DockerManager
 _LOGGER = logging.getLogger(__name__)
 
 class FlynasCoordinator(DataUpdateCoordinator):
-    def __init__(self, hass: HomeAssistant, config) -> None:
+    def __init__(self, hass: HomeAssistant, config, config_entry) -> None:
         self.config = config
+        self.config_entry = config_entry
+        self.hass = hass
         self.host = config[CONF_HOST]
         self.port = config.get(CONF_PORT, DEFAULT_PORT)
         self.username = config[CONF_USERNAME]
@@ -32,21 +35,16 @@ class FlynasCoordinator(DataUpdateCoordinator):
         self.docker_manager = DockerManager(self) if self.enable_docker else None
         self.ssh = None
         self.ssh_closed = True
+        # SSH连接池管理
+        self.ssh_pool = []
+        self.ssh_pool_size = 3  # 连接池大小
+        self.ssh_pool_lock = asyncio.Lock()
         self.ups_manager = UPSManager(self)
         self.vm_manager = VMManager(self)
         self.use_sudo = False
         
-        self.data = {
-            "disks": [],
-            "system": {
-                "uptime": "未知",
-                "cpu_temperature": "未知",
-                "motherboard_temperature": "未知",
-                "status": "off"
-            },
-            "ups": {},
-            "vms": []
-        }
+        # 确保data始终有初始值
+        self.data = self.get_default_data()
         
         scan_interval = config.get(CONF_SCAN_INTERVAL, DEFAULT_SCAN_INTERVAL)
         update_interval = timedelta(seconds=scan_interval)
@@ -60,224 +58,368 @@ class FlynasCoordinator(DataUpdateCoordinator):
         
         self.disk_manager = DiskManager(self)
         self.system_manager = SystemManager(self)
+        self._system_online = False
+        self._ping_task = None
+        self._retry_interval = 30  # 系统离线时的检测间隔（秒）
+        self._last_command_time = 0
+        self._command_count = 0
     
-    async def async_connect(self):
-        if self.ssh is None or self.ssh_closed:
+        # 添加日志方法
+        self.debug_enabled = _LOGGER.isEnabledFor(logging.DEBUG)
+    
+    def get_default_data(self):
+        """返回默认的数据结构"""
+        return {
+            "disks": [],
+            "system": {
+                "uptime": "未知",
+                "cpu_temperature": "未知",
+                "motherboard_temperature": "未知",
+                "status": "off"
+            },
+            "ups": {},
+            "vms": [],
+            "docker_containers": []
+        }
+    
+    def _debug_log(self, message: str):
+        """只在调试模式下输出详细日志"""
+        if self.debug_enabled:
+            _LOGGER.debug(message)
+
+    def _info_log(self, message: str):
+        """重要信息日志"""
+        _LOGGER.info(message)
+
+    def _warning_log(self, message: str):
+        """警告日志"""
+        _LOGGER.warning(message)
+
+    def _error_log(self, message: str):
+        """错误日志"""
+        _LOGGER.error(message)
+
+    async def get_ssh_connection(self):
+        """从连接池获取可用的SSH连接"""
+        async with self.ssh_pool_lock:
+            # 检查现有连接
+            for i, (ssh, in_use) in enumerate(self.ssh_pool):
+                if not in_use:
+                    try:
+                        # 测试连接是否活跃
+                        await asyncio.wait_for(ssh.run("echo 'test'", timeout=1), timeout=2)
+                        self.ssh_pool[i] = (ssh, True)  # 标记为使用中
+                        self._debug_log(f"复用连接池中的连接 {i}")
+                        return ssh, i
+                    except Exception:
+                        # 连接失效，移除
+                        try:
+                            ssh.close()
+                        except:
+                            pass
+                        self.ssh_pool.pop(i)
+                        break
+            
+            # 如果连接池未满，创建新连接
+            if len(self.ssh_pool) < self.ssh_pool_size:
+                try:
+                    ssh = await asyncssh.connect(
+                        self.host,
+                        port=self.port,
+                        username=self.username,
+                        password=self.password,
+                        known_hosts=None,
+                        connect_timeout=5
+                    )
+                    
+                    # 检查并设置权限状态
+                    await self._setup_connection_permissions(ssh)
+                    
+                    connection_id = len(self.ssh_pool)
+                    self.ssh_pool.append((ssh, True))
+                    self._debug_log(f"创建新的SSH连接 {connection_id}")
+                    return ssh, connection_id
+                except Exception as e:
+                    self._debug_log(f"创建SSH连接失败: {e}")
+                    raise
+            
+            # 连接池满且所有连接都在使用中，等待可用连接
+            self._debug_log("所有连接都在使用中，等待可用连接...")
+            for _ in range(50):  # 最多等待5秒
+                await asyncio.sleep(0.1)
+                for i, (ssh, in_use) in enumerate(self.ssh_pool):
+                    if not in_use:
+                        try:
+                            await asyncio.wait_for(ssh.run("echo 'test'", timeout=1), timeout=2)
+                            self.ssh_pool[i] = (ssh, True)
+                            self._debug_log(f"等待后获得连接 {i}")
+                            return ssh, i
+                        except Exception:
+                            try:
+                                ssh.close()
+                            except:
+                                pass
+                            self.ssh_pool.pop(i)
+                            break
+            
+            raise Exception("无法获取SSH连接")
+
+    async def _setup_connection_permissions(self, ssh):
+        """为新连接设置权限状态"""
+        try:
+            # 检查是否为root用户
+            result = await ssh.run("id -u", timeout=3)
+            if result.stdout.strip() == "0":
+                self._debug_log("当前用户是 root")
+                self.use_sudo = False
+                return
+            
+            # 尝试切换到root会话
+            if self.root_password:
+                try:
+                    await ssh.run(
+                        f"echo '{self.root_password}' | sudo -S -i",
+                        input=self.root_password + "\n",
+                        timeout=5
+                    )
+                    whoami = await ssh.run("whoami")
+                    if "root" in whoami.stdout:
+                        self._info_log("成功切换到 root 会话（使用 root 密码）")
+                        self.use_sudo = False
+                        return
+                except Exception:
+                    pass
+            
+            # 尝试使用登录密码sudo
             try:
-                self.ssh = await asyncssh.connect(
-                    self.host,
-                    port=self.port,
-                    username=self.username,
-                    password=self.password,
-                    known_hosts=None
-                )
-                
-                if await self.is_root_user():
-                    _LOGGER.debug("当前用户是 root")
-                    self.use_sudo = False
-                    self.ssh_closed = False
-                    return True
-                
-                result = await self.ssh.run(
+                await ssh.run(
                     f"echo '{self.password}' | sudo -S -i",
                     input=self.password + "\n",
-                    timeout=10
+                    timeout=5
                 )
-                
-                whoami_result = await self.ssh.run("whoami")
-                if "root" in whoami_result.stdout:
-                    _LOGGER.info("成功切换到 root 会话（使用登录密码）")
+                whoami = await ssh.run("whoami")
+                if "root" in whoami.stdout:
+                    self._info_log("成功切换到 root 会话（使用登录密码）")
                     self.use_sudo = False
-                    self.ssh_closed = False
-                    return True
-                else:
-                    if self.root_password:
-                        result = await self.ssh.run(
-                            f"echo '{self.root_password}' | sudo -S -i",
-                            input=self.root_password + "\n",
-                            timeout=10
-                        )
-                        
-                        whoami_result = await self.ssh.run("whoami")
-                        if "root" in whoami_result.stdout:
-                            _LOGGER.info("成功切换到 root 会话（使用 root 密码）")
-                            self.use_sudo = False
-                            self.ssh_closed = False
-                            return True
-                        else:
-                            _LOGGER.warning("切换到 root 会话失败，将使用 sudo")
-                            self.use_sudo = True
-                    else:
-                        _LOGGER.warning("非 root 用户且未提供 root 密码，将使用 sudo")
-                        self.use_sudo = True
+                    return
+            except Exception:
+                pass
                 
-                self.ssh_closed = False
-                _LOGGER.info("SSH 连接已建立到 %s", self.host)
-                return True
-            except Exception as e:
-                self.ssh = None
-                self.ssh_closed = True
-                _LOGGER.error("连接失败: %s", str(e), exc_info=True)
-                return False
-        return True
+            # 设置为使用sudo模式
+            self.use_sudo = True
+            self._debug_log("设置为使用sudo模式")
+            
+        except Exception as e:
+            self._debug_log(f"设置连接权限失败: {e}")
+            self.use_sudo = True
+
+    async def release_ssh_connection(self, connection_id):
+        """释放SSH连接回连接池"""
+        async with self.ssh_pool_lock:
+            if 0 <= connection_id < len(self.ssh_pool):
+                ssh, _ = self.ssh_pool[connection_id]
+                self.ssh_pool[connection_id] = (ssh, False)  # 标记为可用
+                self._debug_log(f"释放SSH连接 {connection_id}")
     
-    async def is_root_user(self):
+    async def close_all_ssh_connections(self):
+        """关闭所有SSH连接"""
+        async with self.ssh_pool_lock:
+            for ssh, _ in self.ssh_pool:
+                try:
+                    ssh.close()
+                except:
+                    pass
+            self.ssh_pool.clear()
+            self._debug_log("已关闭所有SSH连接")
+    
+    async def async_connect(self):
+        """建立并保持持久SSH连接 - 兼容旧代码"""
         try:
-            result = await self.ssh.run("id -u", timeout=5)
-            return result.stdout.strip() == "0"
+            ssh, connection_id = await self.get_ssh_connection()
+            await self.release_ssh_connection(connection_id)
+            return True
         except Exception:
             return False
     
     async def async_disconnect(self):
-        if self.ssh is not None and not self.ssh_closed:
-            try:
-                self.ssh.close()
-                self.ssh_closed = True
-                _LOGGER.info("SSH connection closed")
-            except Exception as e:
-                _LOGGER.error("Error closing SSH connection: %s", str(e))
-            finally:
-                self.ssh = None
-    
-    async def is_ssh_connected(self) -> bool:
-        if self.ssh is None or self.ssh_closed:
-            return False
-        
-        try:
-            test_command = "echo 'connection_test'"
-            result = await self.ssh.run(test_command, timeout=2)
-            return result.exit_status == 0 and "connection_test" in result.stdout
-        except (asyncssh.Error, TimeoutError):
-            return False
+        """断开SSH连接 - 兼容旧代码"""
+        await self.close_all_ssh_connections()
     
     async def run_command(self, command: str, retries=2) -> str:
-        for attempt in range(retries):
-            try:
-                if not await self.is_ssh_connected():
-                    if not await self.async_connect():
-                        if self.data and "system" in self.data:
-                            self.data["system"]["status"] = "off"
-                        raise UpdateFailed("SSH 连接失败")
-                
-                if self.use_sudo:
-                    if self.root_password or self.password:
-                        password = self.root_password if self.root_password else self.password
-                        full_command = f"sudo -S {command}"
-                        result = await self.ssh.run(full_command, input=password + "\n", check=True)
-                    else:
-                        full_command = f"sudo {command}"
-                        result = await self.ssh.run(full_command, check=True)
-                else:
-                    result = await self.ssh.run(command, check=True)
-                
-                return result.stdout.strip()
-            
-            except asyncssh.process.ProcessError as e:
-                if e.exit_status in [4, 32]:
-                    return ""
-                _LOGGER.error("Command failed: %s (exit %d)", command, e.exit_status)
-                self.ssh = None
-                self.ssh_closed = True
-                if attempt == retries - 1:
-                    if self.data and "system" in self.data:
-                        self.data["system"]["status"] = "off"
-                    raise UpdateFailed(f"Command failed after {retries} attempts: {command}") from e
-                
-            except asyncssh.Error as e:
-                _LOGGER.error("SSH connection error: %s", str(e))
-                self.ssh = None
-                self.ssh_closed = True
-                if attempt == retries - 1:
-                    if self.data and "system" in self.data:
-                        self.data["system"]["status"] = "off"
-                    raise UpdateFailed(f"SSH error after {retries} attempts: {str(e)}") from e
-                
-            except Exception as e:
-                self.ssh = None
-                self.ssh_closed = True
-                _LOGGER.error("Unexpected error: %s", str(e), exc_info=True)
-                if attempt == retries - 1:
-                    if self.data and "system" in self.data:
-                        self.data["system"]["status"] = "off"
-                    raise UpdateFailed(f"Unexpected error after {retries} attempts") from e
-    
-    async def get_network_macs(self):
-        try:
-            output = await self.run_command("ip link show")
-            macs = {}
-            
-            pattern = re.compile(r'^\d+: (\w+):.*\n\s+link/\w+\s+([0-9a-fA-F:]{17})', re.MULTILINE)
-            matches = pattern.findall(output)
-            
-            for interface, mac in matches:
-                if interface == "lo" or mac == "00:00:00:00:00:00":
-                    continue
-                macs[mac] = interface
-                
-            return macs
-        except Exception as e:
-            self.logger.error("获取MAC地址失败: %s", str(e))
-            return {}
-    
-    async def _async_update_data(self):
-        _LOGGER.debug("Starting data update...")
+        """执行SSH命令，使用连接池"""
+        # 系统离线时直接返回空字符串
+        if not self._system_online:
+            return ""
+        
+        ssh = None
+        connection_id = None
         
         try:
-            if await self.is_ssh_connected():
-                status = "on"
-            else:
-                if not await self.async_connect():
-                    status = "off"
+            # 从连接池获取连接
+            ssh, connection_id = await self.get_ssh_connection()
+            
+            # 构建完整命令
+            if self.use_sudo:
+                if self.root_password or self.password:
+                    password = self.root_password if self.root_password else self.password
+                    full_command = f"sudo -S {command}"
+                    result = await ssh.run(full_command, input=password + "\n", timeout=10)
                 else:
-                    status = "on"
+                    full_command = f"sudo {command}"
+                    result = await ssh.run(full_command, timeout=10)
+            else:
+                result = await ssh.run(command, timeout=10)
             
-            disks = await self.disk_manager.get_disks_info()
+            return result.stdout.strip()
+        
+        except Exception as e:
+            self._debug_log(f"命令执行失败: {command}, 错误: {str(e)}")
+            return ""
+        
+        finally:
+            # 释放连接回连接池
+            if connection_id is not None:
+                await self.release_ssh_connection(connection_id)
+    
+    async def run_command_direct(self, command: str) -> str:
+        """直接执行命令，获取独立连接 - 用于并发任务"""
+        if not self._system_online:
+            return ""
+        
+        ssh = None
+        connection_id = None
+        
+        try:
+            ssh, connection_id = await self.get_ssh_connection()
+            
+            if self.use_sudo:
+                if self.root_password or self.password:
+                    password = self.root_password if self.root_password else self.password
+                    full_command = f"sudo -S {command}"
+                    result = await ssh.run(full_command, input=password + "\n", timeout=10)
+                else:
+                    full_command = f"sudo {command}"
+                    result = await ssh.run(full_command, timeout=10)
+            else:
+                result = await ssh.run(command, timeout=10)
+            
+            return result.stdout.strip()
+        
+        except Exception as e:
+            self._debug_log(f"直接命令执行失败: {command}, 错误: {str(e)}")
+            return ""
+        
+        finally:
+            if connection_id is not None:
+                await self.release_ssh_connection(connection_id)
+    
+    async def _monitor_system_status(self):
+        """系统离线时轮询检测状态"""
+        self._debug_log(f"启动系统状态监控，每{self._retry_interval}秒检测一次")
+        while True:
+            await asyncio.sleep(self._retry_interval)
+            
+            if await self.ping_system():
+                self._info_log("检测到系统已开机，触发重新加载")
+                # 触发集成重新加载
+                self.hass.async_create_task(
+                    self.hass.config_entries.async_reload(self.config_entry.entry_id)
+                )
+                break
+    
+    async def ping_system(self) -> bool:
+        """轻量级系统状态检测"""
+        # 对于本地主机直接返回True
+        if self.host in ['localhost', '127.0.0.1']:
+            return True
+            
+        try:
+            # 使用异步ping检测
+            proc = await asyncio.create_subprocess_exec(
+                'ping', '-c', '1', '-W', '1', self.host,
+                stdout=asyncio.subprocess.DEVNULL,
+                stderr=asyncio.subprocess.DEVNULL
+            )
+            await proc.wait()
+            return proc.returncode == 0
+        except Exception:
+            return False
+    
+    async def _async_update_data(self):
+        """数据更新入口，优化命令执行频率"""
+        self._debug_log("开始数据更新...")
+        is_online = await self.ping_system()
+        self._system_online = is_online
+        
+        if not is_online:
+            self._debug_log("系统离线，跳过数据更新")
+            # 启动后台监控任务
+            if not self._ping_task or self._ping_task.done():
+                self._ping_task = asyncio.create_task(self._monitor_system_status())
+            await self.close_all_ssh_connections()
+            return self.get_default_data()
+        
+        # 系统在线处理
+        try:
+            # 预热连接池并确保权限设置正确
+            await self.async_connect()
+            
+            # 获取系统状态信息
+            status = "on"
+            
+            # 串行获取信息以确保稳定性
+            self._debug_log("开始获取系统信息...")
             system = await self.system_manager.get_system_info()
-            ups_info = await self.ups_manager.get_ups_info()
-            vms = await self.vm_manager.get_vm_list()
+            self._debug_log("系统信息获取完成")
             
+            self._debug_log("开始获取磁盘信息...")
+            disks = await self.disk_manager.get_disks_info()
+            self._debug_log(f"磁盘信息获取完成，数量: {len(disks)}")
+            
+            self._debug_log("开始获取UPS信息...")
+            ups_info = await self.ups_manager.get_ups_info()
+            self._debug_log("UPS信息获取完成")
+            
+            self._debug_log("开始获取虚拟机信息...")
+            vms = await self.vm_manager.get_vm_list()
+            self._debug_log(f"虚拟机信息获取完成，数量: {len(vms)}")
+            
+            # 为每个虚拟机获取标题
             for vm in vms:
-                vm["title"] = await self.vm_manager.get_vm_title(vm["name"])
-
+                try:
+                    vm["title"] = await self.vm_manager.get_vm_title(vm["name"])
+                except Exception as e:
+                    self._debug_log(f"获取VM标题失败 {vm['name']}: {e}")
+                    vm["title"] = vm["name"]
+            
+            # 获取Docker容器信息
             docker_containers = []
-            if self.enable_docker:
-                docker_containers = await self.docker_manager.get_containers()
+            if self.enable_docker and self.docker_manager:
+                self._debug_log("开始获取Docker信息...")
+                try:
+                    docker_containers = await self.docker_manager.get_containers()
+                    self._debug_log(f"Docker信息获取完成，数量: {len(docker_containers)}")
+                except Exception as e:
+                    self._debug_log(f"Docker信息获取失败: {e}")
             
             data = {
                 "disks": disks,
-                "system": {
-                    **system,
-                    "status": status
-                },
+                "system": {**system, "status": status},
                 "ups": ups_info,
                 "vms": vms,
                 "docker_containers": docker_containers
             }
             
+            self._debug_log(f"数据更新完成: disks={len(disks)}, vms={len(vms)}, containers={len(docker_containers)}")
             return data
         
         except Exception as e:
-            _LOGGER.error("Failed to update data: %s", str(e), exc_info=True)
-            return {
-                "disks": [],
-                "system": {
-                    "uptime": "未知",
-                    "cpu_temperature": "未知",
-                    "motherboard_temperature": "未知",
-                    "status": "off"
-                },
-                "ups": {},
-                "vms": []
-            }
-    
-    async def reboot_system(self):
-        await self.system_manager.reboot_system()
-    
-    async def shutdown_system(self):
-        await self.system_manager.shutdown_system()
-        if self.data and "system" in self.data:
-            self.data["system"]["status"] = "off"
-        self.async_update_listeners()
+            self._error_log(f"数据更新失败: {str(e)}")
+            self._system_online = False
+            if not self._ping_task or self._ping_task.done():
+                self._ping_task = asyncio.create_task(self._monitor_system_status())
+                
+            return self.get_default_data()
 
 class UPSDataUpdateCoordinator(DataUpdateCoordinator):
     def __init__(self, hass: HomeAssistant, config, main_coordinator):
@@ -297,19 +439,20 @@ class UPSDataUpdateCoordinator(DataUpdateCoordinator):
         self.ups_manager = UPSManager(main_coordinator)
     
     async def _async_update_data(self):
+        # 如果主协调器检测到系统离线，跳过UPS更新
+        if not self.main_coordinator._system_online:
+            return {}
+        
         try:
             return await self.ups_manager.get_ups_info()
         except Exception as e:
-            _LOGGER.error("Failed to update UPS data: %s", str(e), exc_info=True)
+            _LOGGER.debug("UPS数据更新失败: %s", str(e))
             return {}
 
     async def control_vm(self, vm_name, action):
         try:
-            if not hasattr(self, 'vm_manager'):
-                self.vm_manager = VMManager(self)
-            
-            result = await self.vm_manager.control_vm(vm_name, action)
+            result = await self.main_coordinator.vm_manager.control_vm(vm_name, action)
             return result
         except Exception as e:
-            _LOGGER.error("虚拟机控制失败: %s", str(e), exc_info=True)
+            _LOGGER.debug("虚拟机控制失败: %s", str(e))
             return False

custom_components/fn_nas/manifest.json

@@ -1,7 +1,7 @@
 {
   "domain": "fn_nas",
   "name": "飞牛NAS",
-  "version": "1.3.1",
+  "version": "1.3.6",
   "documentation": "https://github.com/anxms/fn_nas",
   "dependencies": [],
   "codeowners": ["@anxms"],

custom_components/fn_nas/system_manager.py

@@ -1,7 +1,5 @@
-import re
 import logging
 import asyncio
-import json
 import os
 from datetime import datetime
 
@@ -11,10 +9,41 @@ class SystemManager:
     def __init__(self, coordinator):
         self.coordinator = coordinator
         self.logger = _LOGGER.getChild("system_manager")
-        self.logger.setLevel(logging.DEBUG)
-        self.debug_enabled = False  # 调试模式开关
-        self.sensors_debug_path = "/config/fn_nas_debug"  # 调试文件保存路径
-    
+        # 根据Home Assistant的日志级别动态设置
+        self.logger.setLevel(logging.DEBUG if _LOGGER.isEnabledFor(logging.DEBUG) else logging.INFO)
+        self.debug_enabled = _LOGGER.isEnabledFor(logging.DEBUG)  # 基于HA调试模式
+        self.sensors_debug_path = "/config/fn_nas_debug"
+        
+        # 温度传感器缓存
+        self.cpu_temp_cache = {
+            "hwmon_id": None,
+            "temp_id": None,
+            "driver_type": None,
+            "label": None
+        }
+        self.mobo_temp_cache = {
+            "hwmon_id": None,
+            "temp_id": None,
+            "label": None
+        }
+
+    def _debug_log(self, message: str):
+        """只在调试模式下输出详细日志"""
+        if self.debug_enabled:
+            self.logger.debug(message)
+
+    def _info_log(self, message: str):
+        """重要信息日志"""
+        self.logger.info(message)
+
+    def _warning_log(self, message: str):
+        """警告日志"""
+        self.logger.warning(message)
+
+    def _error_log(self, message: str):
+        """错误日志"""
+        self.logger.error(message)
+
     async def get_system_info(self) -> dict:
         """获取系统信息"""
         system_info = {}
@@ -23,10 +52,8 @@ class SystemManager:
             uptime_output = await self.coordinator.run_command("cat /proc/uptime")
             if uptime_output:
                 try:
-                    # 保存原始秒数
                     uptime_seconds = float(uptime_output.split()[0])
                     system_info["uptime_seconds"] = uptime_seconds
-                    # 保存格式化字符串
                     system_info["uptime"] = self.format_uptime(uptime_seconds)
                 except (ValueError, IndexError):
                     system_info["uptime_seconds"] = 0
@@ -34,43 +61,20 @@ class SystemManager:
             else:
                 system_info["uptime_seconds"] = 0
                 system_info["uptime"] = "未知"
-            
-            # 获取 sensors 命令输出（使用JSON格式）
-            sensors_output = await self.coordinator.run_command(
-                "sensors -j 2>/dev/null || sensors 2>/dev/null || echo 'No sensor data'"
-            )
-            
-            # 保存传感器数据以便调试
-            self.save_sensor_data_for_debug(sensors_output)
-            self.logger.debug("Sensors output: %s", sensors_output[:500] + "..." if len(sensors_output) > 500 else sensors_output)
-            
-            # 提取 CPU 温度（改进算法）
-            cpu_temp = self.extract_cpu_temp(sensors_output)
-            system_info["cpu_temperature"] = cpu_temp
-            
-            # 提取主板温度（改进算法）
-            mobo_temp = self.extract_mobo_temp(sensors_output)
-            system_info["motherboard_temperature"] = mobo_temp
-            
-            # 尝试备用方法获取CPU温度
-            if cpu_temp == "未知":
-                backup_cpu_temp = await self.get_cpu_temp_fallback()
-                if backup_cpu_temp:
-                    system_info["cpu_temperature"] = backup_cpu_temp
-            
-            # 新增：获取内存信息
+
+            # 一次性获取CPU和主板温度
+            temps = await self.get_temperatures_from_sensors()
+            system_info["cpu_temperature"] = temps["cpu"]
+            system_info["motherboard_temperature"] = temps["motherboard"]
+
             mem_info = await self.get_memory_info()
             system_info.update(mem_info)
-            
-            # 新增：获取存储卷信息
             vol_info = await self.get_vol_usage()
             system_info["volumes"] = vol_info
-            
             return system_info
-            
+
         except Exception as e:
             self.logger.error("Error getting system info: %s", str(e))
-            # 在异常处理中返回空数据
             return {
                 "uptime_seconds": 0,
                 "uptime": "未知",
@@ -81,71 +85,165 @@ class SystemManager:
                 "memory_available": "未知",
                 "volumes": {}
             }
-    
-    def save_sensor_data_for_debug(self, sensors_output: str):
-        """保存传感器数据以便调试"""
-        if not self.debug_enabled:
-            return
-            
+
+    async def get_temperatures_from_sensors(self) -> dict:
+        """一次性获取CPU和主板温度"""
         try:
-            # 创建调试目录
-            if not os.path.exists(self.sensors_debug_path):
-                os.makedirs(self.sensors_debug_path)
+            command = "sensors"
+            self._debug_log(f"执行sensors命令获取温度: {command}")
             
-            # 生成文件名
-            timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-            filename = os.path.join(self.sensors_debug_path, f"sensors_{timestamp}.log")
+            sensors_output = await self.coordinator.run_command(command)
+            if self.debug_enabled:
+                self._debug_log(f"sensors命令输出长度: {len(sensors_output) if sensors_output else 0}")
             
-            # 写入文件
-            with open(filename, "w") as f:
-                f.write(sensors_output)
+            if not sensors_output:
+                self._warning_log("sensors命令无输出")
+                return {"cpu": "未知", "motherboard": "未知"}
+            
+            # 同时解析CPU和主板温度
+            cpu_temp = self.extract_cpu_temp_from_sensors(sensors_output)
+            mobo_temp = self.extract_mobo_temp_from_sensors(sensors_output)
+            
+            # 记录获取结果
+            if cpu_temp != "未知":
+                self._info_log(f"通过sensors获取CPU温度成功: {cpu_temp}")
+            else:
+                self._warning_log("sensors命令未找到CPU温度")
+                
+            if mobo_temp != "未知":
+                self._info_log(f"通过sensors获取主板温度成功: {mobo_temp}")
+            else:
+                self._warning_log("sensors命令未找到主板温度")
+            
+            return {"cpu": cpu_temp, "motherboard": mobo_temp}
             
-            self.logger.info("Saved sensors output to %s for debugging", filename)
         except Exception as e:
-            self.logger.error("Failed to save sensor data: %s", str(e))
-    
-    async def get_cpu_temp_fallback(self) -> str:
-        """备用方法获取CPU温度"""
-        self.logger.info("Trying fallback methods to get CPU temperature")
-        
-        # 方法1: 从/sys/class/thermal读取
+            self._error_log(f"使用sensors命令获取温度失败: {e}")
+            return {"cpu": "未知", "motherboard": "未知"}
+
+    async def get_cpu_temp_from_kernel(self) -> str:
+        """获取CPU温度 - 向后兼容"""
+        temps = await self.get_temperatures_from_sensors()
+        return temps["cpu"]
+
+    async def get_mobo_temp_from_kernel(self) -> str:
+        """获取主板温度 - 向后兼容"""
+        temps = await self.get_temperatures_from_sensors()
+        return temps["motherboard"]
+
+    async def get_cpu_temp_from_sensors(self) -> str:
+        """使用sensors命令获取CPU温度 - 向后兼容"""
+        temps = await self.get_temperatures_from_sensors()
+        return temps["cpu"]
+
+    async def get_mobo_temp_from_sensors(self) -> str:
+        """使用sensors命令获取主板温度 - 向后兼容"""
+        temps = await self.get_temperatures_from_sensors()
+        return temps["motherboard"]
+
+    def extract_cpu_temp_from_sensors(self, sensors_output: str) -> str:
+        """从sensors输出中提取CPU温度"""
         try:
-            for i in range(5):  # 检查前5个可能的传感器
-                path = f"/sys/class/thermal/thermal_zone{i}/temp"
-                output = await self.coordinator.run_command(f"cat {path} 2>/dev/null")
-                if output and output.isdigit():
-                    temp = float(output) / 1000.0
-                    self.logger.info("Found CPU temperature via thermal zone: %.1f°C", temp)
-                    return f"{temp:.1f} °C"
-        except Exception:
-            pass
-        
-        # 方法2: 从hwmon设备读取
+            lines = sensors_output.split('\n')
+            self._debug_log(f"解析sensors输出，共{len(lines)}行")
+            
+            for i, line in enumerate(lines):
+                line_lower = line.lower().strip()
+                if self.debug_enabled:
+                    self._debug_log(f"第{i+1}行: {line_lower}")
+                
+                # AMD CPU温度关键词
+                if any(keyword in line_lower for keyword in [
+                    "tctl", "tdie", "k10temp"
+                ]):
+                    self._debug_log(f"找到AMD CPU温度行: {line}")
+                    if '+' in line and '°c' in line_lower:
+                        try:
+                            temp_match = line.split('+')[1].split('°')[0].strip()
+                            temp = float(temp_match)
+                            if 0 < temp < 150:
+                                self._info_log(f"从sensors提取AMD CPU温度: {temp:.1f}°C")
+                                return f"{temp:.1f} °C"
+                        except (ValueError, IndexError) as e:
+                            self._debug_log(f"解析AMD温度失败: {e}")
+                            continue
+                
+                # Intel CPU温度关键词
+                if any(keyword in line_lower for keyword in [
+                    "package id", "core 0", "coretemp"
+                ]) and not any(exclude in line_lower for exclude in ["fan"]):
+                    self._debug_log(f"找到Intel CPU温度行: {line}")
+                    if '+' in line and '°c' in line_lower:
+                        try:
+                            temp_match = line.split('+')[1].split('°')[0].strip()
+                            temp = float(temp_match)
+                            if 0 < temp < 150:
+                                self._info_log(f"从sensors提取Intel CPU温度: {temp:.1f}°C")
+                                return f"{temp:.1f} °C"
+                        except (ValueError, IndexError) as e:
+                            self._debug_log(f"解析Intel温度失败: {e}")
+                            continue
+                
+                # 通用CPU温度模式
+                if ('cpu' in line_lower or 'processor' in line_lower) and '+' in line and '°c' in line_lower:
+                    self._debug_log(f"找到通用CPU温度行: {line}")
+                    try:
+                        temp_match = line.split('+')[1].split('°')[0].strip()
+                        temp = float(temp_match)
+                        if 0 < temp < 150:
+                            self._info_log(f"从sensors提取通用CPU温度: {temp:.1f}°C")
+                            return f"{temp:.1f} °C"
+                    except (ValueError, IndexError) as e:
+                        self._debug_log(f"解析通用CPU温度失败: {e}")
+                        continue
+            
+            self._warning_log("未在sensors输出中找到CPU温度")
+            return "未知"
+            
+        except Exception as e:
+            self._error_log(f"解析sensors CPU温度输出失败: {e}")
+            return "未知"
+
+    def extract_mobo_temp_from_sensors(self, sensors_output: str) -> str:
+        """从sensors输出中提取主板温度"""
         try:
-            for i in range(5):  # 检查前5个可能的hwmon设备
-                for j in range(5):  # 检查每个设备的前5个温度传感器
-                    path = f"/sys/class/hwmon/hwmon{i}/temp{j}_input"
-                    output = await self.coordinator.run_command(f"cat {path} 2>/dev/null")
-                    if output and output.isdigit():
-                        temp = float(output) / 1000.0
-                        self.logger.info("Found CPU temperature via hwmon: %.1f°C", temp)
-                        return f"{temp:.1f} °C"
-        except Exception:
-            pass
-        
-        # 方法3: 使用psutil库（如果可用）
-        try:
-            output = await self.coordinator.run_command("python3 -c 'import psutil; print(psutil.sensors_temperatures().get(\"coretemp\")[0].current)' 2>/dev/null")
-            if output and output.replace('.', '', 1).isdigit():
-                temp = float(output)
-                self.logger.info("Found CPU temperature via psutil: %.1f°C", temp)
-                return f"{temp:.1f} °C"
-        except Exception:
-            pass
-        
-        self.logger.warning("All fallback methods failed to get CPU temperature")
-        return ""
-    
+            lines = sensors_output.split('\n')
+            self._debug_log(f"解析主板温度，共{len(lines)}行")
+            
+            for i, line in enumerate(lines):
+                line_lower = line.lower().strip()
+                
+                # 主板温度关键词
+                if any(keyword in line_lower for keyword in [
+                    "motherboard", "mobo", "mb", "system", "chipset", 
+                    "ambient", "temp1:", "temp2:", "temp3:", "systin"
+                ]) and not any(cpu_keyword in line_lower for cpu_keyword in [
+                    "cpu", "core", "package", "processor", "tctl", "tdie"
+                ]) and not any(exclude in line_lower for exclude in ["fan", "rpm"]):
+                    
+                    self._debug_log(f"找到可能的主板温度行: {line}")
+                    
+                    if '+' in line and '°c' in line_lower:
+                        try:
+                            temp_match = line.split('+')[1].split('°')[0].strip()
+                            temp = float(temp_match)
+                            # 主板温度通常在15-70度之间
+                            if 15 <= temp <= 70:
+                                self._info_log(f"从sensors提取主板温度: {temp:.1f}°C")
+                                return f"{temp:.1f} °C"
+                            else:
+                                self._debug_log(f"主板温度值超出合理范围: {temp:.1f}°C")
+                        except (ValueError, IndexError) as e:
+                            self._debug_log(f"解析主板温度失败: {e}")
+                            continue
+            
+            self._warning_log("未在sensors输出中找到主板温度")
+            return "未知"
+            
+        except Exception as e:
+            self._error_log(f"解析sensors主板温度输出失败: {e}")
+            return "未知"
+
     def format_uptime(self, seconds: float) -> str:
         """格式化运行时间为易读格式"""
         try:
@@ -166,223 +264,6 @@ class SystemManager:
             self.logger.error("Failed to format uptime: %s", str(e))
             return "未知"
     
-    def extract_cpu_temp(self, sensors_output: str) -> str:
-        """从 sensors 输出中提取 CPU 温度，优先获取 Package id 0"""
-        # 优先尝试获取 Package id 0 温度值
-        package_id_pattern = r'Package id 0:\s*\+?(\d+\.?\d*)°C'
-        package_match = re.search(package_id_pattern, sensors_output, re.IGNORECASE)
-        if package_match:
-            try:
-                package_temp = float(package_match.group(1))
-                self.logger.debug("优先使用 Package id 0 温度: %.1f°C", package_temp)
-                return f"{package_temp:.1f} °C"
-            except (ValueError, IndexError) as e:
-                self.logger.debug("Package id 0 解析错误: %s", str(e))
-
-        # 其次尝试解析JSON格式
-        if sensors_output.strip().startswith('{'):
-            try:
-                data = json.loads(sensors_output)
-                self.logger.debug("JSON sensors data: %s", json.dumps(data, indent=2))
-                
-                # 查找包含Package相关键名的温度值
-                for key, values in data.items():
-                    if any(kw in key.lower() for kw in ["package", "pkg", "physical"]):
-                        for subkey, temp_value in values.items():
-                            if any(kw in subkey.lower() for kw in ["temp", "input"]) and not "crit" in subkey.lower():
-                                try:
-                                    if isinstance(temp_value, (int, float)):
-                                        self.logger.debug("JSON中找到Package温度: %s/%s = %.1f°C", key, subkey, temp_value)
-                                        return f"{temp_value:.1f} °C"
-                                except Exception as e:
-                                    self.logger.debug("JSON值错误: %s", str(e))
-                # 新增：尝试直接获取Tdie/Tctl温度（AMD CPU）
-                for key, values in data.items():
-                    if "k10temp" in key.lower():
-                        for subkey, temp_value in values.items():
-                            if "tdie" in subkey.lower() or "tctl" in subkey.lower():
-                                try:
-                                    if isinstance(temp_value, (int, float)):
-                                        self.logger.debug("JSON中找到Tdie/Tctl温度: %s/%s = %.1f°C", key, subkey, temp_value)
-                                        return f"{temp_value:.1f} °C"
-                                except:
-                                    pass
-            except Exception as e:
-                self.logger.warning("JSON解析失败: %s", str(e))
-
-        # 最后尝试其他模式
-        other_patterns = [
-            r'Package id 0:\s*\+?(\d+\.?\d*)°C',  # 再次尝试确保捕获
-            r'CPU Temperature:\s*\+?(\d+\.?\d*)°C',
-            r'cpu_thermal:\s*\+?(\d+\.?\d*)°C',
-            r'Tdie:\s*\+?(\d+\.?\d*)°C',          # AMD CPU
-            r'Tctl:\s*\+?(\d+\.?\d*)°C',          # AMD CPU
-            r'PECI Agent \d:\s*\+?(\d+\.?\d*)°C',
-            r'Composite:\s*\+?(\d+\.?\d*)°C',
-            r'CPU\s+Temp:\s*\+?(\d+\.?\d*)°C',
-            r'k10temp-pci\S*:\s*\+?(\d+\.?\d*)°C',
-            r'Physical id 0:\s*\+?(\d+\.?\d*)°C'
-        ]
-        
-        for pattern in other_patterns:
-            match = re.search(pattern, sensors_output, re.IGNORECASE)
-            if match:
-                try:
-                    temp = float(match.group(1))
-                    self.logger.debug("匹配到CPU温度: %s: %.1f°C", pattern, temp)
-                    return f"{temp:.1f} °C"
-                except (ValueError, IndexError):
-                    continue
-        
-        # 如果所有方法都失败返回未知
-        return "未知"
-
-    def extract_temp_from_systin(self, systin_data: dict) -> float:
-        """从 SYSTIN 数据结构中提取温度值"""
-        if not systin_data:
-            return None
-            
-        # 尝试从不同键名获取温度值
-        for key in ["temp1_input", "input", "value"]:
-            temp = systin_data.get(key)
-            if temp is not None:
-                try:
-                    return float(temp)
-                except (TypeError, ValueError):
-                    continue
-        return None
-    
-    def extract_mobo_temp(self, sensors_output: str) -> str:
-        """从 sensors 输出中提取主板温度"""
-        # 首先尝试解析JSON格式
-        if sensors_output.strip().startswith('{'):
-            try:
-                data = json.loads(sensors_output)
-                
-                # 查找包含主板相关键名的温度值
-                candidates = []
-                for key, values in data.items():
-                    # 优先检查 SYSTIN 键
-                    if "systin" in key.lower():
-                        temp = self.extract_temp_from_systin(values)
-                        if temp is not None:
-                            return f"{temp:.1f} °C"
-                    
-                    if any(kw in key.lower() for kw in ["system", "motherboard", "mb", "board", "pch", "chipset", "sys", "baseboard", "systin"]):
-                        for subkey, temp_value in values.items():
-                            if any(kw in subkey.lower() for kw in ["temp", "input"]) and not "crit" in subkey.lower():
-                                try:
-                                    if isinstance(temp_value, (int, float)):
-                                        candidates.append(temp_value)
-                                        self.logger.debug("Found mobo temp candidate in JSON: %s/%s = %.1f°C", key, subkey, temp_value)
-                                except Exception:
-                                    pass
-                
-                # 如果有候选值，取平均值
-                if candidates:
-                    avg_temp = sum(candidates) / len(candidates)
-                    return f"{avg_temp:.1f} °C"
-                    
-                # 新增：尝试直接获取 SYSTIN 的温度值
-                systin_temp = self.extract_temp_from_systin(data.get("nct6798-isa-02a0", {}).get("SYSTIN", {}))
-                if systin_temp is not None:
-                    return f"{systin_temp:.1f} °C"
-                    
-            except Exception as e:
-                self.logger.warning("Failed to parse sensors JSON: %s", str(e))
-        
-        # 改进SYSTIN提取逻辑
-        systin_patterns = [
-            r'SYSTIN:\s*[+\-]?\s*(\d+\.?\d*)\s*°C',  # 标准格式
-            r'SYSTIN[:\s]+[+\-]?\s*(\d+\.?\d*)\s*°C',  # 兼容无冒号或多余空格
-            r'System Temp:\s*[+\-]?\s*(\d+\.?\d*)\s*°C'  # 备选方案
-        ]
-        
-        for pattern in systin_patterns:
-            systin_match = re.search(pattern, sensors_output, re.IGNORECASE)
-            if systin_match:
-                try:
-                    temp = float(systin_match.group(1))
-                    self.logger.debug("Found SYSTIN temperature: %.1f°C", temp)
-                    return f"{temp:.1f} °C"
-                except (ValueError, IndexError) as e:
-                    self.logger.debug("SYSTIN match error: %s", str(e))
-                    continue
-        for line in sensors_output.splitlines():
-            if 'SYSTIN' in line or 'System Temp' in line:
-                # 改进的温度值提取正则
-                match = re.search(r'[+\-]?\s*(\d+\.?\d*)\s*°C', line)
-                if match:
-                    try:
-                        temp = float(match.group(1))
-                        self.logger.debug("Found mobo temp in line: %s: %.1f°C", line.strip(), temp)
-                        return f"{temp:.1f} °C"
-                    except ValueError:
-                        continue
-        
-        
-        # 如果找不到SYSTIN，尝试其他主板温度模式
-        other_patterns = [
-            r'System Temp:\s*\+?(\d+\.?\d*)°C',
-            r'MB Temperature:\s*\+?(\d+\.?\d*)°C',
-            r'Motherboard:\s*\+?(\d+\.?\d*)°C',
-            r'SYS Temp:\s*\+?(\d+\.?\d*)°C',
-            r'Board Temp:\s*\+?(\d+\.?\d*)°C',
-            r'PCH_Temp:\s*\+?(\d+\.?\d*)°C',
-            r'Chipset:\s*\+?(\d+\.?\d*)°C',
-            r'Baseboard Temp:\s*\+?(\d+\.?\d*)°C',
-            r'System Temperature:\s*\+?(\d+\.?\d*)°C',
-            r'Mainboard Temp:\s*\+?(\d+\.?\d*)°C'
-        ]
-        
-        temp_values = []
-        for pattern in other_patterns:
-            matches = re.finditer(pattern, sensors_output, re.IGNORECASE)
-            for match in matches:
-                try:
-                    temp = float(match.group(1))
-                    temp_values.append(temp)
-                    self.logger.debug("Found motherboard temperature with pattern: %s: %.1f°C", pattern, temp)
-                except (ValueError, IndexError):
-                    continue
-        
-        # 如果有找到温度值，取平均值
-        if temp_values:
-            avg_temp = sum(temp_values) / len(temp_values)
-            return f"{avg_temp:.1f} °C"
-        
-        # 最后，尝试手动扫描所有温度值
-        fallback_candidates = []
-        for line in sensors_output.splitlines():
-            if '°C' in line:
-                # 跳过CPU相关的行
-                if any(kw in line.lower() for kw in ["core", "cpu", "package", "tccd", "k10temp", "processor", "amd", "intel", "nvme"]):
-                    continue
-                    
-                # 跳过风扇和电压行
-                if any(kw in line.lower() for kw in ["fan", "volt", "vin", "+3.3", "+5", "+12", "vdd", "power", "crit", "max", "min"]):
-                    continue
-                    
-                # 查找温度值
-                match = re.search(r'(\d+\.?\d*)\s*°C', line)
-                if match:
-                    try:
-                        temp = float(match.group(1))
-                        # 合理温度范围检查 (0-80°C)
-                        if 0 < temp < 80:
-                            fallback_candidates.append(temp)
-                            self.logger.debug("Fallback mobo candidate: %s -> %.1f°C", line.strip(), temp)
-                    except ValueError:
-                        continue
-        
-        # 如果有候选值，取平均值
-        if fallback_candidates:
-            avg_temp = sum(fallback_candidates) / len(fallback_candidates)
-            self.logger.warning("Using fallback motherboard temperature detection")
-            return f"{avg_temp:.1f} °C"
-        
-        return "未知"
-    
     async def get_memory_info(self) -> dict:
         """获取内存使用信息"""
         try:
@@ -408,7 +289,7 @@ class SystemManager:
             }
             
         except Exception as e:
-            self.logger.error("获取内存信息失败: %s", str(e))
+            self._error_log(f"获取内存信息失败: {str(e)}")
             return {}
     
     async def get_vol_usage(self) -> dict:
@@ -498,28 +379,28 @@ class SystemManager:
         
     async def reboot_system(self):
         """重启系统"""
-        self.logger.info("Initiating system reboot...")
+        self._info_log("Initiating system reboot...")
         try:
             await self.coordinator.run_command("sudo reboot")
-            self.logger.info("Reboot command sent")
+            self._info_log("Reboot command sent")
             
             if "system" in self.coordinator.data:
                 self.coordinator.data["system"]["status"] = "rebooting"
                 self.coordinator.async_update_listeners()
         except Exception as e:
-            self.logger.error("Failed to reboot system: %s", str(e))
+            self._error_log(f"Failed to reboot system: {str(e)}")
             raise
     
     async def shutdown_system(self):
         """关闭系统"""
-        self.logger.info("Initiating system shutdown...")
+        self._info_log("Initiating system shutdown...")
         try:
             await self.coordinator.run_command("sudo shutdown -h now")
-            self.logger.info("Shutdown command sent")
+            self._info_log("Shutdown command sent")
             
             if "system" in self.coordinator.data:
                 self.coordinator.data["system"]["status"] = "off"
                 self.coordinator.async_update_listeners()
         except Exception as e:
-            self.logger.error("Failed to shutdown system: %s", str(e))
+            self._error_log(f"Failed to shutdown system: {str(e)}")
             raise

custom_components/fn_nas/ups_manager.py

@@ -11,9 +11,27 @@ class UPSManager:
     def __init__(self, coordinator):
         self.coordinator = coordinator
         self.logger = _LOGGER.getChild("ups_manager")
-        self.logger.setLevel(logging.DEBUG)
-        self.debug_enabled = False  # UPS调试模式开关
-        self.ups_debug_path = "/config/fn_nas_ups_debug"  # UPS调试文件保存路径
+        # 根据Home Assistant的日志级别动态设置
+        self.logger.setLevel(logging.DEBUG if _LOGGER.isEnabledFor(logging.DEBUG) else logging.INFO)
+        self.debug_enabled = _LOGGER.isEnabledFor(logging.DEBUG)  # 基于HA调试模式
+        self.ups_debug_path = "/config/fn_nas_ups_debug"
+
+    def _debug_log(self, message: str):
+        """只在调试模式下输出详细日志"""
+        if self.debug_enabled:
+            self.logger.debug(message)
+
+    def _info_log(self, message: str):
+        """重要信息日志"""
+        self.logger.info(message)
+
+    def _warning_log(self, message: str):
+        """警告日志"""
+        self.logger.warning(message)
+
+    def _error_log(self, message: str):
+        """错误日志"""
+        self.logger.error(message)
     
     async def get_ups_info(self) -> dict:
         """获取连接的UPS信息"""
@@ -31,7 +49,7 @@ class UPSManager:
         
         try:
             # 尝试使用NUT工具获取UPS信息
-            self.logger.debug("尝试使用NUT工具获取UPS信息")
+            self._debug_log("尝试使用NUT工具获取UPS信息")
             output = await self.coordinator.run_command("upsc -l")
             
             if output and "No such file" not in output:
@@ -39,11 +57,11 @@ class UPSManager:
                 ups_names = output.splitlines()
                 if ups_names:
                     ups_name = ups_names[0].strip()
-                    self.logger.debug("发现UPS: %s", ups_name)
+                    self._debug_log(f"发现UPS: {ups_name}")
                     
                     # 获取详细的UPS信息
                     ups_details = await self.coordinator.run_command(f"upsc {ups_name}")
-                    self.logger.debug("UPS详细信息: %s", ups_details)
+                    self._debug_log(f"UPS详细信息: {ups_details}")
                     
                     # 保存UPS数据以便调试
                     self.save_ups_data_for_debug(ups_details)
@@ -51,20 +69,20 @@ class UPSManager:
                     # 解析UPS信息
                     return self.parse_nut_ups_info(ups_details)
                 else:
-                    self.logger.debug("未找到连接的UPS")
+                    self._debug_log("未找到连接的UPS")
             else:
-                self.logger.debug("未安装NUT工具，尝试备用方法")
+                self._debug_log("未安装NUT工具，尝试备用方法")
             
             # 备用方法：尝试直接读取UPS状态
             return await self.get_ups_info_fallback()
             
         except Exception as e:
-            self.logger.error("获取UPS信息时出错: %s", str(e), exc_info=True)
+            self._error_log(f"获取UPS信息时出错: {str(e)}")
             return ups_info
     
     async def get_ups_info_fallback(self) -> dict:
         """备用方法获取UPS信息"""
-        self.logger.info("尝试备用方法获取UPS信息")
+        self._info_log("尝试备用方法获取UPS信息")
         ups_info = {
             "status": "未知",
             "battery_level": "未知",
@@ -81,7 +99,7 @@ class UPSManager:
             # 方法1: 检查USB连接的UPS
             usb_ups_output = await self.coordinator.run_command("lsusb | grep -i ups || echo 'No USB UPS'")
             if usb_ups_output and "No USB UPS" not in usb_ups_output:
-                self.logger.debug("检测到USB UPS设备: %s", usb_ups_output)
+                self._debug_log(f"检测到USB UPS设备: {usb_ups_output}")
                 ups_info["ups_type"] = "USB"
                 
                 # 尝试从输出中提取型号
@@ -111,7 +129,7 @@ class UPSManager:
             return ups_info
             
         except Exception as e:
-            self.logger.error("备用方法获取UPS信息失败: %s", str(e))
+            self._error_log(f"备用方法获取UPS信息失败: {str(e)}")
             return ups_info
     
     def parse_nut_ups_info(self, ups_output: str) -> dict:
@@ -253,6 +271,6 @@ class UPSManager:
             with open(filename, "w") as f:
                 f.write(ups_output)
             
-            self.logger.info("保存UPS数据到 %s 用于调试", filename)
+            self._info_log(f"保存UPS数据到 {filename} 用于调试")
         except Exception as e:
-            self.logger.error("保存UPS数据失败: %s", str(e))
+            self._error_log(f"保存UPS数据失败: {str(e)}")

custom_components/fn_nas/vm_manager.py

@@ -8,15 +8,40 @@ class VMManager:
     def __init__(self, coordinator):
         self.coordinator = coordinator
         self.vms = []
+        self.logger = _LOGGER.getChild("vm_manager")
+        # 根据Home Assistant的日志级别动态设置
+        self.logger.setLevel(logging.DEBUG if _LOGGER.isEnabledFor(logging.DEBUG) else logging.INFO)
+        self.debug_enabled = _LOGGER.isEnabledFor(logging.DEBUG)
+
+    def _debug_log(self, message: str):
+        """只在调试模式下输出详细日志"""
+        if self.debug_enabled:
+            self.logger.debug(message)
+
+    def _info_log(self, message: str):
+        """重要信息日志"""
+        self.logger.info(message)
+
+    def _warning_log(self, message: str):
+        """警告日志"""
+        self.logger.warning(message)
+
+    def _error_log(self, message: str):
+        """错误日志"""
+        self.logger.error(message)
 
     async def get_vm_list(self):
         """获取虚拟机列表及其状态"""
         try:
+            self._debug_log("开始获取虚拟机列表")
             output = await self.coordinator.run_command("virsh list --all")
+            self._debug_log(f"virsh命令输出: {output}")
+            
             self.vms = self._parse_vm_list(output)
+            self._info_log(f"获取到{len(self.vms)}个虚拟机")
             return self.vms
         except Exception as e:
-            _LOGGER.error("获取虚拟机列表失败: %s", str(e))
+            self._error_log(f"获取虚拟机列表失败: {str(e)}")
             return []
 
     def _parse_vm_list(self, output):
@@ -43,14 +68,18 @@ class VMManager:
     async def get_vm_title(self, vm_name):
         """获取虚拟机的标题"""
         try:
+            self._debug_log(f"获取虚拟机{vm_name}的标题")
             output = await self.coordinator.run_command(f"virsh dumpxml {vm_name}")
             # 在XML输出中查找<title>标签
             match = re.search(r'<title>(.*?)</title>', output, re.DOTALL)
             if match:
-                return match.group(1).strip()
+                title = match.group(1).strip()
+                self._debug_log(f"虚拟机{vm_name}标题: {title}")
+                return title
+            self._debug_log(f"虚拟机{vm_name}无标题，使用名称")
             return vm_name  # 如果没有标题，则返回虚拟机名称
         except Exception as e:
-            _LOGGER.error("获取虚拟机标题失败: %s", str(e))
+            self._error_log(f"获取虚拟机标题失败: {str(e)}")
             return vm_name
 
     async def control_vm(self, vm_name, action):
@@ -61,8 +90,10 @@ class VMManager:
         
         command = f"virsh {action} {vm_name}"
         try:
+            self._info_log(f"执行虚拟机操作: {command}")
             await self.coordinator.run_command(command)
+            self._info_log(f"虚拟机{vm_name}操作{action}成功")
             return True
         except Exception as e:
-            _LOGGER.error("执行虚拟机操作失败: %s", str(e))
+            self._error_log(f"执行虚拟机操作失败: {str(e)}")
             return False