初始化项目：进程监控系统

.idea/.gitignore

@@ -0,0 +1,11 @@
+echo "*.pyc
+__pycache__/
+.env
+*.log
+logs/
+.idea/
+.vscode/
+*.sqlite3
+db.sqlite3
+venv/
+.venv/" > .gitignore

.idea/automated_task_monitor.iml

@@ -0,0 +1,30 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="FacetManager">
+    <facet type="django" name="Django">
+      <configuration>
+        <option name="rootFolder" value="$MODULE_DIR$" />
+        <option name="settingsModule" value="automated_task_monitor/settings.py" />
+        <option name="manageScript" value="$MODULE_DIR$/manage.py" />
+        <option name="environment" value="&lt;map/&gt;" />
+        <option name="doNotUseTestRunner" value="false" />
+        <option name="trackFilePattern" value="migrations" />
+      </configuration>
+    </facet>
+  </component>
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/.venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="TemplatesService">
+    <option name="TEMPLATE_CONFIGURATION" value="Django" />
+    <option name="TEMPLATE_FOLDERS">
+      <list>
+        <option value="$MODULE_DIR$/../automated_task_monitor\templates" />
+      </list>
+    </option>
+  </component>
+</module>

.idea/inspectionProfiles/Project_Default.xml

@@ -0,0 +1,93 @@
+<component name="InspectionProjectProfileManager">
+  <profile version="1.0">
+    <option name="myName" value="Project Default" />
+    <inspection_tool class="Eslint" enabled="true" level="WARNING" enabled_by_default="true" />
+    <inspection_tool class="HtmlUnknownAttribute" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="myValues">
+        <value>
+          <list size="6">
+            <item index="0" class="java.lang.String" itemvalue="folder" />
+            <item index="1" class="java.lang.String" itemvalue="selected_folder" />
+            <item index="2" class="java.lang.String" itemvalue="%}selected{%" />
+            <item index="3" class="java.lang.String" itemvalue="{%" />
+            <item index="4" class="java.lang.String" itemvalue="endif" />
+            <item index="5" class="java.lang.String" itemvalue="%}" />
+          </list>
+        </value>
+      </option>
+      <option name="myCustomValuesEnabled" value="true" />
+    </inspection_tool>
+    <inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredPackages">
+        <value>
+          <list size="50">
+            <item index="0" class="java.lang.String" itemvalue="tensorflow" />
+            <item index="1" class="java.lang.String" itemvalue="ntplib" />
+            <item index="2" class="java.lang.String" itemvalue="sklearn" />
+            <item index="3" class="java.lang.String" itemvalue="mysqlclient" />
+            <item index="4" class="java.lang.String" itemvalue="async-timeout" />
+            <item index="5" class="java.lang.String" itemvalue="cffi" />
+            <item index="6" class="java.lang.String" itemvalue="python-dotenv" />
+            <item index="7" class="java.lang.String" itemvalue="pycparser" />
+            <item index="8" class="java.lang.String" itemvalue="alibabacloud-openapi-util" />
+            <item index="9" class="java.lang.String" itemvalue="frozenlist" />
+            <item index="10" class="java.lang.String" itemvalue="alibabacloud-credentials" />
+            <item index="11" class="java.lang.String" itemvalue="rest-framework-simplejwt" />
+            <item index="12" class="java.lang.String" itemvalue="alibabacloud-tea-console" />
+            <item index="13" class="java.lang.String" itemvalue="certifi" />
+            <item index="14" class="java.lang.String" itemvalue="urllib3" />
+            <item index="15" class="java.lang.String" itemvalue="alibabacloud-market20151101" />
+            <item index="16" class="java.lang.String" itemvalue="django-cors-headers" />
+            <item index="17" class="java.lang.String" itemvalue="alibabacloud-tea-util" />
+            <item index="18" class="java.lang.String" itemvalue="alibabacloud-endpoint-util" />
+            <item index="19" class="java.lang.String" itemvalue="tzdata" />
+            <item index="20" class="java.lang.String" itemvalue="cryptography" />
+            <item index="21" class="java.lang.String" itemvalue="alibabacloud-darabonba-env" />
+            <item index="22" class="java.lang.String" itemvalue="alibabacloud-tea-openapi" />
+            <item index="23" class="java.lang.String" itemvalue="attrs" />
+            <item index="24" class="java.lang.String" itemvalue="jmespath" />
+            <item index="25" class="java.lang.String" itemvalue="alibabacloud-tea" />
+            <item index="26" class="java.lang.String" itemvalue="alibabacloud-gateway-spi" />
+            <item index="27" class="java.lang.String" itemvalue="django-rest-framework" />
+            <item index="28" class="java.lang.String" itemvalue="Django" />
+            <item index="29" class="java.lang.String" itemvalue="typing_extensions" />
+            <item index="30" class="java.lang.String" itemvalue="alibabacloud-tea-xml" />
+            <item index="31" class="java.lang.String" itemvalue="aiohttp" />
+            <item index="32" class="java.lang.String" itemvalue="multidict" />
+            <item index="33" class="java.lang.String" itemvalue="yarl" />
+            <item index="34" class="java.lang.String" itemvalue="aiosignal" />
+            <item index="35" class="java.lang.String" itemvalue="idna" />
+            <item index="36" class="java.lang.String" itemvalue="PyJWT" />
+            <item index="37" class="java.lang.String" itemvalue="rsa" />
+            <item index="38" class="java.lang.String" itemvalue="msal" />
+            <item index="39" class="java.lang.String" itemvalue="django-sslserver" />
+            <item index="40" class="java.lang.String" itemvalue="six" />
+            <item index="41" class="java.lang.String" itemvalue="asgiref" />
+            <item index="42" class="java.lang.String" itemvalue="ecdsa" />
+            <item index="43" class="java.lang.String" itemvalue="pyasn1" />
+            <item index="44" class="java.lang.String" itemvalue="requests" />
+            <item index="45" class="java.lang.String" itemvalue="sqlparse" />
+            <item index="46" class="java.lang.String" itemvalue="charset-normalizer" />
+            <item index="47" class="java.lang.String" itemvalue="pytz" />
+            <item index="48" class="java.lang.String" itemvalue="djangorestframework" />
+            <item index="49" class="java.lang.String" itemvalue="python-jose" />
+          </list>
+        </value>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyPep8NamingInspection" enabled="true" level="WEAK WARNING" enabled_by_default="true">
+      <option name="ignoredErrors">
+        <list>
+          <option value="N806" />
+        </list>
+      </option>
+    </inspection_tool>
+    <inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
+      <option name="ignoredIdentifiers">
+        <list>
+          <option value="MarKet.urls.Market" />
+        </list>
+      </option>
+    </inspection_tool>
+  </profile>
+</component>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.10 (automated_task_monitor)" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (automated_task_monitor)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/automated_task_monitor.iml" filepath="$PROJECT_DIR$/.idea/automated_task_monitor.iml" />
+    </modules>
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,96 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="12eb891e-5234-4edf-9697-982a38ae2f63" name="更改" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;customColor&quot;: &quot;&quot;,
+  &quot;associatedIndex&quot;: 6
+}</component>
+  <component name="ProjectId" id="2ssNC7QAMi8oN4Kv7IADr6QUnp8" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;RunOnceActivity.OpenDjangoStructureViewOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;last_opened_file_path&quot;: &quot;D:/pythonProject/myproject/.venv/Scripts&quot;,
+    &quot;node.js.detected.package.eslint&quot;: &quot;true&quot;,
+    &quot;node.js.detected.package.tslint&quot;: &quot;true&quot;,
+    &quot;node.js.selected.package.eslint&quot;: &quot;(autodetect)&quot;,
+    &quot;node.js.selected.package.tslint&quot;: &quot;(autodetect)&quot;,
+    &quot;nodejs_package_manager_path&quot;: &quot;npm&quot;,
+    &quot;vue.rearranger.settings.migration&quot;: &quot;true&quot;
+  }
+}</component>
+  <component name="RunManager">
+    <configuration name="automated_task_monitor" type="Python.DjangoServer" factoryName="Django server">
+      <module name="automated_task_monitor" />
+      <option name="ENV_FILES" value="" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="" />
+      <option name="IS_MODULE_SDK" value="false" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <option name="launchJavascriptDebuger" value="false" />
+      <option name="port" value="8000" />
+      <option name="host" value="localhost" />
+      <option name="additionalOptions" value="" />
+      <option name="browserUrl" value="" />
+      <option name="runTestServer" value="false" />
+      <option name="runNoReload" value="false" />
+      <option name="useCustomRunCommand" value="false" />
+      <option name="customRunCommand" value="" />
+      <method v="2" />
+    </configuration>
+  </component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-python-sdk-09665e90c3a7-b11f5e8da5ad-com.jetbrains.pycharm.pro.sharedIndexes.bundled-PY-233.15026.15" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="应用程序级" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="默认任务">
+      <changelist id="12eb891e-5234-4edf-9697-982a38ae2f63" name="更改" comment="" />
+      <created>1739240192225</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1739240192225</updated>
+      <workItem from="1739240213323" duration="67000" />
+      <workItem from="1739240288664" duration="1163000" />
+      <workItem from="1739774523802" duration="384000" />
+      <workItem from="1739775058347" duration="988000" />
+      <workItem from="1739864902383" duration="147000" />
+      <workItem from="1739869240489" duration="361000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+</project>

automated_task_monitor/asgi.py

@@ -0,0 +1,16 @@
+"""
+ASGI config for automated_task_monitor project.
+
+It exposes the ASGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/howto/deployment/asgi/
+"""
+
+import os
+
+from django.core.asgi import get_asgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'automated_task_monitor.settings')
+
+application = get_asgi_application()

automated_task_monitor/settings.py

@@ -0,0 +1,143 @@
+"""
+Django settings for automated_task_monitor project.
+
+Generated by 'django-admin startproject' using Django 5.1.6.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/topics/settings/
+
+For the full list of settings and their values, see
+https://docs.djangoproject.com/en/5.1/ref/settings/
+"""
+
+from pathlib import Path
+import os
+
+# Build paths inside the project like this: BASE_DIR / 'subdir'.
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+
+# Quick-start development settings - unsuitable for production
+# See https://docs.djangoproject.com/en/5.1/howto/deployment/checklist/
+
+# SECURITY WARNING: keep the secret key used in production secret!
+SECRET_KEY = 'django-insecure-!1v8ca8ows01-*m5(&9)qgk5jc-my^q+4d+0)s_*^n&vne^&w9'
+
+# SECURITY WARNING: don't run with debug turned on in production!
+DEBUG = True
+
+ALLOWED_HOSTS = [
+    '127.0.0.1',      # 本地开发
+    'localhost',      # 本地开发
+    '81.69.223.133',  # 你的服务器IP
+]
+
+# 监控配置
+MONITOR_INTERVAL = 60  # 监控间隔（秒）
+
+# Application definition
+
+INSTALLED_APPS = [
+    'django.contrib.admin',
+    'django.contrib.auth',
+    'django.contrib.contenttypes',
+    'django.contrib.sessions',
+    'django.contrib.messages',
+    'django.contrib.staticfiles',
+    'monitor.apps.MonitorConfig',
+]
+
+MIDDLEWARE = [
+    'django.middleware.security.SecurityMiddleware',
+    'django.contrib.sessions.middleware.SessionMiddleware',
+    'django.middleware.common.CommonMiddleware',
+    'django.middleware.csrf.CsrfViewMiddleware',
+    'django.contrib.auth.middleware.AuthenticationMiddleware',
+    'django.contrib.messages.middleware.MessageMiddleware',
+    'django.middleware.clickjacking.XFrameOptionsMiddleware',
+]
+
+ROOT_URLCONF = 'automated_task_monitor.urls'
+
+TEMPLATES = [
+    {
+        'BACKEND': 'django.template.backends.django.DjangoTemplates',
+        'DIRS': [BASE_DIR / 'templates']
+        ,
+        'APP_DIRS': True,
+        'OPTIONS': {
+            'context_processors': [
+                'django.template.context_processors.debug',
+                'django.template.context_processors.request',
+                'django.contrib.auth.context_processors.auth',
+                'django.contrib.messages.context_processors.messages',
+            ],
+        },
+    },
+]
+
+WSGI_APPLICATION = 'automated_task_monitor.wsgi.application'
+
+
+# Database
+# https://docs.djangoproject.com/en/5.1/ref/settings/#databases
+
+DATABASES = {
+    'default': {
+        'ENGINE': 'django.db.backends.mysql',
+        'NAME': 'monitoring_db',
+        'USER': 'root',
+        'PASSWORD': '123456',
+        'HOST': 'localhost',
+        'PORT': '3306',
+    }
+}
+
+
+# Password validation
+# https://docs.djangoproject.com/en/5.1/ref/settings/#auth-password-validators
+
+AUTH_PASSWORD_VALIDATORS = [
+    {
+        'NAME': 'django.contrib.auth.password_validation.UserAttributeSimilarityValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.MinimumLengthValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.CommonPasswordValidator',
+    },
+    {
+        'NAME': 'django.contrib.auth.password_validation.NumericPasswordValidator',
+    },
+]
+
+
+# Internationalization
+# https://docs.djangoproject.com/en/5.1/topics/i18n/
+
+LANGUAGE_CODE = 'en-us'
+
+TIME_ZONE = 'Asia/Shanghai'
+
+USE_I18N = True
+
+USE_TZ = True
+
+
+# Static files (CSS, JavaScript, Images)
+# https://docs.djangoproject.com/en/5.1/howto/static-files/
+
+STATIC_URL = 'static/'
+
+# Default primary key field type
+# https://docs.djangoproject.com/en/5.1/ref/settings/#default-auto-field
+
+DEFAULT_AUTO_FIELD = 'django.db.models.BigAutoField'
+
+# 修改日志路径为项目根目录下的 logs 文件夹
+LOG_DIR = os.path.join(BASE_DIR, 'logs', 'process_monitor')
+
+# 确保日志目录存在
+os.makedirs(LOG_DIR, exist_ok=True)
+

automated_task_monitor/urls.py

@@ -0,0 +1,23 @@
+"""
+URL configuration for automated_task_monitor project.
+
+The `urlpatterns` list routes URLs to views. For more information please see:
+    https://docs.djangoproject.com/en/5.1/topics/http/urls/
+Examples:
+Function views
+    1. Add an import:  from my_app import views
+    2. Add a URL to urlpatterns:  path('', views.home, name='home')
+Class-based views
+    1. Add an import:  from other_app.views import Home
+    2. Add a URL to urlpatterns:  path('', Home.as_view(), name='home')
+Including another URLconf
+    1. Import the include() function: from django.urls import include, path
+    2. Add a URL to urlpatterns:  path('blog/', include('blog.urls'))
+"""
+from django.contrib import admin
+from django.urls import path, include
+
+urlpatterns = [
+    path('admin/', admin.site.urls),
+    path('monitor/', include('monitor.urls')),
+]

automated_task_monitor/wsgi.py

@@ -0,0 +1,16 @@
+"""
+WSGI config for automated_task_monitor project.
+
+It exposes the WSGI callable as a module-level variable named ``application``.
+
+For more information on this file, see
+https://docs.djangoproject.com/en/5.1/howto/deployment/wsgi/
+"""
+
+import os
+
+from django.core.wsgi import get_wsgi_application
+
+os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'automated_task_monitor.settings')
+
+application = get_wsgi_application()

logs/process_monitor/gpu/process_22572_20250218.log

@@ -0,0 +1,67 @@
+2025-02-18 17:35:58,750 - INFO - 开始监控进程:
+├─ 进程名称: Lark.exe
+├─ 进程ID: 22572
+├─ 监控类型: gpu
+├─ 监控间隔: 60秒
+└─ 开始时间: 2025-02-18 17:35:58
+2025-02-18 17:35:58,755 - INFO - 创建新的监控记录
+2025-02-18 17:35:58,765 - INFO - 进程状态:
+├─ 状态码: 1
+├─ 状态描述: running
+├─ 监控状态: 活跃
+└─ 运行时长: 7:43:55.278315
+2025-02-18 17:35:59,119 - INFO - GPU信息
+├─ 状态: 正常
+├─ 使用率: 19.0%
+└─ 显存使用: 1499.0MB
+2025-02-18 17:35:59,134 - INFO - 资源使用情况 - 2025-02-18 17:35:59:
+├─ CPU信息
+│  ├─ 使用率: 0.0%
+│  ├─ 用户态时间: 4.9s
+│  ├─ 内核态时间: 5.2s
+│  ├─ CPU核心数: 16
+│  ├─ CPU频率: 4001.0MHz
+│  └─ 上下文切换: 1470919/0
+├─ 内存信息
+│  ├─ 物理内存: 145.8MB (0.9%)
+│  ├─ 虚拟内存: 138.7MB
+│  ├─ 内存映射: 99个
+│  ├─ 系统内存使用: 79.8%
+│  └─ 交换空间使用: 10.0%
+├─ GPU信息
+│  ├─ 状态: 正常
+│  ├─ 使用率: 19.0%
+│  └─ 显存使用: 1499.0MB
+├─ IO信息
+│  ├─ 读取: 112.8MB (135217次)
+
+2025-02-18 17:36:59,149 - INFO - 进程状态:
+├─ 状态码: 1
+├─ 状态描述: running
+├─ 监控状态: 活跃
+└─ 运行时长: 7:44:55.662074
+2025-02-18 17:36:59,272 - INFO - GPU信息
+├─ 状态: 正常
+├─ 使用率: 1.0%
+└─ 显存使用: 1486.0MB
+2025-02-18 17:36:59,284 - INFO - 资源使用情况 - 2025-02-18 17:36:59:
+├─ CPU信息
+│  ├─ 使用率: 0.0%
+│  ├─ 用户态时间: 4.9s
+│  ├─ 内核态时间: 5.2s
+│  ├─ CPU核心数: 16
+│  ├─ CPU频率: 4001.0MHz
+│  └─ 上下文切换: 1473027/0
+├─ 内存信息
+│  ├─ 物理内存: 145.8MB (0.9%)
+│  ├─ 虚拟内存: 138.5MB
+│  ├─ 内存映射: 99个
+│  ├─ 系统内存使用: 80.1%
+│  └─ 交换空间使用: 10.0%
+├─ GPU信息
+│  ├─ 状态: 正常
+│  ├─ 使用率: 1.0%
+│  └─ 显存使用: 1486.0MB
+├─ IO信息
+│  ├─ 读取: 112.9MB (135263次)
+

logs/process_monitor/memory/process_40128_20250218.log

@@ -0,0 +1,15 @@
+2025-02-18 15:49:36,173 - INFO - 开始监控memory进程 pycharm64.exe (PID: 40128)
+2025-02-18 15:49:37,621 - INFO - 内存使用情况:
+ - 物理内存: 2.05GB
+ - 虚拟内存: 1.87GB
+ - 交换空间: 1.45GB
+ - CPU: 1.5%
+ - GPU: 0.0%
+2025-02-18 15:50:38,966 - INFO - 内存使用情况:
+ - 物理内存: 2.03GB
+ - 虚拟内存: 1.85GB
+ - 交换空间: 1.45GB
+ - CPU: 0.0%
+ - GPU: 0.0%
+2025-02-18 15:51:38,972 - ERROR - 进程 40128 已终止
+2025-02-18 15:51:38,975 - INFO - 监控已结束

manage.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+"""Django's command-line utility for administrative tasks."""
+import os
+import sys
+
+
+def main():
+    """Run administrative tasks."""
+    os.environ.setdefault('DJANGO_SETTINGS_MODULE', 'automated_task_monitor.settings')
+    try:
+        from django.core.management import execute_from_command_line
+    except ImportError as exc:
+        raise ImportError(
+            "Couldn't import Django. Are you sure it's installed and "
+            "available on your PYTHONPATH environment variable? Did you "
+            "forget to activate a virtual environment?"
+        ) from exc
+    execute_from_command_line(sys.argv)
+
+
+if __name__ == '__main__':
+    main()

monitor/admin.py

@@ -0,0 +1,3 @@
+from django.contrib import admin
+
+# Register your models here.

monitor/apps.py

@@ -0,0 +1,9 @@
+from django.apps import AppConfig
+
+
+class MonitorConfig(AppConfig):
+    default_auto_field = 'django.db.models.BigAutoField'
+    name = 'monitor'
+
+    def ready(self):
+        pass

monitor/migrations/0001_initial.py

@@ -0,0 +1,83 @@
+# Generated by Django 5.1.6 on 2025-02-18 07:09
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    initial = True
+
+    dependencies = [
+    ]
+
+    operations = [
+        migrations.CreateModel(
+            name='HighCPUProcess',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('pid', models.IntegerField(verbose_name='进程ID')),
+                ('process_name', models.CharField(max_length=255, verbose_name='进程名称')),
+                ('log_path', models.CharField(max_length=255, verbose_name='日志路径')),
+                ('is_active', models.BooleanField(default=True, verbose_name='是否活跃')),
+                ('created_at', models.DateTimeField(auto_now_add=True, verbose_name='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, verbose_name='更新时间')),
+                ('status', models.IntegerField(default=1, help_text='1:运行中, 0:已停止', verbose_name='进程状态')),
+                ('cpu_usage', models.FloatField(default=0, verbose_name='CPU使用率(%)')),
+                ('memory_usage', models.FloatField(default=0, verbose_name='内存使用量(GB)')),
+                ('gpu_usage', models.FloatField(default=0, verbose_name='GPU使用率(%)')),
+                ('gpu_memory', models.FloatField(default=0, verbose_name='GPU显存使用量(MB)')),
+                ('virtual_memory', models.FloatField(default=0, verbose_name='虚拟内存使用量(GB)')),
+                ('cpu_cores', models.IntegerField(default=0, verbose_name='使用的CPU核心数')),
+            ],
+            options={
+                'verbose_name': '高CPU进程',
+                'verbose_name_plural': '高CPU进程',
+            },
+        ),
+        migrations.CreateModel(
+            name='HighGPUProcess',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('pid', models.IntegerField(verbose_name='进程ID')),
+                ('process_name', models.CharField(max_length=255, verbose_name='进程名称')),
+                ('log_path', models.CharField(max_length=255, verbose_name='日志路径')),
+                ('is_active', models.BooleanField(default=True, verbose_name='是否活跃')),
+                ('created_at', models.DateTimeField(auto_now_add=True, verbose_name='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, verbose_name='更新时间')),
+                ('status', models.IntegerField(default=1, help_text='1:运行中, 0:已停止', verbose_name='进程状态')),
+                ('cpu_usage', models.FloatField(default=0, verbose_name='CPU使用率(%)')),
+                ('memory_usage', models.FloatField(default=0, verbose_name='内存使用量(GB)')),
+                ('gpu_usage', models.FloatField(default=0, verbose_name='GPU使用率(%)')),
+                ('gpu_memory', models.FloatField(default=0, verbose_name='GPU显存使用量(MB)')),
+                ('virtual_memory', models.FloatField(default=0, verbose_name='虚拟内存使用量(GB)')),
+                ('gpu_index', models.IntegerField(default=0, verbose_name='GPU设备索引')),
+            ],
+            options={
+                'verbose_name': '高GPU进程',
+                'verbose_name_plural': '高GPU进程',
+            },
+        ),
+        migrations.CreateModel(
+            name='HighMemoryProcess',
+            fields=[
+                ('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
+                ('pid', models.IntegerField(verbose_name='进程ID')),
+                ('process_name', models.CharField(max_length=255, verbose_name='进程名称')),
+                ('log_path', models.CharField(max_length=255, verbose_name='日志路径')),
+                ('is_active', models.BooleanField(default=True, verbose_name='是否活跃')),
+                ('created_at', models.DateTimeField(auto_now_add=True, verbose_name='创建时间')),
+                ('updated_at', models.DateTimeField(auto_now=True, verbose_name='更新时间')),
+                ('status', models.IntegerField(default=1, help_text='1:运行中, 0:已停止', verbose_name='进程状态')),
+                ('cpu_usage', models.FloatField(default=0, verbose_name='CPU使用率(%)')),
+                ('memory_usage', models.FloatField(default=0, verbose_name='内存使用量(GB)')),
+                ('gpu_usage', models.FloatField(default=0, verbose_name='GPU使用率(%)')),
+                ('gpu_memory', models.FloatField(default=0, verbose_name='GPU显存使用量(MB)')),
+                ('virtual_memory', models.FloatField(default=0, verbose_name='虚拟内存使用量(GB)')),
+                ('swap_usage', models.FloatField(default=0, verbose_name='交换空间使用量(GB)')),
+            ],
+            options={
+                'verbose_name': '高内存进程',
+                'verbose_name_plural': '高内存进程',
+            },
+        ),
+    ]

monitor/models.py

@@ -0,0 +1,45 @@
+from django.db import models
+
+class BaseProcessMonitor(models.Model):
+    """进程监控基类"""
+    pid = models.IntegerField(verbose_name="进程ID")
+    process_name = models.CharField(max_length=255, verbose_name="进程名称")
+    log_path = models.CharField(max_length=255, verbose_name="日志路径")
+    is_active = models.BooleanField(default=True, verbose_name="是否活跃")
+    created_at = models.DateTimeField(auto_now_add=True, verbose_name="创建时间")
+    updated_at = models.DateTimeField(auto_now=True, verbose_name="更新时间")
+    status = models.IntegerField(default=1, verbose_name="进程状态", help_text="1:运行中, 0:已停止")
+    
+    # 基本资源信息
+    cpu_usage = models.FloatField(default=0, verbose_name="CPU使用率(%)")
+    memory_usage = models.FloatField(default=0, verbose_name="内存使用量(GB)")
+    gpu_usage = models.FloatField(default=0, verbose_name="GPU使用率(%)")
+    gpu_memory = models.FloatField(default=0, verbose_name="GPU显存使用量(MB)")
+    virtual_memory = models.FloatField(default=0, verbose_name="虚拟内存使用量(GB)")
+
+    class Meta:
+        abstract = True
+
+class HighCPUProcess(BaseProcessMonitor):
+    """高CPU使用进程监控"""
+    cpu_cores = models.IntegerField(default=0, verbose_name="使用的CPU核心数")
+
+    class Meta:
+        verbose_name = "高CPU进程"
+        verbose_name_plural = "高CPU进程"
+
+class HighGPUProcess(BaseProcessMonitor):
+    """高GPU使用进程监控"""
+    gpu_index = models.IntegerField(default=0, verbose_name="GPU设备索引")
+
+    class Meta:
+        verbose_name = "高GPU进程"
+        verbose_name_plural = "高GPU进程"
+
+class HighMemoryProcess(BaseProcessMonitor):
+    """高内存使用进程监控"""
+    swap_usage = models.FloatField(default=0, verbose_name="交换空间使用量(GB)")
+
+    class Meta:
+        verbose_name = "高内存进程"
+        verbose_name_plural = "高内存进程"

monitor/tasks.py

@@ -0,0 +1,406 @@
+import psutil
+import time
+from .models import HighCPUProcess, HighGPUProcess, HighMemoryProcess
+import GPUtil  # 需要安装 gputil
+from django.utils import timezone
+import os
+import logging
+from datetime import datetime
+from django.db import models
+from django.conf import settings
+
+def setup_logger(pid, resource_type):
+    """为每个进程设置独立的日志记录器"""
+    from django.conf import settings
+    import os
+    
+    # 构建完整的日志路径
+    log_dir = os.path.join(settings.BASE_DIR, 'logs', 'process_monitor', resource_type)
+    os.makedirs(log_dir, exist_ok=True)
+    
+    log_file = os.path.abspath(os.path.join(log_dir, f'process_{pid}_{datetime.now().strftime("%Y%m%d")}.log'))
+    
+    logger = logging.getLogger(f'{resource_type}_process_{pid}')
+    logger.setLevel(logging.INFO)
+    
+    if not logger.handlers:
+        # 指定 utf-8 编码
+        handler = logging.FileHandler(log_file, encoding='utf-8')
+        formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
+        handler.setFormatter(formatter)
+        logger.addHandler(handler)
+    
+    return logger, log_file
+
+def get_process_gpu_usage(pid):
+    """获取进程的GPU使用情况"""
+    try:
+        import subprocess
+        import logging
+        
+        logger = logging.getLogger('gpu_check')
+        
+        # 检查 NVIDIA GPU
+        try:
+            # 先检查 nvidia-smi 是否可用
+            gpu_info = subprocess.check_output(['which', 'nvidia-smi']).decode('utf-8').strip()
+            logger.info(f"找到 nvidia-smi: {gpu_info}")
+            
+            # 获取 GPU 列表
+            gpu_list = subprocess.check_output(['nvidia-smi', '-L']).decode('utf-8').strip()
+            logger.info(f"检测到的GPU:\n{gpu_list}")
+            
+            if not gpu_list:
+                logger.warning("未检测到NVIDIA GPU")
+                return 0, 0, "无GPU"
+                
+        except (subprocess.SubprocessError, FileNotFoundError) as e:
+            logger.error(f"nvidia-smi 命令错误: {str(e)}")
+            return 0, 0, "驱动未安装"
+        
+        try:
+            # 获取所有 GPU 的基本信息
+            cmd = ['nvidia-smi', '--format=csv,noheader,nounits', '--query-gpu=index,utilization.gpu,memory.used']
+            gpu_output = subprocess.check_output(cmd, timeout=5).decode('utf-8').strip()
+            logger.info(f"GPU基本信息:\n{gpu_output}")
+            
+            # 获取进程的 GPU 使用情况
+            cmd_process = ['nvidia-smi', '--format=csv,noheader,nounits', '--query-compute-apps=gpu_uuid,pid,used_memory']
+            process_output = subprocess.check_output(cmd_process, timeout=5).decode('utf-8').strip()
+            logger.info(f"GPU进程信息:\n{process_output}")
+            
+            # 如果没有任何进程使用 GPU
+            if not process_output:
+                logger.info(f"进程 {pid} 未使用GPU")
+                return 0, 0, "未使用GPU"
+            
+            # 解析进程的 GPU 使用情况
+            total_memory = 0
+            gpu_util = 0
+            
+            # 从进程输出中查找指定 PID
+            for line in process_output.split('\n'):
+                if str(pid) in line:
+                    try:
+                        _, _, memory = line.split(',')
+                        total_memory += float(memory.strip())
+                    except (ValueError, IndexError) as e:
+                        logger.error(f"解析GPU进程数据错误: {str(e)}, 数据: {line}")
+                        continue
+            
+            # 如果找到了进程的 GPU 使用
+            if total_memory > 0:
+                # 获取最大的 GPU 使用率
+                for line in gpu_output.split('\n'):
+                    try:
+                        _, util, _ = line.split(',')
+                        gpu_util = max(gpu_util, float(util.strip()))
+                    except (ValueError, IndexError) as e:
+                        logger.error(f"解析GPU使用率错误: {str(e)}, 数据: {line}")
+                        continue
+                
+                logger.info(
+                    f"进程 {pid} GPU使用情况:\n"
+                    f"├─ GPU使用率: {gpu_util:.1f}%\n"
+                    f"└─ 显存使用: {total_memory:.1f}MB"
+                )
+                return gpu_util, total_memory, "正常"
+            else:
+                logger.info(f"进程 {pid} 未使用GPU")
+                return 0, 0, "未使用GPU"
+                
+        except subprocess.TimeoutExpired as e:
+            logger.error(f"GPU命令超时: {str(e)}")
+            return 0, 0, "获取超时"
+        except subprocess.CalledProcessError as e:
+            logger.error(f"GPU命令执行错误: {str(e)}, 输出: {e.output.decode('utf-8') if e.output else 'None'}")
+            return 0, 0, "命令错误"
+        except Exception as e:
+            logger.error(f"获取GPU信息时发生错误: {str(e)}")
+            return 0, 0, "获取错误"
+            
+    except Exception as e:
+        logger.error(f"GPU检测失败: {str(e)}")
+        return 0, 0, "检测失败"
+
+def monitor_process(pid, resource_type):
+    """监控进程资源使用情况"""
+    # 从 Django 设置中获取监控间隔，默认为 60 秒
+    from django.conf import settings
+    MONITOR_INTERVAL = getattr(settings, 'MONITOR_INTERVAL', 60)  # 单位：秒
+    
+    logger, log_file = setup_logger(pid, resource_type)
+    monitor = None
+    
+    try:
+        process = psutil.Process(pid)
+        logger.info(
+            f"开始监控进程:\n"
+            f"├─ 进程名称: {process.name()}\n"
+            f"├─ 进程ID: {pid}\n"
+            f"├─ 监控类型: {resource_type}\n"
+            f"├─ 监控间隔: {MONITOR_INTERVAL}秒\n"
+            f"└─ 开始时间: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}"
+        )
+        
+        # 根据资源类型选择模型
+        ModelClass = {
+            'cpu': HighCPUProcess,
+            'gpu': HighGPUProcess,
+            'memory': HighMemoryProcess
+        }.get(resource_type)
+        
+        if not ModelClass:
+            logger.error(f"未知的资源类型: {resource_type}")
+            return
+            
+        # 创建并保存监控记录
+        monitor = ModelClass.objects.create(
+            pid=pid,
+            process_name=process.name(),
+            log_path=log_file,
+            status=1,
+            is_active=True
+        )
+        logger.info("创建新的监控记录")
+        
+        # 设置线程名称
+        import threading
+        current_thread = threading.current_thread()
+        current_thread.name = f'monitor_{pid}_{resource_type}'
+        current_thread.do_run = True
+        
+        while current_thread.do_run:
+            try:
+                # 检查监控记录是否被手动停止
+                try:
+                    monitor.refresh_from_db()
+                    if not monitor.is_active:
+                        logger.info("监控被手动停止")
+                        break
+                except ModelClass.DoesNotExist:
+                    logger.error("监控记录已被删除")
+                    break
+                
+                # 检查进程状态
+                if not process.is_running():
+                    logger.warning(f"进程 {pid} 已终止")
+                    monitor.status = 0
+                    monitor.is_active = False
+                    monitor.save()
+                    break
+                
+                process_status = process.status()
+                status_map = {
+                    psutil.STATUS_RUNNING: 1,      # 运行中
+                    psutil.STATUS_SLEEPING: 1,     # 休眠中（正常）
+                    psutil.STATUS_DISK_SLEEP: 1,   # 磁盘休眠（正常）
+                    psutil.STATUS_STOPPED: 0,      # 已停止
+                    psutil.STATUS_TRACING_STOP: 0, # 跟踪停止
+                    psutil.STATUS_ZOMBIE: 0,       # 僵尸进程
+                    psutil.STATUS_DEAD: 0,         # 已死亡
+                    psutil.STATUS_WAKING: 1,       # 唤醒中
+                    psutil.STATUS_IDLE: 1,         # 空闲（正常）
+                }.get(process_status, 1)  # 默认为1（运行中）
+
+                # 更新监控记录
+                monitor.status = status_map
+                
+                # 记录进程状态
+                logger.info(
+                    f"进程状态:\n"
+                    f"├─ 状态码: {status_map}\n"
+                    f"├─ 状态描述: {process_status}\n"
+                    f"├─ 监控状态: {'活跃' if monitor.is_active else '已停止'}\n"
+                    f"└─ 运行时长: {datetime.now() - datetime.fromtimestamp(process.create_time())}"
+                )
+
+                # 获取资源使用情况
+                with process.oneshot():
+                    # CPU信息
+                    cpu_percent = process.cpu_percent()
+                    cpu_times = process.cpu_times()
+                    cpu_num = psutil.cpu_count()
+                    cpu_freq = psutil.cpu_freq()
+                    
+                    # 内存信息
+                    memory_info = process.memory_info()
+                    memory_percent = process.memory_percent()
+                    memory_maps = len(process.memory_maps())
+                    virtual_memory = psutil.virtual_memory()
+                    swap_memory = psutil.swap_memory()
+                    
+                    # GPU信息
+                    try:
+                        gpu_usage, gpu_memory, gpu_status = get_process_gpu_usage(pid)
+                        gpu_status_map = {
+                            "无GPU": "未检测到GPU",
+                            "驱动未安装": "GPU驱动未安装",
+                            "未使用GPU": "进程未使用GPU",
+                            "获取超时": "GPU信息获取超时",
+                            "命令错误": "GPU命令执行错误",
+                            "获取错误": "GPU信息获取错误",
+                            "检测失败": "GPU检测失败",
+                            "正常": "正常"
+                        }
+                        gpu_status_text = gpu_status_map.get(gpu_status, "未知状态")
+                    except Exception as e:
+                        logger.error(f"获取GPU信息失败: {str(e)}")
+                        gpu_usage, gpu_memory, gpu_status_text = 0, 0, "异常"
+                    
+                    # 在日志中记录GPU状态
+                    logger.info(
+                        f"GPU信息\n"
+                        f"├─ 状态: {gpu_status_text}\n"
+                        f"├─ 使用率: {gpu_usage:.1f}%\n"
+                        f"└─ 显存使用: {gpu_memory:.1f}MB"
+                    )
+                    
+                    # IO信息
+                    try:
+                        io_counters = process.io_counters()
+                        disk_io = psutil.disk_io_counters()
+                    except (psutil.AccessDenied, AttributeError):
+                        io_counters = None
+                        disk_io = None
+                    
+                    # 网络信息
+                    try:
+                        net_connections = len(process.connections())
+                        net_io = psutil.net_io_counters()
+                    except (psutil.AccessDenied, AttributeError):
+                        net_connections = 0
+                        net_io = None
+                    
+                    # 其他系统信息
+                    num_threads = process.num_threads()
+                    num_fds = process.num_fds() if hasattr(process, 'num_fds') else 0
+                    ctx_switches = process.num_ctx_switches()
+                
+                # 更新监控记录
+                monitor.cpu_usage = cpu_percent
+                monitor.memory_usage = memory_info.rss / (1024 * 1024 * 1024)  # GB
+                monitor.virtual_memory = memory_info.vms / (1024 * 1024 * 1024)  # GB
+                monitor.gpu_usage = gpu_usage
+                monitor.gpu_memory = gpu_memory
+                
+                # 记录详细的资源使用情况
+                logger.info(
+                    f"资源使用情况 - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}:\n"
+                    f"├─ CPU信息\n"
+                    f"│  ├─ 使用率: {cpu_percent:.1f}%\n"
+                    f"│  ├─ 用户态时间: {cpu_times.user:.1f}s\n"
+                    f"│  ├─ 内核态时间: {cpu_times.system:.1f}s\n"
+                    f"│  ├─ CPU核心数: {cpu_num}\n"
+                    f"│  ├─ CPU频率: {cpu_freq.current:.1f}MHz\n"
+                    f"│  └─ 上下文切换: {ctx_switches.voluntary}/{ctx_switches.involuntary}\n"
+                    f"├─ 内存信息\n"
+                    f"│  ├─ 物理内存: {memory_info.rss/1024/1024:.1f}MB ({memory_percent:.1f}%)\n"
+                    f"│  ├─ 虚拟内存: {memory_info.vms/1024/1024:.1f}MB\n"
+                    f"│  ├─ 内存映射: {memory_maps}个\n"
+                    f"│  ├─ 系统内存使用: {virtual_memory.percent:.1f}%\n"
+                    f"│  └─ 交换空间使用: {swap_memory.percent:.1f}%\n"
+                    f"├─ GPU信息\n"
+                    f"│  ├─ 状态: {gpu_status_text}\n"
+                    f"│  ├─ 使用率: {gpu_usage:.1f}%\n"
+                    f"│  └─ 显存使用: {gpu_memory:.1f}MB\n"
+                    f"├─ IO信息\n"
+                    f"│  ├─ 读取: {io_counters.read_bytes/1024/1024:.1f}MB ({io_counters.read_count}次)\n" if io_counters else "│  ├─ 读取: 无法获取\n"
+                    f"│  └─ 写入: {io_counters.write_bytes/1024/1024:.1f}MB ({io_counters.write_count}次)\n" if io_counters else "│  └─ 写入: 无法获取\n"
+                    f"├─ 网络信息\n"
+                    f"│  ├─ 连接数: {net_connections}\n"
+                    f"│  ├─ 发送: {net_io.bytes_sent/1024/1024:.1f}MB\n" if net_io else "│  ├─ 发送: 无法获取\n"
+                    f"│  └─ 接收: {net_io.bytes_recv/1024/1024:.1f}MB\n" if net_io else "│  └─ 接收: 无法获取\n"
+                    f"└─ 其他信息\n"
+                    f"   ├─ 线程数: {num_threads}\n"
+                    f"   ├─ 文件描述符: {num_fds}\n"
+                    f"   └─ 子进程数: {len(process.children())}"
+                )
+                
+                # 如果进程已经变为非活跃状态，更新状态并退出
+                if status_map == 0:
+                    monitor.is_active = False
+                    monitor.save()
+                    logger.info(f"进程状态变为 {process_status}，停止监控")
+                    break
+                
+                monitor.save()
+                time.sleep(MONITOR_INTERVAL)  # 使用配置的间隔时间
+                
+            except Exception as e:
+                logger.error(f"监控出错: {str(e)}")
+                logger.exception("详细错误信息:")
+                time.sleep(5)  # 错误后短暂等待
+                continue
+                
+    except Exception as e:
+        logger.error(f"监控初始化失败: {str(e)}")
+        logger.exception("详细错误信息:")
+    finally:
+        if monitor:
+            try:
+                monitor.refresh_from_db()
+                monitor.is_active = False
+                if not process.is_running():
+                    monitor.status = 0
+                monitor.save()
+            except (ModelClass.DoesNotExist, psutil.NoSuchProcess):
+                pass
+            
+            logger.info(
+                f"监控结束:\n"
+                f"├─ 进程名称: {monitor.process_name}\n"
+                f"├─ 进程ID: {monitor.pid}\n"
+                f"├─ 监控类型: {resource_type}\n"
+                f"├─ 进程状态: {'运行中' if monitor.status == 1 else '已终止'}\n"
+                f"├─ 监控状态: 已停止\n"
+                f"├─ 开始时间: {monitor.created_at}\n"
+                f"└─ 结束时间: {monitor.updated_at}"
+            )
+
+def get_high_resource_processes():
+    """获取高资源占用的进程"""
+    high_resource_procs = {
+        'cpu': [],
+        'gpu': [],
+        'memory': []
+    }
+    
+    for proc in psutil.process_iter(['pid', 'name']):
+        try:
+            process = psutil.Process(proc.info['pid'])
+            
+            # 检查CPU使用率
+            cpu_percent = process.cpu_percent(interval=1.0)
+            if cpu_percent > 200:  # 使用超过2个核心
+                high_resource_procs['cpu'].append({
+                    'pid': proc.info['pid'],
+                    'name': proc.info['name'],
+                    'cpu_usage': cpu_percent,
+                    'cpu_cores': cpu_percent / 100
+                })
+            
+            # 检查内存使用量
+            memory_gb = process.memory_info().rss / (1024 * 1024 * 1024)
+            if memory_gb > 20:  # 使用超过20GB内存
+                high_resource_procs['memory'].append({
+                    'pid': proc.info['pid'],
+                    'name': proc.info['name'],
+                    'memory_usage': memory_gb
+                })
+            
+            # 检查GPU使用率
+            gpu_index, gpu_usage, gpu_status = get_process_gpu_usage(proc.info['pid'])
+            if gpu_usage > 50:  # GPU使用率超过50%
+                high_resource_procs['gpu'].append({
+                    'pid': proc.info['pid'],
+                    'name': proc.info['name'],
+                    'gpu_usage': gpu_usage,
+                    'gpu_memory': gpu_memory,
+                    'gpu_index': gpu_index
+                })
+                
+        except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
+            continue
+            
+    return high_resource_procs

monitor/tests.py

@@ -0,0 +1,3 @@
+from django.test import TestCase
+
+# Create your tests here.

monitor/urls.py

@@ -0,0 +1,9 @@
+from django.urls import path
+from . import views
+
+urlpatterns = [
+    path('start_monitor/', views.start_monitor, name='start_monitor'),
+    path('stop_monitor/<int:pid>/', views.stop_monitor, name='stop_monitor'),
+    path('metrics/<int:pid>/', views.get_process_metrics, name='get_process_metrics'),
+    path('auto_detect/', views.auto_detect_monitor, name='auto_detect_monitor'),
+]

monitor/views.py

@@ -0,0 +1,469 @@
+from django.http import JsonResponse
+from .tasks import monitor_process, get_process_gpu_usage
+import threading
+import psutil
+from .models import HighCPUProcess, HighGPUProcess, HighMemoryProcess
+import logging
+import os
+from datetime import datetime
+import time
+import nvidia_smi
+from django.utils import timezone
+from django.views.decorators.http import require_http_methods
+from django.views.decorators.csrf import csrf_exempt
+
+# 配置日志
+LOG_DIR = 'logs/process_monitor'
+os.makedirs(LOG_DIR, exist_ok=True)
+
+def setup_logger(pid):
+    """为每个进程设置独立的日志记录器"""
+    log_file = os.path.join(LOG_DIR, f'process_{pid}_{datetime.now().strftime("%Y%m%d")}.log')
+    logger = logging.getLogger(f'process_{pid}')
+    logger.setLevel(logging.INFO)
+    
+    handler = logging.FileHandler(log_file)
+    formatter = logging.Formatter('%(asctime)s - %(levelname)s - %(message)s')
+    handler.setFormatter(formatter)
+    logger.addHandler(handler)
+    
+    return logger, log_file
+
+def get_process_by_name(process_name):
+    """根据进程名称获取进程PID"""
+    pids = []
+    for proc in psutil.process_iter(['pid', 'name']):
+        try:
+            if process_name.lower() in proc.info['name'].lower():
+                pids.append(proc.info['pid'])
+        except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
+            pass
+    return pids
+
+def get_process_gpu_usage(pid):
+    """获取进程的GPU使用情况"""
+    try:
+        nvidia_smi.nvmlInit()
+        deviceCount = nvidia_smi.nvmlDeviceGetCount()
+        gpu_usage = 0
+        gpu_memory = 0
+        
+        for i in range(deviceCount):
+            handle = nvidia_smi.nvmlDeviceGetHandleByIndex(i)
+            processes = nvidia_smi.nvmlDeviceGetComputeRunningProcesses(handle)
+            for process in processes:
+                if process.pid == pid:
+                    gpu_memory = process.usedGpuMemory / 1024 / 1024  # 转换为MB
+                    gpu_usage = nvidia_smi.nvmlDeviceGetUtilizationRates(handle).gpu
+                    return gpu_usage, gpu_memory
+        
+        return 0, 0
+    except:
+        return 0, 0
+    finally:
+        try:
+            nvidia_smi.nvmlShutdown()
+        except:
+            pass
+
+def get_high_resource_processes():
+    """获取高资源占用的进程"""
+    high_resource_pids = []
+    for proc in psutil.process_iter(['pid', 'name']):
+        try:
+            # 获取进程信息
+            process = psutil.Process(proc.info['pid'])
+            memory_gb = process.memory_info().rss / (1024 * 1024 * 1024)  # 转换为GB
+            
+            # 获取GPU使用情况
+            gpu_usage, gpu_memory = get_process_gpu_usage(proc.info['pid'])
+            
+            # 检查是否满足条件（GPU使用率>50%）
+            if gpu_usage > 50:
+                high_resource_pids.append({
+                    'pid': proc.info['pid'],
+                    'name': proc.info['name'],
+                    'memory_gb': round(memory_gb, 2),
+                    'gpu_usage': gpu_usage,
+                    'gpu_memory': round(gpu_memory, 2)  # GPU显存使用量(MB)
+                })
+        except (psutil.NoSuchProcess, psutil.AccessDenied, psutil.ZombieProcess):
+            continue
+    return high_resource_pids
+
+def auto_detect_high_resource_processes():
+    """定期自动检测新的高资源进程"""
+    while True:
+        try:
+            existing_pids = set(ProcessMonitor.objects.filter(is_active=True).values_list('pid', flat=True))
+            high_resource_procs = get_high_resource_processes()
+            
+            for proc in high_resource_procs:
+                if proc['pid'] not in existing_pids:
+                    logger, log_file = setup_logger(proc['pid'])
+                    
+                    # 记录到数据库
+                    monitor = ProcessMonitor.objects.create(
+                        pid=proc['pid'],
+                        process_name=proc['name'],
+                        cpu_usage=0,
+                        memory_usage=proc['memory_gb'],
+                        network_usage=0,
+                        log_path=log_file
+                    )
+                    
+                    # 启动监控线程
+                    threading.Thread(
+                        target=monitor_process,
+                        args=(proc['pid'], logger)
+                    ).start()
+                    
+                    print(f"发现新的高资源进程: {proc['name']} (PID: {proc['pid']})")
+            
+            # 每5分钟检测一次
+            time.sleep(300)
+            
+        except Exception as e:
+            print(f"自动检测出错: {str(e)}")
+            time.sleep(60)  # 出错后等待1分钟再试
+
+def start_monitor(request):
+    """开始监控进程"""
+    pid = request.GET.get('pid')
+    resource_type = request.GET.get('type', 'all')  # cpu, gpu, memory, all
+    
+    try:
+        if pid:
+            pid = int(pid)
+            process = psutil.Process(pid)
+            
+            # 检查进程是否已经在监控中
+            monitors = {
+                'cpu': HighCPUProcess.objects.filter(pid=pid, is_active=True).exists(),
+                'gpu': HighGPUProcess.objects.filter(pid=pid, is_active=True).exists(),
+                'memory': HighMemoryProcess.objects.filter(pid=pid, is_active=True).exists()
+            }
+            
+            # 根据资源类型启动监控
+            results = []
+            if resource_type == 'all':
+                for rtype, is_monitored in monitors.items():
+                    if not is_monitored:
+                        thread = threading.Thread(
+                            target=monitor_process,
+                            args=(pid, rtype),
+                            daemon=True
+                        )
+                        thread.start()
+                        results.append(f"已启动{rtype}监控")
+                    else:
+                        results.append(f"{rtype}监控已在运行")
+            else:
+                if not monitors.get(resource_type):
+                    thread = threading.Thread(
+                        target=monitor_process,
+                        args=(pid, resource_type),
+                        daemon=True
+                    )
+                    thread.start()
+                    results.append(f"已启动{resource_type}监控")
+                else:
+                    return JsonResponse({"error": f"进程 {pid} 已在{resource_type}监控中"}, status=400)
+            
+            return JsonResponse({
+                "message": f"开始监控进程 {process.name()} (PID: {pid})",
+                "results": results
+            })
+            
+        # 自动检测高资源进程
+        high_resource_procs = {
+            'cpu': [],
+            'gpu': [],
+            'memory': []
+        }
+        
+        for proc in psutil.process_iter(['pid', 'name']):
+            try:
+                process = psutil.Process(proc.info['pid'])
+                
+                # 检查CPU使用率 (>200% 表示使用超过2个核心)
+                cpu_percent = process.cpu_percent(interval=1.0)
+                if cpu_percent > 200:
+                    high_resource_procs['cpu'].append(process)
+                
+                # 检查内存使用量 (>20GB)
+                memory_gb = process.memory_info().rss / (1024 * 1024 * 1024)
+                if memory_gb > 20:
+                    high_resource_procs['memory'].append(process)
+                
+                # 检查GPU使用率 (>50%)
+                gpu_usage, gpu_memory = get_process_gpu_usage(process.pid)
+                if gpu_usage > 50:
+                    high_resource_procs['gpu'].append(process)
+                    
+            except (psutil.NoSuchProcess, psutil.AccessDenied):
+                continue
+        
+        # 启动监控
+        results = {
+            'cpu': [],
+            'gpu': [],
+            'memory': []
+        }
+        
+        for resource_type, processes in high_resource_procs.items():
+            for proc in processes:
+                if not any([
+                    HighCPUProcess.objects.filter(pid=proc.pid, is_active=True).exists(),
+                    HighGPUProcess.objects.filter(pid=proc.pid, is_active=True).exists(),
+                    HighMemoryProcess.objects.filter(pid=proc.pid, is_active=True).exists()
+                ]):
+                    thread = threading.Thread(
+                        target=monitor_process,
+                        args=(proc.pid, resource_type),
+                        daemon=True
+                    )
+                    thread.start()
+                    results[resource_type].append({
+                        'pid': proc.pid,
+                        'name': proc.name()
+                    })
+        
+        return JsonResponse({
+            "message": "开始监控高资源进程",
+            "processes": results
+        })
+        
+    except Exception as e:
+        return JsonResponse({"error": str(e)}, status=500)
+
+@csrf_exempt
+@require_http_methods(["POST"])
+def stop_monitor(request, pid):
+    """停止监控指定进程"""
+    resource_type = request.GET.get('type', 'all')  # 从查询参数获取资源类型
+    
+    try:
+        # 根据资源类型选择要停止的监控
+        monitors = []
+        if resource_type == 'all':
+            monitors.extend(HighCPUProcess.objects.filter(pid=pid, is_active=True))
+            monitors.extend(HighGPUProcess.objects.filter(pid=pid, is_active=True))
+            monitors.extend(HighMemoryProcess.objects.filter(pid=pid, is_active=True))
+        elif resource_type == 'cpu':
+            monitors.extend(HighCPUProcess.objects.filter(pid=pid, is_active=True))
+        elif resource_type == 'gpu':
+            monitors.extend(HighGPUProcess.objects.filter(pid=pid, is_active=True))
+        elif resource_type == 'memory':
+            monitors.extend(HighMemoryProcess.objects.filter(pid=pid, is_active=True))
+        else:
+            return JsonResponse({
+                "error": f"不支持的资源类型: {resource_type}"
+            }, status=400)
+        
+        if not monitors:
+            return JsonResponse({
+                "error": f"未找到进程 {pid} 的{resource_type}监控记录"
+            }, status=404)
+        
+        # 更新所有监控记录的状态
+        for monitor in monitors:
+            # 只更新监控状态，不改变进程状态
+            monitor.is_active = False
+            monitor.save()
+            
+            # 记录停止操作
+            logger = logging.getLogger(f'{monitor.__class__.__name__.lower()}_{pid}')
+            logger.info(
+                f"手动停止监控:\n"
+                f"├─ 进程ID: {pid}\n"
+                f"├─ 监控类型: {monitor.__class__.__name__}\n"
+                f"├─ 进程状态: {'运行中' if monitor.status == 1 else '已终止'}\n"
+                f"├─ 开始时间: {monitor.created_at}\n"
+                f"└─ 停止时间: {timezone.now()}"
+            )
+        
+        # 尝试终止相关的监控线程
+        import threading
+        current_threads = threading.enumerate()
+        monitor_threads = [t for t in current_threads if t.name.startswith(f'monitor_{pid}')]
+        for thread in monitor_threads:
+            try:
+                thread.do_run = False
+            except:
+                pass
+        
+        return JsonResponse({
+            "message": f"已停止对进程 {pid} 的监控",
+            "stopped_monitors": len(monitors),
+            "process_status": "运行中" if monitors[0].status == 1 else "已终止"
+        })
+        
+    except Exception as e:
+        return JsonResponse({
+            "error": f"停止监控失败: {str(e)}"
+        }, status=500)
+
+def get_process_metrics(request, pid):
+    """获取进程监控数据"""
+    resource_type = request.GET.get('type', 'all')
+    try:
+        results = {}
+        monitors = {
+            'cpu': HighCPUProcess,
+            'gpu': HighGPUProcess,
+            'memory': HighMemoryProcess
+        }
+        
+        if resource_type == 'all':
+            for rtype, model in monitors.items():
+                try:
+                    monitor = model.objects.get(pid=pid)
+                    results[rtype] = {
+                        'status': monitor.status,
+                        'cpu_usage': monitor.cpu_usage,
+                        'memory_usage': monitor.memory_usage,
+                        'gpu_usage': monitor.gpu_usage,
+                        'gpu_memory': monitor.gpu_memory,
+                        'virtual_memory': monitor.virtual_memory
+                    }
+                    
+                    # 添加特定资源类型的指标
+                    if rtype == 'cpu':
+                        results[rtype]['cpu_cores'] = monitor.cpu_cores
+                    elif rtype == 'gpu':
+                        results[rtype]['gpu_index'] = monitor.gpu_index
+                    elif rtype == 'memory':
+                        results[rtype]['swap_usage'] = monitor.swap_usage
+                        
+                except model.DoesNotExist:
+                    continue
+        else:
+            model = monitors.get(resource_type)
+            if model:
+                try:
+                    monitor = model.objects.get(pid=pid)
+                    results[resource_type] = {
+                        'status': monitor.status,
+                        'cpu_usage': monitor.cpu_usage,
+                        'memory_usage': monitor.memory_usage,
+                        'gpu_usage': monitor.gpu_usage,
+                        'gpu_memory': monitor.gpu_memory,
+                        'virtual_memory': monitor.virtual_memory
+                    }
+                    
+                    # 添加特定资源类型的指标
+                    if resource_type == 'cpu':
+                        results[resource_type]['cpu_cores'] = monitor.cpu_cores
+                    elif resource_type == 'gpu':
+                        results[resource_type]['gpu_index'] = monitor.gpu_index
+                    elif resource_type == 'memory':
+                        results[resource_type]['swap_usage'] = monitor.swap_usage
+                        
+                except model.DoesNotExist:
+                    pass
+        
+        if not results:
+            return JsonResponse({"error": f"未找到PID为{pid}的监控记录"}, status=404)
+            
+        return JsonResponse({
+            "pid": pid,
+            "metrics": results
+        })
+        
+    except Exception as e:
+        return JsonResponse({"error": str(e)}, status=500)
+
+def auto_detect_monitor(request):
+    """自动检测并监控高资源进程"""
+    try:
+        # 清理已停止的监控
+        HighCPUProcess.objects.filter(is_active=True, status=0).update(is_active=False)
+        HighGPUProcess.objects.filter(is_active=True, status=0).update(is_active=False)
+        HighMemoryProcess.objects.filter(is_active=True, status=0).update(is_active=False)
+        
+        results = {
+            'cpu': [],
+            'gpu': [],
+            'memory': []
+        }
+        
+        # 首先收集所有进程的CPU使用率
+        processes = {}
+        for proc in psutil.process_iter(['pid', 'name', 'cpu_percent']):
+            try:
+                processes[proc.info['pid']] = proc.info
+            except (psutil.NoSuchProcess, psutil.AccessDenied):
+                continue
+        
+        # 等待一秒获取CPU使用率变化
+        time.sleep(1)
+        
+        # 检测高资源进程
+        for proc in psutil.process_iter(['pid', 'name', 'cpu_percent']):
+            try:
+                pid = proc.info['pid']
+                if pid not in processes:
+                    continue
+                
+                process = psutil.Process(pid)
+                cpu_percent = proc.info['cpu_percent']
+                
+                # 检查CPU使用率 (>200% 表示使用超过2个核心)
+                if cpu_percent > 200:
+                    if not HighCPUProcess.objects.filter(pid=pid, is_active=True).exists():
+                        thread = threading.Thread(
+                            target=monitor_process,
+                            args=(pid, 'cpu'),
+                            daemon=True
+                        )
+                        thread.start()
+                        results['cpu'].append({
+                            'pid': pid,
+                            'name': process.name(),
+                            'cpu_usage': cpu_percent
+                        })
+                
+                # 检查内存使用量 (>20GB)
+                memory_gb = process.memory_info().rss / (1024 * 1024 * 1024)
+                if memory_gb > 20:
+                    if not HighMemoryProcess.objects.filter(pid=pid, is_active=True).exists():
+                        thread = threading.Thread(
+                            target=monitor_process,
+                            args=(pid, 'memory'),
+                            daemon=True
+                        )
+                        thread.start()
+                        results['memory'].append({
+                            'pid': pid,
+                            'name': process.name(),
+                            'memory_usage': memory_gb
+                        })
+                
+                # 检查GPU使用率 (>50%)
+                gpu_usage, gpu_memory = get_process_gpu_usage(pid)
+                if gpu_usage > 50:
+                    if not HighGPUProcess.objects.filter(pid=pid, is_active=True).exists():
+                        thread = threading.Thread(
+                            target=monitor_process,
+                            args=(pid, 'gpu'),
+                            daemon=True
+                        )
+                        thread.start()
+                        results['gpu'].append({
+                            'pid': pid,
+                            'name': process.name(),
+                            'gpu_usage': gpu_usage,
+                            'gpu_memory': gpu_memory
+                        })
+                        
+            except (psutil.NoSuchProcess, psutil.AccessDenied):
+                continue
+        
+        return JsonResponse({
+            "message": "已开始监控检测到的高资源进程",
+            "detected_processes": results
+        })
+        
+    except Exception as e:
+        return JsonResponse({"error": str(e)}, status=500)