diff --git a/admin/GlancesMonitor.py b/admin/GlancesMonitor.py deleted file mode 100644 index 5abb2a3..0000000 --- a/admin/GlancesMonitor.py +++ /dev/null @@ -1,157 +0,0 @@ -import time -import threading -import subprocess -import requests - -from loguru import logger - - -class GlancesMonitor: - def __init__(self, email_sender, host='192.168.2.170', port=61208, - cpu_threshold=80.0, load_threshold=None, io_threshold=80.0, - disk_usage_threshold=80.0, handle_threshold=20000, - monitor_interval=30, recipient=None): - """初始化 Glances 监控组件 - - Args: - email_sender: 已初始化的 EmailSender 实例 - host (str): Glances 主机地址 - port (int): Glances Web 服务端口 - cpu_threshold (float): CPU 使用率阈值 (%) - load_threshold (float): 系统负载阈值（默认 CPU 核心数 * 2） - io_threshold (float): 磁盘 I/O 阈值（MB/s） - disk_usage_threshold (float): 磁盘占用阈值 (%) - handle_threshold (int): 句柄数阈值 - recipient (str): 告警邮件接收者 - """ - self.host = host - self.port = port - self.api_url = f"http://{self.host}:{self.port}/api/4" - self.cpu_threshold = cpu_threshold - self.load_threshold = load_threshold or (self.get_cpu_count() * 2) - self.io_threshold = io_threshold - self.disk_usage_threshold = disk_usage_threshold - self.handle_threshold = handle_threshold - self.email_sender = email_sender - self.recipient = recipient - self.glances_process = None - self.last_alert_times = {} - self._running = False - self.monitor_interval = monitor_interval - self._loop_index = 0 - - def get_cpu_count(self): - """获取 CPU 核心数""" - try: - response = requests.get(f"{self.api_url}/cpu") - response.raise_for_status() - return response.json().get('count', 1) - except Exception as e: - logger.error(e) - return 1 - - def start_glances(self): - """启动 Glances Web 服务""" - try: - subprocess.run(['glances', '--version'], check=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE) - self.glances_process = subprocess.Popen( - ['glances', '-w', f'--port', str(self.port)], - stdout=subprocess.PIPE, - stderr=subprocess.PIPE - ) - time.sleep(2) - if self.glances_process.poll() is not None: - raise RuntimeError("Glances 启动失败") - logger.info(f"Glances Web 服务已启动: http://{self.host}:{self.port}") - except subprocess.CalledProcessError: - logger.error("错误: Glances 未安装。请运行: python3.11 -m pip install glances") - raise - except Exception as e: - logger.error(f"启动 Glances 失败: {e}") - raise - - def stop_glances(self): - """停止 Glances 服务""" - if self.glances_process: - self.glances_process.terminate() - self.glances_process.wait() - logger.error("Glances Web 服务已停止") - - def send_alert_email(self, metric, value, threshold): - """发送告警邮件，限制每小时一次""" - if not self.email_sender or not self.recipient: - return - current_time = time.time() - last_alert_time = self.last_alert_times.get(metric, 0) - if current_time - last_alert_time < 3600: - return - subject = f"服务器告警: {metric} 过高" - body = f"警告: {metric} 当前值为 {value}，超过阈值 {threshold}！\n时间: {time.strftime('%Y-%m-%d %H:%M:%S', time.localtime())}" - if self.email_sender.send_email(self.recipient, subject, body): - self.last_alert_times[metric] = current_time - - def monitor(self): - """监控服务器指标并触发告警""" - while self._running: - try: - self._loop_index += 1 - - response = requests.get(f"{self.api_url}/cpu/total") - response.raise_for_status() - cpu_usage = response.json().get('total', 0) - if cpu_usage > self.cpu_threshold: - self.send_alert_email("CPU 使用率", cpu_usage, self.cpu_threshold) - - response = requests.get(f"{self.api_url}/load") - response.raise_for_status() - load_avg = response.json().get('min1', 0) - if load_avg > self.load_threshold: - self.send_alert_email("系统负载（1分钟）", load_avg, self.load_threshold) - - if self._loop_index % 6 == 0: - response = requests.get(f"{self.api_url}/diskio") - response.raise_for_status() - disks = response.json() - max_io_usage = 0 - for disk in disks: - read_bytes = disk.get('read_bytes', 0) - write_bytes = disk.get('write_bytes', 0) - io_usage = (read_bytes + write_bytes) / (2048 * 1024) - max_io_usage = max(max_io_usage, io_usage) - if max_io_usage > self.io_threshold: - self.send_alert_email("磁盘 I/O（MB/s）", max_io_usage, self.io_threshold) - - response = requests.get(f"{self.api_url}/fs") - response.raise_for_status() - filesystems = response.json() - for fs in filesystems: - disk_usage = fs.get('percent', 0) - if disk_usage > self.disk_usage_threshold: - self.send_alert_email(f"磁盘占用 ({fs.get('mnt_point')})", disk_usage, - self.disk_usage_threshold) - - response = requests.get(f"{self.api_url}/processcount") - response.raise_for_status() - handle_count = response.json().get('total', 0) - if handle_count > self.handle_threshold: - self.send_alert_email("句柄数", handle_count, self.handle_threshold) - - time.sleep(self.monitor_interval) - except requests.RequestException as e: - logger.error(f"连接 Glances API 失败: {e}") - time.sleep(60) - except Exception as e: - logger.error(f"监控错误: {e}") - time.sleep(60) - - def run(self): - """启动 Glances 服务和监控线程（非阻塞）""" - self._running = True - self.start_glances() - monitor_thread = threading.Thread(target=self.monitor, daemon=True) - monitor_thread.start() - - def stop(self): - """停止 Glances 服务和监控""" - self._running = False - self.stop_glances() diff --git a/admin/dashboard/blueprints/system.py b/admin/dashboard/blueprints/system.py index 072d8a4..21e0efe 100644 --- a/admin/dashboard/blueprints/system.py +++ b/admin/dashboard/blueprints/system.py @@ -4,6 +4,7 @@ from loguru import logger import os import time import subprocess +import socket from datetime import datetime import platform import psutil @@ -23,6 +24,16 @@ system_bp = Blueprint('system', __name__) # 记录应用启动时间 APP_START_TIME = time.time() +# 记录最近一次网络计数器采样，用于在资源监控页估算上/下行速率。 +# 这里故意只做“页面级轻量采样”： +# 1. 不起额外守护线程，避免为了展示速率再引入常驻后台任务； +# 2. 只有用户刷新/轮询资源页时才计算速率，开销接近于零； +# 3. 即便进程重启缓存丢失，也只会让第一次速率显示为 0，不影响整体可用性。 +NETWORK_IO_SAMPLE = { + "timestamp": 0.0, + "bytes_sent": 0, + "bytes_recv": 0, +} def _system_config_path() -> str: @@ -68,6 +79,178 @@ def _format_bytes_to_mb(value: int) -> float: return round((_safe_float(value, 0.0) / 1024 / 1024), 2) +def _safe_divide(numerator: float, denominator: float, default: float = 0.0) -> float: + """安全除法，避免速率与占比计算时被 0 除打断。""" + try: + if not denominator: + return default + return numerator / denominator + except Exception: + return default + + +def _primary_disk_path() -> str: + """返回当前系统最稳妥的主盘路径。""" + # 资源监控页既要兼容你本地 Windows 开发环境，也要兼容线上 Linux： + # 1. 优先用系统根目录，Linux 下是 /； + # 2. Windows 下会自动变成当前盘符根路径； + # 3. 避免把磁盘路径硬编码成 /，导致本地调试时报错。 + return os.path.abspath(os.sep) + + +def _format_datetime_text(timestamp_value: float | int | None) -> str: + """把时间戳格式化为后台页面可直接展示的文本。""" + if not timestamp_value: + return "-" + try: + return datetime.fromtimestamp(float(timestamp_value)).strftime("%Y-%m-%d %H:%M:%S") + except Exception: + return "-" + + +def _sample_network_speed() -> dict: + """根据两次页面采样估算网络上下行速率。""" + counters = psutil.net_io_counters() + now = time.time() + current_sent = _safe_int(getattr(counters, "bytes_sent", 0)) + current_recv = _safe_int(getattr(counters, "bytes_recv", 0)) + last_timestamp = _safe_float(NETWORK_IO_SAMPLE.get("timestamp")) + elapsed = max(now - last_timestamp, 0.0) + + upload_speed = 0.0 + download_speed = 0.0 + if elapsed > 0 and last_timestamp > 0: + upload_speed = _safe_divide(current_sent - _safe_int(NETWORK_IO_SAMPLE.get("bytes_sent")), elapsed, 0.0) + download_speed = _safe_divide(current_recv - _safe_int(NETWORK_IO_SAMPLE.get("bytes_recv")), elapsed, 0.0) + upload_speed = max(upload_speed, 0.0) + download_speed = max(download_speed, 0.0) + + NETWORK_IO_SAMPLE["timestamp"] = now + NETWORK_IO_SAMPLE["bytes_sent"] = current_sent + NETWORK_IO_SAMPLE["bytes_recv"] = current_recv + + return { + "bytes_sent": current_sent, + "bytes_recv": current_recv, + "upload_speed_bps": round(upload_speed, 2), + "download_speed_bps": round(download_speed, 2), + } + + +def _extract_server_runtime_snapshot() -> dict: + """构建资源监控页使用的轻量服务器运行态快照。""" + # 这套快照有意只覆盖“日常观察最有价值”的内容： + # 1. 主机资源：CPU / 内存 / 磁盘 / 网络； + # 2. 应用进程：当前 ABOT 进程是否活着、吃了多少资源； + # 3. 基础设施：MySQL / Redis 继续复用现有摘要探测； + # 4. 不再依赖 glances 进程，部署和运维负担会轻很多。 + server = current_app.dashboard_server + current_process = psutil.Process(os.getpid()) + virtual_memory = psutil.virtual_memory() + swap_memory = psutil.swap_memory() + cpu_usage = psutil.cpu_percent(interval=None) + process_cpu_usage = current_process.cpu_percent(interval=None) + boot_time = psutil.boot_time() + network_sample = _sample_network_speed() + disk_io = psutil.disk_io_counters() + try: + load_values = os.getloadavg() + except (AttributeError, OSError): + load_values = (0.0, 0.0, 0.0) + + disk_items = [] + seen_mountpoints = set() + for partition in psutil.disk_partitions(all=False): + mountpoint = str(getattr(partition, "mountpoint", "") or "").strip() + if not mountpoint or mountpoint in seen_mountpoints: + continue + seen_mountpoints.add(mountpoint) + try: + usage = psutil.disk_usage(mountpoint) + except Exception: + continue + disk_items.append({ + "device": str(getattr(partition, "device", "") or "").strip() or mountpoint, + "mountpoint": mountpoint, + "fstype": str(getattr(partition, "fstype", "") or "").strip(), + "total_bytes": _safe_int(getattr(usage, "total", 0)), + "used_bytes": _safe_int(getattr(usage, "used", 0)), + "free_bytes": _safe_int(getattr(usage, "free", 0)), + "usage_percent": round(_safe_float(getattr(usage, "percent", 0.0)), 1), + }) + disk_items.sort(key=lambda item: item.get("usage_percent", 0.0), reverse=True) + + primary_disk_usage = psutil.disk_usage(_primary_disk_path()) + process_memory = current_process.memory_info() + try: + open_files = len(current_process.open_files()) + except Exception: + open_files = 0 + + try: + tcp_connections = current_process.connections(kind="inet") + established_connections = sum( + 1 for conn in tcp_connections if str(getattr(conn, "status", "") or "").upper() == "ESTABLISHED" + ) + except Exception: + established_connections = 0 + + return { + "timestamp": datetime.now().strftime("%Y-%m-%d %H:%M:%S"), + "server": { + "hostname": socket.gethostname(), + "os": platform.system(), + "os_version": platform.version(), + "python_version": platform.python_version(), + "boot_time": _format_datetime_text(boot_time), + "uptime_seconds": round(max(time.time() - boot_time, 0), 2), + }, + "cpu": { + "usage_percent": round(cpu_usage, 1), + "logical_count": psutil.cpu_count(logical=True) or 0, + "physical_count": psutil.cpu_count(logical=False) or 0, + "load_1": round(_safe_float(load_values[0]), 2), + "load_5": round(_safe_float(load_values[1]), 2), + "load_15": round(_safe_float(load_values[2]), 2), + }, + "memory": { + "usage_percent": round(_safe_float(getattr(virtual_memory, "percent", 0.0)), 1), + "total_bytes": _safe_int(getattr(virtual_memory, "total", 0)), + "used_bytes": _safe_int(getattr(virtual_memory, "used", 0)), + "available_bytes": _safe_int(getattr(virtual_memory, "available", 0)), + "swap_usage_percent": round(_safe_float(getattr(swap_memory, "percent", 0.0)), 1), + "swap_total_bytes": _safe_int(getattr(swap_memory, "total", 0)), + "swap_used_bytes": _safe_int(getattr(swap_memory, "used", 0)), + }, + "disk": { + "primary_usage_percent": round(_safe_float(getattr(primary_disk_usage, "percent", 0.0)), 1), + "primary_total_bytes": _safe_int(getattr(primary_disk_usage, "total", 0)), + "primary_used_bytes": _safe_int(getattr(primary_disk_usage, "used", 0)), + "io_read_bytes": _safe_int(getattr(disk_io, "read_bytes", 0)) if disk_io else 0, + "io_write_bytes": _safe_int(getattr(disk_io, "write_bytes", 0)) if disk_io else 0, + "items": disk_items[:8], + }, + "network": { + **network_sample, + "established_connections": established_connections, + }, + "process": { + "pid": current_process.pid, + "cpu_percent": round(process_cpu_usage, 1), + "memory_percent": round(current_process.memory_percent(), 2), + "memory_rss_bytes": _safe_int(getattr(process_memory, "rss", 0)), + "thread_count": current_process.num_threads(), + "open_files": open_files, + "create_time": _format_datetime_text(current_process.create_time()), + "uptime_seconds": round(max(time.time() - current_process.create_time(), 0), 2), + }, + "infrastructure": { + "mysql": _extract_mysql_runtime_snapshot(server.db_manager), + "redis": _extract_redis_runtime_snapshot(server.db_manager), + }, + } + + def _extract_mysql_runtime_snapshot(db_manager) -> dict: """采集 MySQL 运行态摘要。 @@ -761,17 +944,11 @@ def api_docs(): @system_bp.route('/system_status') @login_required def system_status(): - src = request.args.get('src') - if not src: - try: - server = current_app.dashboard_server - glances = getattr(server.robot, "config").glances if hasattr(server.robot, "config") else {} - host = glances.get("host", "127.0.0.1") - port = glances.get("port", 61208) - src = f"http://{host}:{port}/" - except Exception: - src = "http://127.0.0.1:61208/" - return render_template('system_status.html', src_url=src) + # 资源监控页改为项目内置轻量面板： + # 1. 不再依赖 glances 独立进程； + # 2. 页面只消费当前服务自身的 API； + # 3. 线上部署时不用额外开放 61208 之类的端口。 + return render_template('system_status.html') @system_bp.route('/system_llm') @@ -811,6 +988,20 @@ def api_system_info(): return jsonify({"success": False, "error": str(e)}), 500 +@system_bp.route('/api/system_status_overview') +@login_required +def api_system_status_overview(): + """返回资源监控页使用的轻量服务器快照。""" + try: + return jsonify({ + "success": True, + "data": _extract_server_runtime_snapshot(), + }) + except Exception as e: + logger.error(f"获取资源监控快照失败: {e}") + return jsonify({"success": False, "error": str(e)}), 500 + + @system_bp.route('/api/system_health_summary') @login_required def api_system_health_summary(): diff --git a/admin/dashboard/templates/system_status.html b/admin/dashboard/templates/system_status.html index 7799ba1..f5a3e69 100644 --- a/admin/dashboard/templates/system_status.html +++ b/admin/dashboard/templates/system_status.html @@ -6,9 +6,23 @@
-
System Workspace
+
Resource Overview

资源监控

-

直接在后台查看系统资源变化与运行状态，保持监控入口简洁清晰。

+

直接观察 ABOT 所在服务器的关键资源、应用进程和基础设施状态，不再依赖额外的 glances 进程。

+
+
+ 最近刷新 + {% raw %}{{ statusOverview.timestamp || '-' }}{% endraw %} +
+
+ 主机 + {% raw %}{{ statusOverview.server.hostname || '-' }}{% endraw %} +
+
+ PID + {% raw %}{{ statusOverview.process.pid || '-' }}{% endraw %} +
+
转图运行时 {% raw %}{{ runtimeTagText }}{% endraw %} @@ -23,27 +37,221 @@ 预热转图 - - 刷新转图状态 + + 刷新监控 + + + 重启服务 - 刷新面板 - 新窗口打开 - 重启服务
- -
-
-

监控面板

-

直接在控制台内查看系统资源变化与运行状态。

+
+ +
CPU 使用率
+
{% raw %}{{ formatPercent(cpu.usage_percent) }}{% endraw %}
+
{% raw %}{{ cpu.logical_count || 0 }}{% endraw %} 线程 · load1 {% raw %}{{ formatNumber(cpu.load_1, 2) }}{% endraw %}
+ + + +
内存使用率
+
{% raw %}{{ formatPercent(memory.usage_percent) }}{% endraw %}
+
{% raw %}{{ formatBytes(memory.used_bytes) }}{% endraw %} / {% raw %}{{ formatBytes(memory.total_bytes) }}{% endraw %}
+ + + +
主盘使用率
+
{% raw %}{{ formatPercent(disk.primary_usage_percent) }}{% endraw %}
+
{% raw %}{{ formatBytes(disk.primary_used_bytes) }}{% endraw %} / {% raw %}{{ formatBytes(disk.primary_total_bytes) }}{% endraw %}
+ + + +
网络速率
+
{% raw %}{{ formatSpeed(network.download_speed_bps) }}{% endraw %}
+
上行 {% raw %}{{ formatSpeed(network.upload_speed_bps) }}{% endraw %} · 连接 {% raw %}{{ network.established_connections || 0 }}{% endraw %}
+
+ 累计上行 {% raw %}{{ formatBytes(network.bytes_sent) }}{% endraw %} + 累计下行 {% raw %}{{ formatBytes(network.bytes_recv) }}{% endraw %}
-
{{ src_url }}
-
-
- -
- + +
+ +
+ +
+
+

系统概览

+

观察主机、Python 运行环境和负载情况，快速判断是不是机器层面的问题。

+
+
+
+
+ 主机名 + {% raw %}{{ server.hostname || '-' }}{% endraw %} +
+
+ 操作系统 + {% raw %}{{ server.os || '-' }}{% endraw %} +
+
+ 系统版本 + {% raw %}{{ server.os_version || '-' }}{% endraw %} +
+
+ Python + {% raw %}{{ server.python_version || '-' }}{% endraw %} +
+
+ 开机时间 + {% raw %}{{ server.boot_time || '-' }}{% endraw %} +
+
+ 系统运行时长 + {% raw %}{{ formatDuration(server.uptime_seconds) }}{% endraw %} +
+
+ Load 1 / 5 / 15 + {% raw %}{{ formatNumber(cpu.load_1, 2) }} / {{ formatNumber(cpu.load_5, 2) }} / {{ formatNumber(cpu.load_15, 2) }}{% endraw %} +
+
+ CPU 核心 + {% raw %}{{ cpu.physical_count || 0 }}{% endraw %} 物理 / {% raw %}{{ cpu.logical_count || 0 }}{% endraw %} 逻辑 +
+
+ Swap 使用率 + {% raw %}{{ formatPercent(memory.swap_usage_percent) }}{% endraw %} +
+
+ + + +
+
+

ABOT 进程

+

确认当前应用自身的资源占用，避免只看主机而忽略进程级热点。

+
+
+
+
+ PID + {% raw %}{{ process.pid || '-' }}{% endraw %} +
+
+ 进程 CPU + {% raw %}{{ formatPercent(process.cpu_percent) }}{% endraw %} +
+
+ 进程内存 + {% raw %}{{ formatBytes(process.memory_rss_bytes) }}{% endraw %} +
+
+ 内存占比 + {% raw %}{{ formatPercent(process.memory_percent) }}{% endraw %} +
+
+ 线程数 + {% raw %}{{ process.thread_count || 0 }}{% endraw %} +
+
+ 打开文件 + {% raw %}{{ process.open_files || 0 }}{% endraw %} +
+
+ 进程启动时间 + {% raw %}{{ process.create_time || '-' }}{% endraw %} +
+
+ 进程运行时长 + {% raw %}{{ formatDuration(process.uptime_seconds) }}{% endraw %} +
+
+ + + +
+
+

基础设施运行态

+

把数据库和缓存的关键摘要放在同一屏里，日常看状态不需要再跳出去。

+
+
+
+
+
+
+
MySQL
+
{% raw %}{{ infrastructure.mysql.summary || '暂无状态' }}{% endraw %}
+
+ {% raw %}{{ statusText(infrastructure.mysql.status) }}{% endraw %} +
+
+
数据库{% raw %}{{ infrastructure.mysql.database || '-' }}{% endraw %}
+
版本{% raw %}{{ infrastructure.mysql.version || '-' }}{% endraw %}
+
连接数{% raw %}{{ infrastructure.mysql.threads_connected || 0 }}{% endraw %} / {% raw %}{{ infrastructure.mysql.max_connections || '-' }}{% endraw %}
+
连接负载{% raw %}{{ formatPercent(infrastructure.mysql.connection_usage_percent) }}{% endraw %}
+
运行线程{% raw %}{{ infrastructure.mysql.threads_running || 0 }}{% endraw %}
+
QPS{% raw %}{{ formatNumber(infrastructure.mysql.questions_per_second, 2) }}{% endraw %}
+
表数量{% raw %}{{ infrastructure.mysql.table_count || 0 }}{% endraw %}
+
库体量{% raw %}{{ formatMb(infrastructure.mysql.schema_size_mb) }}{% endraw %}
+
+
+
+
+
+
Redis
+
{% raw %}{{ infrastructure.redis.summary || '暂无状态' }}{% endraw %}
+
+ {% raw %}{{ statusText(infrastructure.redis.status) }}{% endraw %} +
+
+
DB{% raw %}{{ infrastructure.redis.db_index || 0 }}{% endraw %}
+
Key 数量{% raw %}{{ infrastructure.redis.key_count || 0 }}{% endraw %}
+
客户端{% raw %}{{ infrastructure.redis.connected_clients || 0 }}{% endraw %}
+
阻塞客户端{% raw %}{{ infrastructure.redis.blocked_clients || 0 }}{% endraw %}
+
OPS/s{% raw %}{{ infrastructure.redis.ops_per_sec || 0 }}{% endraw %}
+
命中率{% raw %}{{ formatPercent(infrastructure.redis.hit_rate_percent) }}{% endraw %}
+
已用内存{% raw %}{{ infrastructure.redis.used_memory_human || '-' }}{% endraw %}
+
峰值内存{% raw %}{{ infrastructure.redis.used_memory_peak_human || '-' }}{% endraw %}
+
+
+
+ + + +
+
+

磁盘挂载点

+

按使用率排序展示常用挂载点，方便快速发现哪个分区快满了。

+
+
+ + + + + + + + + + + + + + + +
{% endblock %} @@ -55,14 +263,49 @@ data() { return { currentView: '14', - frameUrl: '{{ src_url }}', restarting: false, + loading: false, md2imgLoading: false, md2imgWarming: false, - md2imgHealth: null + autoRefreshTimer: null, + md2imgHealth: null, + statusOverview: { + timestamp: '', + server: {}, + cpu: {}, + memory: {}, + disk: { items: [] }, + network: {}, + process: {}, + infrastructure: { + mysql: {}, + redis: {} + } + } } }, computed: { + server() { + return this.statusOverview.server || {}; + }, + cpu() { + return this.statusOverview.cpu || {}; + }, + memory() { + return this.statusOverview.memory || {}; + }, + disk() { + return this.statusOverview.disk || { items: [] }; + }, + network() { + return this.statusOverview.network || {}; + }, + process() { + return this.statusOverview.process || {}; + }, + infrastructure() { + return this.statusOverview.infrastructure || { mysql: {}, redis: {} }; + }, runtimeTagText() { const runtime = this.md2imgHealth && this.md2imgHealth.runtime ? this.md2imgHealth.runtime : {}; return runtime.loop_running ? '运行时在线' : '运行时未就绪'; @@ -73,7 +316,7 @@ }, browserTagText() { const browser = this.md2imgHealth && this.md2imgHealth.browser ? this.md2imgHealth.browser : {}; - return browser.connected ? '浏览器已连接' : '浏览器未连接'; + return browser.connected ? '浏览器已连接' : 'info'; }, browserTagType() { const browser = this.md2imgHealth && this.md2imgHealth.browser ? this.md2imgHealth.browser : {}; @@ -91,16 +334,106 @@ }, mounted() { this.currentView = '14'; + this.loadStatusOverview(false); this.loadMd2ImgHealth(); + // 资源页采用前端轮询即可满足日常观察，不需要为了监控再起单独守护进程。 + this.autoRefreshTimer = setInterval(() => { + this.loadStatusOverview(false); + }, 10000); + }, + beforeDestroy() { + if (this.autoRefreshTimer) { + clearInterval(this.autoRefreshTimer); + this.autoRefreshTimer = null; + } }, methods: { - reloadIframe() { - if (this.$refs.monitorFrame) { - this.$refs.monitorFrame.src = this.frameUrl; + async loadStatusOverview(showToast) { + if (this.loading) return; + this.loading = true; + try { + const response = await axios.get('/api/system_status_overview'); + if (response.data && response.data.success) { + this.statusOverview = response.data.data || this.statusOverview; + if (showToast) { + this.$message.success('资源监控已刷新'); + } + } else { + this.$message.error(response.data?.message || '获取资源监控失败'); + } + } catch (error) { + this.$message.error(error.response?.data?.message || '获取资源监控失败'); + } finally { + this.loading = false; } }, - openInNewTab() { - window.open(this.frameUrl, '_blank'); + normalizePercent(value) { + const number = Number(value || 0); + if (Number.isNaN(number)) return 0; + return Math.max(0, Math.min(100, Number(number.toFixed(1)))); + }, + progressStatus(value, warningThreshold, dangerThreshold) { + const percent = this.normalizePercent(value); + if (percent >= dangerThreshold) return 'exception'; + if (percent >= warningThreshold) return 'warning'; + return 'success'; + }, + formatNumber(value, digits = 0) { + if (value === null || value === undefined || value === '') return '-'; + const number = Number(value); + if (Number.isNaN(number)) return String(value); + return number.toFixed(digits); + }, + formatPercent(value) { + if (value === null || value === undefined || value === '') return '-'; + return `${this.formatNumber(value, 1)}%`; + }, + formatBytes(value) { + const bytes = Number(value || 0); + if (!Number.isFinite(bytes) || bytes <= 0) return '0 B'; + const units = ['B', 'KB', 'MB', 'GB', 'TB']; + let size = bytes; + let index = 0; + while (size >= 1024 && index < units.length - 1) { + size /= 1024; + index += 1; + } + const digits = index === 0 ? 0 : (size >= 100 ? 0 : (size >= 10 ? 1 : 2)); + return `${size.toFixed(digits)} ${units[index]}`; + }, + formatSpeed(value) { + return `${this.formatBytes(value)}/s`; + }, + formatDuration(seconds) { + const total = parseInt(seconds || 0, 10); + if (!total || total <= 0) return '-'; + const days = Math.floor(total / 86400); + const hours = Math.floor((total % 86400) / 3600); + const minutes = Math.floor((total % 3600) / 60); + if (days > 0) return `${days}天 ${hours}小时`; + if (hours > 0) return `${hours}小时 ${minutes}分钟`; + return `${minutes}分钟`; + }, + formatMb(value) { + const number = Number(value || 0); + if (!Number.isFinite(number) || number <= 0) return '0 MB'; + return `${number.toFixed(number >= 100 ? 0 : 1)} MB`; + }, + statusText(status) { + const mapping = { + healthy: '健康', + warning: '关注', + danger: '异常' + }; + return mapping[status] || '未知'; + }, + tagType(status) { + const mapping = { + healthy: 'success', + warning: 'warning', + danger: 'danger' + }; + return mapping[status] || 'info'; }, confirmRestart() { this.$confirm('确认执行 ./restart.sh 重启服务吗？这会中断当前服务几秒钟。', '重启确认', { @@ -131,7 +464,6 @@ if (this.md2imgLoading) return; this.md2imgLoading = true; try { - // 默认不强制拉起 runtime，避免纯查看状态时引入副作用。 const response = await axios.get('/api/system/md2img_health'); if (response.data && response.data.success) { this.md2imgHealth = response.data.data || null; @@ -170,44 +502,79 @@ .page-shell { display: flex; flex-direction: column; gap: 16px; } .page-hero { display: flex; align-items: flex-end; justify-content: space-between; gap: 18px; padding: 24px 26px; border-radius: 24px; - background: linear-gradient(135deg, rgba(79,70,229,0.10), rgba(59,130,246,0.08), rgba(255,255,255,0.9)); + background: linear-gradient(135deg, rgba(15,23,42,0.05), rgba(59,130,246,0.10), rgba(255,255,255,0.95)); border: 1px solid rgba(148, 163, 184, 0.16); box-shadow: 0 18px 40px rgba(15, 23, 42, 0.06); } - .page-hero-actions { display: flex; align-items: center; gap: 12px; } - .page-eyebrow { font-size: 12px; text-transform: uppercase; letter-spacing: .08em; color: #6366f1; font-weight: 700; margin-bottom: 8px; } + .page-hero-actions { display: flex; align-items: center; gap: 12px; flex-wrap: wrap; } + .page-eyebrow { font-size: 12px; text-transform: uppercase; letter-spacing: .08em; color: #2563eb; font-weight: 700; margin-bottom: 8px; } .page-hero-copy h1 { font-size: 30px; line-height: 1.1; margin-bottom: 10px; color: #0f172a; } .page-hero-copy p { color: #64748b; font-size: 14px; } + .hero-meta-row { display: flex; gap: 10px; flex-wrap: wrap; margin-top: 14px; } + .hero-meta-pill { + display: inline-flex; align-items: center; gap: 8px; padding: 8px 12px; border-radius: 999px; + background: rgba(255,255,255,0.8); border: 1px solid rgba(148,163,184,0.14); color: #475569; font-size: 12px; + } + .hero-meta-label { color: #94a3b8; } + .hero-meta-value { color: #0f172a; font-weight: 700; } .md2img-health-inline { - margin-top: 12px; - display: flex; - align-items: center; - gap: 8px; - flex-wrap: wrap; - padding: 8px 10px; - border-radius: 12px; - background: rgba(255,255,255,0.72); - border: 1px solid rgba(148, 163, 184, 0.18); + margin-top: 12px; display: flex; align-items: center; gap: 8px; flex-wrap: wrap; padding: 8px 10px; + border-radius: 12px; background: rgba(255,255,255,0.72); border: 1px solid rgba(148, 163, 184, 0.18); } .health-title { font-size: 12px; font-weight: 700; color: #334155; } .health-brief { font-size: 12px; color: #475569; } .health-time { font-size: 12px; color: #94a3b8; } + .stats-grid { display: grid; grid-template-columns: repeat(4, minmax(0, 1fr)); gap: 16px; } + .stat-card { border-radius: 20px; } + .stat-card__label { color: #64748b; font-size: 13px; margin-bottom: 10px; } + .stat-card__value { color: #0f172a; font-size: 30px; font-weight: 700; line-height: 1; margin-bottom: 10px; } + .stat-card__meta { color: #475569; font-size: 12px; margin-bottom: 12px; min-height: 18px; } + .network-balance { margin-top: 12px; display: flex; justify-content: space-between; gap: 10px; color: #64748b; font-size: 12px; } + .monitor-grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 16px; } + .workspace-card { border-radius: 20px; } + .workspace-card--wide { grid-column: 1 / -1; } .workspace-header { display: flex; align-items: center; justify-content: space-between; gap: 16px; } .workspace-header h3 { font-size: 18px; margin-bottom: 4px; } .workspace-header p { font-size: 13px; color: #64748b; } - .iframe-url { - max-width: 40%; overflow: hidden; text-overflow: ellipsis; white-space: nowrap; font-size: 12px; - color: #94a3b8; padding: 8px 12px; border-radius: 999px; background: rgba(248,250,252,0.9); border: 1px solid rgba(148,163,184,0.12); + .detail-grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 12px; } + .detail-item { + display: flex; flex-direction: column; gap: 6px; padding: 14px 16px; border-radius: 16px; + background: rgba(248,250,252,0.82); border: 1px solid rgba(148,163,184,0.12); + } + .detail-item--wide { grid-column: 1 / -1; } + .detail-item__label { color: #64748b; font-size: 12px; } + .detail-item__value { color: #0f172a; font-size: 15px; font-weight: 700; word-break: break-all; } + .infra-grid { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 14px; } + .infra-panel { + padding: 16px; border-radius: 18px; border: 1px solid rgba(148,163,184,0.12); background: rgba(248,250,252,0.86); + } + .infra-panel--healthy { box-shadow: inset 0 0 0 1px rgba(16,185,129,0.08); } + .infra-panel--warning { box-shadow: inset 0 0 0 1px rgba(245,158,11,0.10); } + .infra-panel--danger { box-shadow: inset 0 0 0 1px rgba(239,68,68,0.10); } + .infra-panel__head { display: flex; align-items: flex-start; justify-content: space-between; gap: 12px; margin-bottom: 14px; } + .infra-panel__title { color: #0f172a; font-size: 16px; font-weight: 700; } + .infra-panel__summary { color: #64748b; font-size: 12px; line-height: 1.6; margin-top: 4px; } + .infra-metrics { display: grid; grid-template-columns: repeat(2, minmax(0, 1fr)); gap: 10px 12px; } + .infra-metric { + display: flex; flex-direction: column; gap: 4px; padding: 10px 12px; border-radius: 14px; + background: rgba(255,255,255,0.75); border: 1px solid rgba(148,163,184,0.10); + } + .infra-metric span { color: #64748b; font-size: 12px; } + .infra-metric strong { color: #0f172a; font-size: 14px; font-weight: 700; word-break: break-word; } + .table-progress-cell { display: grid; grid-template-columns: 60px 1fr; align-items: center; gap: 10px; } + @media (max-width: 1200px) { + .stats-grid { grid-template-columns: repeat(2, minmax(0, 1fr)); } + .monitor-grid { grid-template-columns: 1fr; } + .infra-grid { grid-template-columns: 1fr; } } - .iframe-shell-card { height: calc(100vh - 230px); } - .iframe-shell-card .el-card__body { height: calc(100% - 73px); } - .iframe-shell { height: 100%; border-radius: 18px; overflow: hidden; border: 1px solid rgba(148,163,184,0.12); background: rgba(248,250,252,0.82); } - .iframe-shell iframe { width: 100%; height: 100%; border: none; display: block; background: #fff; } @media (max-width: 960px) { .page-hero { flex-direction: column; align-items: flex-start; } - .workspace-header { flex-direction: column; align-items: flex-start; } - .page-hero-actions { flex-wrap: wrap; } - .iframe-url { max-width: 100%; } - .md2img-health-inline { width: 100%; } + .detail-grid { grid-template-columns: 1fr; } + .detail-item--wide { grid-column: auto; } + } + @media (max-width: 640px) { + .stats-grid { grid-template-columns: 1fr; } + .network-balance { flex-direction: column; } + .infra-metrics { grid-template-columns: 1fr; } } {% endblock %} diff --git a/main.py b/main.py index 405f2e8..01e58ad 100644 --- a/main.py +++ b/main.py @@ -3,7 +3,6 @@ import asyncio import threading -from admin.GlancesMonitor import GlancesMonitor from utils.decorator.async_job import async_job from utils.markdown_to_image import warmup_md2img_browser from configuration import Config @@ -126,23 +125,6 @@ def main(): robot.LOG.info(f"Dashboard服务器已在 http://{dashboard_server.host}:{dashboard_server.port} 启动") except Exception as e: robot.LOG.error(f"Dashboard服务器启动失败: {e}") - try: - robot.LOG.debug(f"开始启动GlancesMonitor") - # 初始化 Glances 监控 - monitor = GlancesMonitor( - email_sender=robot.email_sender, - host=config.glances.get("host"), - port=config.glances.get("port"), - cpu_threshold=80.0, - load_threshold=16, # 自动设为 CPU 核心数 * 2 - io_threshold=100.0, - disk_usage_threshold=70.0, - handle_threshold=20000, - recipient=config.email.get("alert_recipient") - ) - monitor.run() - except Exception as e: - robot.LOG.error(f"GlancesMonitor服务器启动失败: {e}") # 启动后在“调度器同一事件循环”中预热 Markdown 转图浏览器。 # 这样可确保预热得到的常驻浏览器与后续截图任务复用同一 loop，避免跨 loop 句柄失效。