Create vps_monitor.py

vps_monitor.py

@@ -0,0 +1,196 @@
+import paramiko
+import schedule
+import time
+import os
+import sys
+from flask import Flask, jsonify, render_template_string
+from threading import Thread
+import logging
+
+app = Flask(__name__)
+
+vps_status = {}
+
+# 设置日志
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    handlers=[
+        logging.StreamHandler(sys.stdout),
+        logging.StreamHandler(sys.stderr)
+    ]
+)
+logger = logging.getLogger()
+
+def get_vps_configs():
+    configs = []
+    index = 1
+    while True:
+        hostname = os.environ.get(f'HOSTNAME_{index}')
+        if not hostname:
+            break
+        
+        config = {
+            'index': index,
+            'hostname': hostname,
+            'username': os.environ.get(f'USERNAME_{index}'),
+            'password': os.environ.get(f'PASSWORD_{index}'),
+            'script_path': os.environ.get(f'SCRIPT_PATH_{index}')
+        }
+        configs.append(config)
+        
+        logger.info(f"Config {index}: {config['hostname']}, {config['username']}, {config['script_path']}")
+        
+        index += 1
+    return configs
+
+def check_and_run_script(config):
+    logger.info(f"Checking VPS {config['index']}: {config['hostname']}")
+    client = None
+    try:
+        client = paramiko.SSHClient()
+        client.set_missing_host_key_policy(paramiko.AutoAddPolicy())
+        
+        client.connect(
+            hostname=config['hostname'],
+            username=config['username'],
+            password=config['password'],
+            port=22
+        )
+        
+        script_path = config['script_path']
+        script_name = os.path.basename(script_path)
+        
+        check_command = f"ps -eo args | grep {script_name} | grep -v grep"
+        
+        stdin, stdout, stderr = client.exec_command(check_command)
+        output = stdout.read().decode('utf-8').strip()
+        
+        if output and script_path in output:
+            status = "Running"
+            logger.info(f"Script is running on {config['hostname']}")
+        else:
+            logger.info(f"Script not running on {config['hostname']}. Executing restart script.")
+            restart_command = f"nohup /bin/sh {script_path} > /dev/null 2>&1 &"
+            stdin, stdout, stderr = client.exec_command(restart_command)
+            
+            status = "Restarted"
+            logger.info(f"Script restarted on {config['hostname']}")
+        
+        vps_status[config['index']] = {
+            'index': config['index'],
+            'hostname': config['hostname'],
+            'status': status,
+            'last_check': time.strftime('%Y-%m-%d %H:%M:%S'),
+            'username': config['username']
+        }
+        
+    except Exception as e:
+        logger.error(f"Error occurred while checking VPS {config['index']} - {config['hostname']}: {str(e)}")
+        vps_status[config['index']] = {
+            'index': config['index'],
+            'hostname': config['hostname'],
+            'status': f"Error: {str(e)}",
+            'last_check': time.strftime('%Y-%m-%d %H:%M:%S'),
+            'username': config['username']
+        }
+    finally:
+        if client:
+            client.close()
+
+def check_all_vps():
+    logger.info("Starting VPS check")
+    vps_configs = get_vps_configs()
+    for config in vps_configs:
+        check_and_run_script(config)
+    
+    # 创建表格头
+    table = "+---------+-----------------------+----------+-------------------------+----------+\n"
+    table += "| Index   | Hostname              | Status   | Last Check              | Username |\n"
+    table += "+---------+-----------------------+----------+-------------------------+----------+\n"
+    
+    # 添加每个VPS的状态
+    for index in sorted(vps_status.keys()):
+        status = vps_status[index]
+        table += "| {:<7} | {:<21} | {:<8} | {:<23} | {:<8} |\n".format(
+            status['index'],
+            status['hostname'][:21],
+            status['status'][:8],
+            status['last_check'],
+            status['username'][:8]
+        )
+        table += "+---------+-----------------------+----------+-------------------------+----------+\n"
+    
+    logger.info("\n" + table)
+
+@app.route('/')
+def index():
+    html = '''
+    <h1>VPS Status Overview</h1>
+    <table border="1">
+        <tr>
+            <th>Index</th>
+            <th>Hostname</th>
+            <th>Status</th>
+            <th>Last Check</th>
+            <th>Username</th>
+        </tr>
+        {% for index in vps_status.keys()|sort %}
+        {% set data = vps_status[index] %}
+        <tr>
+            <td>{{ data['index'] }}</td>
+            <td><a href="/status/{{ data['index'] }}">{{ data['hostname'] }}</a></td>
+            <td>{{ data['status'] }}</td>
+            <td>{{ data['last_check'] }}</td>
+            <td>{{ data['username'] }}</td>
+        </tr>
+        {% endfor %}
+    </table>
+    '''
+    return render_template_string(html, vps_status=vps_status)
+
+@app.route('/status/<int:index>')
+def vps_status_detail(index):
+    if index in vps_status:
+        return jsonify(vps_status[index])
+    else:
+        return jsonify({"error": "VPS not found"}), 404
+
+@app.route('/health')
+def health_check():
+    return jsonify({"status": "healthy", "uptime": time.time() - start_time}), 200
+
+def run_flask():
+    app.run(host='0.0.0.0', port=8080)
+
+def main():
+    global start_time
+    start_time = time.time()
+    
+    logger.info("===== VPS monitoring script is starting =====")
+    
+    flask_thread = Thread(target=run_flask)
+    flask_thread.start()
+    logger.info("Flask server started in background")
+
+    vps_configs = get_vps_configs()
+    logger.info(f"Found {len(vps_configs)} VPS configurations")
+
+    logger.info("Running initial VPS check")
+    check_all_vps()
+
+    schedule.every(15).minutes.do(check_all_vps)
+    logger.info("Scheduled VPS check every 15 minutes")
+    
+    logger.info("===== VPS monitoring script is running =====")
+    
+    heartbeat_count = 0
+    while True:
+        schedule.run_pending()
+        time.sleep(60)
+        heartbeat_count += 1
+        if heartbeat_count % 5 == 0:  # 每5分钟输出一次心跳信息
+            logger.info(f"Heartbeat: Script is still running. Uptime: {heartbeat_count} minutes")
+
+if __name__ == "__main__":
+    main()