Initial commit: Add infrastructure and bot project

infra/monitoring/prometheus_server.py

@@ -0,0 +1,143 @@
+import asyncio
+import logging
+from aiohttp import web
+try:
+    from .metrics_collector import MetricsCollector
+except ImportError:
+    from metrics_collector import MetricsCollector
+
+logger = logging.getLogger(__name__)
+
+
+class PrometheusServer:
+    def __init__(self, host='0.0.0.0', port=9091):
+        self.host = host
+        self.port = port
+        self.metrics_collector = MetricsCollector()
+        self.app = web.Application()
+        self.setup_routes()
+        
+    def setup_routes(self):
+        """Настройка маршрутов для Prometheus"""
+        self.app.router.add_get('/', self.root_handler)
+        self.app.router.add_get('/metrics', self.metrics_handler)
+        self.app.router.add_get('/health', self.health_handler)
+        
+    async def root_handler(self, request):
+        """Главная страница"""
+        return web.Response(
+            text="Prometheus Metrics Server\n\n"
+                 "Available endpoints:\n"
+                 "- /metrics - Prometheus metrics\n"
+                 "- /health - Health check",
+            content_type='text/plain'
+        )
+        
+    async def health_handler(self, request):
+        """Health check endpoint"""
+        return web.Response(
+            text="OK",
+            content_type='text/plain'
+        )
+        
+    async def metrics_handler(self, request):
+        """Endpoint для Prometheus метрик"""
+        try:
+            metrics_data = self.metrics_collector.get_metrics_data()
+            prometheus_metrics = self._format_prometheus_metrics(metrics_data)
+            
+            return web.Response(
+                text=prometheus_metrics,
+                content_type='text/plain'
+            )
+            
+        except Exception as e:
+            logger.error(f"Ошибка при получении метрик: {e}")
+            return web.Response(
+                text=f"Error: {str(e)}",
+                status=500,
+                content_type='text/plain'
+            )
+    
+    def _format_prometheus_metrics(self, metrics_data: dict) -> str:
+        """Форматирование метрик в Prometheus формат"""
+        lines = []
+        
+        # Системная информация
+        lines.append("# HELP system_info System information")
+        lines.append("# TYPE system_info gauge")
+        lines.append(f"system_info{{os=\"{self.metrics_collector.os_type}\"}} 1")
+        
+        # CPU метрики
+        if 'cpu_usage_percent' in metrics_data:
+            lines.append("# HELP cpu_usage_percent CPU usage percentage")
+            lines.append("# TYPE cpu_usage_percent gauge")
+            lines.append(f"cpu_usage_percent {metrics_data['cpu_usage_percent']}")
+            
+        if 'load_average_1m' in metrics_data:
+            lines.append("# HELP load_average_1m 1 minute load average")
+            lines.append("# TYPE load_average_1m gauge")
+            lines.append(f"load_average_1m {metrics_data['load_average_1m']}")
+            
+        if 'load_average_5m' in metrics_data:
+            lines.append("# HELP load_average_5m 5 minute load average")
+            lines.append("# TYPE load_average_5m gauge")
+            lines.append(f"load_average_5m {metrics_data['load_average_5m']}")
+            
+        if 'load_average_15m' in metrics_data:
+            lines.append("# HELP load_average_15m 15 minute load average")
+            lines.append("# TYPE load_average_15m gauge")
+            lines.append(f"load_average_15m {metrics_data['load_average_15m']}")
+        
+        # RAM метрики
+        if 'ram_usage_percent' in metrics_data:
+            lines.append("# HELP ram_usage_percent RAM usage percentage")
+            lines.append("# TYPE ram_usage_percent gauge")
+            lines.append(f"ram_usage_percent {metrics_data['ram_usage_percent']}")
+        
+        # Disk метрики
+        if 'disk_usage_percent' in metrics_data:
+            lines.append("# HELP disk_usage_percent Disk usage percentage")
+            lines.append("# TYPE disk_usage_percent gauge")
+            lines.append(f"disk_usage_percent {metrics_data['disk_usage_percent']}")
+            
+        if 'disk_io_percent' in metrics_data:
+            lines.append("# HELP disk_io_percent Disk I/O usage percentage")
+            lines.append("# TYPE disk_io_percent gauge")
+            lines.append(f"disk_io_percent {metrics_data['disk_io_percent']}")
+        
+        # Swap метрики
+        if 'swap_usage_percent' in metrics_data:
+            lines.append("# HELP swap_usage_percent Swap usage percentage")
+            lines.append("# TYPE swap_usage_percent gauge")
+            lines.append(f"swap_usage_percent {metrics_data['swap_usage_percent']}")
+        
+        # Uptime метрики
+        if 'system_uptime_seconds' in metrics_data:
+            lines.append("# HELP system_uptime_seconds System uptime in seconds")
+            lines.append("# TYPE system_uptime_seconds gauge")
+            lines.append(f"system_uptime_seconds {metrics_data['system_uptime_seconds']}")
+            
+        if 'monitor_uptime_seconds' in metrics_data:
+            lines.append("# HELP monitor_uptime_seconds Monitor uptime in seconds")
+            lines.append("# TYPE monitor_uptime_seconds gauge")
+            lines.append(f"monitor_uptime_seconds {metrics_data['monitor_uptime_seconds']}")
+        
+        return '\n'.join(lines)
+    
+    async def start(self):
+        """Запуск HTTP сервера"""
+        runner = web.AppRunner(self.app)
+        await runner.setup()
+        
+        site = web.TCPSite(runner, self.host, self.port)
+        await site.start()
+        
+        logger.info(f"Prometheus сервер запущен на http://{self.host}:{self.port}")
+        
+        return runner
+    
+    async def stop(self, runner):
+        """Остановка HTTP сервера"""
+        await runner.cleanup()
+        logger.info("Prometheus сервер остановлен")