Files
ai-trade/modules/utils/monitor.py

60 lines
2.1 KiB
Python

import psutil
from datetime import datetime
class SystemMonitor:
def __init__(self, messenger, ollama_manager):
self.messenger = messenger
self.ollama_monitor = ollama_manager
self.last_health_check = datetime.now()
def check_health(self):
"""시스템 상태 점검 및 알림 (CPU, RAM, GPU) - 3분마다 실행"""
now = datetime.now()
if (now - self.last_health_check).total_seconds() < 180: # 5분 → 3분
return
self.last_health_check = now
alerts = []
# 1. CPU Check (non-blocking 측정)
cpu_usage = psutil.cpu_percent(interval=0)
if cpu_usage > 90:
# 검증: 상위 프로세스 CPU 합계 확인
top_processes = []
for proc in psutil.process_iter(['pid', 'name', 'cpu_percent']):
try:
if proc.info['name'] == 'System Idle Process':
continue
top_processes.append(proc.info)
except (psutil.NoSuchProcess, psutil.AccessDenied):
pass
top_processes.sort(key=lambda x: x['cpu_percent'], reverse=True)
total_top_cpu = sum(p['cpu_percent'] for p in top_processes[:3])
if total_top_cpu >= 30.0:
top_3_str = ""
for p in top_processes[:3]:
top_3_str += f"\n- {p['name']} ({p['cpu_percent']}%)"
alerts.append(f"[CPU Overload] Usage: {cpu_usage}%\nTop Processes:{top_3_str}")
# 2. RAM Check
ram = psutil.virtual_memory()
if ram.percent > 90:
alerts.append(f"[RAM High] Usage: {ram.percent}% (Free: {ram.available / 1024**3:.1f}GB)")
# 3. GPU Check
if self.ollama_monitor:
gpu_status = self.ollama_monitor.get_gpu_status()
temp = gpu_status.get('temp', 0)
if temp > 80:
alerts.append(f"[GPU Overheat] Temp: {temp}C")
# 알림 전송
if alerts:
msg = "[System Health Alert]\n" + "\n".join(alerts)
if self.messenger:
self.messenger.send_message(msg)