本文目录导读：
我来介绍几种监控CPU使用率并触发告警的脚本方案：
Shell脚本（Linux）
#!/bin/bash
# CPU告警阈值（百分比）
CPU_THRESHOLD=80
# 检查间隔（秒）
CHECK_INTERVAL=10
# 告警日志文件
ALERT_LOG="/var/log/cpu_alert.log"
while true; do
# 获取CPU使用率（取1分钟平均）
CPU_USAGE=$(top -bn1 | grep "Cpu(s)" | awk '{print $2 + $4}' | cut -d. -f1)
if [ "$CPU_USAGE" -gt "$CPU_THRESHOLD" ]; then
# 记录告警
echo "$(date): CPU使用率告警: ${CPU_USAGE}% > ${CPU_THRESHOLD}%" >> $ALERT_LOG
# 发送邮件告警（需要配置mail服务）
echo "CPU使用率已达 ${CPU_USAGE}%，请及时处理" | mail -s "CPU告警通知" admin@example.com
# 发送系统通知
wall "警告: CPU使用率 ${CPU_USAGE}% 超过阈值 ${CPU_THRESHOLD}%"
fi
sleep $CHECK_INTERVAL
done
Python脚本（跨平台）
#!/usr/bin/env python3
import psutil
import time
import logging
import smtplib
from email.mime.text import MIMEText
import json
class CPUAlertMonitor:
def __init__(self, config_file='cpu_alert_config.json'):
# 默认配置
self.config = {
'cpu_threshold': 80, # CPU阈值 %
'check_interval': 10, # 检查间隔 秒
'duration_threshold': 60, # 持续告警时间 秒
'alert_methods': ['log', 'email'],
'email': {
'smtp_server': 'smtp.example.com',
'smtp_port': 587,
'sender': 'monitor@example.com',
'password': 'your_password',
'recipients': ['admin@example.com']
}
}
# 加载配置文件
try:
with open(config_file, 'r') as f:
self.config.update(json.load(f))
except FileNotFoundError:
pass
# 设置日志
logging.basicConfig(
filename='cpu_alert.log',
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s'
)
self.high_cpu_start_time = None
def get_cpu_usage(self):
"""获取CPU使用率"""
return psutil.cpu_percent(interval=1)
def send_email_alert(self, cpu_usage):
"""发送邮件告警"""
try:
msg = MIMEText(f"CPU使用率告警\n当前CPU使用率: {cpu_usage}%\n阈值: {self.config['cpu_threshold']}%\n时间: {time.strftime('%Y-%m-%d %H:%M:%S')}")
msg['Subject'] = 'CPU告警通知'
msg['From'] = self.config['email']['sender']
msg['To'] = ','.join(self.config['email']['recipients'])
server = smtplib.SMTP(self.config['email']['smtp_server'],
self.config['email']['smtp_port'])
server.starttls()
server.login(self.config['email']['sender'],
self.config['email']['password'])
server.send_message(msg)
server.quit()
logging.info("邮件告警已发送")
except Exception as e:
logging.error(f"邮件发送失败: {e}")
def check_and_alert(self):
"""检查CPU使用率并触发告警"""
cpu_usage = self.get_cpu_usage()
if cpu_usage > self.config['cpu_threshold']:
if self.high_cpu_start_time is None:
self.high_cpu_start_time = time.time()
duration = time.time() - self.high_cpu_start_time
if duration >= self.config['duration_threshold']:
alert_msg = f"CPU使用率告警: {cpu_usage}% (持续{duration:.0f}秒)"
logging.warning(alert_msg)
if 'email' in self.config['alert_methods']:
self.send_email_alert(cpu_usage)
if 'log' in self.config['alert_methods']:
print(alert_msg)
else:
self.high_cpu_start_time = None
def run(self):
"""运行监控"""
print(f"CPU监控启动，阈值: {self.config['cpu_threshold']}%")
while True:
self.check_and_alert()
time.sleep(self.config['check_interval'])
if __name__ == "__main__":
monitor = CPUAlertMonitor()
try:
monitor.run()
except KeyboardInterrupt:
print("\n监控已停止")
配置文件示例 (cpu_alert_config.json)
{
"cpu_threshold": 80,
"check_interval": 10,
"duration_threshold": 60,
"alert_methods": ["log", "email"],
"email": {
"smtp_server": "smtp.gmail.com",
"smtp_port": 587,
"sender": "monitor@gmail.com",
"password": "your_app_password",
"recipients": ["admin@company.com"]
}
}
Windows PowerShell脚本
# CPU监控告警脚本
$threshold = 80
$checkInterval = 10
$alertLog = "C:\Logs\cpu_alert.log"
while ($true) {
# 获取CPU使用率
$cpuUsage = (Get-Counter "\Processor(_Total)\% Processor Time").CounterSamples.CookedValue
if ($cpuUsage -gt $threshold) {
$time = Get-Date -Format "yyyy-MM-dd HH:mm:ss"
$alertMsg = "CPU告警: ${cpuUsage}% > ${threshold}% - ${time}"
# 写入日志
Add-Content -Path $alertLog -Value $alertMsg
# 弹出告警窗口
if ([System.Environment]::UserInteractive) {
[System.Windows.Forms.MessageBox]::Show($alertMsg, "CPU告警",
[System.Windows.Forms.MessageBoxButtons]::OK,
[System.Windows.Forms.MessageBoxIcon]::Warning)
}
# 写入事件日志
Write-EventLog -LogName Application -Source "CPU Monitor" `
-EntryType Warning -EventId 1001 -Message $alertMsg
}
Start-Sleep -Seconds $checkInterval
}
Docker监控方案
# docker-compose.yml
version: '3.8'
services:
cpu-monitor:
image: python:3.9-slim
volumes:
- ./cpu_monitor.py:/app/cpu_monitor.py
- ./config.json:/app/config.json
- /var/run/docker.sock:/var/run/docker.sock
command: python /app/cpu_monitor.py
restart: unless-stopped
environment:
- TZ=Asia/Shanghai
扩展功能
1 多阈值告警
def get_alert_level(cpu_usage):
"""根据CPU使用率返回告警级别"""
if cpu_usage > 95:
return "CRITICAL"
elif cpu_usage > 85:
return "WARNING"
elif cpu_usage > 75:
return "INFO"
return None
2 集成告警通道
# 企业微信通知
def send_wechat_alert(message):
webhook_url = "https://qyapi.weixin.qq.com/cgi-bin/webhook/send?key=YOUR_KEY"
requests.post(webhook_url, json={"msgtype": "text", "text": {"content": message}})
# Slack通知
def send_slack_alert(message):
webhook_url = "https://hooks.slack.com/services/YOUR/WEBHOOK/URL"
requests.post(webhook_url, json={"text": message})
安装依赖
# Python依赖 pip install psutil # Linux邮件服务 apt-get install mailutils # Debian/Ubuntu yum install mailx # CentOS/RHEL
使用建议
- 设置合理阈值：通常80%作为警告，95%作为严重告警
- 加入持续检测：避免短时峰值造成误报
- 记录告警历史：便于后续分析
- 告警升级机制：长时间高负载自动升级告警级别
- 集成运维平台：对接Zabbix、Prometheus等监控系统
这些脚本可以满足不同场景的CPU告警需求,你可以根据实际情况选择合适的方案。
