本文目录导读：
Shell脚本监控
基础进程检查脚本
#!/bin/bash
# 定义要监控的进程名
PROCESS_NAME="nginx"
LOG_FILE="/var/log/process_monitor.log"
# 检查进程是否存在
if pgrep -x "$PROCESS_NAME" > /dev/null; then
echo "$(date): $PROCESS_NAME 运行正常" >> $LOG_FILE
else
echo "$(date): $PROCESS_NAME 未运行，尝试启动..." >> $LOG_FILE
# 尝试启动服务
systemctl start $PROCESS_NAME 2>/dev/null || service $PROCESS_NAME start 2>/dev/null
# 检查是否启动成功
if [ $? -eq 0 ]; then
echo "$(date): $PROCESS_NAME 启动成功" >> $LOG_FILE
else
echo "$(date): $PROCESS_NAME 启动失败" >> $LOG_FILE
fi
fi
资源使用监控
#!/bin/bash
MONITOR_PID=$1
THRESHOLD_CPU=80
THRESHOLD_MEM=90
# 监控指定PID的资源使用
while true; do
if [ -d "/proc/$MONITOR_PID" ]; then
# 获取CPU和内存使用率
CPU_USAGE=$(ps -p $MONITOR_PID -o %cpu --no-headers)
MEM_USAGE=$(ps -p $MONITOR_PID -o %mem --no-headers)
# 检查是否超过阈值
if (( $(echo "$CPU_USAGE > $THRESHOLD_CPU" | bc -l) )); then
echo "警告: 进程 $MONITOR_PID CPU使用率: $CPU_USAGE%"
fi
if (( $(echo "$MEM_USAGE > $THRESHOLD_MEM" | bc -l) )); then
echo "警告: 进程 $MONITOR_PID 内存使用率: $MEM_USAGE%"
fi
sleep 5
else
echo "进程 $MONITOR_PID 已不存在"
exit 1
fi
done
Python监控脚本
完整进程监控
#!/usr/bin/env python3
import psutil
import time
import logging
import subprocess
import os
class ProcessMonitor:
def __init__(self, process_name, restart_command=None):
self.process_name = process_name
self.restart_command = restart_command
self.setup_logging()
def setup_logging(self):
logging.basicConfig(
level=logging.INFO,
format='%(asctime)s - %(levelname)s - %(message)s',
handlers=[
logging.FileHandler('process_monitor.log'),
logging.StreamHandler()
]
)
def find_process(self):
"""查找进程"""
for proc in psutil.process_iter(['pid', 'name', 'cpu_percent', 'memory_percent']):
try:
if self.process_name.lower() in proc.info['name'].lower():
return proc
except (psutil.NoSuchProcess, psutil.AccessDenied):
pass
return None
def check_process_health(self, process):
"""检查进程健康状况"""
cpu_percent = process.cpu_percent(interval=1)
memory_percent = process.memory_percent()
if cpu_percent > 90:
logging.warning(f"CPU使用率过高: {cpu_percent}%")
if memory_percent > 90:
logging.warning(f"内存使用率过高: {memory_percent}%")
# 检查进程状态
if process.status() == psutil.STATUS_ZOMBIE:
logging.error("进程已变为僵尸进程")
return False
return True
def restart_process(self):
"""重启进程"""
if self.restart_command:
try:
subprocess.run(self.restart_command, shell=True, check=True)
logging.info(f"进程 {self.process_name} 重启成功")
return True
except subprocess.CalledProcessError as e:
logging.error(f"重启失败: {e}")
return False
else:
logging.warning("未配置重启命令")
return False
def monitor(self, interval=5):
"""持续监控"""
logging.info(f"开始监控进程: {self.process_name}")
while True:
process = self.find_process()
if process is None:
logging.warning(f"进程 {self.process_name} 未运行")
self.restart_process()
else:
if not self.check_process_health(process):
logging.error("进程异常，尝试重启")
self.restart_process()
else:
logging.info(f"进程 {process.info['name']} (PID: {process.info['pid']}) 运行正常")
time.sleep(interval)
# 使用示例
if __name__ == "__main__":
monitor = ProcessMonitor(
process_name="nginx",
restart_command="systemctl restart nginx"
)
monitor.monitor()
添加告警功能
邮件告警
#!/usr/bin/env python3
import smtplib
from email.mime.text import MIMEText
import psutil
import time
class AlertMonitor:
def __init__(self, process_name, email_config):
self.process_name = process_name
self.email_config = email_config
def send_alert(self, subject, message):
"""发送邮件告警"""
msg = MIMEText(message)
msg['Subject'] = subject
msg['From'] = self.email_config['from']
msg['To'] = self.email_config['to']
try:
with smtplib.SMTP(self.email_config['smtp_server'],
self.email_config['smtp_port']) as server:
server.starttls()
server.login(self.email_config['username'],
self.email_config['password'])
server.send_message(msg)
print(f"告警邮件已发送: {subject}")
except Exception as e:
print(f"发送告警失败: {e}")
def check_and_alert(self):
"""检查并发送告警"""
for proc in psutil.process_iter(['pid', 'name']):
try:
if self.process_name in proc.info['name']:
return # 进程运行正常
except (psutil.NoSuchProcess, psutil.AccessDenied):
pass
# 进程未运行，发送告警
self.send_alert(
f"进程告警: {self.process_name} 已停止",
f"时间: {time.ctime()}\n进程: {self.process_name}\n状态: 未运行"
)
# 配置示例
email_config = {
'from': 'monitor@example.com',
'to': 'admin@example.com',
'smtp_server': 'smtp.gmail.com',
'smtp_port': 587,
'username': 'monitor@example.com',
'password': 'your_password'
}
monitor = AlertMonitor('nginx', email_config)
monitor.check_and_alert()
使用crontab定期执行
# 编辑crontab crontab -e # 每分钟检查一次进程状态 * * * * * /path/to/monitor_script.sh # 或者使用更复杂的调度 */5 * * * * /path/to/monitor_script.sh # 每5分钟 0 * * * * /path/to/monitor_script.sh # 每小时
系统级监控方案
systemd服务监控
# /etc/systemd/system/process-monitor.service [Unit] Description=Process Monitor Service After=network.target [Service] Type=simple ExecStart=/usr/local/bin/monitor.py Restart=always RestartSec=10 User=root [Install] WantedBy=multi-user.target
使用supervisor
# /etc/supervisor/conf.d/monitor.conf [program:process-monitor] command=/usr/local/bin/monitor.py autostart=true autorestart=true stderr_logfile=/var/log/monitor.err.log stdout_logfile=/var/log/monitor.out.log
使用建议
- 选择合适的监控频率：不要太频繁以免消耗资源
- 合理设置日志轮转：避免日志文件过大
- 配置告警机制：及时发现和处理问题
- 测试自动恢复功能：确保重启命令有效
- 设置资源限制：防止监控脚本自身占用过多资源
根据你的具体需求选择合适的方案,可以组合使用多种方法实现完整的进程监控。
