linux自动化巡检脚本集（linux服务器巡检内容以及标准）

以下是一个自动化巡检脚本集的制作方案，包含常见系统检查项和可扩展框架，使用Python和Shell脚本实现：

#!/usr/bin/env python3
# system_inspector.py

import os
import sys
import subprocess
import psutil
import datetime
import socket

class SystemInspector:
    def __init__(self):
        self.report = []
        self.log_file = "/var/log/system_inspector.log"
        
    def log(self, message, level="INFO"):
        timestamp = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
        log_entry = f"[{timestamp}] [{level}] {message}"
        self.report.append(log_entry)
        
    def check_cpu(self):
        try:
            usage = psutil.cpu_percent(interval=1)
            load_avg = os.getloadavg()
            self.log(f"CPU Usage: {usage}% | Load Average: {load_avg}")
            if usage > 90:
                self.log("CPU Warning: Usage over 90%!", "WARNING")
        except Exception as e:
            self.log(f"CPU Check Error: {str(e)}", "ERROR")

    def check_memory(self):
        try:
            mem = psutil.virtual_memory()
            self.log(f"Memory Usage: {mem.percent}% | Available: {mem.available/1024/1024:.2f} MB")
            if mem.percent > 90:
                self.log("Memory Warning: Usage over 90%!", "WARNING")
        except Exception as e:
            self.log(f"Memory Check Error: {str(e)}", "ERROR")

    def check_disk(self):
        try:
            disks = []
            for part in psutil.disk_partitions():
                usage = psutil.disk_usage(part.mountpoint)
                disks.append(f"{part.mountpoint} {usage.percent}%")
                if usage.percent > 90:
                    self.log(f"Disk Warning: {part.mountpoint} over 90%!", "WARNING")
            self.log("Disk Usage: " + " | ".join(disks))
        except Exception as e:
            self.log(f"Disk Check Error: {str(e)}", "ERROR")

    def check_services(self):
        services = ["nginx", "mysql", "redis"]
        try:
            for service in services:
                result = subprocess.run(
                    ["systemctl", "is-active", service],
                    capture_output=True,
                    text=True
                )
                status = result.stdout.strip()
                self.log(f"Service {service}: {status}")
                if status != "active":
                    self.log(f"Service {service} is not active!", "WARNING")
        except Exception as e:
            self.log(f"Service Check Error: {str(e)}", "ERROR")

    def generate_report(self):
        with open(self.log_file, "a") as f:
            f.write("\n".join(self.report) + "\n\n")
        print(f"Inspection completed. Report saved to {self.log_file}")

if __name__ == "__main__":
    inspector = SystemInspector()
    inspector.log("=== Starting System Inspection ===")
    inspector.check_cpu()
    inspector.check_memory()
    inspector.check_disk()
    inspector.check_services()
    inspector.generate_report()

配套Shell脚本（用于基础检查）：

#!/bin/bash
# basic_check.sh

# 系统基本信息
echo "===== System Info ====="
echo "Hostname: $(hostname)"
echo "Uptime: $(uptime)"
echo "Kernel: $(uname -r)"

# 内存检查
echo -e "\n===== Memory Usage ====="
free -h

# 磁盘检查
echo -e "\n===== Disk Usage ====="
df -h | grep -v tmpfs

# 进程检查
echo -e "\n===== Top Processes ====="
ps -eo pid,ppid,cmd,%mem,%cpu --sort=-%cpu | head -n 6

# 网络检查
echo -e "\n===== Network Connections ====="
netstat -ant | awk '{print $6}' | grep -v '^