实践操作提纲 — 完整步骤与注解

$ yum install -y epel-release && yum install -y nginx

# systemctl 全流程
$ systemctl start nginx      # 启动
$ systemctl status nginx     # 查状态 → 看到 active (running)
$ systemctl enable nginx     # 开机自启
$ systemctl stop nginx       # 停止
$ systemctl restart nginx    # 重启
$ systemctl reload nginx     # 热加载配置（不断连接）
$ nginx -t                   # 检查配置语法
nginx: configuration file ... test is successful

$ ps aux | grep nginx        # 搜索进程
root  1234 ... nginx: master process
nginx 1235 ... nginx: worker process

$ top                        # 实时监控（q退出 M按内存排 P按CPU排）

# 杀进程
$ kill 1234                  # SIGTERM（优雅终止）
$ kill -9 1234               # SIGKILL（强制，最后手段）
$ killall nginx              # 按名字杀

# 后台运行
$ nohup python3 server.py &  # nohup 防止退终端后进程被杀

$ lsblk                                  # 查看块设备
sda      20G
├─sda1   20G  /
sdb      10G             ← 新磁盘

$ fdisk /dev/sdb                         # 分区
# 交互：n → p → 1 → 回车 → 回车 → w

$ mkfs.xfs /dev/sdb1                     # 格式化
$ mkdir /mnt/data
$ mount /dev/sdb1 /mnt/data              # 挂载

$ df -h | grep sdb
/dev/sdb1  10G  33M  10G  1% /mnt/data

# 永久挂载（写入fstab）
$ echo '/dev/sdb1  /mnt/data  xfs  defaults  0 0' >> /etc/fstab
$ mount -a                               # 验证fstab配置

[A]$ ssh-keygen -t rsa -b 4096     # 生成密钥对（一路回车）
[A]$ ssh-copy-id root@192.168.1.102 # 把公钥复制到B
[A]$ ssh root@192.168.1.102         # 测试免密登录 → 不用输密码

# scp 简单复制
$ scp /tmp/backup.tar.gz root@192.168.1.102:/tmp/     # 上传
$ scp root@192.168.1.102:/var/log/nginx.log /tmp/      # 下载
$ scp -r /opt/project root@192.168.1.102:/opt/         # 复制目录

# rsync 增量同步（只传变化的部分，比scp高效）
$ rsync -avz /opt/project/ root@192.168.1.102:/opt/project/
# -a 归档(保权限/时间)  -v 显示过程  -z 压缩传输

#!/bin/bash
BACKUP_DIR="/backup"
DATE=$(date +%Y%m%d_%H%M%S)
mkdir -p $BACKUP_DIR
tar czf ${BACKUP_DIR}/project_${DATE}.tar.gz /opt/project
echo "[$(date)] Backup done" >> /var/log/backup.log
find $BACKUP_DIR -name "*.tar.gz" -mtime +30 -delete

$ chmod +x /opt/backup.sh
$ /opt/backup.sh                         # 手动测试

# 设置cron定时任务
$ crontab -e
0 2 * * * /opt/backup.sh               # 每天凌晨2点执行

# cron格式：分 时 日 月 周 命令
# ┌───── 分 (0-59)
# │ ┌─── 时 (0-23)
# │ │ ┌─ 日 (1-31)
# │ │ │ ┌ 月 (1-12)
# │ │ │ │ ┌ 周(0-7)
# 0 2 * * *
#
# 更多示例：
# */5 * * * *     每5分钟
# 0 */2 * * *     每2小时
# 0 9 * * 1-5     工作日9点

$ crontab -l                             # 查看任务列表

#!/bin/bash
echo "===== 系统信息 ====="
echo "主机名: $(hostname)"
echo "IP:     $(hostname -I | awk '{print $1}')"
echo "内核:   $(uname -r)"
echo "运行:   $(uptime -p)"
echo "CPU:    $(nproc) 核 | 负载: $(uptime | awk -F'load average:' '{print $2}')"
free -h | awk '/Mem/{printf "内存: %s/%s (%.0f%%)\n",$3,$2,$3/$2*100}'
df -h | grep '^/dev/' | awk '{printf "磁盘 %s: %s used (%s)\n",$6,$3,$5}'

#!/bin/bash
# 用法: ./check_service.sh nginx
SERVICE=${1:-nginx}
LOG="/var/log/service_monitor.log"

if systemctl is-active --quiet $SERVICE; then
    echo "[$(date)] $SERVICE OK" >> $LOG
else
    echo "[$(date)] $SERVICE DOWN! Restarting..." >> $LOG
    systemctl restart $SERVICE
    sleep 2
    if systemctl is-active --quiet $SERVICE; then
        echo "[$(date)] $SERVICE restarted OK" >> $LOG
    else
        echo "[$(date)] CRITICAL: $SERVICE restart FAILED!" >> $LOG
    fi
fi

#!/bin/bash
USER_FILE=$1
[ -z "$USER_FILE" ] && echo "用法: $0 <用户名文件>" && exit 1
[ ! -f "$USER_FILE" ] && echo "文件不存在: $USER_FILE" && exit 1

while read -r name; do
    [ -z "$name" ] && continue         # 跳过空行
    [[ "$name" =~ ^# ]] && continue    # 跳过注释
    if id "$name" &>/dev/null; then
        echo "[跳过] $name 已存在"
    else
        useradd -m -s /bin/bash "$name"
        echo "$name:Pass@2026" | chpasswd
        echo "[创建] $name 成功"
    fi
done < "$USER_FILE"

$ echo -e "alice\nbob\ncharlie" > /tmp/users.txt
$ bash /opt/scripts/create_users.sh /tmp/users.txt
[创建] alice 成功
[创建] bob 成功
[创建] charlie 成功

$ grep "root" /etc/passwd              # 基本搜索
$ grep -i "error" /var/log/messages    # -i 忽略大小写
$ grep -v "^#" /etc/nginx/nginx.conf   # -v 反选（去掉注释行）
$ grep -c "Failed" /var/log/secure     # -c 统计匹配行数
$ grep -rn "listen" /etc/nginx/        # -r递归 -n行号
$ grep -E "^root|^nginx" /etc/passwd   # -E 扩展正则（多个模式用|）

$ echo "hello world" | sed 's/hello/hi/g'     # 替换
hi world

$ sed -i 's/192.168.1.100/10.0.0.100/g' conf  # -i 直接改文件
$ sed -i '/^#/d' config.txt                    # 删注释行
$ sed -i '/^$/d' config.txt                    # 删空行
$ sed -n '5,10p' file.txt                      # 只打印第5-10行

$ awk -F: '{print $1}' /etc/passwd       # -F: 以冒号分隔，取第1字段
root
daemon
webadmin

$ awk -F: '$3>=1000{print $1,$3}' /etc/passwd   # 条件：UID>=1000
webadmin 1001

# 实战：Nginx日志TOP10 IP
$ awk '{print $1}' access.log | sort | uniq -c | sort -rn | head -10
   523 192.168.1.50
   312 10.0.0.15

$ docker pull nginx:latest                        # 拉镜像
$ docker run -d -p 8080:80 --name web nginx       # 运行（-d后台 -p端口映射）
$ curl http://localhost:8080                       # 验证

$ docker ps                                        # 运行中的容器
$ docker ps -a                                     # 所有容器（含已停止）
$ docker logs -f web                               # 实时日志
$ docker exec -it web bash                         # 进入容器
$ docker stop web && docker rm web                 # 停止并删除

# 绑定挂载
$ mkdir /myhtml && echo "<h1>Hello</h1>" > /myhtml/index.html
$ docker run -d -p 80:80 -v /myhtml:/usr/share/nginx/html nginx
# 修改 /myhtml/index.html → 容器内网页实时变化

# 命名卷
$ docker volume create mydata
$ docker run -d -v mydata:/var/lib/mysql -e MYSQL_ROOT_PASSWORD=123 mysql:8

FROM python:3.9-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
COPY app.py .
EXPOSE 5000
CMD ["python", "app.py"]

from flask import Flask
app = Flask(__name__)
@app.route('/')
def hello(): return 'Hello from Docker!'
if __name__ == '__main__': app.run(host='0.0.0.0', port=5000)

$ echo "flask" > requirements.txt
$ docker build -t myflask:v1 .
$ docker run -d -p 5000:5000 myflask:v1
$ curl localhost:5000
Hello from Docker!

version: '3.8'
services:
  web:
    image: nginx
    ports: ["80:80"]
    depends_on: [app]
  app:
    build: .
    expose: ["5000"]
  redis:
    image: redis:alpine

$ docker-compose up -d           # 后台启动
$ docker-compose ps              # 查看状态
$ docker-compose logs -f app     # 看app日志
$ docker-compose down            # 停止删除
$ docker-compose up -d --build   # 重新构建启动

#!/usr/bin/env python3
import psutil, socket
from datetime import datetime

CPU_WARN, MEM_WARN, DISK_WARN = 80, 85, 90

cpu = psutil.cpu_percent(interval=1)
mem = psutil.virtual_memory()
print(f"=== {socket.gethostname()} [{datetime.now():%Y-%m-%d %H:%M}] ===")
print(f"CPU: {cpu}%  内存: {mem.percent}% ({mem.used//1024//1024}M/{mem.total//1024//1024}M)")
for p in psutil.disk_partitions():
    u = psutil.disk_usage(p.mountpoint)
    flag = " ⚠️" if u.percent > DISK_WARN else ""
    print(f"磁盘 {p.mountpoint}: {u.percent}%{flag}")
if cpu > CPU_WARN: print(f"⚠️ CPU {cpu}% 超阈值!")
if mem.percent > MEM_WARN: print(f"⚠️ 内存 {mem.percent}% 超阈值!")

#!/usr/bin/env python3
import paramiko

SERVERS = [
    {"host": "192.168.1.101", "user": "root", "key": "/root/.ssh/id_rsa"},
    {"host": "192.168.1.102", "user": "root", "key": "/root/.ssh/id_rsa"},
]

def run_remote(host, user, key, cmd):
    c = paramiko.SSHClient()
    c.set_missing_host_key_policy(paramiko.AutoAddPolicy())
    c.connect(host, username=user, key_filename=key, timeout=10)
    _, stdout, _ = c.exec_command(cmd)
    result = stdout.read().decode().strip()
    c.close()
    return result

for s in SERVERS:
    print(f"\n{'='*40}\n{s['host']}\n{'='*40}")
    for cmd in ["hostname", "uptime", "df -h|grep '/$'", "free -h|awk '/Mem/{print $3\"/\"$2}'"]:
        print(f"  {cmd}  →  {run_remote(s['host'], s['user'], s['key'], cmd)}")

[web]
192.168.1.101
192.168.1.102
[db]
192.168.1.103
[all:vars]
ansible_user=root

$ ansible all -m ping                              # 测试连通
192.168.1.101 | SUCCESS => {"ping": "pong"}

$ ansible web -m shell -a "df -h"                  # 查磁盘
$ ansible web -m yum -a "name=nginx state=present" # 安装nginx
$ ansible web -m service -a "name=nginx state=started enabled=yes"

---
- name: Deploy Nginx
  hosts: web
  become: yes                       # sudo提权

  vars:
    nginx_port: 80

  tasks:
    - name: Install EPEL
      yum: name=epel-release state=present

    - name: Install Nginx
      yum: name=nginx state=latest

    - name: Deploy config
      template: src=nginx.conf.j2 dest=/etc/nginx/conf.d/mysite.conf
      notify: Restart Nginx         # 配置变了才触发handler

    - name: Start Nginx
      service: name=nginx state=started enabled=yes

  handlers:
    - name: Restart Nginx
      service: name=nginx state=restarted

$ ansible-playbook deploy_nginx.yml
PLAY RECAP ***
192.168.1.101: ok=5 changed=3 failed=0
192.168.1.102: ok=5 changed=3 failed=0