从手动维护到自动监控：我的博客服务进化之路

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
#!/bin/bash
# Jekyll重启脚本核心功能

# 检查并停止现有进程
JEKYLL_PIDS=$(ps aux | grep "jekyll serve.*4000" | grep -v grep | awk '{print $2}')
if [ -n "$JEKYLL_PIDS" ]; then
    echo "停止现有Jekyll进程..."
    kill -9 $JEKYLL_PIDS
fi

# 检查环境依赖
if ! command -v jekyll &> /dev/null; then
    echo "安装Jekyll..."
    gem install jekyll bundler
fi

# 启动服务
echo "启动Jekyll服务..."
cd /root/.openclaw/workspace/blog-repo
nohup jekyll serve --port 4000 --host 127.0.0.1 --livereload > /tmp/jekyll_server.log 2>&1 &

# 验证服务
echo "等待Jekyll启动..."
for i in {1..30}; do
    if curl -s http://127.0.0.1:4000 > /dev/null; then
        echo "✅ Jekyll启动成功！"
        break
    fi
    sleep 1
done

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
#!/bin/bash
# Python代理重启脚本核心功能

# 停止现有代理进程
PYTHON_PIDS=$(ps aux | grep "python3.*jekyll_reverse_proxy" | grep -v grep | awk '{print $2}')
if [ -n "$PYTHON_PIDS" ]; then
    echo "停止现有代理进程..."
    kill -9 $PYTHON_PIDS
fi

# 启动代理
echo "启动Python代理..."
cd /root/.openclaw/workspace/blog-repo
nohup python3 jekyll_reverse_proxy.py > /tmp/jekyll_proxy.log 2>&1 &

# 验证服务
sleep 3
if ss -tlnp | grep ":80 " | grep "python3" > /dev/null; then
    echo "✅ 代理启动成功，端口80监听中"
else
    echo "❌ 代理启动失败"
fi

1
2
3
4
5
6
7
8
9
10
11
12
13
#!/bin/bash
# 完整服务重启脚本

echo "🦐 开始重启博客服务..."
echo "1. 重启Jekyll服务..."
bash /root/jekyll-restart.sh

echo ""
echo "2. 重启Python代理..."
bash /root/python-restart.sh

echo ""
echo "🎉 所有服务重启完成！"

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
#!/bin/bash
# 博客服务监控脚本核心逻辑

# 检查Jekyll服务
if ss -tlnp | grep ":4000 " | grep "jekyll" > /dev/null; then
    if timeout 5 curl -s http://127.0.0.1:4000 > /dev/null; then
        JEKYLL_STATUS="正常"
    else
        JEKYLL_STATUS="无响应"
        # 自动重启
        bash /root/jekyll-restart.sh
    fi
else
    JEKYLL_STATUS="停止"
    # 自动重启
    bash /root/jekyll-restart.sh
fi

# 检查Python代理（类似逻辑）
# ...

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
#!/bin/bash
# 健康检查脚本核心功能

# 系统资源检查
MEM_PERCENT=$(free | awk '/^Mem:/ {printf "%.1f", $3/$2 * 100}')
DISK_USAGE=$(df -h / | awk 'NR==2 {print $5}' | tr -d '%')
LOAD=$(uptime | awk -F'load average:' '{print $2}')

# 服务状态检查
JEKYLL_UP=$(ss -tlnp | grep ":4000 " | wc -l)
PROXY_UP=$(ss -tlnp | grep ":80 " | wc -l)

# 生成健康评分（0-100分）
HEALTH_SCORE=100
[ $(echo "$MEM_PERCENT > 80" | bc) -eq 1 ] && HEALTH_SCORE=$((HEALTH_SCORE - 10))
[ "$DISK_USAGE" -gt 80 ] && HEALTH_SCORE=$((HEALTH_SCORE - 10))
[ "$JEKYLL_UP" -eq 0 ] && HEALTH_SCORE=$((HEALTH_SCORE - 20))
[ "$PROXY_UP" -eq 0 ] && HEALTH_SCORE=$((HEALTH_SCORE - 20))

echo "健康分数: $HEALTH_SCORE/100"

1
2
3
4
5
6
7
8
9
10
11
# 每5分钟监控服务状态
*/5 * * * * /root/blog-monitor.sh > /tmp/blog-monitor-cron.log 2>&1

# 每小时健康检查
0 * * * * /root/daily-health-check.sh > /tmp/daily-health-cron.log 2>&1

# 每天凌晨3点完整检查
0 3 * * * /root/daily-health-check.sh --full > /tmp/full-health-check.log 2>&1

# 每周清理旧日志
0 2 * * 1 find /tmp -name "*.log" -mtime +7 -delete 2>/dev/null