mirror of
https://gitee.com/xmz7891/ykxmz.git
synced 2026-10-18 21:50:44 +00:00
xmz7891
f4a146056f
用户早上撞上 Cloudflare Error 1033。查出来是设备**掉电重启**：
上次开机到重启之间没有任何日志落盘（直接断电的特征），
dmesg 里还有 "l13: voltage operation not allowed"。
重启本身不是软件问题，但**恢复太慢**：
Startup finished in 3.846s (kernel) + 2min 6.358s (userspace) = 2分10秒
那 2 分钟里浏览器看到的就是 1033。
根因：
这台机器 NetworkManager 和 systemd-networkd 同时在跑，
但 wlan0 归 NetworkManager 管。
NetworkManager-wait-online -> 开机 9 秒成功
systemd-networkd-wait-online -> 等一个不归它管的网络，
干等 2 分钟超时，然后 failed
network-online.target 要等**两个都完成**，
被那个失败的拖了整整 2 分钟，
relay / tunnel / net-tune 全跟着等。
修法：
1. mask 掉 systemd-networkd-wait-online（网络不归它管，只会拖后腿）
2. watchdog 首次检查从"开机后 2 分钟"提前到 45 秒
实测（重启验证过）：
修之前 Startup finished in 3.846s + 2min 6.358s = 2分10秒
修之后 Startup finished in 3.218s + 14.060s = 17.3秒
掉电重启后公网恢复时间：**24 秒**（快了 5 倍多）
配套加了 scripts/speed-up-boot.sh，换设备时直接跑一遍。
顺带确认重启后一切自动恢复：
三个服务 active + enabled ✓
keepalive 30/10/3、MTU 探测、MSS 钳制、slow_start=0 全部持久化 ✓
隧道 4 条连接 http2 ✓
官网 / 管理页 / 截图全部 200 ✓
58 lines
2.6 KiB
Bash
58 lines
2.6 KiB
Bash
#!/bin/bash
|
||
# 重启后全面体检
|
||
set -u
|
||
|
||
echo "════════ 开机信息 ════════"
|
||
uptime -p | sed 's/^/ /'
|
||
systemd-analyze 2>/dev/null | sed 's/^/ /'
|
||
|
||
echo
|
||
echo "════════ 服务 ════════"
|
||
for s in lanremote-relay lanremote-tunnel lanremote-nettune lanremote-watchdog.timer NetworkManager-wait-online; do
|
||
printf " %-30s %-10s %s\n" "$s" "$(systemctl is-active $s 2>&1)" "$(systemctl is-enabled $s 2>&1)"
|
||
done
|
||
echo " ---"
|
||
echo " systemd-networkd-wait-online: $(systemctl is-enabled systemd-networkd-wait-online 2>&1) （应该是 masked）"
|
||
|
||
echo
|
||
echo "════════ 网络调优是否持久化 ════════"
|
||
for k in tcp_keepalive_time tcp_keepalive_intvl tcp_keepalive_probes tcp_mtu_probing tcp_slow_start_after_idle tcp_congestion_control; do
|
||
printf " %-32s = %s\n" "$k" "$(sysctl -n net.ipv4.$k 2>/dev/null || echo '?')"
|
||
done
|
||
echo " MSS 钳制: $(iptables -t mangle -S 2>/dev/null | grep -c TCPMSS) 条"
|
||
|
||
echo
|
||
echo "════════ 隧道 ════════"
|
||
echo " 连接数: $(curl -s --max-time 5 http://127.0.0.1:20241/metrics 2>/dev/null | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}')"
|
||
echo " 落点:"
|
||
grep -E 'Registered tunnel connection' /root/lanremote-relay/tunnel.log 2>/dev/null | tail -4 \
|
||
| grep -oE 'location=[a-z0-9]+ protocol=[a-z0-9]+' | sed 's/^/ /'
|
||
echo " 参数:"
|
||
grep -oE '\-\-protocol [a-z0-9]+|--ha-connections [0-9]+' /etc/systemd/system/lanremote-tunnel.service | sed 's/^/ /'
|
||
|
||
echo
|
||
echo "════════ 本机中转 ════════"
|
||
echo " HTTP $(curl -s -o /dev/null -w '%{http_code}' --max-time 8 http://127.0.0.1:8080/v1/health)"
|
||
|
||
echo
|
||
echo "════════ 公网 12 次 ════════"
|
||
ok=0
|
||
for i in $(seq 1 12); do
|
||
c=$(curl -s -o /dev/null -w '%{http_code}' --max-time 15 \
|
||
-H 'User-Agent: LanRemote/1.4.0' https://relay.xxmxxs.top/v1/health)
|
||
[ "$c" = "200" ] && ok=$((ok+1))
|
||
printf " %2d: %s\n" "$i" "$c"
|
||
sleep 1
|
||
done
|
||
echo " 可用 $ok/12"
|
||
|
||
echo
|
||
echo "════════ 官网 + 管理页 ════════"
|
||
echo " 官网 HTTP $(curl -s -o /dev/null -w '%{http_code}' --max-time 15 https://relay.xxmxxs.top/)"
|
||
echo " 管理页 HTTP $(curl -s -o /dev/null -w '%{http_code}' --max-time 15 https://relay.xxmxxs.top/zhongzhuanzhan)"
|
||
echo " 截图 HTTP $(curl -s -o /dev/null -w '%{http_code}' --max-time 15 https://relay.xxmxxs.top/shot/pc-main.png)"
|
||
|
||
echo
|
||
echo "════════ watchdog 日志 ════════"
|
||
tail -6 /root/lanremote-relay/watchdog.log 2>/dev/null | sed 's/^/ /'
|