mirror of
https://gitee.com/xmz7891/ykxmz.git
synced 2026-10-18 19:30:42 +00:00
xmz7891
bcb089eded
排查公网间歇 530 时发现的：
watchdog 日志显示「公网不通（HTTP 530，ha_connections=1）」
—— 出问题那段时间隧道**只剩 1 条连接**。
原来 watchdog 只把 CONNS == 0 算"零连接"，
CONNS == 1 不当回事。但实测**只剩一条连接时跨机房回源就会失败**
（请求落 SEA，隧道只剩 LAX 一条）。
改法：
* CONNS <= 1 都计入降级计数
* 公网不通 **且** 连接数已在危险区 = 确认的故障（不是短抖动）
-> 立刻重启，不等 3 次
每次检查间隔 20 秒，等 3 次就是白断 40 秒。现在能省下来。
实测：改完公网 15/15 = 100%，连接数 4 条。
顺带说明 watchdog 是怎么跑的：
systemd timer（lanremote-watchdog.timer），每 20 秒调一次
watchdog.service。之前查"服务是 inactive"一度以为它没在跑，
其实是 timer 触发型的 —— oneshot 服务跑完就是 inactive，正常。
67 lines
2.5 KiB
Bash
67 lines
2.5 KiB
Bash
#!/bin/bash
|
|
# 公网间歇 530 —— 查隧道当前真实状态
|
|
set -u
|
|
|
|
echo " relay=$(systemctl is-active lanremote-relay) tunnel=$(systemctl is-active lanremote-tunnel)"
|
|
echo " 隧道连接数: $(curl -s --max-time 5 http://127.0.0.1:20241/metrics 2>/dev/null | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}')"
|
|
|
|
echo
|
|
echo "════════ watchdog 最近 15 行 ════════"
|
|
tail -15 /root/lanremote-relay/watchdog.log 2>/dev/null | sed 's/^/ /'
|
|
|
|
echo
|
|
echo "════════ watchdog 怎么被调起来的 ════════"
|
|
echo " 服务: $(systemctl is-active lanremote-watchdog 2>&1)"
|
|
crontab -l 2>/dev/null | grep -i watch | sed 's/^/ cron: /'
|
|
systemctl list-timers --all 2>/dev/null | grep -i watch | sed 's/^/ timer: /'
|
|
|
|
echo
|
|
echo "════════ 隧道最近的重连频率（1500 行内）════════"
|
|
for kw in 'Registered tunnel connection' 'Lost connection' 'Retrying connection' 'i/o timeout' 'context deadline'; do
|
|
n=$(tail -1500 /root/lanremote-relay/tunnel.log 2>/dev/null | grep -c "$kw")
|
|
printf " %-34s %s 次\n" "$kw" "$n"
|
|
done
|
|
|
|
echo
|
|
echo "════════ 出口 IP 可达性 ════════"
|
|
python3 - <<'PY'
|
|
import socket, time
|
|
ips = ["198.41.192.107", "198.41.200.43", "198.41.192.77",
|
|
"198.41.200.113", "198.41.192.227", "198.41.200.193",
|
|
"198.41.192.37", "198.41.200.63"]
|
|
ok = 0
|
|
for ip in ips:
|
|
s = socket.socket(); s.settimeout(3)
|
|
t = time.perf_counter()
|
|
try:
|
|
s.connect((ip, 7844))
|
|
print(" %-16s %4.0f ms" % (ip, (time.perf_counter()-t)*1000)); ok += 1
|
|
except OSError:
|
|
print(" %-16s 不通" % ip)
|
|
finally:
|
|
s.close()
|
|
print(" => %d/%d 可达" % (ok, len(ips)))
|
|
PY
|
|
|
|
echo
|
|
echo "════════ 公网连打 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 $ok/12"
|
|
|
|
echo
|
|
echo "════════ 本机 relay（排除源站问题）════════"
|
|
for i in 1 2 3; do
|
|
printf " %d: HTTP %s\n" "$i" "$(curl -s -o /dev/null -w '%{http_code}' --max-time 8 http://127.0.0.1:8080/v1/health)"
|
|
done
|
|
|
|
echo
|
|
echo "════════ 网络质量 ════════"
|
|
ping -c 10 -W 2 1.1.1.1 2>/dev/null | tail -2 | sed 's/^/ /'
|