# -*- coding: utf-8 -*-
r'''修设备上的几个卡住的状态。

发现的问题：
  1. lanremote-tunnel（主隧道）inactive —— 只剩 h2 副本在跑，
     公网返回 530。这是网站"挂了"的直接原因。
  2. lanremote-nettune 卡在 activating —— 所以 MTU 还是 1400
     （而实测 1400 反而掉到 50%）。
  3. monitor.timer 没起来。

按顺序修，每步都验。
'''
from __future__ import annotations

import sys
from pathlib import Path

ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(ROOT / "_build"))
from devssh import run      # noqa: E402

STEPS = [
    ("1. 看 nettune 为什么卡住（它挡着 MTU）",
     "systemctl status lanremote-nettune --no-pager -n 12 2>&1 | tail -12; "
     "echo '--- 有没有残留的 iptables 进程 ---'; pgrep -a iptables || echo 无"),

    ("2. 把卡住的 nettune 停掉、直接跑一次 net-tune.sh",
     "systemctl stop lanremote-nettune 2>/dev/null; "
     "systemctl reset-failed lanremote-nettune 2>/dev/null; "
     "bash /root/lanremote-relay/net-tune.sh 2>&1 | tail -12; "
     "echo '--- 结果 ---'; "
     "echo \"MTU=$(cat /sys/class/net/wlan0/mtu)\"; "
     "echo \"MSS 规则=$(iptables -t mangle -L -n 2>/dev/null | grep -ci mss) 条\""),

    ("3. 拉起主隧道（网站 530 的直接原因）",
     "systemctl reset-failed lanremote-tunnel 2>/dev/null; "
     "systemctl restart lanremote-tunnel; sleep 12; "
     "systemctl is-active lanremote-tunnel; "
     "systemctl is-active lanremote-tunnel-h2"),

    ("4. 重启中转（让新的 admin.py 生效，后台才有「抢救报告」分区）",
     "systemctl restart lanremote-relay; sleep 4; "
     "systemctl is-active lanremote-relay"),

    ("5. 启用监测定时器",
     "systemctl enable lanremote-monitor.timer >/dev/null 2>&1; "
     "systemctl start lanremote-monitor.timer; sleep 3; "
     "systemctl is-active lanremote-monitor.timer"),

    ("6. 验证：公网通了没 / 隧道连接数 / 后台分区",
     "echo \"公网 /v1/health: $(curl -s -o /dev/null -w '%{http_code}' "
     "--max-time 20 https://relay.xxmxxs.top/v1/health)\"; "
     "echo \"公网首页:       $(curl -s -o /dev/null -w '%{http_code}' "
     "--max-time 20 https://relay.xxmxxs.top/)\"; "
     "for p in 20241 20242; do "
     "n=$(curl -s --max-time 5 http://127.0.0.1:$p/metrics 2>/dev/null "
     "| grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}' | head -1); "
     "echo \"  连接数($p): ${n:-拿不到}\"; done; "
     "echo \"后台「抢救报告」出现次数: "
     "$(curl -s --max-time 8 http://127.0.0.1:8080/zhongzhuanzhan "
     "| grep -c '抢救报告')\""),
]


def main() -> int:
    for title, cmd in STEPS:
        print()
        print("=" * 66)
        print("  " + title)
        print("=" * 66)
        try:
            out = run(cmd, timeout=180)
            text = out[1] if isinstance(out, tuple) else str(out)
        except Exception as exc:                          # noqa: BLE001
            text = "  [执行失败] %s: %s" % (type(exc).__name__, exc)
        for ln in text.strip().splitlines():
            print("  " + ln)
    return 0


if __name__ == "__main__":
    sys.exit(main())