#!/bin/bash
# 查清 metrics 端口到底归哪个实例 —— 这是 watchdog 判定的基础，错不得。
set -u

echo "════════ 1. 两个服务的完整配置（找 --metrics）════════"
for svc in lanremote-tunnel lanremote-tunnel-h2; do
    echo "  ── $svc ──"
    systemctl cat "$svc" 2>/dev/null | grep -A10 'ExecStart=' | sed 's/^/    /'
    echo
done

echo "════════ 2. 进程和端口的实时对应 ════════"
for p in $(pgrep cloudflared); do
    cg=$(cat /proc/$p/cgroup 2>/dev/null | head -1)
    echo "  ── pid $p ──"
    echo "    服务: $(basename "$cg" 2>/dev/null)"
    echo "    命令行: $(tr '\0' ' ' < /proc/$p/cmdline 2>/dev/null | grep -oE '\-\-protocol [a-z0-9]+|\-\-metrics [^ ]+|\-\-ha-connections [0-9]+' | tr '\n' ' ')"
    echo "    监听的端口:"
    ss -tlnp 2>/dev/null | grep "pid=$p" | awk '{print "      " $4}' 
done

echo
echo "════════ 3. 每个端口报的实例特征 ════════"
for port in 20241 20242 20243; do
    body=$(curl -s --max-time 4 "http://127.0.0.1:$port/metrics" 2>/dev/null)
    if [ -z "$body" ]; then
        echo "  ── 端口 $port: 无响应 ──"
        continue
    fi
    conns=$(echo "$body" | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}')
    # 用协议特征区分：QUIC 实例的报告里会有 quic 相关指标
    quic=$(echo "$body" | grep -ci 'quic')
    echo "  ── 端口 $port: ha_connections=$conns  quic相关指标行数=$quic ──"
    echo "$body" | grep -E 'server_locations.*1$' | sed 's/^/      /'
done

echo
echo "════════ 4. 反复重启，看端口分配会不会变 ════════"
echo "  （这个很重要：watchdog 写死了 20241=主 20242=副，"
echo "    如果 cloudflared 是"谁先起谁拿 20241"，那这个假设就不成立）"
for round in 1 2 3; do
    echo "  ── 第 $round 轮：先重启 h2，再重启主 ──"
    systemctl restart lanremote-tunnel-h2
    sleep 8
    systemctl restart lanremote-tunnel
    sleep 12
    for p in $(pgrep cloudflared); do
        cg=$(cat /proc/$p/cgroup 2>/dev/null | head -1)
        svc=$(basename "$cg" 2>/dev/null)
        ports=$(ss -tlnp 2>/dev/null | grep "pid=$p" | awk '{print $4}' | tr '\n' ' ')
        echo "    $svc -> ${ports:-（没绑端口）}"
    done
done

echo
echo "════════ 5. 现在的状态 ════════"
ss -tlnp 2>/dev/null | grep -E '2024[0-9]' | sed 's/^/  /'