#!/bin/bash
# 端到端验证 watchdog 的"单实例掉线"识别（真改配置，跑完立刻还原）
set -u

H2=/etc/systemd/system/lanremote-tunnel-h2.service
BAK=/tmp/h2.bak.$(date +%s)
cp -a "$H2" "$BAK"

restore() {
    cp -a "$BAK" "$H2"
    systemctl daemon-reload
    systemctl restart lanremote-tunnel-h2
    rm -f "$BAK"
}
trap restore EXIT

echo "════════ 1. 把副实例的 --metrics 改成一个没人听的端口 ════════"
sed -i 's#--metrics 127.0.0.1:20242#--metrics 127.0.0.1:20299#' "$H2"
grep -oE '\-\-metrics [0-9.:]+' "$H2" | sed 's/^/  h2: /'
systemctl daemon-reload
systemctl restart lanremote-tunnel-h2
sleep 10

echo
echo "  现在实际监听:"
ss -tlnp 2>/dev/null | grep -E '2024[0-9]|20299' | sed 's/^/    /'

echo
echo "════════ 2. watchdog 预演（DRY_RUN=1，不会真重启）════════"
echo "  期望：认出 lanremote-tunnel-h2 无响应，**只**重启它"
DRY_RUN=1 bash /root/lanremote-relay/watchdog.sh 2>&1 | sed 's/^/    /'

echo
echo "════════ 3. 对照：不改配置时的预演（应该什么都不做）════════"
restore
sleep 20
echo "  实际监听:"
ss -tlnp 2>/dev/null | grep -E '2024[0-9]' | sed 's/^/    /'
echo "  预演:"
DRY_RUN=1 bash /root/lanremote-relay/watchdog.sh 2>&1 | sed 's/^/    /'
echo "  （没输出 = 正常，符合预期）"

echo
echo "════════ 4. 最终状态 ════════"
for p in $(pgrep cloudflared); do
    cg=$(cat /proc/$p/cgroup 2>/dev/null | head -1)
    svc=$(basename "$cg" 2>/dev/null | sed 's/\.service$//')
    port=$(ss -tlnp 2>/dev/null | grep "pid=$p" | grep -oE '2024[0-9]' | head -1)
    n=$(curl -s --max-time 4 "http://127.0.0.1:$port/metrics" 2>/dev/null | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}')
    echo "  $svc -> 端口 ${port:-?}  连接 ${n:-?}"
done