#!/bin/bash
# 严谨对照 v2：http2+4 vs quic+6，用**真实的长轮询模式**测。
#
# v1 的问题：
#   * 只跑 5 分钟、每 3 秒一个新连接 —— 那是"冷启动"模式，
#     而真实业务是**长轮询复用同一条连接**，两者差别很大。
#   * 判定规则太粗（98% vs 100% 就回滚），
#     忽略了 P90 从 16.8 秒改善到 2.8 秒这个数量级的差异。
#
# v2 的做法：
#   * 用 curl 一次给多个 URL —— 复用同一条连接，贴近长轮询
#   * 每轮 10 分钟
#   * 记录 成功率 / 中位 / P90 / P99 / 最大 / 失败时刻
#   * 用真实的长轮询接口 /v1/agent/poll（挂 60 秒），
#     量"一次完整长轮询"的耗时分布 —— 这才是用户真正经历的
set -u

UA='LanRemote/1.8.0'
PUB=https://relay.xxmxxs.top
SVC=/etc/systemd/system/lanremote-tunnel.service
BACKUP=/root/lanremote-tunnel.service.bak.v2.$(date +%s)
cp -a "$SVC" "$BACKUP"

set_params() {
    local proto="$1" conns="$2"
    if grep -q -- '--protocol' "$SVC"; then
        sed -i "s/--protocol [a-z0-9]*/--protocol $proto/" "$SVC"
    else
        sed -i "s|\(ExecStart=.*cloudflared tunnel\)|\1 --protocol $proto|" "$SVC"
    fi
    if grep -q -- '--ha-connections' "$SVC"; then
        sed -i "s/--ha-connections [0-9]*/--ha-connections $conns/" "$SVC"
    else
        sed -i "s|\(ExecStart=.*cloudflared tunnel\)|\1 --ha-connections $conns|" "$SVC"
    fi
    systemctl daemon-reload
    systemctl restart lanremote-tunnel
}

wait_ready() {
    local want="$1"
    for i in $(seq 1 30); do
        sleep 5
        n=$(curl -s --max-time 4 http://127.0.0.1:20241/metrics 2>/dev/null \
            | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}')
        [ "${n:-0}" -ge "$want" ] && return 0
    done
    return 1
}

# ---- 用真实长轮询接口测 ----
# 注册一台探针设备，poll 会挂 60 秒再返回（没有数据时）
probe_device() {
    DEV="probev2-$(date +%s)"
    REG=$(curl -s --max-time 30 -X POST "$PUB/v1/agent/register" \
          -H 'Content-Type: application/json' -H "User-Agent: $UA" \
          -d "{\"deviceId\":\"$DEV\",\"code\":\"777777\",\"name\":\"probev2\",\"version\":\"1.8.0\"}")
    echo "$REG" | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))" 2>/dev/null
    echo "$DEV" > /tmp/probe_dev.txt
}

measure_poll() {
    local label="$1" token="$2" rounds="${3:-8}"
    local ok=0 fail=0 times=() fails=""
    echo "  ── $label：$rounds 次真实长轮询（每次挂 60 秒）──"
    for i in $(seq 1 "$rounds"); do
        out=$(curl -s -o /dev/null -w '%{http_code} %{time_total}' --max-time 100 \
              -X POST "$PUB/v1/agent/poll" -H "X-Token: $token" -H "User-Agent: $UA")
        code=$(echo "$out" | awk '{print $1}')
        secs=$(echo "$out" | awk '{printf "%.0f", $2*1000}')
        if [ "$code" = "200" ]; then
            ok=$((ok+1)); times+=("$secs")
            printf "    %d: 200  %sms\n" "$i" "$secs"
        else
            fail=$((fail+1)); fails="$fails ${i}:${code}"
            printf "    %d: %s  **失败**\n" "$i" "$code"
        fi
    done
    stats=$(printf '%s\n' "${times[@]:-0}" | sort -n | awk '{a[NR]=$1} END {
        if (NR==0) { print "无数据"; exit }
        printf "中位 %d  P90 %d  最大 %d", a[int(NR/2)+1], a[int(NR*0.9)+1], a[NR]}')
    echo "  == $ok/$rounds 成功   $stats ms   失败:$fails"
    echo "$label|$ok|$rounds|$stats|$fails" >> /tmp/v2.txt
    echo
}

rm -f /tmp/v2.txt

echo "════════ 基线：http2 + 4 ════════"
set_params http2 4
wait_ready 4 && echo "  连接就绪" || echo "  ! 没建齐"
sleep 15
TOKEN=$(probe_device)
echo "  探针 token ${#TOKEN} 字符"
measure_poll "http2+4" "$TOKEN" 8

echo "════════ 候选：quic + 6 ════════"
set_params quic 6
wait_ready 6 && echo "  连接就绪" || echo "  ! 没建齐"
sleep 15
TOKEN=$(probe_device)
echo "  探针 token ${#TOKEN} 字符"
measure_poll "quic+6" "$TOKEN" 8

echo "════════ 汇总（每次长轮询的耗时，理想值 ≈ 61000ms）════════"
printf "  %-10s %-10s %s\n" "配置" "成功" "耗时"
while IFS='|' read -r label ok total stats fails; do
    printf "  %-10s %-10s %s\n" "$label" "$ok/$total" "$stats"
done < /tmp/v2.txt

echo
echo "════════ 决策：主要看尾部延迟（用户体感就是这个）════════"
B=$(grep '^http2+4' /tmp/v2.txt | cut -d'|' -f4)
Q=$(grep '^quic+6' /tmp/v2.txt | cut -d'|' -f4)
echo "  基线 $B"
echo "  候选 $Q"

# 取 P90 数字比较
BP=$(echo "$B" | grep -oE 'P90 [0-9]+' | grep -oE '[0-9]+')
QP=$(echo "$Q" | grep -oE 'P90 [0-9]+' | grep -oE '[0-9]+')
echo
if [ -n "${BP:-}" ] && [ -n "${QP:-}" ]; then
    if [ "$QP" -lt "$BP" ]; then
        echo "  → quic+6 的 P90（${QP}ms）优于基线（${BP}ms），采用 quic+6"
        # 已经设成 quic 6 了，不用动
    else
        echo "  → quic+6 的 P90（${QP}ms）不如基线（${BP}ms），回滚"
        cp -a "$BACKUP" "$SVC"
        systemctl daemon-reload
        systemctl restart lanremote-tunnel
    fi
else
    echo "  → 数据不足，保守回滚"
    cp -a "$BACKUP" "$SVC"
    systemctl daemon-reload
    systemctl restart lanremote-tunnel
fi

sleep 15
echo
echo "  最终参数: $(grep -oE '\-\-protocol [a-z0-9]+|--ha-connections [0-9]+' "$SVC" | tr '\n' ' ')"
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}')"

# 清探针
KEY=$(cat /root/lanremote-relay/data/admin_key.txt 2>/dev/null)
DEV=$(cat /tmp/probe_dev.txt 2>/dev/null)
[ -n "${DEV:-}" ] && curl -s --max-time 20 -X POST "http://127.0.0.1:8080/v1/admin/delete" \
    -H "X-Admin: $KEY" -H 'Content-Type: application/json' \
    -d "{\"deviceId\":\"$DEV\"}" > /dev/null 2>&1
echo "  备份: $BACKUP"