#!/bin/bash
# quic+6 vs http2+4：用**真实长轮询**对照，方法完全一致。
#
# 为什么必须用长轮询测：
#   之前用 /v1/health 那种"每次新建连接"的方式测，
#   量到的是冷启动开销，和真实业务（复用连接的长轮询）差很多。
#   而且那种方式会看到 18 秒的尾巴 —— 长轮询完全没有。
#
# 为什么这次结果可信：
#   上一轮 A/B 里 quic 那组因为**两次探针用了同一个配对码**，
#   第二次注册被"一个码只能一台设备"规则拒掉，token 拿到空的，
#   8 次全 401 —— 那一轮数据作废。这次每个探针都用唯一的新码。
#
# 为什么值得测 QUIC：
#   刚才查出来：隧道连接 30 分钟 0 掉线、0 重连，很稳；
#   但请求级偶发 000（10 分钟 6 次）。
#   这是 HTTP/2 over TCP 的**队头阻塞** ——
#   一条 TCP 上丢一个包，那条连接上所有流一起卡。
#   QUIC 每个流独立恢复，理论上正好治这个。
set -u

PUB=https://relay.xxmxxs.top
UA='LanRemote/1.8.1'
SVC=/etc/systemd/system/lanremote-tunnel.service
BACKUP=/root/lanremote-tunnel.service.bak.q.$(date +%s)
cp -a "$SVC" "$BACKUP"
ROUNDS=${1:-10}

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
}

new_probe() {
    # 每次都用全新的 deviceId + 全新的配对码，避免被"一码一机"拒掉
    local stamp
    stamp=$(date +%s%N | cut -c1-13)
    local dev="qprobe-${stamp}"
    local code
    code=$(printf "%06d" $(( (stamp / 7) % 1000000 )))
    local reg
    reg=$(curl -s --max-time 30 -X POST "$PUB/v1/agent/register" \
          -H 'Content-Type: application/json' -H "User-Agent: $UA" \
          -d "{\"deviceId\":\"$dev\",\"code\":\"$code\",\"name\":\"qprobe\",\"version\":\"1.8.1\"}")
    local tok
    tok=$(echo "$reg" | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))" 2>/dev/null)
    PROBE_DEV="$dev"
    PROBE_TOK="$tok"
    PROBE_CODE="$code"
}

cleanup_probe() {
    local key
    key=$(cat /root/lanremote-relay/data/admin_key.txt 2>/dev/null)
    [ -n "${PROBE_DEV:-}" ] && curl -s --max-time 20 -X POST \
        "http://127.0.0.1:8080/v1/admin/delete" -H "X-Admin: $key" \
        -H 'Content-Type: application/json' \
        -d "{\"deviceId\":\"$PROBE_DEV\"}" > /dev/null 2>&1
}

run_round() {
    local label="$1" proto="$2" conns="$3"

    echo "════════ $label ════════"
    set_params "$proto" "$conns"
    if wait_ready "$conns"; then
        echo "  连接就绪（$(curl -s --max-time 4 http://127.0.0.1:20241/metrics 2>/dev/null | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}') 条）"
    else
        echo "  ! 连接没建齐，仍然继续测"
    fi
    echo "  落点:"
    curl -s --max-time 5 http://127.0.0.1:20241/metrics 2>/dev/null \
        | grep 'server_locations.*} 1' | sed 's/^/    /'
    sleep 15

    new_probe
    if [ -z "${PROBE_TOK:-}" ]; then
        echo "  [失败] 探针注册没拿到 token，这轮作废"
        echo "$label|REGFAIL|0|0|0" >> /tmp/qab.txt
        return 1
    fi
    echo "  探针 code=$PROBE_CODE token=${#PROBE_TOK} 字符"

    local mark
    mark=$(wc -l < /root/lanremote-relay/tunnel.log 2>/dev/null || echo 0)
    local ok=0 fail=0 times=() fails=""
    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: $PROBE_TOK" \
              -H "User-Agent: $UA")
        code=$(echo "$out" | awk '{print $1}')
        ms=$(echo "$out" | awk '{printf "%d", $2*1000}')
        if [ "$code" = "200" ]; then
            ok=$((ok+1)); times+=("$ms")
            printf "  %2d: 200  %6dms\n" "$i" "$ms"
        else
            fail=$((fail+1)); fails="$fails ${i}:${code}"
            printf "  %2d: %-4s **失败**\n" "$i" "$code"
        fi
    done

    local stats
    if [ "${#times[@]}" -gt 0 ]; then
        stats=$(printf '%s\n' "${times[@]}" | sort -n | awk '{a[NR]=$1} END {
            printf "中位 %d  P90 %d  最大 %d", a[int(NR/2)+1], a[int(NR*0.9)+1], a[NR]}')
    else
        stats="无数据"
    fi

    local reconn
    reconn=$(tail -n +$((mark+1)) /root/lanremote-relay/tunnel.log 2>/dev/null \
             | grep -c 'Registered tunnel connection' || echo 0)

    echo "  == $ok/$ROUNDS 成功   耗时: $stats ms   本轮重连 $reconn 次"
    echo "     失败:$fails"
    echo "$label|$ok|$ROUNDS|$((ok*100/ROUNDS))|$stats|$reconn" >> /tmp/qab.txt
    cleanup_probe
    echo
}

rm -f /tmp/qab.txt

# 先基线，再候选 —— 同一网络条件下先后测，尽量公平
run_round "http2+4" http2 4 || true
run_round "quic+6"  quic  6 || true

echo "════════ 汇总 ════════"
printf "  %-10s %-10s %-8s %-32s %s\n" "配置" "成功" "可用率" "耗时" "本轮重连"
while IFS='|' read -r label ok total pct stats reconn; do
    if [ "$ok" = "REGFAIL" ]; then
        printf "  %-10s 探针注册失败，作废\n" "$label"
    else
        printf "  %-10s %-10s %-8s %-32s %s\n" "$label" "$ok/$total" "${pct}%" "$stats" "$reconn"
    fi
done < /tmp/qab.txt

echo
echo "════════ 决策 ════════"
B_OK=$(grep '^http2+4' /tmp/qab.txt | cut -d'|' -f4)
Q_OK=$(grep '^quic+6' /tmp/qab.txt | cut -d'|' -f4)
B_REC=$(grep '^http2+4' /tmp/qab.txt | cut -d'|' -f6)
Q_REC=$(grep '^quic+6' /tmp/qab.txt | cut -d'|' -f6)
echo "  基线: 可用率 ${B_OK:-?}%  重连 ${B_REC:-?}"
echo "  候选: 可用率 ${Q_OK:-?}%  重连 ${Q_REC:-?}"
if [ "${Q_OK:-0}" -ge "${B_OK:-0}" ] && [ "${Q_OK:-0}" -ge 90 ]; then
    echo "  → 采用 quic+6"
else
    echo "  → 保留 http2+4"
    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 "  备份: $BACKUP"