#!/bin/bash
# 2 小时综合长测（task-3 第 1、3 项）。
#
# 同时测四件事，并且都带**时间戳**，这样才能回答
# "失败是不是集中在某个时段"（运营商时段性抖动）：
#
#   1. 公网可用率    每 15 秒一次 /v1/health，连续 2 小时
#   2. 长轮询成功率  30 次真实 poll（每次挂 60 秒），后台跑
#   3. 连接数波动    每 60 秒采样两个 metrics 端口
#   4. 重连/拨号失败 从两个 tunnel 日志的事件增量算
#
# 输出:
#   /root/long2h_health.tsv   时间戳 状态码 耗时ms
#   /root/long2h_poll.tsv     序号 状态码 耗时ms 起始时间
#   /root/long2h_conns.tsv    时间戳 quic连接 http2连接
#   /root/long2h_summary.txt  汇总
set -u

BASE=https://relay.xxmxxs.top
UA='LanRemote/1.8.2'
DUR=${1:-7200}          # 默认 2 小时
HEALTH_EVERY=15
CONN_EVERY=60
POLLS=30

H=/root/long2h_health.tsv
P=/root/long2h_poll.tsv
C=/root/long2h_conns.tsv
S=/root/long2h_summary.txt
MAINLOG=/root/lanremote-relay/tunnel.log
H2LOG=/root/lanremote-relay/tunnel-h2.log

rm -f "$H" "$P" "$C" "$S"

conns_of() {
    curl -s --max-time 4 "http://127.0.0.1:$1/metrics" 2>/dev/null \
        | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}'
}

# ---------- 后台任务 1：长轮询 ----------
poll_worker() {
    local stamp dev code reg token
    stamp=$(date +%s)
    dev="l2h-${stamp}"
    code=$(printf "%06d" $(( stamp % 1000000 )))
    reg=$(curl -s --max-time 30 -X POST "$BASE/v1/agent/register" \
          -H 'Content-Type: application/json' -H "User-Agent: $UA" \
          -d "{\"deviceId\":\"$dev\",\"code\":\"$code\",\"name\":\"l2h\",\"version\":\"1.8.2\"}")
    token=$(echo "$reg" | python3 -c "import sys,json; print(json.load(sys.stdin).get('token',''))" 2>/dev/null)
    if [ -z "$token" ]; then
        echo "0	0	0	REGFAIL" >> "$P"
        return
    fi
    local i
    for i in $(seq 1 "$POLLS"); do
        local t0 out c ms
        t0=$(date '+%H:%M:%S')
        out=$(curl -s -o /dev/null -w '%{http_code} %{time_total}' --max-time 130 \
              -X POST "$BASE/v1/agent/poll" -H "X-Token: $token" -H "User-Agent: $UA")
        c=$(echo "$out" | awk '{print $1}')
        ms=$(echo "$out" | awk '{printf "%d", $2*1000}')
        echo "$i	$c	$ms	$t0" >> "$P"
    done
    # 清理探针
    local key
    key=$(cat /root/lanremote-relay/data/admin_key.txt 2>/dev/null)
    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
}

poll_worker &
POLL_PID=$!

# ---------- 记录起始的日志行号，用于算增量 ----------
M0=$(wc -l < "$MAINLOG" 2>/dev/null || echo 0)
H0=$(wc -l < "$H2LOG" 2>/dev/null || echo 0)

T0=$(date +%s)
NEXT_CONN=$T0
echo "  开始: $(date '+%Y-%m-%d %H:%M:%S')  持续 ${DUR} 秒"

# ---------- 主循环：公网健康 ----------
while true; do
    NOW=$(date +%s)
    [ $((NOW - T0)) -ge "$DUR" ] && break

    out=$(curl -s -o /dev/null -w '%{http_code} %{time_total}' --max-time 25 \
          -H "User-Agent: $UA" "$BASE/v1/health")
    code=$(echo "$out" | awk '{print $1}')
    ms=$(echo "$out" | awk '{printf "%d", $2*1000}')
    echo "$(date '+%Y-%m-%d %H:%M:%S')	$code	$ms" >> "$H"

    # 连接数采样
    if [ "$NOW" -ge "$NEXT_CONN" ]; then
        a=$(conns_of 20241); b=$(conns_of 20242)
        echo "$(date '+%Y-%m-%d %H:%M:%S')	${a:-X}	${b:-X}" >> "$C"
        NEXT_CONN=$((NOW + CONN_EVERY))
    fi

    sleep "$HEALTH_EVERY"
done

wait "$POLL_PID" 2>/dev/null || true

# ---------- 汇总 ----------
T1=$(date +%s)
M1=$(wc -l < "$MAINLOG" 2>/dev/null || echo 0)
H1=$(wc -l < "$H2LOG" 2>/dev/null || echo 0)

{
    echo "================================================================"
    echo "  2 小时综合长测 · $(date '+%Y-%m-%d %H:%M:%S')"
    echo "  实际时长: $((T1 - T0)) 秒"
    echo "================================================================"
    echo

    echo "── 1. 公网可用率 ──"
    total=$(wc -l < "$H")
    ok=$(awk -F'\t' '$2=="200"' "$H" | wc -l)
    echo "  样本 $total 次，成功 $ok 次 = $((ok * 100 / (total > 0 ? total : 1)))%"
    echo "  各状态码分布:"
    awk -F'\t' '{print $2}' "$H" | sort | uniq -c | sort -rn | sed 's/^/    /'
    echo "  耗时分布（成功的）:"
    awk -F'\t' '$2=="200" {print $3}' "$H" | sort -n | awk '
        {a[NR]=$1}
        END {
            if (NR == 0) { print "    无数据"; exit }
            printf "    最小 %d  中位 %d  P90 %d  P99 %d  最大 %d ms\n",
                a[1], a[int(NR/2)+1], a[int(NR*0.9)+1], a[int(NR*0.99)+1], a[NR]
        }' | sed 's/^/  /'
    echo
    echo "  ★ 失败时刻（时间线，用来判断是不是集中在某时段）:"
    awk -F'\t' '$2!="200" {print "    " $1 "  码=" $2 "  耗时=" $3 "ms"}' "$H"
    echo

    echo "── 2. 长轮询成功率 ──"
    ptotal=$(grep -c . "$P" 2>/dev/null || echo 0)
    pok=$(awk -F'\t' '$2=="200"' "$P" 2>/dev/null | wc -l)
    echo "  $pok/$ptotal = $((pok * 100 / (ptotal > 0 ? ptotal : 1)))%"
    awk -F'\t' '$2=="200" {print $3}' "$P" | sort -n | awk '
        {a[NR]=$1}
        END {
            if (NR == 0) { print "    无数据"; exit }
            printf "    最小 %d  P50 %d  P90 %d  P99 %d  最大 %d ms（理想 ≈ 61000）\n",
                a[1], a[int(NR/2)+1], a[int(NR*0.9)+1], a[int(NR*0.99)+1], a[NR]
        }'
    echo "  失败的:"
    awk -F'\t' '$2!="200" {print "    #" $1 " 码=" $2 " 起始 " $4}' "$P"
    echo

    echo "── 3. 连接数波动 ──"
    echo "  quic 实例: 最小 $(awk -F'\t' 'NR>1{print $2}' "$C" | grep -E '^[0-9]+$' | sort -n | head -1)  最大 $(awk -F'\t' '{print $2}' "$C" | grep -E '^[0-9]+$' | sort -n | tail -1)"
    echo "  http2 实例: 最小 $(awk -F'\t' '{print $3}' "$C" | grep -E '^[0-9]+$' | sort -n | head -1)  最大 $(awk -F'\t' '{print $3}' "$C" | grep -E '^[0-9]+$' | sort -n | tail -1)"
    echo "  出现过的组合（次数）:"
    awk -F'\t' 'NR>1{print "quic="$2" http2="$3}' "$C" | sort | uniq -c | sort -rn | head -8 | sed 's/^/    /'
    echo

    echo "── 4. 隧道事件（本轮增量）──"
    echo "  QUIC 实例:"
    for kw in 'Registered tunnel connection' 'Failed to dial' 'Lost connection' 'i/o timeout'; do
        n=$(tail -n +$((M0 + 1)) "$MAINLOG" 2>/dev/null | grep -c "$kw")
        printf "    %-34s %s\n" "$kw" "$n"
    done
    echo "  HTTP/2 实例:"
    for kw in 'Registered tunnel connection' 'Failed to dial' 'Lost connection' 'i/o timeout'; do
        n=$(tail -n +$((H0 + 1)) "$H2LOG" 2>/dev/null | grep -c "$kw")
        printf "    %-34s %s\n" "$kw" "$n"
    done
    echo
    echo "  失败事件的时间线（QUIC）:"
    tail -n +$((M0 + 1)) "$MAINLOG" 2>/dev/null \
        | grep -E 'Failed to dial|Lost connection' | tail -20 \
        | sed -E 's/^(....-..-..T..:..):.*(Failed to dial|Lost connection).*/    \1 \2/' | sed 's/^/  /'
} > "$S" 2>&1

cat "$S"