linux-BBR算法的bbr_update_ack_aggregation()函数理解

linux算法的bbr_update_ack_aggregation实现如下：

static void bbr_update_ack_aggregation(struct sock *sk,
				       const struct rate_sample *rs)
{
	u32 epoch_us, expected_acked, extra_acked;
	struct bbr *bbr = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 ||
	    rs->delivered < 0 || rs->interval_us <= 0)
		return;

	if (bbr->round_start) {
		bbr->extra_acked_win_rtts = min(0x1F,
						bbr->extra_acked_win_rtts + 1);
		if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) {
			bbr->extra_acked_win_rtts = 0;
			bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ?
						   0 : 1;
			bbr->extra_acked[bbr->extra_acked_win_idx] = 0;
		}
	}

	/* Compute how many packets we expected to be delivered over epoch. */
	epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp,
				      bbr->ack_epoch_mstamp);
	expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT;

	/* Reset the aggregation epoch if ACK rate is below expected rate or
	 * significantly large no. of ack received since epoch (potentially
	 * quite old epoch).
	 */
	if (bbr->ack_epoch_acked <= expected_acked ||
	    (bbr->ack_epoch_acked + rs->acked_sacked >=
	     bbr_ack_epoch_acked_reset_thresh)) {
		bbr->ack_epoch_acked = 0;
		bbr->ack_epoch_mstamp = tp->delivered_mstamp;
		expected_acked = 0;
	}

	/* Compute excess data delivered, beyond what was expected. */
	bbr->ack_epoch_acked = min_t(u32, 0xFFFFF,
				     bbr->ack_epoch_acked + rs->acked_sacked);
	extra_acked = bbr->ack_epoch_acked - expected_acked;
	extra_acked = min(extra_acked, tcp_snd_cwnd(tp));
	if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx])
		bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked;
}

其中最为关键的代码如下:

/* Compute how many packets we expected to be delivered over epoch. */
	epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp,
				      bbr->ack_epoch_mstamp);
	expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT;

	/* Reset the aggregation epoch if ACK rate is below expected rate or
	 * significantly large no. of ack received since epoch (potentially
	 * quite old epoch).
	 */
	if (bbr->ack_epoch_acked <= expected_acked ||
	    (bbr->ack_epoch_acked + rs->acked_sacked >=
	     bbr_ack_epoch_acked_reset_thresh)) {
		bbr->ack_epoch_acked = 0;
		bbr->ack_epoch_mstamp = tp->delivered_mstamp;
		expected_acked = 0;
	}

	/* Compute excess data delivered, beyond what was expected. */
	bbr->ack_epoch_acked = min_t(u32, 0xFFFFF,
				     bbr->ack_epoch_acked + rs->acked_sacked);
	extra_acked = bbr->ack_epoch_acked - expected_acked;
	extra_acked = min(extra_acked, tcp_snd_cwnd(tp));
	if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx])
		bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked;

这部分代码解决的问题是bbr失速的问题。

可以看到，在tcp trace图中，ack曲线一定是阶梯形的，就上图这种情况，红色曲线对应的jujiack到达之前，其实还有一段小的正常ack线，所以在interval开始计时阶段，是需要把这段小的垂直线对应的ack加上，这才是actual_acked。所以这对应于代码也就解释了问什么在计时开始后需要加上计时开始时的ack。其次是bbr->ack_epoch_acked里的值加上的都是超额ack的值，判断超额ack就是看之前interval收到的ack与之后interval收到的ack，这里假设interval相同，只有之前interval结束后收到的ack大于之后interval收到的ack，那么判断这个ack为超额ack，从而认定这个为超额ack的计算周期。