brr 算法流程：
bbr算是一个完全独立的拥塞算法，具有自己的拥塞状态机．tcp_cong_control函数已经被bbr_main函数接管了
static void tcp_cong_control(struct sock *sk, u32 ack, u32 acked_sacked,
int flag, const struct rate_sample *rs)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
if (icsk->icsk_ca_ops->cong_control) {//bbr算法实现了cong_control回调函数
icsk->icsk_ca_ops->cong_control(sk, rs);
return;
}
----------------------
}
static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
.flags = TCP_CONG_NON_RESTRICTED,
.name = "bbr",
.owner = THIS_MODULE,
.init = bbr_init,
.cong_control = bbr_main,
.sndbuf_expand = bbr_sndbuf_expand,
.undo_cwnd = bbr_undo_cwnd,
.cwnd_event = bbr_cwnd_event,
.ssthresh = bbr_ssthresh,
.min_tso_segs = bbr_min_tso_segs,
.get_info = bbr_get_info,
.set_state = bbr_set_state,
};
/* Bottleneck Bandwidth and RTT (BBR) congestion control
*
* BBR congestion control computes the sending rate based on the delivery
* rate (throughput) estimated from ACKs. In a nutshell:
*
* On each ACK, update our model of the network path:
* bottleneck_bandwidth = windowed_max(delivered / elapsed, 10 round trips)
* min_rtt = windowed_min(rtt, 10 seconds)
* pacing_rate = pacing_gain * bottleneck_bandwidth
* cwnd = max(cwnd_gain * bottleneck_bandwidth * min_rtt, 4)
*
* The core algorithm does not react directly to packet losses or delays,
* although BBR may adjust the size of next send per ACK when loss is
* observed, or adjust the sending rate if it estimates there is a
* traffic policer, in order to keep the drop rate reasonable.
*
* Here is a state transition diagram for BBR:
*
* |
* V
* +---> STARTUP ----+
* | | |
* | V |
* | DRAIN ----+
* | | |
* | V |
* +---> PROBE_BW ----+
* | ^ | |
* | | | |
* | +----+ |
* | |
* +---- PROBE_RTT <--+
*
* A BBR flow starts in STARTUP, and ramps up its sending rate quickly.
* When it estimates the pipe is full, it enters DRAIN to drain the queue.
* In steady state a BBR flow only uses PROBE_BW and PROBE_RTT.
* A long-lived BBR flow spends the vast majority of its time remaining
* (repeatedly) in PROBE_BW, fully probing and utilizing the pipe's bandwidth
* in a fair manner, with a small, bounded queue. *If* a flow has been
* continuously sending for the entire min_rtt window, and hasn't seen an RTT
* sample that matches or decreases its min_rtt estimate for 10 seconds, then
* it briefly enters PROBE_RTT to cut inflight to a minimum value to re-probe
* the path's two-way propagation delay (min_rtt). When exiting PROBE_RTT, if
* we estimated that we reached the full bw of the pipe then we enter PROBE_BW;
* otherwise we enter STARTUP to try to fill the pipe.
*
* BBR is described in detail in:
* "BBR: Congestion-Based Congestion Control",
* Neal Cardwell, Yuchung Cheng, C. Stephen Gunn, Soheil Hassas Yeganeh,
* Van Jacobson. ACM Queue, Vol. 14 No. 5, September-October 2016.
*
* There is a public e-mail list for discussing BBR development and testing:
* https://groups.google.com/forum/#!forum/bbr-dev
*
* NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled,
* otherwise TCP stack falls back to an internal pacing using one high
* resolution timer per TCP socket and may use more resources.
*/
#include <linux/btf.h>
#include <linux/btf_ids.h>
#include <linux/module.h>
#include <net/tcp.h>
#include <linux/inet_diag.h>
#include <linux/inet.h>
#include <linux/random.h>
#include <linux/win_minmax.h>
/* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth
* estimation. The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps.
* This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32.
* Since the minimum window is >=4 packets, the lower bound isn't
* an issue. The upper bound isn't an issue with existing technologies.
*/
#define BW_SCALE 24
#define BW_UNIT (1 << BW_SCALE)
#define BBR_SCALE 8
/* 带宽和延迟的值从实际的微秒或字节单位缩放为一个固定的精度scaling factor for fractions in BBR (e.g. gains)
The rate unit ~= (1500 bytes / 1 usec / 2^24) ~= 715 bps.*/
#define BBR_UNIT (1 << BBR_SCALE)
/* BBR has the following modes for deciding how fast to send: */
enum bbr_mode {
BBR_STARTUP, /* ramp up sending rate rapidly to fill pipe */
BBR_DRAIN, /* drain any queue created during startup */
BBR_PROBE_BW, /* discover, share bw: pace around estimated bw */
BBR_PROBE_RTT, /* cut inflight to min to probe min_rtt */
};
/* BBR congestion control block */
struct bbr {
u32 min_rtt_us; /* min RTT in min_rtt_win_sec window 在 min_rtt_win_sec 窗口内观察到的最小往返时延（RTT)*/
u32 min_rtt_stamp; /* timestamp of min_rtt_us观察到最小RTT的时间戳 */
u32 probe_rtt_done_stamp; /* end time for BBR_PROBE_RTT mode BBR_PROBE_RTT模式结束的时间*/
struct minmax bw; /* Max recent delivery rate in pkts/uS << 24
用于跟踪最近的传输速率（以每微秒的数据包数为单位）的最大值*/
u32 rtt_cnt; /* count of packet-timed rounds elapsed 已经经历的基于数据包计时的轮数*/
u32 next_rtt_delivered; /* scb->tx.delivered at end of round 本轮结束时scb->tx.delivered的值*/
u64 cycle_mstamp; /* time of this cycle phase start 当前周期阶段开始的时间戳*/
u32 mode : 3, /* current bbr_mode in state machine */
prev_ca_state : 3, /* CA state on previous ACK 上一个ACK时的拥塞避免（CA）状态*/
packet_conservation : 1, /* use packet conservation? 是否使用数据包保护*/
round_start : 1, /* start of packet-timed tx->ack round? 数据包计时的传输确认（tx->ack）轮次的开始*/
idle_restart : 1, /* restarting after idle?是否在空闲期后重新开始 */
probe_rtt_round_done : 1, /* a BBR_PROBE_RTT round at 4 pkts? 是否完成了一个包含4个数据包的BBR_PROBE_RTT轮次*/
unused : 13,
lt_is_sampling : 1, /* taking long-term ("LT") samples now? */
lt_rtt_cnt : 7, /* round trips in long-term interval 长期间隔内的往返轮数*/
lt_use_bw : 1; /* use lt_bw as our bw estimate?是否使用lt_bw作为带宽估计值 */
//在BBR算法中，通过采集和跟踪一段时间内的传输速率数据，可以对网络链路的带宽进行估计。lt_bw就是这个长期间隔内的估计传输速率。
u32 lt_bw; /* LT est delivery rate in pkts/uS << 24 长期间隔内的估计传输速率*/
u32 lt_last_delivered; /* LT intvl start: tp->delivered长期间隔的开始：tp->delivered的值*/
u32 lt_last_stamp; /* LT intvl start: tp->delivered_mstamp 长期间隔的开始：tp->delivered_mstamp的值*/
u32 lt_last_lost; /* LT intvl start: tp->lost 长期间隔的开始：tp->lost的值*/
u32 pacing_gain : 10, /* current gain for setting pacing rate 调整速率的当前增益 */
cwnd_gain : 10, /* current gain for setting cwnd */
full_bw_reached : 1, /* reached full bw in Startup? 是否在启动阶段达到了满带宽*/
full_bw_cnt : 2, /* number of rounds without large bw gains 连续几轮没有较大带宽增益的次数*/
cycle_idx : 3, /* current index in pacing_gain cycle array 当前在pacing_gain循环数组中的索引*/
has_seen_rtt : 1, /* have we seen an RTT sample yet? 是否已经观察到了RTT样本*/
unused_b : 5;
u32 prior_cwnd; /* prior cwnd upon entering loss recovery 进入丢包恢复状态时的cwnd */
u32 full_bw; /* recent bw, to estimate if pipe is full 用于存储最近的带宽估计*/
/* For tracking ACK aggregation: */
u64 ack_epoch_mstamp; /* start of ACK sampling epoch ACK采样周期的开始时间戳*/
u16 extra_acked
[2]; /* max excess data ACKed in epoch 周期内最大的额外ACKed数据量 */
u32 ack_epoch_acked : 20, /* packets (S)ACKed in sampling epoch */
extra_acked_win_rtts : 5, /* age of extra_acked, in round trips */
extra_acked_win_idx : 1, /* current index in extra_acked array */
unused_c : 6;
};
#define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */
/* Window length of bw filter (in rounds): */
static const int bbr_bw_rtts = CYCLE_LEN + 2;
/* Window length of min_rtt filter (in sec): */
static const u32 bbr_min_rtt_win_sec = 10;
/* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */
static const u32 bbr_probe_rtt_mode_ms = 200;
/* Skip TSO below the following bandwidth (bits/sec): */
static const int bbr_min_tso_rate = 1200000;
/* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck.
* In order to help drive the network toward lower queues and low latency while
* maintaining high utilization, the average pacing rate aims to be slightly
* lower than the estimated bandwidth. This is an important aspect of the
* design.
*/
static const int bbr_pacing_margin_percent = 1;
/* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain
* that will allow a smoothly increasing pacing rate that will double each RTT
* and send the same number of packets per RTT that an un-paced, slow-starting
* Reno or CUBIC flow would:
*/
static const int bbr_high_gain = BBR_UNIT * 2885 / 1000 + 1;
/* The pacing gain of 1/high_gain in BBR_DRAIN is calculated to typically drain
* the queue created in BBR_STARTUP in a single round:
*/
static const int bbr_drain_gain = BBR_UNIT * 1000 / 2885;
/* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */
static const int bbr_cwnd_gain = BBR_UNIT * 2;
/* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */
static const int bbr_pacing_gain[] = {
BBR_UNIT * 5 / 4, /* probe for more available bw */
BBR_UNIT * 3 / 4, /* drain queue and/or yield bw to other flows */
BBR_UNIT, BBR_UNIT,
BBR_UNIT, /* cruise at 1.0*bw to utilize pipe, */
BBR_UNIT, BBR_UNIT,
BBR_UNIT /* without creating excess queue... */
};
/* Randomize the starting gain cycling phase over N phases: */
static const u32 bbr_cycle_rand = 7;
/* Try to keep at least this many packets in flight, if things go smoothly. For
* smooth functioning, a sliding window protocol ACKing every other packet
* needs at least 4 packets in flight:
*/
static const u32 bbr_cwnd_min_target = 4;
/* To estimate if BBR_STARTUP mode (i.e. high_gain) has filled pipe... */
/* If bw has increased significantly (1.25x), there may be more bw available: */
static const u32 bbr_full_bw_thresh = BBR_UNIT * 5 / 4;
/* But after 3 rounds w/o significant bw growth, estimate pipe is full: */
static const u32 bbr_full_bw_cnt = 3;
/* "long-term" ("LT") bandwidth estimator parameters... */
/* The minimum number of rounds in an LT bw sampling interval: */
static const u32 bbr_lt_intvl_min_rtts = 4;
/* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */
static const u32 bbr_lt_loss_thresh = 50;
/* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */
static const u32 bbr_lt_bw_ratio = BBR_UNIT / 8;
/* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */
static const u32 bbr_lt_bw_diff = 4000 / 8;
/* If we estimate we're policed, use lt_bw for this many round trips: */
static const u32 bbr_lt_bw_max_rtts = 48;
/* Gain factor for adding extra_acked to target cwnd: */
static const int bbr_extra_acked_gain = BBR_UNIT;
/* Window length of extra_acked window. */
static const u32 bbr_extra_acked_win_rtts = 5;
/* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */
static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20;
/* Time period for clamping cwnd increment due to ack aggregation */
static const u32 bbr_extra_acked_max_us = 100 * 1000;
static void bbr_check_probe_rtt_done(struct sock *sk);
/* Do we estimate that STARTUP filled the pipe? */
static bool bbr_full_bw_reached(const struct sock *sk)
{
const struct bbr *bbr = inet_csk_ca(sk);
return bbr->full_bw_reached;
}
/* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */
static u32 bbr_max_bw(const struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
return minmax_get(&bbr->bw);
}
/* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */
static u32 bbr_bw(const struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk);
}
/* Return maximum extra acked in past k-2k round trips,
* where k = bbr_extra_acked_win_rtts.
*/
static u16 bbr_extra_acked(const struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
return max(bbr->extra_acked[0], bbr->extra_acked[1]);
}
/* Return rate in bytes per second, optionally with a gain.
* The order here is chosen carefully to avoid overflow of u64. This should
* work for input rates of up to 2.9Tbit/sec and gain of 2.89x.
*/
static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
{
unsigned int mss = tcp_sk(sk)->mss_cache;
rate *= mss; //mss大小，byte
rate *= gain;
rate >>= BBR_SCALE; //右移8位,即除以2^8 256
//通过调整 "bbr_pacing_margin_percent" 的值，可以控制发送方在计算发送速率时预留的余地大小
rate *= USEC_PER_SEC / 100 * (100 - bbr_pacing_margin_percent);
return rate >> BW_SCALE; //右移24位
}
/* Convert a BBR bw and gain factor to a pacing rate in bytes per second. */
static unsigned long bbr_bw_to_pacing_rate(struct sock *sk, u32 bw, int gain)
{
u64 rate = bw;
rate = bbr_rate_bytes_per_sec(sk, rate, gain);
rate = min_t(u64, rate, sk->sk_max_pacing_rate);
return rate;
}
/* Initialize pacing rate to: high_gain * init_cwnd / RTT. */
static void bbr_init_pacing_rate_from_rtt(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u64 bw;
u32 rtt_us;
if (tp->srtt_us) { /* any RTT sample yet? */
rtt_us = max(tp->srtt_us >> 3, 1U);
bbr->has_seen_rtt = 1;
} else { /* no RTT sample yet */
rtt_us = USEC_PER_MSEC; /* use nominal default RTT */
}
bw = (u64)tcp_snd_cwnd(tp) * BW_UNIT;
do_div(bw, rtt_us);
sk->sk_pacing_rate = bbr_bw_to_pacing_rate(sk, bw, bbr_high_gain);
}
/* Pace using current bw estimate and a gain factor. */
static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
//通过bw算出pacing rate
unsigned long rate = bbr_bw_to_pacing_rate(sk, bw, gain);
//如果还没采样到rtt，并且之前有测过得到平滑的rtt，则尝试通过平滑的rtt来算pacing_rate,并更新到sk->sk_pacing_rate中
if (unlikely(!bbr->has_seen_rtt && tp->srtt_us))
bbr_init_pacing_rate_from_rtt(sk);
if (bbr_full_bw_reached(sk) || rate > sk->sk_pacing_rate)
sk->sk_pacing_rate = rate; //更新pacing rate
}
/* override sysctl_tcp_min_tso_segs */
__bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk)
{
return sk->sk_pacing_rate < (bbr_min_tso_rate >> 3) ? 1 : 2;
}
static u32 bbr_tso_segs_goal(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
u32 segs, bytes;
/* Sort of tcp_tso_autosize() but ignoring
* driver provided sk_gso_max_size.
*/
bytes = min_t(unsigned long,
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift),
GSO_LEGACY_MAX_SIZE - 1 - MAX_TCP_HEADER);
segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk));
return min(segs, 0x7FU);
}
/* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */
static void bbr_save_cwnd(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
if (bbr->prev_ca_state < TCP_CA_Recovery && bbr->mode != BBR_PROBE_RTT)
bbr->prior_cwnd =
tcp_snd_cwnd(tp); /* this cwnd is good enough */
else /* loss recovery or BBR_PROBE_RTT have temporarily cut cwnd */
bbr->prior_cwnd = max(bbr->prior_cwnd, tcp_snd_cwnd(tp));
}
__bpf_kfunc static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
if (event == CA_EVENT_TX_START && tp->app_limited) {
bbr->idle_restart = 1;
bbr->ack_epoch_mstamp = tp->tcp_mstamp;
bbr->ack_epoch_acked = 0;
/* Avoid pointless buffer overflows: pace at est. bw if we don't
* need more speed (we're restarting from idle and app-limited).
*/
if (bbr->mode == BBR_PROBE_BW)
bbr_set_pacing_rate(sk, bbr_bw(sk), BBR_UNIT);
else if (bbr->mode == BBR_PROBE_RTT)
bbr_check_probe_rtt_done(sk);
}
}
/* Calculate bdp based on min RTT and the estimated bottleneck bandwidth:
*
* bdp = ceil(bw * min_rtt * gain)
*
* The key factor, gain, controls the amount of queue. While a small gain
* builds a smaller queue, it becomes more vulnerable to noise in RTT
* measurements (e.g., delayed ACKs or other ACK compression effects). This
* noise may cause BBR to under-estimate the rate.
*/
static u32 bbr_bdp(struct sock *sk, u32 bw, int gain)
{
struct bbr *bbr = inet_csk_ca(sk);
u32 bdp;
u64 w;
/* If we've never had a valid RTT sample, cap cwnd at the initial
* default. This should only happen when the connection is not using TCP
* timestamps and has retransmitted all of the SYN/SYNACK/data packets
* ACKed so far. In this case, an RTO can cut cwnd to 1, in which
* case we need to slow-start up toward something safe: TCP_INIT_CWND.
*/
if (unlikely(bbr->min_rtt_us == ~0U)) /* no valid RTT samples yet? */
return TCP_INIT_CWND; /* be safe: cap at default initial cwnd*/
w = (u64)bw * bbr->min_rtt_us;
/* Apply a gain to the given value, remove the BW_SCALE shift, and
* round the value up to avoid a negative feedback loop.
*/
bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT;
return bdp;
}
/* To achieve full performance in high-speed paths, we budget enough cwnd to
* fit full-sized skbs in-flight on both end hosts to fully utilize the path:
* - one skb in sending host Qdisc,在发送端主机的 Qdisc（队列调度器）中，有一个 skb 在等待发送
* - one skb in sending host TSO/GSO engine在发送端主机的 TSO/GSO（TCP Segmentation Offload/Generic Segmentation Offload）引擎中，
* 有一个 skb 正在被分段为多个网络包
* - one skb being received by receiver host LRO/GRO/delayed-ACK engine
* 在接收端主机的 LRO/GRO（Large Receive Offload/Generic Receive Offload）或者延迟确认引擎中，有一个 skb 正在被接收和处理
* Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because
* in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets,
* which allows 2 outstanding 2-packet sequences, to try to keep pipe
* full even with ACK-every-other-packet delayed ACKs.
*/
static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd)
{
struct bbr *bbr = inet_csk_ca(sk);
/* Allow enough full-sized skbs in flight to utilize end systems. */
cwnd += 3 * bbr_tso_segs_goal(sk);
/* Reduce delayed ACKs by rounding up cwnd to the next even number. */
cwnd = (cwnd + 1) & ~1U;
/* Ensure gain cycling gets inflight above BDP even for small BDPs. */
if (bbr->mode == BBR_PROBE_BW && bbr->cycle_idx == 0)
cwnd += 2;
return cwnd;
}
/* Find inflight based on min RTT and the estimated bottleneck bandwidth. */
static u32 bbr_inflight(struct sock *sk, u32 bw, int gain)
{
u32 inflight;
inflight = bbr_bdp(sk, bw, gain); //通过rtt和bw算出bdp
//在一些高速场景(tso)下需要补偿一点
inflight = bbr_quantization_budget(sk, inflight);
return inflight;
}
/* With pacing at lower layers, there's often less data "in the network" than
* "in flight". With TSQ and departure time pacing at lower layers (e.g. fq),
* we often have several skbs queued in the pacing layer with a pre-scheduled
* earliest departure time (EDT). BBR adapts its pacing rate based on the
* inflight level that it estimates has already been "baked in" by previous
* departure time decisions. We calculate a rough estimate of the number of our
* packets that might be in the network at the earliest departure time for the
* next skb scheduled:
* in_network_at_edt = inflight_at_edt - (EDT - now) * bw
* If we're increasing inflight, then we want to know if the transmit of the
* EDT skb will push inflight above the target, so inflight_at_edt includes
* bbr_tso_segs_goal() from the skb departing at EDT. If decreasing inflight,
* then estimate if inflight will sink too low just before the EDT transmit.
*/
static u32 bbr_packets_in_net_at_edt(struct sock *sk, u32 inflight_now)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u64 now_ns, edt_ns, interval_us;
u32 interval_delivered, inflight_at_edt;
now_ns = tp->tcp_clock_cache;
edt_ns = max(tp->tcp_wstamp_ns, now_ns);
interval_us = div_u64(edt_ns - now_ns, NSEC_PER_USEC);
interval_delivered = (u64)bbr_bw(sk) * interval_us >> BW_SCALE;
inflight_at_edt = inflight_now;
if (bbr->pacing_gain > BBR_UNIT) /* increasing inflight */
inflight_at_edt += bbr_tso_segs_goal(sk); /* include EDT skb */
if (interval_delivered >= inflight_at_edt)
return 0;
return inflight_at_edt - interval_delivered;
}
/* Find the cwnd increment based on estimate of ack aggregation */
static u32 bbr_ack_aggregation_cwnd(struct sock *sk)
{
u32 max_aggr_cwnd, aggr_cwnd = 0;
if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) {
max_aggr_cwnd =
((u64)bbr_bw(sk) * bbr_extra_acked_max_us) / BW_UNIT;
aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk)) >>
BBR_SCALE;
aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd);
}
return aggr_cwnd;
}
/* An optimization in BBR to reduce losses: On the first round of recovery, we
* follow the packet conservation principle: send P packets per P packets acked.
* After that, we slow-start and send at most 2*P packets per P packets acked.
* After recovery finishes, or upon undo, we restore the cwnd we had when
* recovery started (capped by the target cwnd based on estimated BDP).
*
* TODO(ycheng/ncardwell): implement a rate-based approach.
*/
static bool bbr_set_cwnd_to_recover_or_restore(struct sock *sk,
const struct rate_sample *rs,
u32 acked, u32 *new_cwnd)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u8 prev_state = bbr->prev_ca_state, state = inet_csk(sk)->icsk_ca_state;
u32 cwnd = tcp_snd_cwnd(tp);
/* An ACK for P pkts should release at most 2*P packets. We do this
* in two steps. First, here we deduct the number of lost packets.
* Then, in bbr_set_cwnd() we slow start up toward the target cwnd.
*/
if (rs->losses > 0)
cwnd = max_t(s32, cwnd - rs->losses, 1);
if (state == TCP_CA_Recovery && prev_state != TCP_CA_Recovery) {
/* Starting 1st round of Recovery, so do packet conservation. */
bbr->packet_conservation = 1;
bbr->next_rtt_delivered = tp->delivered; /* start round now */
/* Cut unused cwnd from app behavior, TSQ, or TSO deferral: */
cwnd = tcp_packets_in_flight(tp) + acked;
} else if (prev_state >= TCP_CA_Recovery && state < TCP_CA_Recovery) {
/* Exiting loss recovery; restore cwnd saved before recovery. */
cwnd = max(cwnd, bbr->prior_cwnd);
bbr->packet_conservation = 0;
}
bbr->prev_ca_state = state;
if (bbr->packet_conservation) {
*new_cwnd = max(cwnd, tcp_packets_in_flight(tp) + acked);
return true; /* yes, using packet conservation */
}
*new_cwnd = cwnd;
return false;
}
/* Slow-start up toward target cwnd (if bw estimate is growing, or packet loss
* has drawn us down below target), or snap down to target if we're above it.
*/
static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs,
u32 acked, u32 bw, int gain)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u32 cwnd = tcp_snd_cwnd(tp), target_cwnd = 0;
//若当前的ack没有acked任何包，则跳过
if (!acked)
goto done; /* no packet fully ACKed; just apply caps */
//在外部拥塞控制状态为recovery或丢包等外部参数给进来判断，控制拥塞窗口大小
if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd))
goto done;
//目标拥塞窗口大小为bdp
target_cwnd = bbr_bdp(sk, bw, gain);
/* Increment the cwnd to account for excess ACKed data that seems
* due to aggregation (of data and/or ACKs) visible in the ACK stream.
*/
//加上补偿
target_cwnd += bbr_ack_aggregation_cwnd(sk);
target_cwnd = bbr_quantization_budget(sk, target_cwnd);
/* If we're below target cwnd, slow start cwnd toward target cwnd.
若小于target,则slow start */
if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */
cwnd = min(cwnd + acked, target_cwnd);
//若当前拥塞窗口小于目标拥塞窗口或已成功传递的数量小于10，则用当前拥塞窗口+acked
else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND)
cwnd = cwnd + acked;
cwnd = max(cwnd, bbr_cwnd_min_target); //后者为4，至少为4
done:
tcp_snd_cwnd_set(tp,
min(cwnd, tp->snd_cwnd_clamp)); /* apply global cap */
if (bbr->mode == BBR_PROBE_RTT) /* drain queue, refresh min_rtt */
//此时在探测最小rtt,应该减小窗口值，<=4,因为要探测最小rtt,发送不能过快
tcp_snd_cwnd_set(tp,
min(tcp_snd_cwnd(tp), bbr_cwnd_min_target));
}
/* End cycle phase if it's time and/or we hit the phase's in-flight target. */
static bool bbr_is_next_cycle_phase(struct sock *sk,
const struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
bool is_full_length =
tcp_stamp_us_delta(tp->delivered_mstamp, bbr->cycle_mstamp) >
bbr->min_rtt_us;
u32 inflight, bw;
/* The pacing_gain of 1.0 paces at the estimated bw to try to fully
* use the pipe without increasing the queue.
*/
if (bbr->pacing_gain == BBR_UNIT)
return is_full_length; /* just use wall clock time */
inflight = bbr_packets_in_net_at_edt(sk, rs->prior_in_flight);
bw = bbr_max_bw(sk);
/* A pacing_gain > 1.0 probes for bw by trying to raise inflight to at
* least pacing_gain*BDP; this may take more than min_rtt if min_rtt is
* small (e.g. on a LAN). We do not persist if packets are lost, since
* a path with small buffers may not hold that much.
*/
if (bbr->pacing_gain > BBR_UNIT)
return is_full_length &&
(rs->losses || /* perhaps pacing_gain*BDP won't fit */
inflight >= bbr_inflight(sk, bw, bbr->pacing_gain));
/* A pacing_gain < 1.0 tries to drain extra queue we added if bw
* probing didn't find more bw. If inflight falls to match BDP then we
* estimate queue is drained; persisting would underutilize the pipe.
*/
return is_full_length || inflight <= bbr_inflight(sk, bw, BBR_UNIT);
}
static void bbr_advance_cycle_phase(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
//下一阶段增益表对应index
bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1);
bbr->cycle_mstamp = tp->delivered_mstamp; //当前阶段开始的时间戳
}
/* Gain cycling: cycle pacing gain to converge to fair share of available bw. */
static void bbr_update_cycle_phase(struct sock *sk,
const struct rate_sample *rs)
{
struct bbr *bbr = inet_csk_ca(sk);
//当前处于 ProbeBW状态时且到时间切换到下个增益，会去更新cycle_idx。
if (bbr->mode == BBR_PROBE_BW && bbr_is_next_cycle_phase(sk, rs))
bbr_advance_cycle_phase(sk);
}
static void bbr_reset_startup_mode(struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
bbr->mode = BBR_STARTUP;
}
static void bbr_reset_probe_bw_mode(struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
bbr->mode = BBR_PROBE_BW;
bbr->cycle_idx = CYCLE_LEN - 1 - get_random_u32_below(bbr_cycle_rand);
bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */
}
static void bbr_reset_mode(struct sock *sk)
{
if (!bbr_full_bw_reached(sk))
bbr_reset_startup_mode(sk);
else
bbr_reset_probe_bw_mode(sk);
}
/* Start a new long-term sampling interval. */
static void bbr_reset_lt_bw_sampling_interval(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
bbr->lt_last_stamp = div_u64(tp->delivered_mstamp, USEC_PER_MSEC);
bbr->lt_last_delivered = tp->delivered;
bbr->lt_last_lost = tp->lost;
bbr->lt_rtt_cnt = 0;
}
/* Completely reset long-term bandwidth sampling. */
static void bbr_reset_lt_bw_sampling(struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
bbr->lt_bw = 0;
bbr->lt_use_bw = 0;
bbr->lt_is_sampling = false;
bbr_reset_lt_bw_sampling_interval(sk);
}
/* Long-term bw sampling interval is done. Estimate whether we're policed. */
static void bbr_lt_bw_interval_done(struct sock *sk, u32 bw)
{
struct bbr *bbr = inet_csk_ca(sk);
u32 diff;
if (bbr->lt_bw) { /* do we have bw from a previous interval? */
/* Is new bw close to the lt_bw from the previous interval? */
diff = abs(bw - bbr->lt_bw);
if ((diff * BBR_UNIT <= bbr_lt_bw_ratio * bbr->lt_bw) ||
(bbr_rate_bytes_per_sec(sk, diff, BBR_UNIT) <=
bbr_lt_bw_diff)) {
/* All criteria are met; estimate we're policed. */
bbr->lt_bw = (bw + bbr->lt_bw) >> 1; /* avg 2 intvls */
bbr->lt_use_bw = 1;
bbr->pacing_gain = BBR_UNIT; /* try to avoid drops */
bbr->lt_rtt_cnt = 0;
return;
}
}
bbr->lt_bw = bw;
bbr_reset_lt_bw_sampling_interval(sk);
}
/* Token-bucket traffic policers are common (see "An Internet-Wide Analysis of
* Traffic Policing", SIGCOMM 2016). BBR detects token-bucket policers and
* explicitly models their policed rate, to reduce unnecessary losses. We
* estimate that we're policed if we see 2 consecutive sampling intervals with
* consistent throughput and high packet loss. If we think we're being policed,
* set lt_bw to the "long-term" average delivery rate from those 2 intervals.
*/
static void bbr_lt_bw_sampling(struct sock *sk, const struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u32 lost, delivered;
u64 bw;
u32 t;
if (bbr->lt_use_bw) { /* already using long-term rate, lt_bw? */
if (bbr->mode == BBR_PROBE_BW && bbr->round_start &&
++bbr->lt_rtt_cnt >= bbr_lt_bw_max_rtts) {
bbr_reset_lt_bw_sampling(sk); /* stop using lt_bw */
bbr_reset_probe_bw_mode(sk); /* restart gain cycling */
}
return;
}
/* Wait for the first loss before sampling, to let the policer exhaust
* its tokens and estimate the steady-state rate allowed by the policer.
* Starting samples earlier includes bursts that over-estimate the bw.
*/
if (!bbr->lt_is_sampling) {
if (!rs->losses)
return;
bbr_reset_lt_bw_sampling_interval(sk);
bbr->lt_is_sampling = true;
}
/* To avoid underestimates, reset sampling if we run out of data. */
if (rs->is_app_limited) {
bbr_reset_lt_bw_sampling(sk);
return;
}
if (bbr->round_start)
bbr->lt_rtt_cnt++; /* count round trips in this interval */
if (bbr->lt_rtt_cnt < bbr_lt_intvl_min_rtts)
return; /* sampling interval needs to be longer */
if (bbr->lt_rtt_cnt > 4 * bbr_lt_intvl_min_rtts) {
bbr_reset_lt_bw_sampling(sk); /* interval is too long */
return;
}
/* End sampling interval when a packet is lost, so we estimate the
* policer tokens were exhausted. Stopping the sampling before the
* tokens are exhausted under-estimates the policed rate.
*/
if (!rs->losses)
return;
/* Calculate packets lost and delivered in sampling interval. */
lost = tp->lost - bbr->lt_last_lost;
delivered = tp->delivered - bbr->lt_last_delivered;
/* Is loss rate (lost/delivered) >= lt_loss_thresh? If not, wait. */
if (!delivered || (lost << BBR_SCALE) < bbr_lt_loss_thresh * delivered)
return;
/* Find average delivery rate in this sampling interval. */
t = div_u64(tp->delivered_mstamp, USEC_PER_MSEC) - bbr->lt_last_stamp;
if ((s32)t < 1)
return; /* interval is less than one ms, so wait */
/* Check if can multiply without overflow */
if (t >= ~0U / USEC_PER_MSEC) {
bbr_reset_lt_bw_sampling(sk); /* interval too long; reset */
return;
}
t *= USEC_PER_MSEC;
bw = (u64)delivered * BW_UNIT;
do_div(bw, t);
bbr_lt_bw_interval_done(sk, bw);
}
/* Estimate the bandwidth based on how fast packets are delivered */
static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u64 bw;
bbr->round_start = 0;
if (rs->delivered < 0 || rs->interval_us <= 0)
return; /* Not a valid observation */
/* See if we've reached the next RTT
判断是否达到下一个RTT */
if (!before(rs->prior_delivered, bbr->next_rtt_delivered)) {
bbr->next_rtt_delivered = tp->delivered;
bbr->rtt_cnt++;
bbr->round_start = 1;
bbr->packet_conservation = 0;
}
bbr_lt_bw_sampling(sk, rs);
/* Divide delivered by the interval to find a (lower bound) bottleneck
* bandwidth sample. Delivered is in packets and interval_us in uS and
* ratio will be <<1 for most connections. So delivered is first scaled.
* 将rs->delivered乘以BW_UNIT，然后除以rs->interval_us，计算出一个（下界）瓶颈带宽样本
* 前面是算出每us的包数,这里乘以一个系数2^24,后面要除去
* Scale factor for rate in pkt/uSec unit to avoid truncation in bandwidth pkt/uSec 单位中速率的比例因子，以避免带宽截断估计。
* //即 1500*8 * 1000000(1s=1000000us) / 2^24 ~= 715bps,
* 1500为一个mtu,这里算的是一个速率单位，即通过每us的包数，转换为每s的bit数 再/ 2^24
* This handles bandwidths from 0.06pps (715bps) to 256Mpps (3Tbps) in a u32.//若0.06表示715，则可以存储更多值
* Since the minimum window is >=4 packets, the lower bound isn't
* an issue. The upper bound isn't an issue with existing technologies.//因为最小窗口>=4,所以下限不是问题。
*/
bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us);
/* If this sample is application-limited, it is likely to have a very
* low delivered count that represents application behavior rather than
* the available network rate. Such a sample could drag down estimated
* bw, causing needless slow-down. Thus, to continue to send at the
* last measured network rate, we filter out app-limited samples unless
* they describe the path bw at least as well as our bw model.
*
* So the goal during app-limited phase is to proceed with the best
* network rate no matter how long. We automatically leave this
* phase when app writes faster than the network can deliver :)
* 如果样本不是应用程序限制的，或者样本的带宽值大于等于当前的最大带宽（由bbr_max_bw函数返回），
* 则将该样本纳入最大带宽滤波器中，使用minmax_running_max函数更新最大带宽的值。
*/
if (!rs->is_app_limited || bw >= bbr_max_bw(sk)) {
/* Incorporate new sample into our max bw filter. */
minmax_running_max(&bbr->bw, bbr_bw_rtts, bbr->rtt_cnt, bw);
}
}
/* Estimates the windowed max degree of ack aggregation.-->估计 ack 聚合的窗口最大程度
* This is used to provision extra in-flight data to keep sending during inter-ACK silences.
*
* Degree of ack aggregation is estimated as extra data acked beyond expected.
*
* max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval"
* cwnd += max_extra_acked
*
* Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms).
* Max filter is an approximate sliding window of 5-10 (packet timed) round
* trips.
* 某种情况下会有大量ack延迟到达，而在延迟之前，cwnd被递减
发送减缓，等到这些突发的ack聚集到达时，需要快速恢复，这里会出现一个
带宽缺口，所以bbr从cwnd递减时机 和快速恢复两点，对带宽进行补偿
rfc: 4.5.5. BBR.extra_acked
*/
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) { //rtt周期计算最开始
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; //根据发送得到预期接收的ack
/* Reset the aggregation epoch if ACK rate is below expected rate or
* significantly large no. of ack received since epoch (potentially
* quite old epoch).
*///ack没超过预期，置位0
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; //算出超过预期的ack数量
extra_acked =
min(extra_acked, tcp_snd_cwnd(tp)); //和拥塞窗口比较取最小值
if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx])
bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked;
//这个在后面算cwnd时，会用到： target_cwnd += bbr_ack_aggregation_cwnd(sk);
}
/* Estimate when the pipe is full, using the change in delivery rate: BBR
* estimates that STARTUP filled the pipe if the estimated bw hasn't changed by
* at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited
* rounds. Why 3 rounds: 1: rwin autotuning grows the rwin, 2: we fill the
* higher rwin, 3: we get higher delivery rate samples. Or transient
* cross-traffic or radio noise can go away. CUBIC Hystart shares a similar
* design goal, but uses delay and inter-ACK spacing instead of bandwidth.
* 使用delivery rate的变化来估计管道何时充满
* 如果在 bbr_full_bw_cnt (3次) 非应用程序限制轮次之后估计的 bw 没有改变至少 bbr_full_bw_thresh (25%)，
则估计 STARTUP 填充了管道。 为什么要进行 3 轮：
1：rwin 自动调整使 rwin 增长，
2：我们填充更高的 rwin，
3：我们获得更高的delivery rate样本。 或者瞬态交叉流量或无线电噪声可以消失。
3次相当于给恢复的机会，或容错成本
CUBIC Hystart 具有类似的设计目标，但使用延迟和 ACK 间间隔而不是带宽。
*/
static void bbr_check_full_bw_reached(struct sock *sk,
const struct rate_sample *rs)
{
struct bbr *bbr = inet_csk_ca(sk);
u32 bw_thresh;
//如果已经达到full bw( /* reached full bw in Startup? */)
//或者round 还没开始当前在app发送没充分利用信道带宽的情况下，直接返回
if (bbr_full_bw_reached(sk) || !bbr->round_start || rs->is_app_limited)
return;
//注意这里用1.25倍上次的最大值
bw_thresh = (u64)bbr->full_bw * bbr_full_bw_thresh >> BBR_SCALE;
if (bbr_max_bw(sk) >=
bw_thresh) { //max算出来的比上次的大25%，说明还在增长。
bbr->full_bw = bbr_max_bw(sk);
bbr->full_bw_cnt = 0;
return;
}
++bbr->full_bw_cnt; //否则累计，三次不增长则说明到最大值了。
bbr->full_bw_reached = bbr->full_bw_cnt >=
bbr_full_bw_cnt; //达到三次认为是达到最大值
}
/* If pipe is probably full, drain the queue and then enter steady-state. */
static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs)
{
struct bbr *bbr = inet_csk_ca(sk);
//如果达到full bw,则进入drain
if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) {
bbr->mode = BBR_DRAIN; /* drain queue we created */
tcp_sk(sk)->snd_ssthresh =
bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT);
} /* fall through to check if in-flight is already small: */
/* from rfc:
在 Drain 中，当传输中的数据量小于或等于估计的 BDP 时，意味着 BBR 估计队列已经完全排空，然后 BBR 退出 Drain 并进入 ProbeBW。
为了实现这一点，在每个 ACK BBR 执行时：
BBRCheckDrain():
if (BBR.state == Drain and packets_in_flight <= BBRInflight(1.0))
BBREnterProbeBW() /* BBR estimates the queue was drained */
* / if (bbr->mode == BBR_DRAIN &&
bbr_packets_in_net_at_edt(sk,
tcp_packets_in_flight(tcp_sk(sk))) <=
bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT))
bbr_reset_probe_bw_mode(sk);
/* we estimate queue is drained 满足条件进入到PROBE_BW状态*/
}
static void bbr_check_probe_rtt_done(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
if (!(bbr->probe_rtt_done_stamp &&
after(tcp_jiffies32, bbr->probe_rtt_done_stamp)))
return;
bbr->min_rtt_stamp = tcp_jiffies32; /* wait a while until PROBE_RTT */
tcp_snd_cwnd_set(tp, max(tcp_snd_cwnd(tp), bbr->prior_cwnd));
//重置回startUp或Probebw状态
bbr_reset_mode(sk);
}
/* The goal of PROBE_RTT mode is to have BBR flows cooperatively and
* periodically drain the bottleneck queue, to converge to measure the true
* min_rtt (unloaded propagation delay). This allows the flows to keep queues
* small (reducing queuing delay and packet loss) and achieve fairness among
* BBR flows.
*
* The min_rtt filter window is 10 seconds. When the min_rtt estimate expires,
* we enter PROBE_RTT mode and cap the cwnd at bbr_cwnd_min_target=4 packets.
* After at least bbr_probe_rtt_mode_ms=200ms and at least one packet-timed
* round trip elapsed with that flight size <= 4, we leave PROBE_RTT mode and
* re-enter the previous mode. BBR uses 200ms to approximately bound the
* performance penalty of PROBE_RTT's cwnd capping to roughly 2% (200ms/10s).
*
* Note that flows need only pay 2% if they are busy sending over the last 10
* seconds. Interactive applications (e.g., Web, RPCs, video chunks) often have
* natural silences or low-rate periods within 10 seconds where the rate is low
* enough for long enough to drain its queue in the bottleneck. We pick up
* these min RTT measurements opportunistically with our min_rtt filter. :-)
* PROBE_RTT 模式的目标是让 BBR 流协同并定期排空瓶颈队列，以收敛以测量真正的 min_rtt。
这允许流保持较小的队列（减少排队延迟和丢包）并实现 BBR 流之间的公平。
min_rtt 过滤器窗口为 10 秒。当 min_rtt 估计过期时，我们进入 PROBE_RTT 模式并将 cwnd 限制在 bbr_cwnd_min_target=4 个数据包
至少 bbr_probe_rtt_mode_ms=200ms 和至少一个数据包定时后,该空中包数大小 <= 4 的往返已过去，
我们离开 PROBE_RTT 模式并重新进入先前的模式。 BBR 使用 200 毫秒将 PROBE_RTT 的 cwnd 上限的性能损失大致限制在大约 2%（200 毫秒/10 秒）。
请注意，如果流在过去 10 秒内忙于发送，则只需支付 2%。交互式应用程序（例如，Web、RPC、视频块）通常在 10 秒内具有自然静默或低速率周期，
其中速率足够低，足以耗尽瓶颈中的队列。我们使用我们的 min_rtt 过滤器机会性地获取这些最小 RTT 测量值。
*/
static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
bool filter_expired;
/* Track min RTT seen in the min_rtt_win_sec filter window: bbr_min_rtt_win_sec是10s*/
filter_expired = after(tcp_jiffies32,
bbr->min_rtt_stamp + bbr_min_rtt_win_sec * HZ);
if (rs->rtt_us >= 0 && (rs->rtt_us < bbr->min_rtt_us ||
(filter_expired && !rs->is_ack_delayed))) {
//更新最小rtt，rtt通过参数代入进来
bbr->min_rtt_us = rs->rtt_us;
bbr->min_rtt_stamp = tcp_jiffies32;
}
if (bbr_probe_rtt_mode_ms > 0 && filter_expired && !bbr->idle_restart &&
bbr->mode != BBR_PROBE_RTT) {
/* dip, drain queue 进入rtt探测阶段 */
bbr->mode = BBR_PROBE_RTT;
bbr_save_cwnd(sk); /* note cwnd so we can restore it */
bbr->probe_rtt_done_stamp = 0;
}
//尝试退出这个状态
if (bbr->mode == BBR_PROBE_RTT) {
/* Ignore low rate samples during this mode. */
tp->app_limited = (tp->delivered + tcp_packets_in_flight(tp)) ?:
1;
/* Maintain min packets in flight for max(200 ms, 1 round). */
if (!bbr->probe_rtt_done_stamp &&
tcp_packets_in_flight(tp) <= bbr_cwnd_min_target) {
//设置结束时间，只有这里更新，这里是200ms
bbr->probe_rtt_done_stamp =
tcp_jiffies32 +
msecs_to_jiffies(bbr_probe_rtt_mode_ms);
bbr->probe_rtt_round_done = 0;
bbr->next_rtt_delivered = tp->delivered;
} else if (bbr->probe_rtt_done_stamp) {
if (bbr->round_start)
bbr->probe_rtt_round_done = 1;
if (bbr->probe_rtt_round_done)
bbr_check_probe_rtt_done(sk);
}
}
/* Restart after idle ends only once we process a new S/ACK for data */
if (rs->delivered > 0)
bbr->idle_restart = 0;
}
static void bbr_update_gains(struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
switch (bbr->mode) {
case BBR_STARTUP:
bbr->pacing_gain = bbr_high_gain;
bbr->cwnd_gain = bbr_high_gain;
break;
case BBR_DRAIN:
bbr->pacing_gain = bbr_drain_gain; /* slow, to drain */
bbr->cwnd_gain = bbr_high_gain; /* keep cwnd */
break;
case BBR_PROBE_BW:
bbr->pacing_gain = (bbr->lt_use_bw ?
BBR_UNIT :
bbr_pacing_gain[bbr->cycle_idx]);
bbr->cwnd_gain = bbr_cwnd_gain;
break;
case BBR_PROBE_RTT:
bbr->pacing_gain = BBR_UNIT;
bbr->cwnd_gain = BBR_UNIT;
break;
default:
WARN_ONCE(1, "BBR bad mode: %u\n", bbr->mode);
break;
}
}
static void bbr_update_model(struct sock *sk, const struct rate_sample *rs)
{
/*
1、更新带宽和延迟的估计值：根据收到的ACK信息和经过的时间，更新带宽和延迟的估计值，
以便在后续的拥塞控制决策中使用。
2、调整拥塞窗口和发送速率：根据带宽估计和拥塞控制模式，调整拥塞窗口和发送速率，
以控制数据发送的速率和量，以及适应网络的拥塞情况。
3、更新拥塞控制参数：根据网络状态和拥塞控制模式，更新相关的拥塞控制参数，
如拥塞窗口增加因子、发送速率增加因子等。
4、监测网络状况和事件：监测网络的RTT、丢包情况以及其他事件，以便对拥塞控制算法进行相应的调整和决策。
*///估计带宽：更新rtt周期，将带宽和minrtt加入新的rtt,bw样本
bbr_update_bw(sk, rs);
//计算inflight:计算预期的ack,重置ack统计周期，计算超出预期的多余数据，维护extra_acked最大值
bbr_update_ack_aggregation(sk, rs);
bbr_update_cycle_phase(sk, rs); //增益循环PROBE_BW
bbr_check_full_bw_reached(sk, rs); //填充BDP管道
bbr_check_drain(sk, rs); //状态转移到drain 排空队列
bbr_update_min_rtt(sk, rs); //更新最小rtt
bbr_update_gains(sk); //更新增益
}
__bpf_kfunc static void bbr_main(struct sock *sk, const struct rate_sample *rs)
{
struct bbr *bbr = inet_csk_ca(sk);
u32 bw;
/*更新拥塞控制模式（mode）从启动模式（Startup mode）到拥塞避免模式（Congestion Avoidance mode），
或从拥塞避免模式到拥塞控制模式（Congestion Control mode）等*/
bbr_update_model(sk, rs);
bw = bbr_bw(sk);
bbr_set_pacing_rate(sk, bw, bbr->pacing_gain);
bbr_set_cwnd(sk, rs, rs->acked_sacked, bw, bbr->cwnd_gain);
}
__bpf_kfunc static void bbr_init(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
bbr->prior_cwnd = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
bbr->rtt_cnt = 0;
bbr->next_rtt_delivered = tp->delivered;
bbr->prev_ca_state = TCP_CA_Open;
bbr->packet_conservation = 0;
bbr->probe_rtt_done_stamp = 0;
bbr->probe_rtt_round_done = 0;
bbr->min_rtt_us = tcp_min_rtt(tp);
bbr->min_rtt_stamp = tcp_jiffies32;
minmax_reset(&bbr->bw, bbr->rtt_cnt, 0); /* init max bw to 0 */
bbr->has_seen_rtt = 0;
bbr_init_pacing_rate_from_rtt(sk);
bbr->round_start = 0;
bbr->idle_restart = 0;
bbr->full_bw_reached = 0;
bbr->full_bw = 0;
bbr->full_bw_cnt = 0;
bbr->cycle_mstamp = 0;
bbr->cycle_idx = 0;
bbr_reset_lt_bw_sampling(sk);
bbr_reset_startup_mode(sk);
bbr->ack_epoch_mstamp = tp->tcp_mstamp;
bbr->ack_epoch_acked = 0;
bbr->extra_acked_win_rtts = 0;
bbr->extra_acked_win_idx = 0;
bbr->extra_acked[0] = 0;
bbr->extra_acked[1] = 0;
cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED);
}
__bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk)
{
/* Provision 3 * cwnd since BBR may slow-start even during recovery. */
return 3;
}
/* In theory BBR does not need to undo the cwnd since it does not
* always reduce cwnd on losses (see bbr_main()). Keep it for now.
*/
__bpf_kfunc static u32 bbr_undo_cwnd(struct sock *sk)
{
struct bbr *bbr = inet_csk_ca(sk);
bbr->full_bw = 0; /* spurious slow-down; reset full pipe detection */
bbr->full_bw_cnt = 0;
bbr_reset_lt_bw_sampling(sk);
return tcp_snd_cwnd(tcp_sk(sk));
}
/* Entering loss recovery, so save cwnd for when we exit or undo recovery. */
__bpf_kfunc static u32 bbr_ssthresh(struct sock *sk)
{
bbr_save_cwnd(sk);
return tcp_sk(sk)->snd_ssthresh;
}
static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr,
union tcp_cc_info *info)
{
if (ext & (1 << (INET_DIAG_BBRINFO - 1)) ||
ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
struct tcp_sock *tp = tcp_sk(sk);
struct bbr *bbr = inet_csk_ca(sk);
u64 bw = bbr_bw(sk);
bw = bw * tp->mss_cache * USEC_PER_SEC >> BW_SCALE;
memset(&info->bbr, 0, sizeof(info->bbr));
info->bbr.bbr_bw_lo = (u32)bw;
info->bbr.bbr_bw_hi = (u32)(bw >> 32);
info->bbr.bbr_min_rtt = bbr->min_rtt_us;
info->bbr.bbr_pacing_gain = bbr->pacing_gain;
info->bbr.bbr_cwnd_gain = bbr->cwnd_gain;
*attr = INET_DIAG_BBRINFO;
return sizeof(info->bbr);
}
return 0;
}
__bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state)
{
struct bbr *bbr = inet_csk_ca(sk);
if (new_state == TCP_CA_Loss) {
struct rate_sample rs = { .losses = 1 };
bbr->prev_ca_state = TCP_CA_Loss;
bbr->full_bw = 0;
bbr->round_start = 1; /* treat RTO like end of a round */
bbr_lt_bw_sampling(sk, &rs);
}
}
static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = {
.flags = TCP_CONG_NON_RESTRICTED,
.name = "bbr",
.owner = THIS_MODULE,
.init = bbr_init,
.cong_control = bbr_main,
.sndbuf_expand = bbr_sndbuf_expand,
.undo_cwnd = bbr_undo_cwnd,
.cwnd_event = bbr_cwnd_event,
.ssthresh = bbr_ssthresh,
.min_tso_segs = bbr_min_tso_segs,
.get_info = bbr_get_info,
.set_state = bbr_set_state,
};
BTF_SET8_START(tcp_bbr_check_kfunc_ids)
#ifdef CONFIG_X86
#ifdef CONFIG_DYNAMIC_FTRACE
BTF_ID_FLAGS(func, bbr_init)
BTF_ID_FLAGS(func, bbr_main)
BTF_ID_FLAGS(func, bbr_sndbuf_expand)
BTF_ID_FLAGS(func, bbr_undo_cwnd)
BTF_ID_FLAGS(func, bbr_cwnd_event)
BTF_ID_FLAGS(func, bbr_ssthresh)
BTF_ID_FLAGS(func, bbr_min_tso_segs)
BTF_ID_FLAGS(func, bbr_set_state)
#endif
#endif
BTF_SET8_END(tcp_bbr_check_kfunc_ids)
static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = {
.owner = THIS_MODULE,
.set = &tcp_bbr_check_kfunc_ids,
};
static int __init bbr_register(void)
{
int ret;
BUILD_BUG_ON(sizeof(struct bbr) > ICSK_CA_PRIV_SIZE);
ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
&tcp_bbr_kfunc_set);
if (ret < 0)
return ret;
return tcp_register_congestion_control(&tcp_bbr_cong_ops);
}
static void __exit bbr_unregister(void)
{
tcp_unregister_congestion_control(&tcp_bbr_cong_ops);
}
标签：struct,代码,tcp,sk,rtt,bw,cwnd,bbr From： https://www.cnblogs.com/codestack/p/17506780.html