/* 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 … #define BW_UNIT … #define BBR_SCALE … #define BBR_UNIT … /* BBR has the following modes for deciding how fast to send: */ enum bbr_mode { … }; /* BBR congestion control block */ struct bbr { … }; #define CYCLE_LEN … /* Window length of bw filter (in rounds): */ static const int bbr_bw_rtts = …; /* Window length of min_rtt filter (in sec): */ static const u32 bbr_min_rtt_win_sec = …; /* Minimum time (in ms) spent at bbr_cwnd_min_target in BBR_PROBE_RTT mode: */ static const u32 bbr_probe_rtt_mode_ms = …; /* Skip TSO below the following bandwidth (bits/sec): */ static const int bbr_min_tso_rate = …; /* 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 = …; /* 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 = …; /* 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 = …; /* The gain for deriving steady-state cwnd tolerates delayed/stretched ACKs: */ static const int bbr_cwnd_gain = …; /* The pacing_gain values for the PROBE_BW gain cycle, to discover/share bw: */ static const int bbr_pacing_gain[] = …; /* Randomize the starting gain cycling phase over N phases: */ static const u32 bbr_cycle_rand = …; /* 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 = …; /* 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 = …; /* But after 3 rounds w/o significant bw growth, estimate pipe is full: */ static const u32 bbr_full_bw_cnt = …; /* "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 = …; /* If lost/delivered ratio > 20%, interval is "lossy" and we may be policed: */ static const u32 bbr_lt_loss_thresh = …; /* If 2 intervals have a bw ratio <= 1/8, their bw is "consistent": */ static const u32 bbr_lt_bw_ratio = …; /* If 2 intervals have a bw diff <= 4 Kbit/sec their bw is "consistent": */ static const u32 bbr_lt_bw_diff = …; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = …; /* Gain factor for adding extra_acked to target cwnd: */ static const int bbr_extra_acked_gain = …; /* Window length of extra_acked window. */ static const u32 bbr_extra_acked_win_rtts = …; /* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */ static const u32 bbr_ack_epoch_acked_reset_thresh = …; /* Time period for clamping cwnd increment due to ack aggregation */ static const u32 bbr_extra_acked_max_us = …; 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) { … } /* Return the windowed max recent bandwidth sample, in pkts/uS << BW_SCALE. */ static u32 bbr_max_bw(const struct sock *sk) { … } /* Return the estimated bandwidth of the path, in pkts/uS << BW_SCALE. */ static u32 bbr_bw(const struct sock *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) { … } /* 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) { … } /* 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) { … } /* Initialize pacing rate to: high_gain * init_cwnd / RTT. */ static void bbr_init_pacing_rate_from_rtt(struct sock *sk) { … } /* Pace using current bw estimate and a gain factor. */ static void bbr_set_pacing_rate(struct sock *sk, u32 bw, int gain) { … } /* override sysctl_tcp_min_tso_segs */ __bpf_kfunc static u32 bbr_min_tso_segs(struct sock *sk) { … } static u32 bbr_tso_segs_goal(struct sock *sk) { … } /* Save "last known good" cwnd so we can restore it after losses or PROBE_RTT */ static void bbr_save_cwnd(struct sock *sk) { … } __bpf_kfunc static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) { … } /* 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) { … } /* 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, * - one skb in sending host TSO/GSO engine * - one skb being received by receiver host LRO/GRO/delayed-ACK engine * 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) { … } /* Find inflight based on min RTT and the estimated bottleneck bandwidth. */ static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) { … } /* 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) { … } /* Find the cwnd increment based on estimate of ack aggregation */ static u32 bbr_ack_aggregation_cwnd(struct sock *sk) { … } /* 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) { … } /* 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) { … } /* 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) { … } static void bbr_advance_cycle_phase(struct sock *sk) { … } /* 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) { … } static void bbr_reset_startup_mode(struct sock *sk) { … } static void bbr_reset_probe_bw_mode(struct sock *sk) { … } static void bbr_reset_mode(struct sock *sk) { … } /* Start a new long-term sampling interval. */ static void bbr_reset_lt_bw_sampling_interval(struct sock *sk) { … } /* Completely reset long-term bandwidth sampling. */ static void bbr_reset_lt_bw_sampling(struct sock *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) { … } /* 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) { … } /* Estimate the bandwidth based on how fast packets are delivered */ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) { … } /* Estimates the windowed max degree of ack aggregation. * 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. */ static void bbr_update_ack_aggregation(struct sock *sk, const struct rate_sample *rs) { … } /* 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. */ static void bbr_check_full_bw_reached(struct sock *sk, const struct rate_sample *rs) { … } /* 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) { … } static void bbr_check_probe_rtt_done(struct sock *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. :-) */ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) { … } static void bbr_update_gains(struct sock *sk) { … } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) { … } __bpf_kfunc static void bbr_main(struct sock *sk, u32 ack, int flag, const struct rate_sample *rs) { … } __bpf_kfunc static void bbr_init(struct sock *sk) { … } __bpf_kfunc static u32 bbr_sndbuf_expand(struct sock *sk) { … } /* 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) { … } /* Entering loss recovery, so save cwnd for when we exit or undo recovery. */ __bpf_kfunc static u32 bbr_ssthresh(struct sock *sk) { … } static size_t bbr_get_info(struct sock *sk, u32 ext, int *attr, union tcp_cc_info *info) { … } __bpf_kfunc static void bbr_set_state(struct sock *sk, u8 new_state) { … } static struct tcp_congestion_ops tcp_bbr_cong_ops __read_mostly = …; BTF_KFUNCS_START(tcp_bbr_check_kfunc_ids) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_ID_FLAGS(…) BTF_KFUNCS_END(…) static const struct btf_kfunc_id_set tcp_bbr_kfunc_set = …; static int __init bbr_register(void) { … } static void __exit bbr_unregister(void) { … } module_init(…) …; module_exit(bbr_unregister); MODULE_AUTHOR(…) …; MODULE_AUTHOR(…) …; MODULE_AUTHOR(…) …; MODULE_AUTHOR(…) …; MODULE_LICENSE(…) …; MODULE_DESCRIPTION(…) …;
Codebase Browser
linux