diff options
| -rw-r--r-- | net/ipv4/tcp_bbr.c | 77 |
1 files changed, 65 insertions, 12 deletions
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index b88081285fd1..9277abdd822a 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -369,6 +369,39 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) return cwnd; } +/* 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; +} + /* 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. @@ -460,7 +493,7 @@ static bool bbr_is_next_cycle_phase(struct sock *sk, if (bbr->pacing_gain == BBR_UNIT) return is_full_length; /* just use wall clock time */ - inflight = rs->prior_in_flight; /* what was in-flight before ACK? */ + 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 @@ -488,8 +521,6 @@ static void bbr_advance_cycle_phase(struct sock *sk) bbr->cycle_idx = (bbr->cycle_idx + 1) & (CYCLE_LEN - 1); bbr->cycle_mstamp = tp->delivered_mstamp; - bbr->pacing_gain = bbr->lt_use_bw ? BBR_UNIT : - bbr_pacing_gain[bbr->cycle_idx]; } /* Gain cycling: cycle pacing gain to converge to fair share of available bw. */ @@ -507,8 +538,6 @@ static void bbr_reset_startup_mode(struct sock *sk) struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_STARTUP; - bbr->pacing_gain = bbr_high_gain; - bbr->cwnd_gain = bbr_high_gain; } static void bbr_reset_probe_bw_mode(struct sock *sk) @@ -516,8 +545,6 @@ static void bbr_reset_probe_bw_mode(struct sock *sk) struct bbr *bbr = inet_csk_ca(sk); bbr->mode = BBR_PROBE_BW; - bbr->pacing_gain = BBR_UNIT; - bbr->cwnd_gain = bbr_cwnd_gain; bbr->cycle_idx = CYCLE_LEN - 1 - prandom_u32_max(bbr_cycle_rand); bbr_advance_cycle_phase(sk); /* flip to next phase of gain cycle */ } @@ -735,13 +762,11 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { bbr->mode = BBR_DRAIN; /* drain queue we created */ - bbr->pacing_gain = bbr_drain_gain; /* pace slow to drain */ - bbr->cwnd_gain = bbr_high_gain; /* maintain cwnd */ tcp_sk(sk)->snd_ssthresh = bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT); } /* fall through to check if in-flight is already small: */ if (bbr->mode == BBR_DRAIN && - tcp_packets_in_flight(tcp_sk(sk)) <= + bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <= bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT)) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } @@ -798,8 +823,6 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) if (bbr_probe_rtt_mode_ms > 0 && filter_expired && !bbr->idle_restart && bbr->mode != BBR_PROBE_RTT) { bbr->mode = BBR_PROBE_RTT; /* dip, drain queue */ - bbr->pacing_gain = BBR_UNIT; - bbr->cwnd_gain = BBR_UNIT; bbr_save_cwnd(sk); /* note cwnd so we can restore it */ bbr->probe_rtt_done_stamp = 0; } @@ -827,6 +850,35 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) 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) { bbr_update_bw(sk, rs); @@ -834,6 +886,7 @@ static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) bbr_check_full_bw_reached(sk, rs); bbr_check_drain(sk, rs); bbr_update_min_rtt(sk, rs); + bbr_update_gains(sk); } static void bbr_main(struct sock *sk, const struct rate_sample *rs) |