From a262f0cdf1f2916ea918dc329492abb5323d9a6c Mon Sep 17 00:00:00 2001 From: Nandita Dukkipati Date: Sun, 21 Aug 2011 20:21:57 +0000 Subject: [PATCH] Proportional Rate Reduction for TCP. This patch implements Proportional Rate Reduction (PRR) for TCP. PRR is an algorithm that determines TCP's sending rate in fast recovery. PRR avoids excessive window reductions and aims for the actual congestion window size at the end of recovery to be as close as possible to the window determined by the congestion control algorithm. PRR also improves accuracy of the amount of data sent during loss recovery. The patch implements the recommended flavor of PRR called PRR-SSRB (Proportional rate reduction with slow start reduction bound) and replaces the existing rate halving algorithm. PRR improves upon the existing Linux fast recovery under a number of conditions including: 1) burst losses where the losses implicitly reduce the amount of outstanding data (pipe) below the ssthresh value selected by the congestion control algorithm and, 2) losses near the end of short flows where application runs out of data to send. As an example, with the existing rate halving implementation a single loss event can cause a connection carrying short Web transactions to go into the slow start mode after the recovery. This is because during recovery Linux pulls the congestion window down to packets_in_flight+1 on every ACK. A short Web response often runs out of new data to send and its pipe reduces to zero by the end of recovery when all its packets are drained from the network. Subsequent HTTP responses using the same connection will have to slow start to raise cwnd to ssthresh. PRR on the other hand aims for the cwnd to be as close as possible to ssthresh by the end of recovery. A description of PRR and a discussion of its performance can be found at the following links: - IETF Draft: http://tools.ietf.org/html/draft-mathis-tcpm-proportional-rate-reduction-01 - IETF Slides: http://www.ietf.org/proceedings/80/slides/tcpm-6.pdf http://tools.ietf.org/agenda/81/slides/tcpm-2.pdf - Paper to appear in Internet Measurements Conference (IMC) 2011: Improving TCP Loss Recovery Nandita Dukkipati, Matt Mathis, Yuchung Cheng Signed-off-by: Nandita Dukkipati Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 +++ net/ipv4/tcp_input.c | 58 ++++++++++++++++++++++++++++++++++++++----- net/ipv4/tcp_output.c | 7 +++++- 3 files changed, 62 insertions(+), 7 deletions(-) diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 531ede8006d9..6b63b310af36 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -379,6 +379,10 @@ struct tcp_sock { u32 snd_cwnd_clamp; /* Do not allow snd_cwnd to grow above this */ u32 snd_cwnd_used; u32 snd_cwnd_stamp; + u32 prior_cwnd; /* Congestion window at start of Recovery. */ + u32 prr_delivered; /* Number of newly delivered packets to + * receiver in Recovery. */ + u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 rcv_wnd; /* Current receiver window */ u32 write_seq; /* Tail(+1) of data held in tcp send buffer */ diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ea0d2183df4b..385c470195eb 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2830,9 +2830,13 @@ static int tcp_try_undo_loss(struct sock *sk) static inline void tcp_complete_cwr(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - /* Do not moderate cwnd if it's already undone in cwr or recovery */ - if (tp->undo_marker && tp->snd_cwnd > tp->snd_ssthresh) { - tp->snd_cwnd = tp->snd_ssthresh; + + /* Do not moderate cwnd if it's already undone in cwr or recovery. */ + if (tp->undo_marker) { + if (inet_csk(sk)->icsk_ca_state == TCP_CA_CWR) + tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh); + else /* PRR */ + tp->snd_cwnd = tp->snd_ssthresh; tp->snd_cwnd_stamp = tcp_time_stamp; } tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); @@ -2950,6 +2954,38 @@ void tcp_simple_retransmit(struct sock *sk) } EXPORT_SYMBOL(tcp_simple_retransmit); +/* This function implements the PRR algorithm, specifcally the PRR-SSRB + * (proportional rate reduction with slow start reduction bound) as described in + * http://www.ietf.org/id/draft-mathis-tcpm-proportional-rate-reduction-01.txt. + * It computes the number of packets to send (sndcnt) based on packets newly + * delivered: + * 1) If the packets in flight is larger than ssthresh, PRR spreads the + * cwnd reductions across a full RTT. + * 2) If packets in flight is lower than ssthresh (such as due to excess + * losses and/or application stalls), do not perform any further cwnd + * reductions, but instead slow start up to ssthresh. + */ +static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, + int fast_rexmit, int flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + int sndcnt = 0; + int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp); + + if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + + tp->prior_cwnd - 1; + sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; + } else { + sndcnt = min_t(int, delta, + max_t(int, tp->prr_delivered - tp->prr_out, + newly_acked_sacked) + 1); + } + + sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); + tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2961,7 +2997,8 @@ EXPORT_SYMBOL(tcp_simple_retransmit); * It does _not_ decide what to send, it is made in function * tcp_xmit_retransmit_queue(). */ -static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) +static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, + int newly_acked_sacked, int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -3111,13 +3148,17 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) tp->bytes_acked = 0; tp->snd_cwnd_cnt = 0; + tp->prior_cwnd = tp->snd_cwnd; + tp->prr_delivered = 0; + tp->prr_out = 0; tcp_set_ca_state(sk, TCP_CA_Recovery); fast_rexmit = 1; } if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk))) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_down(sk, flag); + tp->prr_delivered += newly_acked_sacked; + tcp_update_cwnd_in_recovery(sk, newly_acked_sacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3632,6 +3673,8 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) u32 prior_in_flight; u32 prior_fackets; int prior_packets; + int prior_sacked = tp->sacked_out; + int newly_acked_sacked = 0; int frto_cwnd = 0; /* If the ack is older than previous acks @@ -3703,6 +3746,9 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + newly_acked_sacked = (prior_packets - prior_sacked) - + (tp->packets_out - tp->sacked_out); + if (tp->frto_counter) frto_cwnd = tcp_process_frto(sk, flag); /* Guarantee sacktag reordering detection against wrap-arounds */ @@ -3715,7 +3761,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag) tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, - flag); + newly_acked_sacked, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 0377c061f22f..081dcd6fd0c4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1796,11 +1796,13 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, tcp_event_new_data_sent(sk, skb); tcp_minshall_update(tp, mss_now, skb); - sent_pkts++; + sent_pkts += tcp_skb_pcount(skb); if (push_one) break; } + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + tp->prr_out += sent_pkts; if (likely(sent_pkts)) { tcp_cwnd_validate(sk); @@ -2294,6 +2296,9 @@ begin_fwd: return; NET_INC_STATS_BH(sock_net(sk), mib_idx); + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Recovery) + tp->prr_out += tcp_skb_pcount(skb); + if (skb == tcp_write_queue_head(sk)) inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, inet_csk(sk)->icsk_rto, -- 2.20.1