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 <nanditad@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

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 */

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);

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,