[TCP] CUBIC v2.3

Signed-off-by: Sangtae Ha <sha2@ncsu.edu>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/ipv4/tcp_cubic.c

@@ -1,13 +1,23 @@
 /*
- * TCP CUBIC: Binary Increase Congestion control for TCP v2.2
+ * TCP CUBIC: Binary Increase Congestion control for TCP v2.3
  * Home page:
  *      http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC
  * This is from the implementation of CUBIC TCP in
- * Injong Rhee, Lisong Xu.
+ * Sangtae Ha, Injong Rhee and Lisong Xu,
- *  "CUBIC: A New TCP-Friendly High-Speed TCP Variant
+ *  "CUBIC: A New TCP-Friendly High-Speed TCP Variant"
- *  in PFLDnet 2005
+ *  in ACM SIGOPS Operating System Review, July 2008.
  * Available from:
- *  http://netsrv.csc.ncsu.edu/export/cubic-paper.pdf
+ *  http://netsrv.csc.ncsu.edu/export/cubic_a_new_tcp_2008.pdf
+ *
+ * CUBIC integrates a new slow start algorithm, called HyStart.
+ * The details of HyStart are presented in
+ *  Sangtae Ha and Injong Rhee,
+ *  "Taming the Elephants: New TCP Slow Start", NCSU TechReport 2008.
+ * Available from:
+ *  http://netsrv.csc.ncsu.edu/export/hystart_techreport_2008.pdf
+ *
+ * All testing results are available from:
+ * http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing
  *
  * Unless CUBIC is enabled and congestion window is large
  * this behaves the same as the original Reno.
@@ -23,12 +33,26 @@
 					 */
 #define	BICTCP_HZ		10	/* BIC HZ 2^10 = 1024 */
 
+/* Two methods of hybrid slow start */
+#define HYSTART_ACK_TRAIN	0x1
+#define HYSTART_DELAY		0x2
+
+/* Number of delay samples for detecting the increase of delay */
+#define HYSTART_MIN_SAMPLES	8
+#define HYSTART_DELAY_MIN	(2U<<3)
+#define HYSTART_DELAY_MAX	(16U<<3)
+#define HYSTART_DELAY_THRESH(x)	clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
+
 static int fast_convergence __read_mostly = 1;
 static int beta __read_mostly = 717;	/* = 717/1024 (BICTCP_BETA_SCALE) */
 static int initial_ssthresh __read_mostly;
 static int bic_scale __read_mostly = 41;
 static int tcp_friendliness __read_mostly = 1;
 
+static int hystart __read_mostly = 1;
+static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY;
+static int hystart_low_window __read_mostly = 16;
+
 static u32 cube_rtt_scale __read_mostly;
 static u32 beta_scale __read_mostly;
 static u64 cube_factor __read_mostly;
@@ -44,6 +68,13 @@ module_param(bic_scale, int, 0444);
 MODULE_PARM_DESC(bic_scale, "scale (scaled by 1024) value for bic function (bic_scale/1024)");
 module_param(tcp_friendliness, int, 0644);
 MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness");
+module_param(hystart, int, 0644);
+MODULE_PARM_DESC(hystart, "turn on/off hybrid slow start algorithm");
+module_param(hystart_detect, int, 0644);
+MODULE_PARM_DESC(hystart_detect, "hyrbrid slow start detection mechanisms"
+		 " 1: packet-train 2: delay 3: both packet-train and delay");
+module_param(hystart_low_window, int, 0644);
+MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start");
 
 /* BIC TCP Parameters */
 struct bictcp {
@@ -59,7 +90,13 @@ struct bictcp {
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
 #define ACK_RATIO_SHIFT	4
-	u32	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
+	u16	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
+	u8	sample_cnt;	/* number of samples to decide curr_rtt */
+	u8	found;		/* the exit point is found? */
+	u32	round_start;	/* beginning of each round */
+	u32	end_seq;	/* end_seq of the round */
+	u32	last_jiffies;	/* last time when the ACK spacing is close */
+	u32	curr_rtt;	/* the minimum rtt of current round */
 };
 
 static inline void bictcp_reset(struct bictcp *ca)
@@ -76,12 +113,28 @@ static inline void bictcp_reset(struct bictcp *ca)
 	ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
 	ca->ack_cnt = 0;
 	ca->tcp_cwnd = 0;
+	ca->found = 0;
+}
+
+static inline void bictcp_hystart_reset(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	ca->round_start = ca->last_jiffies = jiffies;
+	ca->end_seq = tp->snd_nxt;
+	ca->curr_rtt = 0;
+	ca->sample_cnt = 0;
 }
 
 static void bictcp_init(struct sock *sk)
 {
 	bictcp_reset(inet_csk_ca(sk));
-	if (initial_ssthresh)
+
+	if (hystart)
+		bictcp_hystart_reset(sk);
+
+	if (!hystart && initial_ssthresh)
 		tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
@@ -235,9 +288,11 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
 	if (!tcp_is_cwnd_limited(sk, in_flight))
 		return;
 
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
+	if (tp->snd_cwnd <= tp->snd_ssthresh) {
+		if (hystart && after(ack, ca->end_seq))
+			bictcp_hystart_reset(sk);
 		tcp_slow_start(tp);
-	else {
+	} else {
 		bictcp_update(ca, tp->snd_cwnd);
 
 		/* In dangerous area, increase slowly.
@@ -281,8 +336,45 @@ static u32 bictcp_undo_cwnd(struct sock *sk)
 
 static void bictcp_state(struct sock *sk, u8 new_state)
 {
-	if (new_state == TCP_CA_Loss)
+	if (new_state == TCP_CA_Loss) {
 		bictcp_reset(inet_csk_ca(sk));
+		bictcp_hystart_reset(sk);
+	}
+}
+
+static void hystart_update(struct sock *sk, u32 delay)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct bictcp *ca = inet_csk_ca(sk);
+
+	if (!(ca->found & hystart_detect)) {
+		u32 curr_jiffies = jiffies;
+
+		/* first detection parameter - ack-train detection */
+		if (curr_jiffies - ca->last_jiffies <= msecs_to_jiffies(2)) {
+			ca->last_jiffies = curr_jiffies;
+			if (curr_jiffies - ca->round_start >= ca->delay_min>>4)
+				ca->found |= HYSTART_ACK_TRAIN;
+		}
+
+		/* obtain the minimum delay of more than sampling packets */
+		if (ca->sample_cnt < HYSTART_MIN_SAMPLES) {
+			if (ca->curr_rtt == 0 || ca->curr_rtt > delay)
+				ca->curr_rtt = delay;
+
+			ca->sample_cnt++;
+		} else {
+			if (ca->curr_rtt > ca->delay_min +
+			    HYSTART_DELAY_THRESH(ca->delay_min>>4))
+				ca->found |= HYSTART_DELAY;
+		}
+		/*
+		 * Either one of two conditions are met,
+		 * we exit from slow start immediately.
+		 */
+		if (ca->found & hystart_detect)
+			tp->snd_ssthresh = tp->snd_cwnd;
+	}
 }
 
 /* Track delayed acknowledgment ratio using sliding window
@@ -291,6 +383,7 @@ static void bictcp_state(struct sock *sk, u8 new_state)
 static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 delay;
 
@@ -314,6 +407,11 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 	/* first time call or link delay decreases */
 	if (ca->delay_min == 0 || ca->delay_min > delay)
 		ca->delay_min = delay;
+
+	/* hystart triggers when cwnd is larger than some threshold */
+	if (hystart && tp->snd_cwnd <= tp->snd_ssthresh &&
+	    tp->snd_cwnd >= hystart_low_window)
+		hystart_update(sk, delay);
 }
 
 static struct tcp_congestion_ops cubictcp = {
@@ -372,4 +470,4 @@ module_exit(cubictcp_unregister);
 MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("CUBIC TCP");
-MODULE_VERSION("2.2");
+MODULE_VERSION("2.3");