aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/tcp_cubic.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/tcp_cubic.c')
-rw-r--r--net/ipv4/tcp_cubic.c74
1 files changed, 51 insertions, 23 deletions
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 71d5f2f29fa..a9bd8a4828a 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -39,7 +39,7 @@
/* Number of delay samples for detecting the increase of delay */
#define HYSTART_MIN_SAMPLES 8
-#define HYSTART_DELAY_MIN (2U<<3)
+#define HYSTART_DELAY_MIN (4U<<3)
#define HYSTART_DELAY_MAX (16U<<3)
#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX)
@@ -52,6 +52,7 @@ 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 int hystart_ack_delta __read_mostly = 2;
static u32 cube_rtt_scale __read_mostly;
static u32 beta_scale __read_mostly;
@@ -75,6 +76,8 @@ 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");
+module_param(hystart_ack_delta, int, 0644);
+MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)");
/* BIC TCP Parameters */
struct bictcp {
@@ -85,17 +88,18 @@ struct bictcp {
u32 last_time; /* time when updated last_cwnd */
u32 bic_origin_point;/* origin point of bic function */
u32 bic_K; /* time to origin point from the beginning of the current epoch */
- u32 delay_min; /* min delay */
+ u32 delay_min; /* min delay (msec << 3) */
u32 epoch_start; /* beginning of an epoch */
u32 ack_cnt; /* number of acks */
u32 tcp_cwnd; /* estimated tcp cwnd */
#define ACK_RATIO_SHIFT 4
+#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
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 last_ack; /* last time when the ACK spacing is close */
u32 curr_rtt; /* the minimum rtt of current round */
};
@@ -103,7 +107,6 @@ static inline void bictcp_reset(struct bictcp *ca)
{
ca->cnt = 0;
ca->last_max_cwnd = 0;
- ca->loss_cwnd = 0;
ca->last_cwnd = 0;
ca->last_time = 0;
ca->bic_origin_point = 0;
@@ -116,12 +119,21 @@ static inline void bictcp_reset(struct bictcp *ca)
ca->found = 0;
}
+static inline u32 bictcp_clock(void)
+{
+#if HZ < 1000
+ return ktime_to_ms(ktime_get_real());
+#else
+ return jiffies_to_msecs(jiffies);
+#endif
+}
+
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->round_start = ca->last_ack = bictcp_clock();
ca->end_seq = tp->snd_nxt;
ca->curr_rtt = 0;
ca->sample_cnt = 0;
@@ -129,7 +141,10 @@ static inline void bictcp_hystart_reset(struct sock *sk)
static void bictcp_init(struct sock *sk)
{
- bictcp_reset(inet_csk_ca(sk));
+ struct bictcp *ca = inet_csk_ca(sk);
+
+ bictcp_reset(ca);
+ ca->loss_cwnd = 0;
if (hystart)
bictcp_hystart_reset(sk);
@@ -191,8 +206,8 @@ static u32 cubic_root(u64 a)
*/
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
- u64 offs;
- u32 delta, t, bic_target, max_cnt;
+ u32 delta, bic_target, max_cnt;
+ u64 offs, t;
ca->ack_cnt++; /* count the number of ACKs */
@@ -235,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
* if the cwnd < 1 million packets !!!
*/
+ t = (s32)(tcp_time_stamp - ca->epoch_start);
+ t += msecs_to_jiffies(ca->delay_min >> 3);
/* change the unit from HZ to bictcp_HZ */
- t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start)
- << BICTCP_HZ) / HZ;
+ t <<= BICTCP_HZ;
+ do_div(t, HZ);
if (t < ca->bic_K) /* t - K */
offs = ca->bic_K - t;
@@ -258,6 +275,13 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
ca->cnt = 100 * cwnd; /* very small increment*/
}
+ /*
+ * The initial growth of cubic function may be too conservative
+ * when the available bandwidth is still unknown.
+ */
+ if (ca->last_max_cwnd == 0 && ca->cnt > 20)
+ ca->cnt = 20; /* increase cwnd 5% per RTT */
+
/* TCP Friendly */
if (tcp_friendliness) {
u32 scale = beta_scale;
@@ -280,18 +304,18 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
ca->cnt = 1;
}
-static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
+static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked)
{
struct tcp_sock *tp = tcp_sk(sk);
struct bictcp *ca = inet_csk_ca(sk);
- if (!tcp_is_cwnd_limited(sk, in_flight))
+ if (!tcp_is_cwnd_limited(sk))
return;
if (tp->snd_cwnd <= tp->snd_ssthresh) {
if (hystart && after(ack, ca->end_seq))
bictcp_hystart_reset(sk);
- tcp_slow_start(tp);
+ tcp_slow_start(tp, acked);
} else {
bictcp_update(ca, tp->snd_cwnd);
tcp_cong_avoid_ai(tp, ca->cnt);
@@ -322,7 +346,7 @@ static u32 bictcp_undo_cwnd(struct sock *sk)
{
struct bictcp *ca = inet_csk_ca(sk);
- return max(tcp_sk(sk)->snd_cwnd, ca->last_max_cwnd);
+ return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
}
static void bictcp_state(struct sock *sk, u8 new_state)
@@ -339,12 +363,12 @@ static void hystart_update(struct sock *sk, u32 delay)
struct bictcp *ca = inet_csk_ca(sk);
if (!(ca->found & hystart_detect)) {
- u32 curr_jiffies = jiffies;
+ u32 now = bictcp_clock();
/* 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)
+ if ((s32)(now - ca->last_ack) <= hystart_ack_delta) {
+ ca->last_ack = now;
+ if ((s32)(now - ca->round_start) > ca->delay_min >> 4)
ca->found |= HYSTART_ACK_TRAIN;
}
@@ -379,8 +403,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
u32 delay;
if (icsk->icsk_ca_state == TCP_CA_Open) {
- cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
- ca->delayed_ack += cnt;
+ u32 ratio = ca->delayed_ack;
+
+ ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
+ ratio += cnt;
+
+ ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
}
/* Some calls are for duplicates without timetamps */
@@ -388,10 +416,10 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
return;
/* Discard delay samples right after fast recovery */
- if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
+ if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
return;
- delay = usecs_to_jiffies(rtt_us) << 3;
+ delay = (rtt_us << 3) / USEC_PER_MSEC;
if (delay == 0)
delay = 1;
@@ -405,7 +433,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
hystart_update(sk, delay);
}
-static struct tcp_congestion_ops cubictcp = {
+static struct tcp_congestion_ops cubictcp __read_mostly = {
.init = bictcp_init,
.ssthresh = bictcp_recalc_ssthresh,
.cong_avoid = bictcp_cong_avoid,
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-04 13:25:57 +0000