e73ebb0881
LRO, GRO, delayed ACKs, and middleboxes can cause "stretch ACKs" that cover more than the RFC-specified maximum of 2 packets. These stretch ACKs can cause serious performance shortfalls in common congestion control algorithms that were designed and tuned years ago with receiver hosts that were not using LRO or GRO, and were instead politely ACKing every other packet. This patch series fixes Reno and CUBIC to handle stretch ACKs. This patch prepares for the upcoming stretch ACK bug fix patches. It adds an "acked" parameter to tcp_cong_avoid_ai() to allow for future fixes to tcp_cong_avoid_ai() to correctly handle stretch ACKs, and changes all congestion control algorithms to pass in 1 for the ACKed count. It also changes tcp_slow_start() to return the number of packet ACK "credits" that were not processed in slow start mode, and can be processed by the congestion control module in additive increase mode. In future patches we will fix tcp_cong_avoid_ai() to handle stretch ACKs, and fix Reno and CUBIC handling of stretch ACKs in slow start and additive increase mode. Reported-by: Eyal Perry <eyalpe@mellanox.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
240 lines
6.2 KiB
C
240 lines
6.2 KiB
C
/*
|
|
* Binary Increase Congestion control for TCP
|
|
* Home page:
|
|
* http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC
|
|
* This is from the implementation of BICTCP in
|
|
* Lison-Xu, Kahaled Harfoush, and Injong Rhee.
|
|
* "Binary Increase Congestion Control for Fast, Long Distance
|
|
* Networks" in InfoComm 2004
|
|
* Available from:
|
|
* http://netsrv.csc.ncsu.edu/export/bitcp.pdf
|
|
*
|
|
* Unless BIC is enabled and congestion window is large
|
|
* this behaves the same as the original Reno.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/module.h>
|
|
#include <net/tcp.h>
|
|
|
|
#define BICTCP_BETA_SCALE 1024 /* Scale factor beta calculation
|
|
* max_cwnd = snd_cwnd * beta
|
|
*/
|
|
#define BICTCP_B 4 /*
|
|
* In binary search,
|
|
* go to point (max+min)/N
|
|
*/
|
|
|
|
static int fast_convergence = 1;
|
|
static int max_increment = 16;
|
|
static int low_window = 14;
|
|
static int beta = 819; /* = 819/1024 (BICTCP_BETA_SCALE) */
|
|
static int initial_ssthresh;
|
|
static int smooth_part = 20;
|
|
|
|
module_param(fast_convergence, int, 0644);
|
|
MODULE_PARM_DESC(fast_convergence, "turn on/off fast convergence");
|
|
module_param(max_increment, int, 0644);
|
|
MODULE_PARM_DESC(max_increment, "Limit on increment allowed during binary search");
|
|
module_param(low_window, int, 0644);
|
|
MODULE_PARM_DESC(low_window, "lower bound on congestion window (for TCP friendliness)");
|
|
module_param(beta, int, 0644);
|
|
MODULE_PARM_DESC(beta, "beta for multiplicative increase");
|
|
module_param(initial_ssthresh, int, 0644);
|
|
MODULE_PARM_DESC(initial_ssthresh, "initial value of slow start threshold");
|
|
module_param(smooth_part, int, 0644);
|
|
MODULE_PARM_DESC(smooth_part, "log(B/(B*Smin))/log(B/(B-1))+B, # of RTT from Wmax-B to Wmax");
|
|
|
|
/* BIC TCP Parameters */
|
|
struct bictcp {
|
|
u32 cnt; /* increase cwnd by 1 after ACKs */
|
|
u32 last_max_cwnd; /* last maximum snd_cwnd */
|
|
u32 loss_cwnd; /* congestion window at last loss */
|
|
u32 last_cwnd; /* the last snd_cwnd */
|
|
u32 last_time; /* time when updated last_cwnd */
|
|
u32 epoch_start; /* beginning of an epoch */
|
|
#define ACK_RATIO_SHIFT 4
|
|
u32 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */
|
|
};
|
|
|
|
static inline void bictcp_reset(struct bictcp *ca)
|
|
{
|
|
ca->cnt = 0;
|
|
ca->last_max_cwnd = 0;
|
|
ca->last_cwnd = 0;
|
|
ca->last_time = 0;
|
|
ca->epoch_start = 0;
|
|
ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
|
|
}
|
|
|
|
static void bictcp_init(struct sock *sk)
|
|
{
|
|
struct bictcp *ca = inet_csk_ca(sk);
|
|
|
|
bictcp_reset(ca);
|
|
ca->loss_cwnd = 0;
|
|
|
|
if (initial_ssthresh)
|
|
tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
|
|
}
|
|
|
|
/*
|
|
* Compute congestion window to use.
|
|
*/
|
|
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
|
|
{
|
|
if (ca->last_cwnd == cwnd &&
|
|
(s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
|
|
return;
|
|
|
|
ca->last_cwnd = cwnd;
|
|
ca->last_time = tcp_time_stamp;
|
|
|
|
if (ca->epoch_start == 0) /* record the beginning of an epoch */
|
|
ca->epoch_start = tcp_time_stamp;
|
|
|
|
/* start off normal */
|
|
if (cwnd <= low_window) {
|
|
ca->cnt = cwnd;
|
|
return;
|
|
}
|
|
|
|
/* binary increase */
|
|
if (cwnd < ca->last_max_cwnd) {
|
|
__u32 dist = (ca->last_max_cwnd - cwnd)
|
|
/ BICTCP_B;
|
|
|
|
if (dist > max_increment)
|
|
/* linear increase */
|
|
ca->cnt = cwnd / max_increment;
|
|
else if (dist <= 1U)
|
|
/* binary search increase */
|
|
ca->cnt = (cwnd * smooth_part) / BICTCP_B;
|
|
else
|
|
/* binary search increase */
|
|
ca->cnt = cwnd / dist;
|
|
} else {
|
|
/* slow start AMD linear increase */
|
|
if (cwnd < ca->last_max_cwnd + BICTCP_B)
|
|
/* slow start */
|
|
ca->cnt = (cwnd * smooth_part) / BICTCP_B;
|
|
else if (cwnd < ca->last_max_cwnd + max_increment*(BICTCP_B-1))
|
|
/* slow start */
|
|
ca->cnt = (cwnd * (BICTCP_B-1))
|
|
/ (cwnd - ca->last_max_cwnd);
|
|
else
|
|
/* linear increase */
|
|
ca->cnt = cwnd / max_increment;
|
|
}
|
|
|
|
/* if in slow start or link utilization is very low */
|
|
if (ca->last_max_cwnd == 0) {
|
|
if (ca->cnt > 20) /* increase cwnd 5% per RTT */
|
|
ca->cnt = 20;
|
|
}
|
|
|
|
ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
|
|
if (ca->cnt == 0) /* cannot be zero */
|
|
ca->cnt = 1;
|
|
}
|
|
|
|
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))
|
|
return;
|
|
|
|
if (tp->snd_cwnd <= tp->snd_ssthresh)
|
|
tcp_slow_start(tp, acked);
|
|
else {
|
|
bictcp_update(ca, tp->snd_cwnd);
|
|
tcp_cong_avoid_ai(tp, ca->cnt, 1);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* behave like Reno until low_window is reached,
|
|
* then increase congestion window slowly
|
|
*/
|
|
static u32 bictcp_recalc_ssthresh(struct sock *sk)
|
|
{
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
struct bictcp *ca = inet_csk_ca(sk);
|
|
|
|
ca->epoch_start = 0; /* end of epoch */
|
|
|
|
/* Wmax and fast convergence */
|
|
if (tp->snd_cwnd < ca->last_max_cwnd && fast_convergence)
|
|
ca->last_max_cwnd = (tp->snd_cwnd * (BICTCP_BETA_SCALE + beta))
|
|
/ (2 * BICTCP_BETA_SCALE);
|
|
else
|
|
ca->last_max_cwnd = tp->snd_cwnd;
|
|
|
|
ca->loss_cwnd = tp->snd_cwnd;
|
|
|
|
if (tp->snd_cwnd <= low_window)
|
|
return max(tp->snd_cwnd >> 1U, 2U);
|
|
else
|
|
return max((tp->snd_cwnd * beta) / BICTCP_BETA_SCALE, 2U);
|
|
}
|
|
|
|
static u32 bictcp_undo_cwnd(struct sock *sk)
|
|
{
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
const struct bictcp *ca = inet_csk_ca(sk);
|
|
|
|
return max(tp->snd_cwnd, ca->loss_cwnd);
|
|
}
|
|
|
|
static void bictcp_state(struct sock *sk, u8 new_state)
|
|
{
|
|
if (new_state == TCP_CA_Loss)
|
|
bictcp_reset(inet_csk_ca(sk));
|
|
}
|
|
|
|
/* Track delayed acknowledgment ratio using sliding window
|
|
* ratio = (15*ratio + sample) / 16
|
|
*/
|
|
static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt)
|
|
{
|
|
const struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
if (icsk->icsk_ca_state == TCP_CA_Open) {
|
|
struct bictcp *ca = inet_csk_ca(sk);
|
|
|
|
cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT;
|
|
ca->delayed_ack += cnt;
|
|
}
|
|
}
|
|
|
|
static struct tcp_congestion_ops bictcp __read_mostly = {
|
|
.init = bictcp_init,
|
|
.ssthresh = bictcp_recalc_ssthresh,
|
|
.cong_avoid = bictcp_cong_avoid,
|
|
.set_state = bictcp_state,
|
|
.undo_cwnd = bictcp_undo_cwnd,
|
|
.pkts_acked = bictcp_acked,
|
|
.owner = THIS_MODULE,
|
|
.name = "bic",
|
|
};
|
|
|
|
static int __init bictcp_register(void)
|
|
{
|
|
BUILD_BUG_ON(sizeof(struct bictcp) > ICSK_CA_PRIV_SIZE);
|
|
return tcp_register_congestion_control(&bictcp);
|
|
}
|
|
|
|
static void __exit bictcp_unregister(void)
|
|
{
|
|
tcp_unregister_congestion_control(&bictcp);
|
|
}
|
|
|
|
module_init(bictcp_register);
|
|
module_exit(bictcp_unregister);
|
|
|
|
MODULE_AUTHOR("Stephen Hemminger");
|
|
MODULE_LICENSE("GPL");
|
|
MODULE_DESCRIPTION("BIC TCP");
|