Compare commits

..

1 Commits

Author SHA1 Message Date
Lukas Prause
e5c3729522 Adds ECN handling managed by ROCCET. 2026-02-09 13:40:16 +01:00
2 changed files with 85 additions and 82 deletions

View File

@@ -1,4 +1,4 @@
// SPDX-License-Identifier: GPL-2.0
// SPDX-License-Identifier: GPL-2.0-only
/*
* TCP ROCCET: An RTT-Oriented CUBIC Congestion Control
* Extension for 5G and Beyond Networks
@@ -72,26 +72,30 @@
static int sr_rtt_upper_bound __read_mostly = 100;
static int ack_rate_diff_ss __read_mostly = 10;
static int ack_rate_diff_ca __read_mostly = 200;
static bool calculate_min_rtt __read_mostly;
static bool ignore_loss __read_mostly;
static int roccet_min_rtt_interpolation_factor __read_mostly = 70;
static int calculate_min_rtt __read_mostly = 0;
static int ignore_loss __read_mostly = 0;
static int roccet_minRTT_interpolation_factor __read_mostly = 70;
module_param(sr_rtt_upper_bound, int, 0644);
MODULE_PARM_DESC(sr_rtt_upper_bound, "ROCCET's upper bound for srRTT.");
module_param(ack_rate_diff_ss, int, 0644);
MODULE_PARM_DESC(ack_rate_diff_ss,
"ROCCET's threshold to exit slow start if ACK-rate defer by given amount of segments.");
"ROCCET's threshold to exit slow start if ACK-rate defer by "
"given amount of segments.");
module_param(ack_rate_diff_ca, int, 0644);
MODULE_PARM_DESC(ack_rate_diff_ca,
"ROCCET's threshold for ack-rate and cum_cwnd, in percantage of the current cwnd.");
module_param(calculate_min_rtt, bool, 0644);
"ROCCET's threshold for ack-rate and cum_cwnd, in percantage "
"of the current cwnd.");
module_param(calculate_min_rtt, int, 0644);
MODULE_PARM_DESC(calculate_min_rtt,
"Calculate min RTT if no lower RTT occurs after 10 sec.");
module_param(ignore_loss, bool, 0644);
module_param(ignore_loss, int, 0644);
MODULE_PARM_DESC(ignore_loss, "Ignore loss as a congestion event.");
module_param(roccet_min_rtt_interpolation_factor, int, 0644);
MODULE_PARM_DESC(roccet_min_rtt_interpolation_factor,
"ROCCET factor for interpolating the current RTT with the last minRTT (minRTT = (factor * currRTT + (100-factor) * minRTT) / 100)");
module_param(roccet_minRTT_interpolation_factor, int, 0644);
MODULE_PARM_DESC(
roccet_minRTT_interpolation_factor,
"ROCCET factor for interpolating the current RTT with the last minRTT "
"(minRTT = (factor * currRTT + (100-factor) * minRTT) / 100)");
static int fast_convergence __read_mostly = 1;
static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */
@@ -111,7 +115,8 @@ 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(bic_scale, int, 0444);
MODULE_PARM_DESC(bic_scale,
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");
@@ -124,8 +129,7 @@ static inline void roccettcp_reset(struct roccettcp *ca)
ca->bw_limit.next_check = 0;
ca->curr_min_rtt_timed.rtt = ~0U;
ca->curr_min_rtt_timed.time = ~0U;
ca->last_rtt = 0;
ca->ece_received = false;
ca->ece_received = 0;
}
static inline void update_min_rtt(struct sock *sk)
@@ -140,9 +144,9 @@ static inline void update_min_rtt(struct sock *sk)
u32 old_min_rtt = ca->curr_min_rtt_timed.rtt;
u32 interpolated_min_rtt =
(new_min_rtt * roccet_min_rtt_interpolation_factor +
(new_min_rtt * roccet_minRTT_interpolation_factor +
old_min_rtt *
(100 - roccet_min_rtt_interpolation_factor)) /
(100 - roccet_minRTT_interpolation_factor)) /
100;
ca->curr_min_rtt_timed.rtt = interpolated_min_rtt;
@@ -193,12 +197,13 @@ static inline void update_srrtt(struct sock *sk)
/* Calculate the new rRTT (Scaled by 100).
* 100 * ((sRTT - sRTT_min) / sRTT_min)
*/
u32 rrtt = (100 * (ca->curr_rtt - ca->curr_min_rtt_timed.rtt)) /
u32 rRTT = (100 * (ca->curr_rtt - ca->curr_min_rtt_timed.rtt)) /
ca->curr_min_rtt_timed.rtt;
// (1 - alpha) * srRTT + alpha * rRTT
ca->curr_srrtt = ((100 - ROCCET_ALPHA_TIMES_100) * ca->curr_srrtt +
ROCCET_ALPHA_TIMES_100 * rrtt) / 100;
ca->curr_srRTT = ((100 - ROCCET_ALPHA_TIMES_100) * ca->curr_srRTT +
ROCCET_ALPHA_TIMES_100 * rRTT) /
100;
}
__bpf_kfunc static void roccettcp_init(struct sock *sk)
@@ -210,7 +215,7 @@ __bpf_kfunc static void roccettcp_init(struct sock *sk)
if (initial_ssthresh)
tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
/* Initial roccet parameters */
/* Initial roccet paramters */
ca->roccet_last_event_time_us = 0;
ca->curr_min_rtt = ~0U;
ca->ack_rate.last_rate = 0;
@@ -334,7 +339,7 @@ static inline void bictcp_update(struct roccettcp *ca, u32 cwnd, u32 acked)
* (so time^3 is done by using 64 bit)
* and without the support of division of 64bit numbers
* (so all divisions are done by using 32 bit)
* also NOTE the unit of those variables
* also NOTE the unit of those veriables
* time = (t - K) / 2^bictcp_HZ
* c = bic_scale >> 10
* rtt = (srtt >> 3) / HZ
@@ -362,10 +367,11 @@ static inline void bictcp_update(struct roccettcp *ca, u32 cwnd, u32 acked)
bic_target = ca->bic_origin_point + delta;
/* cubic function - calc bictcp_cnt*/
if (bic_target > cwnd)
if (bic_target > cwnd) {
ca->cnt = cwnd / (bic_target - cwnd);
else
} else {
ca->cnt = 100 * cwnd; /* very small increment*/
}
/* The initial growth of cubic function may be too conservative
* when the available bandwidth is still unknown.
@@ -408,13 +414,13 @@ __bpf_kfunc static void roccettcp_cong_avoid(struct sock *sk, u32 ack,
u32 bw_limit_detect = 0;
u32 roccet_xj;
u32 jitter;
if (ca->last_rtt > ca->curr_rtt)
if (ca->last_rtt > ca->curr_rtt) {
jitter = ca->last_rtt - ca->curr_rtt;
else
} else {
jitter = ca->curr_rtt - ca->last_rtt;
}
/* Update roccet parameters */
/* Update roccet paramters */
update_ack_rate(sk);
update_min_rtt(sk);
update_srrtt(sk);
@@ -432,12 +438,13 @@ __bpf_kfunc static void roccettcp_cong_avoid(struct sock *sk, u32 ack,
* data rate.
*/
if ((tcp_in_slow_start(tp) && ca->curr_srrtt > sr_rtt_upper_bound &&
if ((tcp_in_slow_start(tp) && ca->curr_srRTT > sr_rtt_upper_bound &&
get_ack_rate_diff(ca) >= ack_rate_diff_ss) ||
(!tcp_is_cwnd_limited(sk) && tcp_in_slow_start(tp))) {
(!tcp_is_cwnd_limited(sk) && tcp_in_slow_start(tp))
) {
ca->epoch_start = 0;
/* Handle initial slow start. Here we observe the most problems */
/* Handle inital slow start. Here we observe the most problems */
if (tp->snd_ssthresh == TCP_INFINITE_SSTHRESH) {
tcp_sk(sk)->snd_ssthresh = tcp_snd_cwnd(tp) / 2;
tcp_snd_cwnd_set(tp, tcp_snd_cwnd(tp) / 2);
@@ -485,9 +492,9 @@ __bpf_kfunc static void roccettcp_cong_avoid(struct sock *sk, u32 ack,
if (roccet_xj < sr_rtt_upper_bound)
roccet_xj = sr_rtt_upper_bound;
if (ca->curr_srrtt > roccet_xj && (bw_limit_detect || ca->ece_received)) {
if (ca->curr_srRTT > roccet_xj && (bw_limit_detect || ca->ece_received)) {
if(ca->ece_received)
ca->ece_received = false;
ca->ece_received = 0;
ca->epoch_start = 0;
ca->roccet_last_event_time_us = now;
ca->cnt = 100 * tcp_snd_cwnd(tp);
@@ -544,7 +551,6 @@ __bpf_kfunc static u32 roccettcp_recalc_ssthresh(struct sock *sk)
__bpf_kfunc static void roccettcp_state(struct sock *sk, u8 new_state)
{
struct roccettcp *ca = inet_csk_ca(sk);
if (new_state == TCP_CA_Loss)
roccettcp_reset(ca);
}
@@ -563,7 +569,6 @@ __bpf_kfunc static void roccettcp_acked(struct sock *sk,
return;
u32 delay = sample->rtt_us;
if (delay == 0)
delay = 1;
@@ -583,10 +588,11 @@ __bpf_kfunc static void roccet_in_ack_event(struct sock *sk, u32 flags)
struct roccettcp *ca = inet_csk_ca(sk);
/* Handle ECE bit.
* Processing of ECE events is done in roccettcp_cong_avoid()
* Pocessing of ECE events is done in roccettcp_cong_avoid()
*/
if (flags & CA_ACK_ECE)
ca->ece_received = true;
if (flags & CA_ACK_ECE) {
ca->ece_received = 1;
}
}
static struct tcp_congestion_ops roccet_tcp __read_mostly = {

View File

@@ -1,4 +1,3 @@
/* SPDX-License-Identifier: GPL-2.0 */
/*
* TCP ROCCET congestion control interface
*/
@@ -7,21 +6,21 @@
#include <linux/math64.h>
struct ack_rate {
struct AckRate {
u16 last_rate; /* Last ACK-rate */
u32 last_rate_time; /* Timestamp of the last ACK-rate */
u16 curr_rate; /* Current ACK-rate */
u16 cnt; /* Used for counting acks */
};
struct bandwidth_limit_detect {
struct BandwidthLimitDetect {
u32 sum_cwnd; /* sum of cwnd during time interval */
u32 sum_acked; /* sum of received acks during time interval */
u32 next_check; /* end/upper bound of time interval */
};
struct timed_rtt {
u32 time; /* Time of recording */
struct TimedRTT {
u32 time; /* Time of recoding */
u32 rtt; /* Measured RTT */
};
@@ -33,8 +32,7 @@ struct roccettcp {
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
*/
beginning of the current epoch */
u32 delay_min; /* min delay (usec) */
u32 epoch_start; /* beginning of an epoch */
u32 ack_cnt; /* number of acks */
@@ -42,14 +40,13 @@ struct roccettcp {
u32 curr_rtt; /* the minimum rtt of current round */
u32 roccet_last_event_time_us; /* The last time ROCCET was triggered */
bool ece_received; /* Set to true if an ECE bit was received */
u32 ece_received; /* Set to true if an ECE bit was received */
u32 curr_min_rtt; /* The current observed minRTT */
struct timed_rtt curr_min_rtt_timed; /* The current observed minRTT with
* the timestamp when it was observed
*/
u32 curr_srrtt; /* The srRTT calculated based on the latest ACK */
struct ack_rate ack_rate; /* The last and the current ACK rate */
struct bandwidth_limit_detect bw_limit;
struct TimedRTT curr_min_rtt_timed; /* The current observed minRTT with
the timestamp when it was observed */
u32 curr_srRTT; /* The srRTT calculated based on the latest ACK */
struct AckRate ack_rate; /* The last and the current ACK rate */
struct BandwidthLimitDetect bw_limit;
u32 last_rtt; /* Used for jitter calculation */
};