mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-16 09:26:47 +07:00
aecfde2310
RFC8257 §3.5 explicitly states that "A DCTCP sender MUST react to loss episodes in the same way as conventional TCP". Currently, Linux DCTCP performs no cwnd reduction when losses are encountered. Optionally, the dctcp_clamp_alpha_on_loss resets alpha to its maximal value if a RTO happens. This behavior is sub-optimal for at least two reasons: i) it ignores losses triggering fast retransmissions; and ii) it causes unnecessary large cwnd reduction in the future if the loss was isolated as it resets the historical term of DCTCP's alpha EWMA to its maximal value (i.e., denoting a total congestion). The second reason has an especially noticeable effect when using DCTCP in high BDP environments, where alpha normally stays at low values. This patch replace the clamping of alpha by setting ssthresh to half of cwnd for both fast retransmissions and RTOs, at most once per RTT. Consequently, the dctcp_clamp_alpha_on_loss module parameter has been removed. The table below shows experimental results where we measured the drop probability of a PIE AQM (not applying ECN marks) at a bottleneck in the presence of a single TCP flow with either the alpha-clamping option enabled or the cwnd halving proposed by this patch. Results using reno or cubic are given for comparison. | Link | RTT | Drop TCP CC | speed | base+AQM | probability ==================|=========|==========|============ CUBIC | 40Mbps | 7+20ms | 0.21% RENO | | | 0.19% DCTCP-CLAMP-ALPHA | | | 25.80% DCTCP-HALVE-CWND | | | 0.22% ------------------|---------|----------|------------ CUBIC | 100Mbps | 7+20ms | 0.03% RENO | | | 0.02% DCTCP-CLAMP-ALPHA | | | 23.30% DCTCP-HALVE-CWND | | | 0.04% ------------------|---------|----------|------------ CUBIC | 800Mbps | 1+1ms | 0.04% RENO | | | 0.05% DCTCP-CLAMP-ALPHA | | | 18.70% DCTCP-HALVE-CWND | | | 0.06% We see that, without halving its cwnd for all source of losses, DCTCP drives the AQM to large drop probabilities in order to keep the queue length under control (i.e., it repeatedly faces RTOs). Instead, if DCTCP reacts to all source of losses, it can then be controlled by the AQM using similar drop levels than cubic or reno. Signed-off-by: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com> Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com> Cc: Bob Briscoe <research@bobbriscoe.net> Cc: Lawrence Brakmo <brakmo@fb.com> Cc: Florian Westphal <fw@strlen.de> Cc: Daniel Borkmann <borkmann@iogearbox.net> Cc: Yuchung Cheng <ycheng@google.com> Cc: Neal Cardwell <ncardwell@google.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Andrew Shewmaker <agshew@gmail.com> Cc: Glenn Judd <glenn.judd@morganstanley.com> Acked-by: Florian Westphal <fw@strlen.de> Acked-by: Neal Cardwell <ncardwell@google.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Signed-off-by: David S. Miller <davem@davemloft.net>
274 lines
7.6 KiB
C
274 lines
7.6 KiB
C
/* DataCenter TCP (DCTCP) congestion control.
|
|
*
|
|
* http://simula.stanford.edu/~alizade/Site/DCTCP.html
|
|
*
|
|
* This is an implementation of DCTCP over Reno, an enhancement to the
|
|
* TCP congestion control algorithm designed for data centers. DCTCP
|
|
* leverages Explicit Congestion Notification (ECN) in the network to
|
|
* provide multi-bit feedback to the end hosts. DCTCP's goal is to meet
|
|
* the following three data center transport requirements:
|
|
*
|
|
* - High burst tolerance (incast due to partition/aggregate)
|
|
* - Low latency (short flows, queries)
|
|
* - High throughput (continuous data updates, large file transfers)
|
|
* with commodity shallow buffered switches
|
|
*
|
|
* The algorithm is described in detail in the following two papers:
|
|
*
|
|
* 1) Mohammad Alizadeh, Albert Greenberg, David A. Maltz, Jitendra Padhye,
|
|
* Parveen Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan:
|
|
* "Data Center TCP (DCTCP)", Data Center Networks session
|
|
* Proc. ACM SIGCOMM, New Delhi, 2010.
|
|
* http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp-final.pdf
|
|
*
|
|
* 2) Mohammad Alizadeh, Adel Javanmard, and Balaji Prabhakar:
|
|
* "Analysis of DCTCP: Stability, Convergence, and Fairness"
|
|
* Proc. ACM SIGMETRICS, San Jose, 2011.
|
|
* http://simula.stanford.edu/~alizade/Site/DCTCP_files/dctcp_analysis-full.pdf
|
|
*
|
|
* Initial prototype from Abdul Kabbani, Masato Yasuda and Mohammad Alizadeh.
|
|
*
|
|
* Authors:
|
|
*
|
|
* Daniel Borkmann <dborkman@redhat.com>
|
|
* Florian Westphal <fw@strlen.de>
|
|
* Glenn Judd <glenn.judd@morganstanley.com>
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify
|
|
* it under the terms of the GNU General Public License as published by
|
|
* the Free Software Foundation; either version 2 of the License, or (at
|
|
* your option) any later version.
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/mm.h>
|
|
#include <net/tcp.h>
|
|
#include <linux/inet_diag.h>
|
|
#include "tcp_dctcp.h"
|
|
|
|
#define DCTCP_MAX_ALPHA 1024U
|
|
|
|
struct dctcp {
|
|
u32 acked_bytes_ecn;
|
|
u32 acked_bytes_total;
|
|
u32 prior_snd_una;
|
|
u32 prior_rcv_nxt;
|
|
u32 dctcp_alpha;
|
|
u32 next_seq;
|
|
u32 ce_state;
|
|
u32 loss_cwnd;
|
|
};
|
|
|
|
static unsigned int dctcp_shift_g __read_mostly = 4; /* g = 1/2^4 */
|
|
module_param(dctcp_shift_g, uint, 0644);
|
|
MODULE_PARM_DESC(dctcp_shift_g, "parameter g for updating dctcp_alpha");
|
|
|
|
static unsigned int dctcp_alpha_on_init __read_mostly = DCTCP_MAX_ALPHA;
|
|
module_param(dctcp_alpha_on_init, uint, 0644);
|
|
MODULE_PARM_DESC(dctcp_alpha_on_init, "parameter for initial alpha value");
|
|
|
|
static struct tcp_congestion_ops dctcp_reno;
|
|
|
|
static void dctcp_reset(const struct tcp_sock *tp, struct dctcp *ca)
|
|
{
|
|
ca->next_seq = tp->snd_nxt;
|
|
|
|
ca->acked_bytes_ecn = 0;
|
|
ca->acked_bytes_total = 0;
|
|
}
|
|
|
|
static void dctcp_init(struct sock *sk)
|
|
{
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
if ((tp->ecn_flags & TCP_ECN_OK) ||
|
|
(sk->sk_state == TCP_LISTEN ||
|
|
sk->sk_state == TCP_CLOSE)) {
|
|
struct dctcp *ca = inet_csk_ca(sk);
|
|
|
|
ca->prior_snd_una = tp->snd_una;
|
|
ca->prior_rcv_nxt = tp->rcv_nxt;
|
|
|
|
ca->dctcp_alpha = min(dctcp_alpha_on_init, DCTCP_MAX_ALPHA);
|
|
|
|
ca->loss_cwnd = 0;
|
|
ca->ce_state = 0;
|
|
|
|
dctcp_reset(tp, ca);
|
|
return;
|
|
}
|
|
|
|
/* No ECN support? Fall back to Reno. Also need to clear
|
|
* ECT from sk since it is set during 3WHS for DCTCP.
|
|
*/
|
|
inet_csk(sk)->icsk_ca_ops = &dctcp_reno;
|
|
INET_ECN_dontxmit(sk);
|
|
}
|
|
|
|
static u32 dctcp_ssthresh(struct sock *sk)
|
|
{
|
|
struct dctcp *ca = inet_csk_ca(sk);
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
ca->loss_cwnd = tp->snd_cwnd;
|
|
return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
|
|
}
|
|
|
|
static void dctcp_update_alpha(struct sock *sk, u32 flags)
|
|
{
|
|
const struct tcp_sock *tp = tcp_sk(sk);
|
|
struct dctcp *ca = inet_csk_ca(sk);
|
|
u32 acked_bytes = tp->snd_una - ca->prior_snd_una;
|
|
|
|
/* If ack did not advance snd_una, count dupack as MSS size.
|
|
* If ack did update window, do not count it at all.
|
|
*/
|
|
if (acked_bytes == 0 && !(flags & CA_ACK_WIN_UPDATE))
|
|
acked_bytes = inet_csk(sk)->icsk_ack.rcv_mss;
|
|
if (acked_bytes) {
|
|
ca->acked_bytes_total += acked_bytes;
|
|
ca->prior_snd_una = tp->snd_una;
|
|
|
|
if (flags & CA_ACK_ECE)
|
|
ca->acked_bytes_ecn += acked_bytes;
|
|
}
|
|
|
|
/* Expired RTT */
|
|
if (!before(tp->snd_una, ca->next_seq)) {
|
|
u64 bytes_ecn = ca->acked_bytes_ecn;
|
|
u32 alpha = ca->dctcp_alpha;
|
|
|
|
/* alpha = (1 - g) * alpha + g * F */
|
|
|
|
alpha -= min_not_zero(alpha, alpha >> dctcp_shift_g);
|
|
if (bytes_ecn) {
|
|
/* If dctcp_shift_g == 1, a 32bit value would overflow
|
|
* after 8 Mbytes.
|
|
*/
|
|
bytes_ecn <<= (10 - dctcp_shift_g);
|
|
do_div(bytes_ecn, max(1U, ca->acked_bytes_total));
|
|
|
|
alpha = min(alpha + (u32)bytes_ecn, DCTCP_MAX_ALPHA);
|
|
}
|
|
/* dctcp_alpha can be read from dctcp_get_info() without
|
|
* synchro, so we ask compiler to not use dctcp_alpha
|
|
* as a temporary variable in prior operations.
|
|
*/
|
|
WRITE_ONCE(ca->dctcp_alpha, alpha);
|
|
dctcp_reset(tp, ca);
|
|
}
|
|
}
|
|
|
|
static void dctcp_react_to_loss(struct sock *sk)
|
|
{
|
|
struct dctcp *ca = inet_csk_ca(sk);
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
|
|
ca->loss_cwnd = tp->snd_cwnd;
|
|
tp->snd_ssthresh = max(tp->snd_cwnd >> 1U, 2U);
|
|
}
|
|
|
|
static void dctcp_state(struct sock *sk, u8 new_state)
|
|
{
|
|
if (new_state == TCP_CA_Recovery &&
|
|
new_state != inet_csk(sk)->icsk_ca_state)
|
|
dctcp_react_to_loss(sk);
|
|
/* We handle RTO in dctcp_cwnd_event to ensure that we perform only
|
|
* one loss-adjustment per RTT.
|
|
*/
|
|
}
|
|
|
|
static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
|
|
{
|
|
struct dctcp *ca = inet_csk_ca(sk);
|
|
|
|
switch (ev) {
|
|
case CA_EVENT_ECN_IS_CE:
|
|
case CA_EVENT_ECN_NO_CE:
|
|
dctcp_ece_ack_update(sk, ev, &ca->prior_rcv_nxt, &ca->ce_state);
|
|
break;
|
|
case CA_EVENT_LOSS:
|
|
dctcp_react_to_loss(sk);
|
|
break;
|
|
default:
|
|
/* Don't care for the rest. */
|
|
break;
|
|
}
|
|
}
|
|
|
|
static size_t dctcp_get_info(struct sock *sk, u32 ext, int *attr,
|
|
union tcp_cc_info *info)
|
|
{
|
|
const struct dctcp *ca = inet_csk_ca(sk);
|
|
|
|
/* Fill it also in case of VEGASINFO due to req struct limits.
|
|
* We can still correctly retrieve it later.
|
|
*/
|
|
if (ext & (1 << (INET_DIAG_DCTCPINFO - 1)) ||
|
|
ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
|
|
memset(&info->dctcp, 0, sizeof(info->dctcp));
|
|
if (inet_csk(sk)->icsk_ca_ops != &dctcp_reno) {
|
|
info->dctcp.dctcp_enabled = 1;
|
|
info->dctcp.dctcp_ce_state = (u16) ca->ce_state;
|
|
info->dctcp.dctcp_alpha = ca->dctcp_alpha;
|
|
info->dctcp.dctcp_ab_ecn = ca->acked_bytes_ecn;
|
|
info->dctcp.dctcp_ab_tot = ca->acked_bytes_total;
|
|
}
|
|
|
|
*attr = INET_DIAG_DCTCPINFO;
|
|
return sizeof(info->dctcp);
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
static u32 dctcp_cwnd_undo(struct sock *sk)
|
|
{
|
|
const struct dctcp *ca = inet_csk_ca(sk);
|
|
|
|
return max(tcp_sk(sk)->snd_cwnd, ca->loss_cwnd);
|
|
}
|
|
|
|
static struct tcp_congestion_ops dctcp __read_mostly = {
|
|
.init = dctcp_init,
|
|
.in_ack_event = dctcp_update_alpha,
|
|
.cwnd_event = dctcp_cwnd_event,
|
|
.ssthresh = dctcp_ssthresh,
|
|
.cong_avoid = tcp_reno_cong_avoid,
|
|
.undo_cwnd = dctcp_cwnd_undo,
|
|
.set_state = dctcp_state,
|
|
.get_info = dctcp_get_info,
|
|
.flags = TCP_CONG_NEEDS_ECN,
|
|
.owner = THIS_MODULE,
|
|
.name = "dctcp",
|
|
};
|
|
|
|
static struct tcp_congestion_ops dctcp_reno __read_mostly = {
|
|
.ssthresh = tcp_reno_ssthresh,
|
|
.cong_avoid = tcp_reno_cong_avoid,
|
|
.undo_cwnd = tcp_reno_undo_cwnd,
|
|
.get_info = dctcp_get_info,
|
|
.owner = THIS_MODULE,
|
|
.name = "dctcp-reno",
|
|
};
|
|
|
|
static int __init dctcp_register(void)
|
|
{
|
|
BUILD_BUG_ON(sizeof(struct dctcp) > ICSK_CA_PRIV_SIZE);
|
|
return tcp_register_congestion_control(&dctcp);
|
|
}
|
|
|
|
static void __exit dctcp_unregister(void)
|
|
{
|
|
tcp_unregister_congestion_control(&dctcp);
|
|
}
|
|
|
|
module_init(dctcp_register);
|
|
module_exit(dctcp_unregister);
|
|
|
|
MODULE_AUTHOR("Daniel Borkmann <dborkman@redhat.com>");
|
|
MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
|
|
MODULE_AUTHOR("Glenn Judd <glenn.judd@morganstanley.com>");
|
|
|
|
MODULE_LICENSE("GPL v2");
|
|
MODULE_DESCRIPTION("DataCenter TCP (DCTCP)");
|