summaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_dctcp.c
blob: 10d728b6804c259e459cc81a82e5c961839cc578 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
/* 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>

#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 delayed_ack_reserved;
};

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 unsigned int dctcp_clamp_alpha_on_loss __read_mostly;
module_param(dctcp_clamp_alpha_on_loss, uint, 0644);
MODULE_PARM_DESC(dctcp_clamp_alpha_on_loss,
		 "parameter for clamping alpha on loss");

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->delayed_ack_reserved = 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)
{
	const struct dctcp *ca = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	return max(tp->snd_cwnd - ((tp->snd_cwnd * ca->dctcp_alpha) >> 11U), 2U);
}

/* Minimal DCTP CE state machine:
 *
 * S:	0 <- last pkt was non-CE
 *	1 <- last pkt was CE
 */

static void dctcp_ce_state_0_to_1(struct sock *sk)
{
	struct dctcp *ca = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	/* State has changed from CE=0 to CE=1 and delayed
	 * ACK has not sent yet.
	 */
	if (!ca->ce_state && ca->delayed_ack_reserved) {
		u32 tmp_rcv_nxt;

		/* Save current rcv_nxt. */
		tmp_rcv_nxt = tp->rcv_nxt;

		/* Generate previous ack with CE=0. */
		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
		tp->rcv_nxt = ca->prior_rcv_nxt;

		tcp_send_ack(sk);

		/* Recover current rcv_nxt. */
		tp->rcv_nxt = tmp_rcv_nxt;
	}

	ca->prior_rcv_nxt = tp->rcv_nxt;
	ca->ce_state = 1;

	tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
}

static void dctcp_ce_state_1_to_0(struct sock *sk)
{
	struct dctcp *ca = inet_csk_ca(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	/* State has changed from CE=1 to CE=0 and delayed
	 * ACK has not sent yet.
	 */
	if (ca->ce_state && ca->delayed_ack_reserved) {
		u32 tmp_rcv_nxt;

		/* Save current rcv_nxt. */
		tmp_rcv_nxt = tp->rcv_nxt;

		/* Generate previous ack with CE=1. */
		tp->ecn_flags |= TCP_ECN_DEMAND_CWR;
		tp->rcv_nxt = ca->prior_rcv_nxt;

		tcp_send_ack(sk);

		/* Recover current rcv_nxt. */
		tp->rcv_nxt = tmp_rcv_nxt;
	}

	ca->prior_rcv_nxt = tp->rcv_nxt;
	ca->ce_state = 0;

	tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
}

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_state(struct sock *sk, u8 new_state)
{
	if (dctcp_clamp_alpha_on_loss && new_state == TCP_CA_Loss) {
		struct dctcp *ca = inet_csk_ca(sk);

		/* If this extension is enabled, we clamp dctcp_alpha to
		 * max on packet loss; the motivation is that dctcp_alpha
		 * is an indicator to the extend of congestion and packet
		 * loss is an indicator of extreme congestion; setting
		 * this in practice turned out to be beneficial, and
		 * effectively assumes total congestion which reduces the
		 * window by half.
		 */
		ca->dctcp_alpha = DCTCP_MAX_ALPHA;
	}
}

static void dctcp_update_ack_reserved(struct sock *sk, enum tcp_ca_event ev)
{
	struct dctcp *ca = inet_csk_ca(sk);

	switch (ev) {
	case CA_EVENT_DELAYED_ACK:
		if (!ca->delayed_ack_reserved)
			ca->delayed_ack_reserved = 1;
		break;
	case CA_EVENT_NON_DELAYED_ACK:
		if (ca->delayed_ack_reserved)
			ca->delayed_ack_reserved = 0;
		break;
	default:
		/* Don't care for the rest. */
		break;
	}
}

static void dctcp_cwnd_event(struct sock *sk, enum tcp_ca_event ev)
{
	switch (ev) {
	case CA_EVENT_ECN_IS_CE:
		dctcp_ce_state_0_to_1(sk);
		break;
	case CA_EVENT_ECN_NO_CE:
		dctcp_ce_state_1_to_0(sk);
		break;
	case CA_EVENT_DELAYED_ACK:
	case CA_EVENT_NON_DELAYED_ACK:
		dctcp_update_ack_reserved(sk, ev);
		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 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,
	.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,
	.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)");
OpenPOWER on IntegriCloud