aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_illinois.c
blob: 91a2a34604cdb4f2d5df108b203e857e16b86ab9 (plain) (blame)
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
/*
 * TCP Illinois congestion control.
 * Home page:
 *	http://www.ews.uiuc.edu/~shaoliu/tcpillinois/index.html
 *
 * The algorithm is described in:
 * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm
 *  for High-Speed Networks"
 * http://www.ews.uiuc.edu/~shaoliu/papersandslides/liubassri06perf.pdf
 *
 * Implemented from description in paper and ns-2 simulation.
 * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org>
 */

#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/inet_diag.h>
#include <asm/div64.h>
#include <net/tcp.h>

#define ALPHA_SHIFT	7
#define ALPHA_SCALE	(1u<<ALPHA_SHIFT)
#define ALPHA_MIN	((3*ALPHA_SCALE)/10)	/* ~0.3 */
#define ALPHA_MAX	(10*ALPHA_SCALE)	/* 10.0 */
#define ALPHA_BASE	ALPHA_SCALE		/* 1.0 */

#define BETA_SHIFT	6
#define BETA_SCALE	(1u<<BETA_SHIFT)
#define BETA_MIN	(BETA_SCALE/8)		/* 0.8 */
#define BETA_MAX	(BETA_SCALE/2)
#define BETA_BASE	BETA_MAX		/* 0.5 */

#define THETA		5

static int win_thresh __read_mostly = 15;
module_param(win_thresh, int, 0644);
MODULE_PARM_DESC(win_thresh, "Window threshold for starting adaptive sizing");

#define MAX_RTT		0x7fffffff

/* TCP Illinois Parameters */
struct tcp_illinois {
	u32	last_alpha;
	u32	min_rtt;
	u32	max_rtt;
	u32	rtt_low;
	u32	rtt_cnt;
	u64	sum_rtt;
};

static void tcp_illinois_init(struct sock *sk)
{
	struct tcp_illinois *ca = inet_csk_ca(sk);

	ca->last_alpha = ALPHA_BASE;
	ca->min_rtt = 0x7fffffff;
}

/*
 * Keep track of min, max and average RTT
 */
static void tcp_illinois_rtt_calc(struct sock *sk, u32 rtt)
{
	struct tcp_illinois *ca = inet_csk_ca(sk);

	if (rtt < ca->min_rtt)
		ca->min_rtt = rtt;
	if (rtt > ca->max_rtt)
		ca->max_rtt = rtt;

	if (++ca->rtt_cnt == 1)
		ca->sum_rtt = rtt;
	else
		ca->sum_rtt += rtt;
}

/* max queuing delay */
static inline u32 max_delay(const struct tcp_illinois *ca)
{
	return ca->max_rtt - ca->min_rtt;
}

/* average queueing delay */
static u32 avg_delay(struct tcp_illinois *ca)
{
	u64 avg_rtt = ca->sum_rtt;

	do_div(avg_rtt, ca->rtt_cnt);

	ca->sum_rtt = 0;
	ca->rtt_cnt = 0;

	return avg_rtt - ca->min_rtt;
}

/*
 * Compute value of alpha used for additive increase.
 * If small window then use 1.0, equivalent to Reno.
 *
 * For larger windows, adjust based on average delay.
 * A. If average delay is at minimum (we are uncongested),
 *    then use large alpha (10.0) to increase faster.
 * B. If average delay is at maximum (getting congested)
 *    then use small alpha (1.0)
 *
 * The result is a convex window growth curve.
 */
static u32 alpha(const struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_illinois *ca = inet_csk_ca(sk);
	u32 dm = max_delay(ca);
	u32 da = avg_delay(ca);
	u32 d1, a;

	if (tp->snd_cwnd < win_thresh)
		return ALPHA_BASE;	/* same as Reno (1.0) */

	d1 = dm / 100;
	if (da <= d1) {
		/* Don't let noise force agressive response */
		if (ca->rtt_low < THETA) {
			++ca->rtt_low;
			return ca->last_alpha;
		} else
			return ALPHA_MAX;
	}

	ca->rtt_low = 0;

	/*
	 * Based on:
	 *
	 *      (dm - d1) amin amax
	 * k1 = -------------------
	 *         amax - amin
	 *
	 *       (dm - d1) amin
	 * k2 = ----------------  - d1
	 *        amax - amin
	 *
	 *             k1
	 * alpha = ----------
	 *          k2 + da
	 */

	dm -= d1;
	da -= d1;

	a = (dm * ALPHA_MAX) / (dm - (da  * (ALPHA_MAX - ALPHA_MIN)) / ALPHA_MIN);
	ca->last_alpha = a;
	return a;
}

/*
 * Increase window in response to successful acknowledgment.
 */
static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 rtt,
				    u32 in_flight, int flag)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* RFC2861 only increase cwnd if fully utilized */
	if (!tcp_is_cwnd_limited(sk, in_flight))
		return;

	/* In slow start */
	if (tp->snd_cwnd <= tp->snd_ssthresh)
		tcp_slow_start(tp);

	else {
		/* additive increase  cwnd += alpha / cwnd */
		if ((tp->snd_cwnd_cnt * alpha(sk)) >> ALPHA_SHIFT >= tp->snd_cwnd) {
			if (tp->snd_cwnd < tp->snd_cwnd_clamp)
				tp->snd_cwnd++;
			tp->snd_cwnd_cnt = 0;
		} else
			tp->snd_cwnd_cnt++;
	}
}

/*
 * Beta used for multiplicative decrease.
 * For small window sizes returns same value as Reno (0.5)
 *
 * If delay is small (10% of max) then beta = 1/8
 * If delay is up to 80% of max then beta = 1/2
 * In between is a linear function
 */
static inline u32 beta(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_illinois *ca = inet_csk_ca(sk);
	u32 dm = max_delay(ca);
	u32 da = avg_delay(ca);
	u32 d2, d3;

	if (tp->snd_cwnd < win_thresh)
		return BETA_BASE;

	d2 = dm / 10;
	if (da <= d2)
		return BETA_MIN;
	d3 = (8 * dm) / 10;
	if (da >= d3 || d3 <= d2)
		return BETA_MAX;

	/*
	 * Based on:
	 *
	 *       bmin d3 - bmax d2
	 * k3 = -------------------
	 *         d3 - d2
	 *
	 *       bmax - bmin
	 * k4 = -------------
	 *         d3 - d2
	 *
	 * b = k3 + k4 da
	 */
	return (BETA_MIN * d3 - BETA_MAX * d2 + (BETA_MAX - BETA_MIN) * da)
		/ (d3 - d2);
}

static u32 tcp_illinois_ssthresh(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Multiplicative decrease */
	return max((tp->snd_cwnd * beta(sk)) >> BETA_SHIFT, 2U);
}

/* Extract info for TCP socket info provided via netlink.
 * We aren't really doing Vegas, but we can provide RTT info
 */
static void tcp_illinois_get_info(struct sock *sk, u32 ext,
			       struct sk_buff *skb)
{
	const struct tcp_illinois *ca = inet_csk_ca(sk);

	if (ext & (1 << (INET_DIAG_VEGASINFO - 1))) {
		struct tcpvegas_info info = {
			.tcpv_enabled = 1,
			.tcpv_rttcnt = ca->rtt_cnt,
			.tcpv_minrtt = ca->min_rtt,
		};
		u64 avg_rtt = ca->sum_rtt;
		do_div(avg_rtt, ca->rtt_cnt);
		info.tcpv_rtt = avg_rtt;

		nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
	}
}

static struct tcp_congestion_ops tcp_illinois = {
	.init		= tcp_illinois_init,
	.ssthresh	= tcp_illinois_ssthresh,
	.min_cwnd	= tcp_reno_min_cwnd,
	.cong_avoid	= tcp_illinois_cong_avoid,
	.rtt_sample	= tcp_illinois_rtt_calc,
	.get_info	= tcp_illinois_get_info,

	.owner		= THIS_MODULE,
	.name		= "illinois",
};

static int __init tcp_illinois_register(void)
{
	BUILD_BUG_ON(sizeof(struct tcp_illinois) > ICSK_CA_PRIV_SIZE);
	return tcp_register_congestion_control(&tcp_illinois);
}

static void __exit tcp_illinois_unregister(void)
{
	tcp_unregister_congestion_control(&tcp_illinois);
}

module_init(tcp_illinois_register);
module_exit(tcp_illinois_unregister);

MODULE_AUTHOR("Stephen Hemminger, Shao Liu");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("TCP Illinois");
MODULE_VERSION("0.3");