aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/tcp_rate.c
blob: 6ab197928abbcef968a72d2da5ce6667d027fce7 (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
// SPDX-License-Identifier: GPL-2.0-only
#include <net/tcp.h>

/* The bandwidth estimator estimates the rate at which the network
 * can currently deliver outbound data packets for this flow. At a high
 * level, it operates by taking a delivery rate sample for each ACK.
 *
 * A rate sample records the rate at which the network delivered packets
 * for this flow, calculated over the time interval between the transmission
 * of a data packet and the acknowledgment of that packet.
 *
 * Specifically, over the interval between each transmit and corresponding ACK,
 * the estimator generates a delivery rate sample. Typically it uses the rate
 * at which packets were acknowledged. However, the approach of using only the
 * acknowledgment rate faces a challenge under the prevalent ACK decimation or
 * compression: packets can temporarily appear to be delivered much quicker
 * than the bottleneck rate. Since it is physically impossible to do that in a
 * sustained fashion, when the estimator notices that the ACK rate is faster
 * than the transmit rate, it uses the latter:
 *
 *    send_rate = #pkts_delivered/(last_snd_time - first_snd_time)
 *    ack_rate  = #pkts_delivered/(last_ack_time - first_ack_time)
 *    bw = min(send_rate, ack_rate)
 *
 * Notice the estimator essentially estimates the goodput, not always the
 * network bottleneck link rate when the sending or receiving is limited by
 * other factors like applications or receiver window limits.  The estimator
 * deliberately avoids using the inter-packet spacing approach because that
 * approach requires a large number of samples and sophisticated filtering.
 *
 * TCP flows can often be application-limited in request/response workloads.
 * The estimator marks a bandwidth sample as application-limited if there
 * was some moment during the sampled window of packets when there was no data
 * ready to send in the write queue.
 */

/* Snapshot the current delivery information in the skb, to generate
 * a rate sample later when the skb is (s)acked in tcp_rate_skb_delivered().
 */
void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);

	 /* In general we need to start delivery rate samples from the
	  * time we received the most recent ACK, to ensure we include
	  * the full time the network needs to deliver all in-flight
	  * packets. If there are no packets in flight yet, then we
	  * know that any ACKs after now indicate that the network was
	  * able to deliver those packets completely in the sampling
	  * interval between now and the next ACK.
	  *
	  * Note that we use packets_out instead of tcp_packets_in_flight(tp)
	  * because the latter is a guess based on RTO and loss-marking
	  * heuristics. We don't want spurious RTOs or loss markings to cause
	  * a spuriously small time interval, causing a spuriously high
	  * bandwidth estimate.
	  */
	if (!tp->packets_out) {
		u64 tstamp_us = tcp_skb_timestamp_us(skb);

		tp->first_tx_mstamp  = tstamp_us;
		tp->delivered_mstamp = tstamp_us;
	}

	TCP_SKB_CB(skb)->tx.first_tx_mstamp	= tp->first_tx_mstamp;
	TCP_SKB_CB(skb)->tx.delivered_mstamp	= tp->delivered_mstamp;
	TCP_SKB_CB(skb)->tx.delivered		= tp->delivered;
	TCP_SKB_CB(skb)->tx.is_app_limited	= tp->app_limited ? 1 : 0;
}

/* When an skb is sacked or acked, we fill in the rate sample with the (prior)
 * delivery information when the skb was last transmitted.
 *
 * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is
 * called multiple times. We favor the information from the most recently
 * sent skb, i.e., the skb with the most recently sent time and the highest
 * sequence.
 */
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
			    struct rate_sample *rs)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
	u64 tx_tstamp;

	if (!scb->tx.delivered_mstamp)
		return;

	tx_tstamp = tcp_skb_timestamp_us(skb);
	if (!rs->prior_delivered ||
	    tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp,
			       scb->end_seq, rs->last_end_seq)) {
		rs->prior_delivered  = scb->tx.delivered;
		rs->prior_mstamp     = scb->tx.delivered_mstamp;
		rs->is_app_limited   = scb->tx.is_app_limited;
		rs->is_retrans	     = scb->sacked & TCPCB_RETRANS;
		rs->last_end_seq     = scb->end_seq;

		/* Record send time of most recently ACKed packet: */
		tp->first_tx_mstamp  = tx_tstamp;
		/* Find the duration of the "send phase" of this window: */
		rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp,
						     scb->tx.first_tx_mstamp);

	}
	/* Mark off the skb delivered once it's sacked to avoid being
	 * used again when it's cumulatively acked. For acked packets
	 * we don't need to reset since it'll be freed soon.
	 */
	if (scb->sacked & TCPCB_SACKED_ACKED)
		scb->tx.delivered_mstamp = 0;
}

/* Update the connection delivery information and generate a rate sample. */
void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
		  bool is_sack_reneg, struct rate_sample *rs)
{
	struct tcp_sock *tp = tcp_sk(sk);
	u32 snd_us, ack_us;

	/* Clear app limited if bubble is acked and gone. */
	if (tp->app_limited && after(tp->delivered, tp->app_limited))
		tp->app_limited = 0;

	/* TODO: there are multiple places throughout tcp_ack() to get
	 * current time. Refactor the code using a new "tcp_acktag_state"
	 * to carry current time, flags, stats like "tcp_sacktag_state".
	 */
	if (delivered)
		tp->delivered_mstamp = tp->tcp_mstamp;

	rs->acked_sacked = delivered;	/* freshly ACKed or SACKed */
	rs->losses = lost;		/* freshly marked lost */
	/* Return an invalid sample if no timing information is available or
	 * in recovery from loss with SACK reneging. Rate samples taken during
	 * a SACK reneging event may overestimate bw by including packets that
	 * were SACKed before the reneg.
	 */
	if (!rs->prior_mstamp || is_sack_reneg) {
		rs->delivered = -1;
		rs->interval_us = -1;
		return;
	}
	rs->delivered   = tp->delivered - rs->prior_delivered;

	/* Model sending data and receiving ACKs as separate pipeline phases
	 * for a window. Usually the ACK phase is longer, but with ACK
	 * compression the send phase can be longer. To be safe we use the
	 * longer phase.
	 */
	snd_us = rs->interval_us;				/* send phase */
	ack_us = tcp_stamp_us_delta(tp->tcp_mstamp,
				    rs->prior_mstamp); /* ack phase */
	rs->interval_us = max(snd_us, ack_us);

	/* Record both segment send and ack receive intervals */
	rs->snd_interval_us = snd_us;
	rs->rcv_interval_us = ack_us;

	/* Normally we expect interval_us >= min-rtt.
	 * Note that rate may still be over-estimated when a spuriously
	 * retransmistted skb was first (s)acked because "interval_us"
	 * is under-estimated (up to an RTT). However continuously
	 * measuring the delivery rate during loss recovery is crucial
	 * for connections suffer heavy or prolonged losses.
	 */
	if (unlikely(rs->interval_us < tcp_min_rtt(tp))) {
		if (!rs->is_retrans)
			pr_debug("tcp rate: %ld %d %u %u %u\n",
				 rs->interval_us, rs->delivered,
				 inet_csk(sk)->icsk_ca_state,
				 tp->rx_opt.sack_ok, tcp_min_rtt(tp));
		rs->interval_us = -1;
		return;
	}

	/* Record the last non-app-limited or the highest app-limited bw */
	if (!rs->is_app_limited ||
	    ((u64)rs->delivered * tp->rate_interval_us >=
	     (u64)tp->rate_delivered * rs->interval_us)) {
		tp->rate_delivered = rs->delivered;
		tp->rate_interval_us = rs->interval_us;
		tp->rate_app_limited = rs->is_app_limited;
	}
}

/* If a gap is detected between sends, mark the socket application-limited. */
void tcp_rate_check_app_limited(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	if (/* We have less than one packet to send. */
	    tp->write_seq - tp->snd_nxt < tp->mss_cache &&
	    /* Nothing in sending host's qdisc queues or NIC tx queue. */
	    sk_wmem_alloc_get(sk) < SKB_TRUESIZE(1) &&
	    /* We are not limited by CWND. */
	    tcp_packets_in_flight(tp) < tp->snd_cwnd &&
	    /* All lost packets have been retransmitted. */
	    tp->lost_out <= tp->retrans_out)
		tp->app_limited =
			(tp->delivered + tcp_packets_in_flight(tp)) ? : 1;
}
EXPORT_SYMBOL_GPL(tcp_rate_check_app_limited);