tcp: internal implementation for pacing

BBR congestion control depends on pacing, and pacing is
currently handled by sch_fq packet scheduler for performance reasons,
and also because implemening pacing with FQ was convenient to truly
avoid bursts.

However there are many cases where this packet scheduler constraint
is not practical.
- Many linux hosts are not focusing on handling thousands of TCP
  flows in the most efficient way.
- Some routers use fq_codel or other AQM, but still would like
  to use BBR for the few TCP flows they initiate/terminate.

This patch implements an automatic fallback to internal pacing.

Pacing is requested either by BBR or use of SO_MAX_PACING_RATE option.

If sch_fq happens to be in the egress path, pacing is delegated to
the qdisc, otherwise pacing is done by TCP itself.

One advantage of pacing from TCP stack is to get more precise rtt
estimations, and less work done from TX completion, since TCP Small
queue limits are not generally hit. Setups with single TX queue but
many cpus might even benefit from this.

Note that unlike sch_fq, we do not take into account header sizes.
Taking care of these headers would add additional complexity for
no practical differences in behavior.

Some performance numbers using 800 TCP_STREAM flows rate limited to
~48 Mbit per second on 40Gbit NIC.

If MQ+pfifo_fast is used on the NIC :

$ sar -n DEV 1 5 | grep eth
14:48:44         eth0 725743.00 2932134.00  46776.76 4335184.68      0.00      0.00      1.00
14:48:45         eth0 725349.00 2932112.00  46751.86 4335158.90      0.00      0.00      0.00
14:48:46         eth0 725101.00 2931153.00  46735.07 4333748.63      0.00      0.00      0.00
14:48:47         eth0 725099.00 2931161.00  46735.11 4333760.44      0.00      0.00      1.00
14:48:48         eth0 725160.00 2931731.00  46738.88 4334606.07      0.00      0.00      0.00
Average:         eth0 725290.40 2931658.20  46747.54 4334491.74      0.00      0.00      0.40
$ vmstat 1 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st
 4  0      0 259825920  45644 2708324    0    0    21     2  247   98  0  0 100  0  0
 4  0      0 259823744  45644 2708356    0    0     0     0 2400825 159843  0 19 81  0  0
 0  0      0 259824208  45644 2708072    0    0     0     0 2407351 159929  0 19 81  0  0
 1  0      0 259824592  45644 2708128    0    0     0     0 2405183 160386  0 19 80  0  0
 1  0      0 259824272  45644 2707868    0    0     0    32 2396361 158037  0 19 81  0  0

Now use MQ+FQ :

lpaa23:~# echo fq >/proc/sys/net/core/default_qdisc
lpaa23:~# tc qdisc replace dev eth0 root mq

$ sar -n DEV 1 5 | grep eth
14:49:57         eth0 678614.00 2727930.00  43739.13 4033279.14      0.00      0.00      0.00
14:49:58         eth0 677620.00 2723971.00  43674.69 4027429.62      0.00      0.00      1.00
14:49:59         eth0 676396.00 2719050.00  43596.83 4020125.02      0.00      0.00      0.00
14:50:00         eth0 675197.00 2714173.00  43518.62 4012938.90      0.00      0.00      1.00
14:50:01         eth0 676388.00 2719063.00  43595.47 4020171.64      0.00      0.00      0.00
Average:         eth0 676843.00 2720837.40  43624.95 4022788.86      0.00      0.00      0.40
$ vmstat 1 5
procs -----------memory---------- ---swap-- -----io---- -system-- ------cpu-----
 r  b   swpd   free   buff  cache   si   so    bi    bo   in   cs us sy id wa st
 2  0      0 259832240  46008 2710912    0    0    21     2  223  192  0  1 99  0  0
 1  0      0 259832896  46008 2710744    0    0     0     0 1702206 198078  0 17 82  0  0
 0  0      0 259830272  46008 2710596    0    0     0     0 1696340 197756  1 17 83  0  0
 4  0      0 259829168  46024 2710584    0    0    16     0 1688472 197158  1 17 82  0  0
 3  0      0 259830224  46024 2710408    0    0     0     0 1692450 197212  0 18 82  0  0

As expected, number of interrupts per second is very different.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Cc: Van Jacobson <vanj@google.com>
Cc: Jerry Chu <hkchu@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 13 insertions, 1 deletions

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index b6d5adcee8fc..22854f028434 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -293,6 +293,8 @@ struct tcp_sock {
 	u32	sacked_out;	/* SACK'd packets			*/
 	u32	fackets_out;	/* FACK'd packets			*/
 
+	struct hrtimer	pacing_timer;
+
 	/* from STCP, retrans queue hinting */
 	struct sk_buff* lost_skb_hint;
 	struct sk_buff *retransmit_skb_hint;
diff --git a/include/net/sock.h b/include/net/sock.h
index 42264035dec0..3467d9e89e7d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -253,6 +253,7 @@ struct sock_common {
   *	@sk_ll_usec: usecs to busypoll when there is no data
   *	@sk_allocation: allocation mode
   *	@sk_pacing_rate: Pacing rate (if supported by transport/packet scheduler)
+  *	@sk_pacing_status: Pacing status (requested, handled by sch_fq)
   *	@sk_max_pacing_rate: Maximum pacing rate (%SO_MAX_PACING_RATE)
   *	@sk_sndbuf: size of send buffer in bytes
   *	@sk_padding: unused element for alignment
@@ -396,7 +397,7 @@ struct sock {
 	__s32			sk_peek_off;
 	int			sk_write_pending;
 	__u32			sk_dst_pending_confirm;
-	/* Note: 32bit hole on 64bit arches */
+	u32			sk_pacing_status; /* see enum sk_pacing */
 	long			sk_sndtimeo;
 	struct timer_list	sk_timer;
 	__u32			sk_priority;
@@ -475,6 +476,12 @@ struct sock {
 	struct rcu_head		sk_rcu;
 };
 
+enum sk_pacing {
+	SK_PACING_NONE		= 0,
+	SK_PACING_NEEDED	= 1,
+	SK_PACING_FQ		= 2,
+};
+
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
 
 #define rcu_dereference_sk_user_data(sk)	rcu_dereference(__sk_user_data((sk)))
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 38a7427ae902..b4dc93dae98c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -574,6 +574,7 @@ void tcp_fin(struct sock *sk);
 void tcp_init_xmit_timers(struct sock *);
 static inline void tcp_clear_xmit_timers(struct sock *sk)
 {
+	hrtimer_cancel(&tcp_sk(sk)->pacing_timer);
 	inet_csk_clear_xmit_timers(sk);
 }
 
@@ -1945,4 +1946,6 @@ static inline void tcp_listendrop(const struct sock *sk)
 	__NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENDROPS);
 }
 
+enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer);
+
 #endif	/* _TCP_H */