aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
authorEric Dumazet <edumazet@google.com>2017-05-16 04:24:36 -0700
committerDavid S. Miller <davem@davemloft.net>2017-05-16 15:43:31 -0400
commit218af599fa635b107cfe10acf3249c4dfe5e4123 (patch)
tree7275a28c48cbcf4f10cab95885a16f44e6d8eede /net/ipv4
parentMerge branch 'udp-scalability-improvements' (diff)
downloadlinux-dev-218af599fa635b107cfe10acf3249c4dfe5e4123.tar.xz
linux-dev-218af599fa635b107cfe10acf3249c4dfe5e4123.zip
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>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/tcp_bbr.c9
-rw-r--r--net/ipv4/tcp_output.c80
-rw-r--r--net/ipv4/tcp_timer.c3
3 files changed, 88 insertions, 4 deletions
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index b89bce4c721e..92b045c72163 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -52,10 +52,9 @@
* There is a public e-mail list for discussing BBR development and testing:
* https://groups.google.com/forum/#!forum/bbr-dev
*
- * NOTE: BBR *must* be used with the fq qdisc ("man tc-fq") with pacing enabled,
- * since pacing is integral to the BBR design and implementation.
- * BBR without pacing would not function properly, and may incur unnecessary
- * high packet loss rates.
+ * NOTE: BBR might be used with the fq qdisc ("man tc-fq") with pacing enabled,
+ * otherwise TCP stack falls back to an internal pacing using one high
+ * resolution timer per TCP socket and may use more resources.
*/
#include <linux/module.h>
#include <net/tcp.h>
@@ -830,6 +829,8 @@ static void bbr_init(struct sock *sk)
bbr->cycle_idx = 0;
bbr_reset_lt_bw_sampling(sk);
bbr_reset_startup_mode(sk);
+
+ cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED);
}
static u32 bbr_sndbuf_expand(struct sock *sk)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4858e190f6ac..a32172d69a03 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -904,6 +904,72 @@ out:
sk_free(sk);
}
+/* Note: Called under hard irq.
+ * We can not call TCP stack right away.
+ */
+enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer)
+{
+ struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer);
+ struct sock *sk = (struct sock *)tp;
+ unsigned long nval, oval;
+
+ for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) {
+ struct tsq_tasklet *tsq;
+ bool empty;
+
+ if (oval & TSQF_QUEUED)
+ break;
+
+ nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED;
+ nval = cmpxchg(&sk->sk_tsq_flags, oval, nval);
+ if (nval != oval)
+ continue;
+
+ if (!atomic_inc_not_zero(&sk->sk_wmem_alloc))
+ break;
+ /* queue this socket to tasklet queue */
+ tsq = this_cpu_ptr(&tsq_tasklet);
+ empty = list_empty(&tsq->head);
+ list_add(&tp->tsq_node, &tsq->head);
+ if (empty)
+ tasklet_schedule(&tsq->tasklet);
+ break;
+ }
+ return HRTIMER_NORESTART;
+}
+
+/* BBR congestion control needs pacing.
+ * Same remark for SO_MAX_PACING_RATE.
+ * sch_fq packet scheduler is efficiently handling pacing,
+ * but is not always installed/used.
+ * Return true if TCP stack should pace packets itself.
+ */
+static bool tcp_needs_internal_pacing(const struct sock *sk)
+{
+ return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
+}
+
+static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
+{
+ u64 len_ns;
+ u32 rate;
+
+ if (!tcp_needs_internal_pacing(sk))
+ return;
+ rate = sk->sk_pacing_rate;
+ if (!rate || rate == ~0U)
+ return;
+
+ /* Should account for header sizes as sch_fq does,
+ * but lets make things simple.
+ */
+ len_ns = (u64)skb->len * NSEC_PER_SEC;
+ do_div(len_ns, rate);
+ hrtimer_start(&tcp_sk(sk)->pacing_timer,
+ ktime_add_ns(ktime_get(), len_ns),
+ HRTIMER_MODE_ABS_PINNED);
+}
+
/* This routine actually transmits TCP packets queued in by
* tcp_do_sendmsg(). This is used by both the initial
* transmission and possible later retransmissions.
@@ -1034,6 +1100,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
if (skb->len != tcp_header_size) {
tcp_event_data_sent(tp, sk);
tp->data_segs_out += tcp_skb_pcount(skb);
+ tcp_internal_pacing(sk, skb);
}
if (after(tcb->end_seq, tp->snd_nxt) || tcb->seq == tcb->end_seq)
@@ -2086,6 +2153,12 @@ static int tcp_mtu_probe(struct sock *sk)
return -1;
}
+static bool tcp_pacing_check(const struct sock *sk)
+{
+ return tcp_needs_internal_pacing(sk) &&
+ hrtimer_active(&tcp_sk(sk)->pacing_timer);
+}
+
/* TCP Small Queues :
* Control number of packets in qdisc/devices to two packets / or ~1 ms.
* (These limits are doubled for retransmits)
@@ -2210,6 +2283,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
+ if (tcp_pacing_check(sk))
+ break;
+
tso_segs = tcp_init_tso_segs(skb, mss_now);
BUG_ON(!tso_segs);
@@ -2878,6 +2954,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
if (skb == tcp_send_head(sk))
break;
+
+ if (tcp_pacing_check(sk))
+ break;
+
/* we could do better than to assign each time */
if (!hole)
tp->retransmit_skb_hint = skb;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 14672543cf0b..86934bcf685a 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -710,4 +710,7 @@ void tcp_init_xmit_timers(struct sock *sk)
{
inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
&tcp_keepalive_timer);
+ hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS_PINNED);
+ tcp_sk(sk)->pacing_timer.function = tcp_pace_kick;
}