From ab408b6dc7449c0f791e9e5f8de72fa7428584f2 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 21 Sep 2018 08:51:52 -0700 Subject: tcp: switch tcp and sch_fq to new earliest departure time model TCP keeps track of tcp_wstamp_ns by itself, meaning sch_fq no longer has to do it. Thanks to this model, TCP can get more accurate RTT samples, since pacing no longer inflates them. This has the nice effect of removing some delays caused by FQ quantum mechanism, causing inflated max/P99 latencies. Also we might relax TCP Small Queue tight limits in the future, since this new model allow TCP to build bigger batches, since sch_fq (or a device with earliest departure time offload) ensure these packets will be delivered on time. Note that other protocols are not converted (they will probably never be) so sch_fq has still support for SO_MAX_PACING_RATE Tested: Test showing FQ pacing quantum artifact for low-rate flows, adding unexpected throttles for RPC flows, inflating max and P99 latencies. The parameters chosen here are to show what happens typically when a TCP flow has a reduced pacing rate (this can be caused by a reduced cwin after few losses, or/and rtt above few ms) MIBS="MIN_LATENCY,MEAN_LATENCY,MAX_LATENCY,P99_LATENCY,STDDEV_LATENCY" Before : $ netperf -H 10.246.7.133 -t TCP_RR -Cc -T6,6 -- -q 2000000 -r 100,100 -o $MIBS MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.133 () port 0 AF_INET : first burst 0 : cpu bind Minimum Latency Microseconds,Mean Latency Microseconds,Maximum Latency Microseconds,99th Percentile Latency Microseconds,Stddev Latency Microseconds 19,82.78,5279,3825,482.02 After : $ netperf -H 10.246.7.133 -t TCP_RR -Cc -T6,6 -- -q 2000000 -r 100,100 -o $MIBS MIGRATED TCP REQUEST/RESPONSE TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 10.246.7.133 () port 0 AF_INET : first burst 0 : cpu bind Minimum Latency Microseconds,Mean Latency Microseconds,Maximum Latency Microseconds,99th Percentile Latency Microseconds,Stddev Latency Microseconds 20,49.94,128,63,3.18 Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_output.c') diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index a87068fa9b1a..2adb719e97b8 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1012,9 +1012,23 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) sock_hold(sk); } -static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) +static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; + if (sk->sk_pacing_status != SK_PACING_NONE) { + u32 rate = sk->sk_pacing_rate; + + /* Original sch_fq does not pace first 10 MSS + * Note that tp->data_segs_out overflows after 2^32 packets, + * this is a minor annoyance. + */ + if (rate != ~0U && rate && tp->data_segs_out >= 10) { + tp->tcp_wstamp_ns += div_u64((u64)skb->len * NSEC_PER_SEC, rate); + /* TODO: update internal pacing here */ + } + } list_move_tail(&skb->tcp_tsorted_anchor, &tp->tsorted_sent_queue); } @@ -1178,7 +1192,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, err = net_xmit_eval(err); } if (!err && oskb) { - tcp_update_skb_after_send(tp, oskb); + tcp_update_skb_after_send(sk, oskb); tcp_rate_skb_sent(sk, oskb); } return err; @@ -2327,7 +2341,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE) { /* "skb_mstamp" is used as a start point for the retransmit timer */ - tcp_update_skb_after_send(tp, skb); + tcp_update_skb_after_send(sk, skb); goto repair; /* Skip network transmission */ } @@ -2902,7 +2916,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) } tcp_skb_tsorted_restore(skb); if (!err) { - tcp_update_skb_after_send(tp, skb); + tcp_update_skb_after_send(sk, skb); tcp_rate_skb_sent(sk, skb); } } else { -- cgit v1.2.3-70-g09d2