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_bbr.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'net/ipv4/tcp_bbr.c') diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 02ff2dde9609..a5786e3e2c16 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -128,6 +128,9 @@ static const u32 bbr_probe_rtt_mode_ms = 200; /* Skip TSO below the following bandwidth (bits/sec): */ static const int bbr_min_tso_rate = 1200000; +/* Pace at ~1% below estimated bw, on average, to reduce queue at bottleneck. */ +static const int bbr_pacing_marging_percent = 1; + /* We use a high_gain value of 2/ln(2) because it's the smallest pacing gain * that will allow a smoothly increasing pacing rate that will double each RTT * and send the same number of packets per RTT that an un-paced, slow-starting @@ -208,12 +211,10 @@ static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain) { unsigned int mss = tcp_sk(sk)->mss_cache; - if (!tcp_needs_internal_pacing(sk)) - mss = tcp_mss_to_mtu(sk, mss); rate *= mss; rate *= gain; rate >>= BBR_SCALE; - rate *= USEC_PER_SEC; + rate *= USEC_PER_SEC / 100 * (100 - bbr_pacing_marging_percent); return rate >> BW_SCALE; } -- cgit v1.2.3-59-g8ed1b