diff options
author | Eric Dumazet <edumazet@google.com> | 2019-12-23 21:27:54 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2019-12-28 01:29:14 +0100 |
commit | ede656e8465839530c3287c7f54adf75dc2b9563 (patch) | |
tree | a22b91ec73fb450b14d7079d13b9f780dd68b06e | |
parent | tcp_cubic: tweak Hystart detection for short RTT flows (diff) | |
download | linux-ede656e8465839530c3287c7f54adf75dc2b9563.tar.xz linux-ede656e8465839530c3287c7f54adf75dc2b9563.zip |
tcp_cubic: make Hystart aware of pacing
For years we disabled Hystart ACK train detection at Google
because it was fooled by TCP pacing.
ACK train detection uses a simple heuristic, detecting if
we receive ACK past half the RTT, to exit slow start before
hitting the bottleneck and experience massive drops.
But pacing by design might delay packets up to RTT/2,
so we need to tweak the Hystart logic to be aware of this
extra delay.
Tested:
Added a 100 usec delay at receiver.
Before:
nstat -n;for f in {1..10}; do ./super_netperf 1 -H lpaa24 -l -4000000; done;nstat|egrep "Hystart"
9117
7057
9553
8300
7030
6849
9533
10126
6876
8473
TcpExtTCPHystartTrainDetect 10 0.0
TcpExtTCPHystartTrainCwnd 1230 0.0
After :
nstat -n;for f in {1..10}; do ./super_netperf 1 -H lpaa24 -l -4000000; done;nstat|egrep "Hystart"
9845
10103
10866
11096
11936
11487
11773
12188
11066
11894
TcpExtTCPHystartTrainDetect 10 0.0
TcpExtTCPHystartTrainCwnd 6462 0.0
Disabling Hystart ACK Train detection gives similar numbers
echo 2 >/sys/module/tcp_cubic/parameters/hystart_detect
nstat -n;for f in {1..10}; do ./super_netperf 1 -H lpaa24 -l -4000000; done;nstat|egrep "Hystart"
11173
10954
12455
10627
11578
11583
11222
10880
10665
11366
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | net/ipv4/tcp_cubic.c | 13 |
1 files changed, 12 insertions, 1 deletions
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 0e5428ed04fe..d02bb283c689 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -376,6 +376,7 @@ static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); + u32 threshold; if (hystart_detect & HYSTART_ACK_TRAIN) { u32 now = bictcp_clock_us(sk); @@ -383,7 +384,17 @@ static void hystart_update(struct sock *sk, u32 delay) /* first detection parameter - ack-train detection */ if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; - if ((s32)(now - ca->round_start) > ca->delay_min >> 1) { + + threshold = ca->delay_min; + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((s32)(now - ca->round_start) > threshold) { ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); |