netdev - Re: [PATCH net-next v2 5/5] tcp_cubic: make Hystart aware of pacing

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CADVnQy=-a4z57vD-9mHA9=oC0R3O0vtNPkpnfJQpTRt2vP2qGw@mail.gmail.com>
Date:   Fri, 27 Dec 2019 12:06:05 -0500
From:   Neal Cardwell <ncardwell@...gle.com>
To:     Eric Dumazet <edumazet@...gle.com>
Cc:     "David S . Miller" <davem@...emloft.net>,
        netdev <netdev@...r.kernel.org>,
        Eric Dumazet <eric.dumazet@...il.com>,
        Soheil Hassas Yeganeh <soheil@...gle.com>,
        Yuchung Cheng <ycheng@...gle.com>,
        Martin KaFai Lau <kafai@...com>
Subject: Re: [PATCH net-next v2 5/5] tcp_cubic: make Hystart aware of pacing

On Mon, Dec 23, 2019 at 3:28 PM Eric Dumazet <edumazet@...gle.com> wrote:
>
> 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

I guess all these tests are with the "fq" qdisc with pacing enabled?

> Signed-off-by: Eric Dumazet <edumazet@...gle.com>
> ---
>  net/ipv4/tcp_cubic.c | 13 ++++++++++++-
>  1 file changed, 12 insertions(+), 1 deletion(-)

Thanks, Eric. The revised heuristic for paced traffic seems like a
nice improvement.

Acked-by: Neal Cardwell <ncardwell@...gle.com>

thanks,
neal