netdev - Re: [PATCH v4 net-next 13/16] tcp: allow congestion control to expand send buffer differently

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 for Android: free password hash cracker in your pocket

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

Message-ID: <CAK6E8=epAijzFg4HUVA3Xfk-z6qJWdgbG4Qu8VYLPL0g7Pz02g@mail.gmail.com>
Date:   Tue, 20 Sep 2016 11:43:52 -0700
From:   Yuchung Cheng <ycheng@...gle.com>
To:     Stephen Hemminger <stephen@...workplumber.org>
Cc:     Neal Cardwell <ncardwell@...gle.com>,
        David Miller <davem@...emloft.net>,
        netdev <netdev@...r.kernel.org>, Van Jacobson <vanj@...gle.com>,
        Nandita Dukkipati <nanditad@...gle.com>,
        Eric Dumazet <edumazet@...gle.com>,
        Soheil Hassas Yeganeh <soheil@...gle.com>
Subject: Re: [PATCH v4 net-next 13/16] tcp: allow congestion control to expand
 send buffer differently

On Tue, Sep 20, 2016 at 10:48 AM, Stephen Hemminger
<stephen@...workplumber.org> wrote:
>
> On Mon, 19 Sep 2016 23:39:20 -0400
> Neal Cardwell <ncardwell@...gle.com> wrote:
>
> > From: Yuchung Cheng <ycheng@...gle.com>
> >
> > Currently the TCP send buffer expands to twice cwnd, in order to allow
> > limited transmits in the CA_Recovery state. This assumes that cwnd
> > does not increase in the CA_Recovery.
> >
> > For some congestion control algorithms, like the upcoming BBR module,
> > if the losses in recovery do not indicate congestion then we may
> > continue to raise cwnd multiplicatively in recovery. In such cases the
> > current multiplier will falsely limit the sending rate, much as if it
> > were limited by the application.
> >
> > This commit adds an optional congestion control callback to use a
> > different multiplier to expand the TCP send buffer. For congestion
> > control modules that do not specificy this callback, TCP continues to
> > use the previous default of 2.
> >
> > Signed-off-by: Van Jacobson <vanj@...gle.com>
> > Signed-off-by: Neal Cardwell <ncardwell@...gle.com>
> > Signed-off-by: Yuchung Cheng <ycheng@...gle.com>
> > Signed-off-by: Nandita Dukkipati <nanditad@...gle.com>
> > Signed-off-by: Eric Dumazet <edumazet@...gle.com>
> > Signed-off-by: Soheil Hassas Yeganeh <soheil@...gle.com>
> > ---
> >  include/net/tcp.h    | 2 ++
> >  net/ipv4/tcp_input.c | 4 +++-
> >  2 files changed, 5 insertions(+), 1 deletion(-)
> >
> > diff --git a/include/net/tcp.h b/include/net/tcp.h
> > index 3492041..1aa9628 100644
> > --- a/include/net/tcp.h
> > +++ b/include/net/tcp.h
> > @@ -917,6 +917,8 @@ struct tcp_congestion_ops {
> >       void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);
> >       /* suggest number of segments for each skb to transmit (optional) */
> >       u32 (*tso_segs_goal)(struct sock *sk);
> > +     /* returns the multiplier used in tcp_sndbuf_expand (optional) */
> > +     u32 (*sndbuf_expand)(struct sock *sk);
> >       /* get info for inet_diag (optional) */
> >       size_t (*get_info)(struct sock *sk, u32 ext, int *attr,
> >                          union tcp_cc_info *info);
> > diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
> > index 17de77d..5af0bf3 100644
> > --- a/net/ipv4/tcp_input.c
> > +++ b/net/ipv4/tcp_input.c
> > @@ -289,6 +289,7 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
> >  static void tcp_sndbuf_expand(struct sock *sk)
> >  {
> >       const struct tcp_sock *tp = tcp_sk(sk);
> > +     const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
> >       int sndmem, per_mss;
> >       u32 nr_segs;
> >
> > @@ -309,7 +310,8 @@ static void tcp_sndbuf_expand(struct sock *sk)
> >        * Cubic needs 1.7 factor, rounded to 2 to include
> >        * extra cushion (application might react slowly to POLLOUT)
> >        */
> > -     sndmem = 2 * nr_segs * per_mss;
> > +     sndmem = ca_ops->sndbuf_expand ? ca_ops->sndbuf_expand(sk) : 2;
>
> You could avoid the conditional (if it mattered) by inheriting a default value
> that would mean changing all existing congestion control modules.
> So doing it this way makes life easier.
Good point. But we've not really tested raising it to 3 on other
C.C.s, esp loss-based ones tend to have big cwnd on bloated buffers.
so we like to change locally for now.

>
> Acked-by: Stephen Hemminger <stephen@...workplumber.org>