Re: Socket buffer sizes with autotuning

["Jerry Chu" <hkchu@google.com>]

On Mon, Apr 28, 2008 at 12:21 PM, John Heffner <johnwheffner@gmail.com> wrote:
>
> On Mon, Apr 28, 2008 at 11:30 AM, Jerry Chu <hkchu@google.com> wrote:
> >  Correct, but its counterpart doesn't exist in tcp_is_cwnd_limited(). So
> >  cwnd will continue to grow when left < cwnd/sysctl_tcp_tso_win_divisor,
> >  which can be very large when cwnd is large.
> >
> >  If I change tcp_tso_win_divisor to 0, cwnd max out at 695 rather than 1037,
> >  exactly off by 1/3. I tried to add the same check to tcp_is_cwnd_limited():
> >
> >  diff -c /tmp/tcp.h.old tcp.h
> >  *** /tmp/tcp.h.old      Mon Apr 28 11:00:44 2008
> >  --- tcp.h       Mon Apr 28 10:54:10 2008
> >  ***************
> >  *** 828,833 ****
> >  --- 828,835 ----
> >                 return 0;
> >
> >         left = tp->snd_cwnd - in_flight;
> >  +       if (left >= 65536)
> >  +               return 0;
> >         if (sysctl_tcp_tso_win_divisor)
> >                 return left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd;
> >         else
> >
> >  >
> >
> >  But it doesn't seem to help (cwnd still grows to 1037).
>
> Cwnd is in packets, not bytes.

Yes, of course.

>
> Try this series of patches, against net-next.

Ah, you already know about this problem. Yes it does the trick.

Jerry

>
>  -John
>