netdev - Re: [PATCH net 1/5] tcp_bbr: cut pacing rate only if filled pipe

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: <CADVnQykrv=U=jXa2SeOun8yGZbYJ4zoLvek-_GEo7sN02PsZLg@mail.gmail.com>
Date:   Fri, 14 Jul 2017 18:54:02 -0400
From:   Neal Cardwell <ncardwell@...gle.com>
To:     Stephen Hemminger <stephen@...workplumber.org>
Cc:     David Miller <davem@...emloft.net>,
        Netdev <netdev@...r.kernel.org>,
        Yuchung Cheng <ycheng@...gle.com>,
        Soheil Hassas Yeganeh <soheil@...gle.com>
Subject: Re: [PATCH net 1/5] tcp_bbr: cut pacing rate only if filled pipe

On Fri, Jul 14, 2017 at 6:36 PM, Stephen Hemminger
<stephen@...workplumber.org> wrote:
> On Fri, 14 Jul 2017 17:49:21 -0400
> Neal Cardwell <ncardwell@...gle.com> wrote:
>
>> In bbr_set_pacing_rate(), which decides whether to cut the pacing
>> rate, there was some code that considered exiting STARTUP to be
>> equivalent to the notion of filling the pipe (i.e.,
>> bbr_full_bw_reached()). Specifically, as the code was structured,
>> exiting STARTUP and going into PROBE_RTT could cause us to cut the
>> pacing rate down to something silly and low, based on whatever
>> bandwidth samples we've had so far, when it's possible that all of
>> them have been small app-limited bandwidth samples that are not
>> representative of the bandwidth available in the path. (The code was
>> correct at the time it was written, but the state machine changed
>> without this spot being adjusted correspondingly.)
>>
>> Fixes: 0f8782ea1497 ("tcp_bbr: add BBR congestion control")
>> Signed-off-by: Neal Cardwell <ncardwell@...gle.com>
>> Signed-off-by: Yuchung Cheng <ycheng@...gle.com>
>> Signed-off-by: Soheil Hassas Yeganeh <soheil@...gle.com>
>
> Looks good, but net-next is closed at this time. Please resubmit later.
>
> http://vger.kernel.org/~davem/net-next.html

Thanks, Stephen. We see your point on the net-next patch "tcp: adjust
tail loss probe timeout"; we'll resubmit that patch when net-next
opens. Sorry about that!

But for the tcp_bbr patch series, those are bug fixes, and we were
marking them as being for "net" with Fixes: footers in the hopes that
they could go into the "net" branch and be queued up for inclusion in
-stable releases. Are you saying that in your estimation the substance
of the fixes doesn't rise to the level of "net" material? If that is
the consensus then we can resubmit for net-next when that opens.

thanks,
neal