netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Dave Taht <dave.taht@gmail.com>
To: "Ilpo Järvinen" <ilpo.jarvinen@helsinki.fi>
Cc: Linux Kernel Network Developers <netdev@vger.kernel.org>,
	Yuchung Cheng <ycheng@google.com>,
	Neal Cardwell <ncardwell@google.com>,
	Eric Dumazet <eric.dumazet@gmail.com>,
	Olivier Tilmans <olivier.tilmans@nokia-bell-labs.com>
Subject: Re: [RFC PATCH 28/28] tcp: AccECN sysctl documentation
Date: Thu, 19 Mar 2020 16:02:36 -0700	[thread overview]
Message-ID: <CAA93jw7_YG-KMns8UP-aTPHNjPG+A_rwWUWbt1+8i4+UNhALnA@mail.gmail.com> (raw)
In-Reply-To: <1584524612-24470-29-git-send-email-ilpo.jarvinen@helsinki.fi>

On Wed, Mar 18, 2020 at 2:44 AM Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> wrote:
>
> From: Ilpo Järvinen <ilpo.jarvinen@cs.helsinki.fi>
>
> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@cs.helsinki.fi>
> ---
>  Documentation/networking/ip-sysctl.txt | 12 +++++++++---
>  1 file changed, 9 insertions(+), 3 deletions(-)
>
> diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
> index 5f53faff4e25..ecca6e1d6bea 100644
> --- a/Documentation/networking/ip-sysctl.txt
> +++ b/Documentation/networking/ip-sysctl.txt
> @@ -301,15 +301,21 @@ tcp_ecn - INTEGER
>                 0 Disable ECN.  Neither initiate nor accept ECN.
>                 1 Enable ECN when requested by incoming connections and
>                   also request ECN on outgoing connection attempts.
> -               2 Enable ECN when requested by incoming connections
> +               2 Enable ECN or AccECN when requested by incoming connections
>                   but do not request ECN on outgoing connections.

Changing existing user-behavior for this default seems to be overly
optimistic. Useful for testing, but...

> +               3 Enable AccECN when requested by incoming connections and
> +                 also request AccECN on outgoing connection attempts.
> +           0x102 Enable AccECN in optionless mode for incoming connections.
> +           0x103 Enable AccECN in optionless mode for incoming and outgoing
> +                 connections.

In terms of the logic bits here, it might make more sense

0: disable ecn
1: enable std ecn on in or out
2: enable std ecn when requested on in (the default)
3: essentially unused
4: enable accecn when requested on in
5: enable std ecn and accecn on in or out
6: enable accecn and ecn on in but not out

Do we have any data on how often the tcp ns bit is a source of
firewalling problems yet?

0x102 strikes me as a bit more magical than required and I don't know
what optionless means in this context.

>         Default: 2
>
>  tcp_ecn_fallback - BOOLEAN
>         If the kernel detects that ECN connection misbehaves, enable fall
>         back to non-ECN. Currently, this knob implements the fallback
> -       from RFC3168, section 6.1.1.1., but we reserve that in future,
> -       additional detection mechanisms could be implemented under this
> +       from RFC3168, section 6.1.1.1., as well as the ECT codepoint mangling
> +       detection during the Accurate ECN handshake, but we reserve that in
> +       future, additional detection mechanisms could be implemented under this
>         knob. The value is not used, if tcp_ecn or per route (or congestion
>         control) ECN settings are disabled.
>         Default: 1 (fallback enabled)
> --
> 2.20.1
>


-- 
Make Music, Not War

Dave Täht
CTO, TekLibre, LLC
http://www.teklibre.com
Tel: 1-831-435-0729

  reply	other threads:[~2020-03-19 23:02 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-18  9:43 [RFC PATCH 00/28]: Accurate ECN for TCP Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 01/28] tcp: add tp to prepare for AccECN code Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 02/28] tcp: fast path functions later Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 03/28] tcp: move tcp_in_ack_event later Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 04/28] tcp: create FLAG_TS_PROGRESS Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 05/28] tcp: extend TCP flags to allow AE bit/ACE field Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 06/28] tcp: reorganize SYN ECN code Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 07/28] tcp: rework {__,}tcp_ecn_check_ce() -> tcp_data_ecn_check() Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 08/28] tcp: helpers for ECN mode handling Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 09/28] gso: AccECN support Ilpo Järvinen
2020-03-19  3:44   ` Eric Dumazet
2020-03-19 22:36     ` Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 10/28] gro: prevent ACE field corruption & better AccECN handling Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 11/28] tcp: AccECN support to tcp_add_backlog Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 12/28] tcp: AccECN core Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 13/28] tcp: Pass flags to tcp_send_ack Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 14/28] tcp: AccECN negotiation Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 15/28] tcp: add AccECN rx byte counters Ilpo Järvinen
2020-03-19  3:36   ` Eric Dumazet
2020-03-18  9:43 ` [RFC PATCH 16/28] tcp: allow embedding leftover into option padding Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 17/28] tcp: AccECN needs to know delivered bytes Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 18/28] tcp: don't early return when sack doesn't fit Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 19/28] tcp: AccECN option Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 20/28] tcp: AccECN option send control Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 21/28] tcp: AccECN option beacon Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 22/28] tcp: AccECN option order bit & failure handling Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 23/28] tcp: AccECN option ceb/cep heuristic Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 24/28] tcp: try to fit AccECN option with SACK Ilpo Järvinen
2020-03-19  3:29   ` Eric Dumazet
2020-03-19 20:33     ` Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 25/28] tcp: try to avoid safer when ACKs are thinned Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 26/28] tcp: to prevent runaway AccECN cep/ACE deficit, limit GSO size Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 27/28] gro: flushing when CWR is set negatively affects AccECN Ilpo Järvinen
2020-03-18  9:43 ` [RFC PATCH 28/28] tcp: AccECN sysctl documentation Ilpo Järvinen
2020-03-19 23:02   ` Dave Taht [this message]
2020-03-20 22:40     ` Ilpo Järvinen
2020-03-20 23:22       ` Yuchung Cheng
2020-03-23 13:34         ` Ilpo Järvinen
2020-03-23 19:03           ` Yuchung Cheng
2020-03-24 12:50             ` Ilpo Järvinen
2020-03-24 17:05               ` Yuchung Cheng
2020-03-18 23:29 ` [RFC PATCH 00/28]: Accurate ECN for TCP David Miller
2020-03-19 20:25   ` Ilpo Järvinen
2020-03-20  4:38     ` David Miller
  -- strict thread matches above, loose matches on Subject: below --
2020-03-18  9:37 [RFC PATCH 02/28] tcp: fast path functions later Ilpo Järvinen
2020-03-18  9:38 ` [RFC PATCH 28/28] tcp: AccECN sysctl documentation Ilpo Järvinen

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=CAA93jw7_YG-KMns8UP-aTPHNjPG+A_rwWUWbt1+8i4+UNhALnA@mail.gmail.com \
    --to=dave.taht@gmail.com \
    --cc=eric.dumazet@gmail.com \
    --cc=ilpo.jarvinen@helsinki.fi \
    --cc=ncardwell@google.com \
    --cc=netdev@vger.kernel.org \
    --cc=olivier.tilmans@nokia-bell-labs.com \
    --cc=ycheng@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).