Re: [aqm] I-D Action: draft-ietf-aqm-codel-09.txt

Dave Taht <> Mon, 02 October 2017 19:13 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id D478D13479C for <>; Mon, 2 Oct 2017 12:13:54 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -1.9
X-Spam-Status: No, score=-1.9 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=ham autolearn_force=no
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id YdY5MsGtllFl for <>; Mon, 2 Oct 2017 12:13:53 -0700 (PDT)
Received: from ( [IPv6:2a01:7e00::f03c:91ff:feae:7028]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by (Postfix) with ESMTPS id 1794E1347AA for <>; Mon, 2 Oct 2017 12:13:53 -0700 (PDT)
Received: from (unknown [IPv6:2603:3024:1536:86f0:2e0:4cff:fec1:1206]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by (Postfix) with ESMTPSA id AB52121425 for <>; Mon, 2 Oct 2017 19:13:50 +0000 (UTC)
From: Dave Taht <>
References: <>
Date: Mon, 02 Oct 2017 12:13:49 -0700
In-Reply-To: <> ('s message of "Fri, 29 Sep 2017 17:59:08 -0700")
Message-ID: <>
User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.5 (gnu/linux)
MIME-Version: 1.0
Content-Type: text/plain
Archived-At: <>
Subject: Re: [aqm] I-D Action: draft-ietf-aqm-codel-09.txt
X-Mailman-Version: 2.1.22
Precedence: list
List-Id: "Discussion list for active queue management and flow isolation." <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Mon, 02 Oct 2017 19:13:55 -0000

I have reviewed this draft, and my only complaint is that the new text:

"Packets arriving at a full buffer SHOULD be dropped" is really jarring,
where it landed, in section 4.4.

If this MUST be discussed somewhere, I'd suggest opening a new section
for it entirely. Still... I'd suggest dropping this sentence entirely
and letting the fq_codel draft handle it.

There are, incidentally, several strategies for a dealing with a full
buffer in a multi-queue system besides drop tail (which the above
appears to recommend for codel).

How fq_codel does drop on full, incidentally, has improved greatly since
we created the last version of the fq_codel draft, based on field

And I'd be willing to update some future fq_codel.bis document to
reflect that.


I like the new definitions section.


Aside from that, I have not looked at this in going on two years, and
bits are falling out of date, and NONE of my nits are substantive
enough to warrant holding up publication a microsecond longer. It's a
*experimental* draft, not a standard.

If we want to discuss how to produce a fq_codel.bis and codel.bis, and
for that matter pie.bis and fq_pie.bis... on standards track, one day, great. writes:

> A New Internet-Draft is available from the on-line Internet-Drafts directories.
> This draft is a work item of the Active Queue Management and Packet Scheduling WG of the IETF.
>         Title           : Controlled Delay Active Queue Management
>         Authors         : Kathleen Nichols
>                           Van Jacobson
>                           Andrew McGregor
>                           Janardhan Iyengar
> 	Filename        : draft-ietf-aqm-codel-09.txt
> 	Pages           : 25
> 	Date            : 2017-09-29
> Abstract:
>    This document describes a general framework called CoDel (Controlled
>    Delay) that controls bufferbloat-generated excess delay in modern
>    networking environments.  CoDel consists of an estimator, a setpoint,
>    and a control loop.  It requires no configuration in normal Internet
>    deployments.
> The IETF datatracker status page for this draft is:
> There are also htmlized versions available at:
> A diff from the previous version is available at:
> Please note that it may take a couple of minutes from the time of submission
> until the htmlized version and diff are available at
> Internet-Drafts are also available by anonymous FTP at:
> _______________________________________________
> aqm mailing list