Re: [p2pi] [tana] TANA proposed charter -- packet marking question

"Woundy, Richard" <> Fri, 24 October 2008 17:41 UTC

Return-Path: <>
Received: from [] (localhost []) by (Postfix) with ESMTP id E9CA628C14C; Fri, 24 Oct 2008 10:41:25 -0700 (PDT)
Received: from localhost (localhost []) by (Postfix) with ESMTP id ED0903A6A69; Fri, 24 Oct 2008 10:41:24 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -0.274
X-Spam-Status: No, score=-0.274 tagged_above=-999 required=5 tests=[AWL=0.189, BAYES_00=-2.599, HELO_EQ_MODEMCABLE=0.768, HOST_EQ_MODEMCABLE=1.368]
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id Eq0ibk++ED4q; Fri, 24 Oct 2008 10:41:24 -0700 (PDT)
Received: from ( []) by (Postfix) with ESMTP id C3D213A6841; Fri, 24 Oct 2008 10:41:23 -0700 (PDT)
Received: from ([]) by with ESMTP id KP-TDCH7.52310873; Fri, 24 Oct 2008 13:42:15 -0400
Received: from ([]) by with Microsoft SMTPSVC(6.0.3790.3959); Fri, 24 Oct 2008 13:42:14 -0400
X-MimeOLE: Produced By Microsoft Exchange V6.5
Content-class: urn:content-classes:message
MIME-Version: 1.0
Date: Fri, 24 Oct 2008 13:42:14 -0400
Message-ID: <>
In-Reply-To: <13265179-F62E-480F-B233-0F6160EC5701@ICSI.Berkeley.EDU>
Thread-Topic: [tana] [p2pi] TANA proposed charter -- packet marking question
Thread-Index: Ack1/YqzPIVCLHb2QWCb5AbhSukfSAAAam4Q
References: <><><><20081024145218.GB88592@verdi><><20081024161246.GD88592@verdi> <13265179-F62E-480F-B233-0F6160EC5701@ICSI.Berkeley.EDU>
From: "Woundy, Richard" <>
To: "Nicholas Weaver" <nweaver@ICSI.Berkeley.EDU>, "John Leslie" <>
X-OriginalArrivalTime: 24 Oct 2008 17:42:14.0867 (UTC) FILETIME=[DA176A30:01C935FF]
Subject: Re: [p2pi] [tana] TANA proposed charter -- packet marking question
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: P2P Infrastructure Discussion <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit

I suspect that cable modems and DSL modems have been over-buffered in
the upstream direction for many years, and it will take many years to
purge the old modems out of the installed base. So I believe it is
important for 'TANA' transport to work in that environment.

However, there may be an opportunity to point future modem developers in
the correct direction, e.g. correct buffering, AQM and ECN. It would be
helpful if the 'TANA' transport could take advantage of that support in
the future.

> just have only 30ms of packet buffer, not 3s

I've heard from other experts that 100ms or so of packet buffer makes
sense. I think we can agree that 1-3 seconds does not make sense.

-- Rich

-----Original Message-----
From: [] On Behalf Of
Nicholas Weaver
Sent: Friday, October 24, 2008 1:25 PM
To: John Leslie
Cc:;; Nicholas Weaver
Subject: Re: [tana] [p2pi] TANA proposed charter -- packet marking

On Oct 24, 2008, at 9:12 AM, John Leslie wrote:
>> I start a full rate, SINGLE TCP flow to this remote system.  The ping
>> time jumps up to 3 seconds!  Yes, the stupid NAT box or DSL modem  
>> (not
>> sure which at this moment) has a 3 second packet buffer, and simple
>> FIFO behavior.  Any full rate upload and I can kiss my connection
>> goodbye.  Period.  End of story.  Have a nice day.
>   Fortunately, the Linksys _could_ be easily programmed to fix that --
> and if the problem becomes obvious enough to enough buyers, the
> competition will fix it...

I disagree.

I've had DSL or cable modem connectivity for damn-near a decade now.   
And fixing it is easy: the data rates are trivial, the devices are  
often programmable, and the solution straightforward: just have only  
30ms of packet buffer, not 3s.  Yet these devices STILL have this  

And the only reason that as a clued user it would be fixable if its  
the Linksys box is I DELIBERATELY purchased the version where I can  
replace the firmware to fix something the vendors refused to fix for  
themselves.  And I just unplugged the linksys: its the DSL modem,  
purchased within the past 2.5 years.

(The reason its not a problem for me is I don't use P2P apps, and only  
rarely upload large quantities of photos)

So I think the conclusion should be there has been a market failure in  
this area, and that absent a miracle, this problem will remain.

tana mailing list
p2pi mailing list