Re: [tcpm] taking RFC 2861 (Congestion Window Validation) to Proposed Standard?
Sally Floyd <sallyfloyd@mac.com> Fri, 13 July 2007 00:13 UTC
Return-path: <tcpm-bounces@ietf.org>
Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1I98nF-0005Ii-B3; Thu, 12 Jul 2007 20:13:57 -0400
Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1I98nD-0005Fa-VM for tcpm@ietf.org; Thu, 12 Jul 2007 20:13:55 -0400
Received: from smtpout.mac.com ([17.250.248.175]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1I98n9-0001wN-IK for tcpm@ietf.org; Thu, 12 Jul 2007 20:13:55 -0400
Received: from mac.com (smtpin07-en2 [10.13.10.152]) by smtpout.mac.com (Xserve/smtpout05/MantshX 4.0) with ESMTP id l6D0Deiv024296; Thu, 12 Jul 2007 17:13:41 -0700 (PDT)
Received: from [192.150.186.170] (laptop170.icsi.berkeley.edu [192.150.186.170]) (authenticated bits=0) by mac.com (Xserve/smtpin07/MantshX 4.0) with ESMTP id l6D0DeCS007401; Thu, 12 Jul 2007 17:13:40 -0700 (PDT)
In-Reply-To: <468DA85C.1000500@psc.edu>
References: <b1e79256f18fcb6f81ae417fde5ca646@mac.com> <46770412.8090307@psc.edu> <46ffa03042528d92a9ea2875e1764b19@mac.com> <468DA85C.1000500@psc.edu>
Mime-Version: 1.0 (Apple Message framework v624)
Content-Type: text/plain; charset="US-ASCII"; format="flowed"
Message-Id: <350d2cecde2aa453588abd6c8f72882c@mac.com>
Content-Transfer-Encoding: 7bit
From: Sally Floyd <sallyfloyd@mac.com>
Subject: Re: [tcpm] taking RFC 2861 (Congestion Window Validation) to Proposed Standard?
Date: Thu, 12 Jul 2007 17:13:40 -0700
To: John Heffner <jheffner@psc.edu>
X-Mailer: Apple Mail (2.624)
X-Spam-Score: 0.0 (/)
X-Scan-Signature: 8b30eb7682a596edff707698f4a80f7d
Cc: Murari Sridharan <muraris@microsoft.com>, Jitu Padhye <padhye@microsoft.com>, tcpm <tcpm@ietf.org>, Mark Handley <M.Handley@cs.ucl.ac.uk>
X-BeenThere: tcpm@ietf.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: TCP Maintenance and Minor Extensions Working Group <tcpm.ietf.org>
List-Unsubscribe: <https://www1.ietf.org/mailman/listinfo/tcpm>, <mailto:tcpm-request@ietf.org?subject=unsubscribe>
List-Post: <mailto:tcpm@ietf.org>
List-Help: <mailto:tcpm-request@ietf.org?subject=help>
List-Subscribe: <https://www1.ietf.org/mailman/listinfo/tcpm>, <mailto:tcpm-request@ietf.org?subject=subscribe>
Errors-To: tcpm-bounces@ietf.org
>> I understand that bursty applications would often rather not reduce >> cwnd after an idle or application-limited periiod. (It *might* be >> in their own interests, if it helps the flow to avoid unnecessary >> packet drops, but it *might not* be in their own interests, e.g., >> if that flow doesn't receive any packet drops when bursting after >> an idle period. >> But the following question also matters: >> (1) What about when there are N possibly-bursty flows sharing the >> same congested link? Are there any reports about whether the *N >> flows* do better when all flows use CWV, or whether they do better >> when none of them use CWV, and none of them reduce cwnd after an >> idle period? >> (If there is no congestion, I would expect that the N flows do >> better without CWV. If there *is* congestion, I would expect that >> the N flows in general do better *with* CWV, as opposed to not >> reducing cwnd after idle periods. But it is not something that one >> could tell from reports from individual users...) > > > This agrees with my intuition, for what it's worth. :) I'm not aware > of any experiments along these lines. I'm also really interested in > how much difference pacing out bursts after an idle period might make. Many thanks. I assume that pacing would be a big win, with or without Congestion Window Validation. (With CWV, the window is not set right away to the initial window, but is halved each RTO.) RFC 2861 also has a paragraph at the end of Section 2 arguing that pacing by itself would not be sufficient, without *some* reduction of cwnd after a long idle period. (Would one really want connections with a cwnd of 1000 packets or more to start up with that cwnd after an idle period of an hour? With or pacing? Even though there very well *might* not be any congestion after the hour-long idle period?) - Sally http://www.icir.org/floyd/ _______________________________________________ tcpm mailing list tcpm@ietf.org https://www1.ietf.org/mailman/listinfo/tcpm
- [tcpm] taking RFC 2861 (Congestion Window Validat… Sally Floyd
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Salman Abdul Baset
- RE: [tcpm] taking RFC 2861 (Congestion Window Val… Salman Abdul Baset
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… John Heffner
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Sally Floyd
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Sally Floyd
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Janardhan Iyengar
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… John Heffner
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Sally Floyd
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Sally Floyd
- RE: [tcpm] taking RFC 2861 (Congestion Window Val… Murari Sridharan
- Re: [tcpm] taking RFC 2861 (Congestion Window Val… Sally Floyd