IETF Logo Mail Archive

Re: [Banana] diff (banana load distribution, next-hop selection of multipath)

Joe Touch <touch@isi.edu> Sat, 04 February 2017 07:48 UTC

Return-Path: <touch@isi.edu>
X-Original-To: banana@ietfa.amsl.com
Delivered-To: banana@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 5BEB7128B38 for <banana@ietfa.amsl.com>; Fri, 3 Feb 2017 23:48:15 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -10.099
X-Spam-Level:
X-Spam-Status: No, score=-10.099 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_HI=-5, RP_MATCHES_RCVD=-3.199] autolearn=ham autolearn_force=no
Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id js7PBVY-CfKK for <banana@ietfa.amsl.com>; Fri, 3 Feb 2017 23:48:14 -0800 (PST)
Received: from vapor.isi.edu (vapor.isi.edu [128.9.64.64]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 45610127058 for <banana@ietf.org>; Fri, 3 Feb 2017 23:48:14 -0800 (PST)
Received: from [192.168.1.158] (cpe-172-250-240-132.socal.res.rr.com [172.250.240.132]) (authenticated bits=0) by vapor.isi.edu (8.13.8/8.13.8) with ESMTP id v147lhuf025806 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Fri, 3 Feb 2017 23:47:53 -0800 (PST)
Content-Type: text/plain; charset="us-ascii"
Mime-Version: 1.0 (1.0)
From: Joe Touch <touch@isi.edu>
X-Mailer: iPad Mail (14D27)
In-Reply-To: <4552F0907735844E9204A62BBDD325E7A63A1C49@NKGEML515-MBX.china.huawei.com>
Date: Fri, 03 Feb 2017 23:47:42 -0800
Content-Transfer-Encoding: quoted-printable
Message-Id: <99F04B22-01AC-476C-A15A-1696B686A953@isi.edu>
References: <4552F0907735844E9204A62BBDD325E7A6386E6A@NKGEML515-MBX.china.huawei.com> <C328BFD1-A2B7-4E95-956A-D553A8167922@gmail.com> <f5bc7430-45dd-c5a6-d376-9d349d40a373@isi.edu> <4552F0907735844E9204A62BBDD325E7A63A1C49@NKGEML515-MBX.china.huawei.com>
To: Mingui Zhang <zhangmingui@huawei.com>
X-ISI-4-43-8-MailScanner: Found to be clean
X-MailScanner-From: touch@isi.edu
Archived-At: <https://mailarchive.ietf.org/arch/msg/banana/dZrMvl1MYhctvgBXfl_Qu06_wBY>
Cc: Margaret Cullen <margaretw42@gmail.com>, "banana@ietf.org" <banana@ietf.org>
Subject: Re: [Banana] diff (banana load distribution, next-hop selection of multipath)
X-BeenThere: banana@ietf.org
X-Mailman-Version: 2.1.17
Precedence: list
List-Id: "Bandwidth Aggregation for interNet Access: Discussion of bandwidth aggregation solutions based on IETF technologies." <banana.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/banana>, <mailto:banana-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/banana/>
List-Post: <mailto:banana@ietf.org>
List-Help: <mailto:banana-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/banana>, <mailto:banana-request@ietf.org?subject=subscribe>
X-List-Received-Date: Sat, 04 Feb 2017 07:48:15 -0000


> On Feb 3, 2017, at 10:51 PM, Mingui Zhang <zhangmingui@huawei.com> wrote:
> 
> Hi Joe, all,
> 
>> -----Original Message-----
>> From: Joe Touch [mailto:touch@isi.edu]
>> Sent: Saturday, February 04, 2017 12:46 AM
>> To: Margaret Cullen; Mingui Zhang
>> Cc: banana@ietf.org
>> Subject: Re: [Banana] diff (banana load distribution, next-hop selection of
>> multipath)
>> 
>> Hi, all,
>> 
>> So am I to understand that the "problem statement" is:
>> 
>>    - given two cooperating devices, how to manage a set of bonded links
>> between them?
>> 
>> Isn't that what routers already do?
> 
> There is one key difference. What is routers nowadays doing is per-flow load balancing using hashing rather than flow splitting across this set of bonded links and then reordering. 

True for many commercial routers but channel bonding isn't new. 

I'm asking what the goal here is - new channel bonding algs? Thats IRTF space. What's left?

Joe


> 
> Thanks,
> Mingui
> 
>> 
>> (yes, I know that I've glossed over the fact that these "links" might be tunnels -
>> because we have dozens of ways of doing that already)
>> 
>> Joe

v2.23.0 | Report a Bug | By Email