Re: [cso] Directional Changes for CSO work

Young Lee <ylee@huawei.com> Fri, 10 September 2010 21:12 UTC

Return-Path: <ylee@huawei.com>
X-Original-To: cso@core3.amsl.com
Delivered-To: cso@core3.amsl.com
Received: from localhost (localhost [127.0.0.1]) by core3.amsl.com (Postfix) with ESMTP id EFC5E3A6AED for <cso@core3.amsl.com>; Fri, 10 Sep 2010 14:12:39 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -0.144
X-Spam-Level:
X-Spam-Status: No, score=-0.144 tagged_above=-999 required=5 tests=[AWL=-1.240, BAYES_00=-2.599, DC_GIF_UNO_LARGO=2.275, HTML_MESSAGE=0.001, SARE_GIF_ATTACH=1.42]
Received: from mail.ietf.org ([64.170.98.32]) by localhost (core3.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id HrMFktZJ3v9f for <cso@core3.amsl.com>; Fri, 10 Sep 2010 14:12:32 -0700 (PDT)
Received: from usaga04-in.huawei.com (usaga04-in.huawei.com [206.16.17.180]) by core3.amsl.com (Postfix) with ESMTP id A0D103A6B15 for <cso@ietf.org>; Fri, 10 Sep 2010 14:12:31 -0700 (PDT)
Received: from huawei.com (usaga04-in [172.18.4.101]) by usaga04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14 (built Aug 8 2006)) with ESMTP id <0L8J00KT5UXLCT@usaga04-in.huawei.com> for cso@ietf.org; Fri, 10 Sep 2010 16:12:58 -0500 (CDT)
Received: from L73682 ([10.124.12.96]) by usaga04-in.huawei.com (iPlanet Messaging Server 5.2 HotFix 2.14 (built Aug 8 2006)) with ESMTPA id <0L8J0062LUXK2D@usaga04-in.huawei.com> for cso@ietf.org; Fri, 10 Sep 2010 16:12:57 -0500 (CDT)
Date: Fri, 10 Sep 2010 16:12:56 -0500
From: Young Lee <ylee@huawei.com>
In-reply-to: <221543.75527.qm@web84102.mail.mud.yahoo.com>
To: cso@ietf.org
Message-id: <005d01cb512c$f07c9b20$600c7c0a@china.huawei.com>
MIME-version: 1.0
X-MIMEOLE: Produced By Microsoft MimeOLE V6.00.2900.3664
X-Mailer: Microsoft Office Outlook 11
Content-type: multipart/related; boundary="Boundary_(ID_ZaX5OxGD5Yi0SixT54JCFg)"
Thread-index: ActQ+8c/PVjByNU4TESdoZyQGoEBfQALfnlA
References: <009b01cb505f$109b9ce0$600c7c0a@china.huawei.com> <4C8A4C37.20203@grotto-networking.com> <221543.75527.qm@web84102.mail.mud.yahoo.com>
Subject: Re: [cso] Directional Changes for CSO work
X-BeenThere: cso@ietf.org
X-Mailman-Version: 2.1.9
Precedence: list
List-Id: This list is for pre-WG technical discussion of cross stratum optimization <cso.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/listinfo/cso>, <mailto:cso-request@ietf.org?subject=unsubscribe>
List-Archive: <http://www.ietf.org/mail-archive/web/cso>
List-Post: <mailto:cso@ietf.org>
List-Help: <mailto:cso-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/cso>, <mailto:cso-request@ietf.org?subject=subscribe>
X-List-Received-Date: Fri, 10 Sep 2010 21:12:40 -0000

Greg and Ning,

 

I concur with you. Please see in-line for my comments.

 

Thanks.

Young

 

  _____  

From: cso-bounces@ietf.org [mailto:cso-bounces@ietf.org] On Behalf Of Ning
So
Sent: Friday, September 10, 2010 10:20 AM
To: Greg Bernstein; cso@ietf.org
Subject: Re: [cso] Directional Changes for CSO work

 

Greg,

 

I agree with your view.

 

Ning

 

  _____  

From: Greg Bernstein <gregb@grotto-networking.com>
To: cso@ietf.org
Sent: Fri, September 10, 2010 10:18:15 AM
Subject: Re: [cso] Directional Changes for CSO work

Hi Young and all, from the point of view of finding out what the network has
to offer the application (or what it is currently providing) the emphasis on
data centers seems appropriate.
It seems to me that we potentially have three networking scenarios of
interest:
(1) Internal to the data center (between processors, storage, external
communications) (intra-data center)

 

YOUNG>> I think L2 LAN network connecting servers/applications (Ethernet
Bridge and L2 network protocols) can be a constraining factor for user
experience. We tend to overlook intra-data center networking issue, which
needs to be factored in overall quality of experience estimation.  


(2) Between data centers (for larger distributed applications, for
migration, data distribution, etc..) (inter-data center)

 

YOUNG>> Application mobility between data center can be very dynamic in
nature. Application profile needs to be conveyed to networks (such as
security level on sharing, b/w, latency, etc) clearly so that networks would
be able to route the application successfully meeting the application needs.



(3) Between end users and data centers 

 

YOUNG>> Perhaps this is between end-users to data centers through networks
---Oscar brought up an important issue on if "user profile" (including the
contents, preference in case of gaming server) needs to be conveyed to
application and network and if the protocol scope should include this
aspect. I think Oscar will bring this issue to the mailing list next week.  


These three areas also represent sucessively larger network contexts where
we would have limits on what we can expect (or ask) of the underlying
network.
Is this in line with what folks are thinking? Young, I'll separately send
you some possible additional text on the NS Query document.

Cheers

Greg B.

On 9/9/2010 1:39 PM, Young Lee wrote: 

Hi, 

 

After a couple of conference calls with Ron Bonica (OPS AD) and Dan
Romanscanu (OPS AD), we narrowed down the scope of work and have broken the
CSO work into two pieces:

 

(i) Network Aware Application Mobility (NAAM)  

 

(ii) Network Stratum Query (NS Query)

 

Please see the draft charter descriptions in the attachment. 

 

Depending on the result of the IESG approval, we might pursue these two
pieces as separate work items down the road if both are approved. 

 

Please also note that among many potential CSO applicability, we have
narrowed the work in the context of Data Centers.  The following diagram
depicts the contexts of both NAAM and NS Query. 

 



 

If you are still interested in the new scope, we'd appreciate your comments
on the charter descriptions or any other related matters. 

Thanks. 

 

Best Regards,
Young

 

-- 
===================================================
Dr Greg Bernstein, Grotto Networking (510) 573-2237