RE: [Sipping] Re: draft-rosenberg-sipping-overload-reqs recovery
Janet P Gunn <jgunn6@csc.com> Wed, 08 November 2006 22:54 UTC
Received: from [127.0.0.1] (helo=stiedprmman1.va.neustar.com) by megatron.ietf.org with esmtp (Exim 4.43) id 1GhwJ3-0002AM-3e; Wed, 08 Nov 2006 17:54:05 -0500
Received: from [10.91.34.44] (helo=ietf-mx.ietf.org) by megatron.ietf.org with esmtp (Exim 4.43) id 1GhwJ0-0001xh-4L for sipping@ietf.org; Wed, 08 Nov 2006 17:54:02 -0500
Received: from amer-mta08.csc.com ([20.137.52.152]) by ietf-mx.ietf.org with esmtp (Exim 4.43) id 1GhwIx-0007VU-Lu for sipping@ietf.org; Wed, 08 Nov 2006 17:54:02 -0500
Received: from amer-gw09.amer.csc.com (amer-gw09.amer.csc.com [20.6.39.245]) by amer-mta08.csc.com (Switch-3.1.6/Switch-3.1.0) with ESMTP id kA8MrocX028043 for <sipping@ietf.org>; Wed, 8 Nov 2006 17:53:55 -0500 (EST)
In-Reply-To: <CD6CE349CFD30D40BF5E13B3E0D8480401DECBCE@srvxchg.cablelabs.com>
Subject: RE: [Sipping] Re: draft-rosenberg-sipping-overload-reqs recovery
To: Jean-Francois Mule <jf.mule@cablelabs.com>
X-Mailer: Lotus Notes 652HF83 November 04, 2004
Message-ID: <OFCC9B615D.6F30E968-ON85257220.007DB692-85257220.007DC662@csc.com>
From: Janet P Gunn <jgunn6@csc.com>
Date: Wed, 08 Nov 2006 17:53:47 -0500
X-MIMETrack: Serialize by Router on AMER-GW09/SRV/CSC(Release 6.5.3|September 14, 2004) at 11/08/2006 05:52:47 PM
MIME-Version: 1.0
Content-type: text/plain; charset="US-ASCII"
X-Spam-Score: 0.0 (/)
X-Scan-Signature: 0770535483960d190d4a0d020e7060bd
Cc: Cullen Jennings <fluffy@cisco.com>, Volker Hilt <volkerh@bell-labs.com>, sipping <sipping@ietf.org>
X-BeenThere: sipping@ietf.org
X-Mailman-Version: 2.1.5
Precedence: list
List-Id: "SIPPING Working Group \(applications of SIP\)" <sipping.ietf.org>
List-Unsubscribe: <https://www1.ietf.org/mailman/listinfo/sipping>, <mailto:sipping-request@ietf.org?subject=unsubscribe>
List-Post: <mailto:sipping@ietf.org>
List-Help: <mailto:sipping-request@ietf.org?subject=help>
List-Subscribe: <https://www1.ietf.org/mailman/listinfo/sipping>, <mailto:sipping-request@ietf.org?subject=subscribe>
Errors-To: sipping-bounces@ietf.org
I think it is ineveitable that the overload control system WILL oscillate. The thing is to make sure it is STABLE oscillation, not UNSTABLE. Janet "Jean-Francois Mule" <jf.mule@cablelabs.com> wrote on 11/08/2006 05:42:20 PM: > > Volker wrote: > > I think that stability of overload control is an important > requirement. > > We certainly want to avoid building something that starts to oscillate > > once it reaches overload state. > > Oscillations are often unavoidable in overload conditions, it's the > characterization of these oscillations (amplitude, duration, frequency, > ...) that may lead to instability. > > > Cullen wrote: > > >>> A possible additional requirement.... > > >>> Imagine a system (perhaps a single proxy) that could do 100cps. It > > >>> is in steady state doing 80cps with very few retransmission. Then > > >>> for 5 minutes the incoming requests goes to 500cps then drops > > back > > >>> to an incoming call rate of 80cps. The question is, how long > > before > > >>> the system gets back to the state where it if is successfully > > >>> processing all the 80cps? > > Volker added: > > It may be somehow implicit to REQ 1 > > since an unstable system will hardly be able to maintain the overall > > useful throughput at a high level. > > Following in Cullen's example, I interpret requirement #1 to mean: out > of the 500 cps, the system under load should pick up the *useful* > transactions to keep the using applications happy. > > May be a way to help formulate Cullen's example is to introduce some > wording or requirements around oscillations or the characteristics of > the overload, and say something around the recovery time like: > the overload control mechanism should help predict the time a system > will take to recover based on the characterization of the overload? > > Jean-Francois. > > > -----Original Message----- > > From: Volker Hilt [mailto:volkerh@bell-labs.com] > > Sent: Wednesday, November 08, 2006 9:18 AM > > To: Cullen Jennings > > Cc: sipping > > Subject: Re: [Sipping] Re: draft-rosenberg-sipping-overload-reqs > > recovery > > > > I think that stability of overload control is an important > requirement. > > We certainly want to avoid building something that starts to oscillate > > once it reaches overload state. It may be somehow implicit to REQ 1 > > since an unstable system will hardly be able to maintain the overall > > useful throughput at a high level. > > > > Volker > > > > > > > > Cullen Jennings wrote: > > > Clearly this was a long way from the text for a requirement but, > yes, > > I > > > was proposing that this be added as one of the requirements. I don't > > > feel strongly about this and if we can't figure out how to express > > this > > > as a requirement that is useful, I can certainly live with not > > adding it. > > > > > > The reason I think it is a requirement is I can easily imagine that > > the > > > mechanism for doing overload push-back causes the systems to fail in > > the > > > way I described below (i.e. never recover back to steady state). > > > > > > > > > On Nov 6, 2006, at 11:17 AM, Jonathan Rosenberg wrote: > > > > > >> > > >> > > >> Cullen Jennings wrote: > > >> > > >>> A possible additional requirement.... > > >>> Imagine a system (perhaps a single proxy) that could do 100cps. It > > >>> is in steady state doing 80cps with very few retransmission. Then > > >>> for 5 minutes the incoming requests goes to 500cps then drops > > back > > >>> to an incoming call rate of 80cps. The question is, how long > > before > > >>> the system gets back to the state where it if is successfully > > >>> processing all the 80cps? > > >> > > >> As soon as it can. Are you suggesting a requirement here? Seems > > like > > >> this is an implementation thing and wouldn't impact any protocol > > >> mechanisms. > > >> > > >>> I have seen systems that never recover - that is bad. I think one > > of > > >>> the design goals is that it is at least possible to build to > > systems > > >>> that recover back to steady state relatively quickly after an > > >>> overload impulse. > > >> > > >> Sure; but I'm not sure I see the protocol requirement. > > >> > > >> -Jonathan R. > > >> > > >> > > >> > > >> --Jonathan D. Rosenberg, Ph.D. 600 Lanidex Plaza > > >> Cisco Fellow Parsippany, NJ > > 07054-2711 > > >> Cisco Systems > > >> jdrosen@cisco.com FAX: (973) 952- > > 5050 > > >> http://www.jdrosen.net PHONE: (973) 952- > > 5000 > > >> http://www.cisco.com > > > > > > _______________________________________________ > > > Sipping mailing list https://www1.ietf.org/mailman/listinfo/sipping > > > This list is for NEW development of the application of SIP > > > Use sip-implementors@cs.columbia.edu for questions on current sip > > > Use sip@ietf.org for new developments of core SIP > > > > > > _______________________________________________ > > Sipping mailing list https://www1.ietf.org/mailman/listinfo/sipping > > This list is for NEW development of the application of SIP > > Use sip-implementors@cs.columbia.edu for questions on current sip > > Use sip@ietf.org for new developments of core SIP > > > > _______________________________________________ > Sipping mailing list https://www1.ietf.org/mailman/listinfo/sipping > This list is for NEW development of the application of SIP > Use sip-implementors@cs.columbia.edu for questions on current sip > Use sip@ietf.org for new developments of core SIP _______________________________________________ Sipping mailing list https://www1.ietf.org/mailman/listinfo/sipping This list is for NEW development of the application of SIP Use sip-implementors@cs.columbia.edu for questions on current sip Use sip@ietf.org for new developments of core SIP
- [Sipping] draft-rosenberg-sipping-overload-reqs r… Cullen Jennings
- RE: [Sipping] draft-rosenberg-sipping-overload-re… Poretsky, Scott
- [Sipping] Re: draft-rosenberg-sipping-overload-re… Jonathan Rosenberg
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Spencer Dawkins
- [Sipping] Re: draft-rosenberg-sipping-overload-re… Cullen Jennings
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Volker Hilt
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Jean-Francois Mule
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Janet P Gunn
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Michael Hammer (mhammer)
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Michael Hammer (mhammer)
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Albrecht.Schwarz
- [Sipping] SIP Malformed messages SUNIL J. KUMAR
- RE: [Sipping] SIP Malformed messages Geneiatakis Dimitris
- RE: [Sipping] SIP Malformed messages Gaurav Kheterpal
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Jonathan Rosenberg
- [Sipping] proxy in DMZ while B2BUA as an ALG SUNIL J. KUMAR
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Volker Hilt
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Albrecht.Schwarz
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Dolly, Martin C, ALABS
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Widjaja, Indra (Indra)
- RE: [Sipping] Re: draft-rosenberg-sipping-overloa… Albrecht.Schwarz
- Re: [Sipping] Re: draft-rosenberg-sipping-overloa… Cullen Jennings